nference study flags need to monitor frailty risks with GLP-1 drugs for older adults

nference has been featured in major publications including Bloomberg, New York Times and Scientific America. For media inquiries contact media@nference.net

nference | Featured News

Harness diverse real-world data types to gain insights across genomic, clinical, and operational dimensions

Data Modality

nference’s platform and tools transform real world data into actionable insights for healthcare innovation.

Join leaders across biopharma, clinical research, data science, and healthcare to explore how AI is advancing immunology research—from decoding complex disease biology to accelerating evidence generation and improving translational decision-making.

Join our upcoming events to explore the latest industry trends, discover technological breakthroughs, and gain expert insights. Network with leaders and stay at the forefront of healthcare innovation.

Streamline research with AI-powered tools that transform complex data into actionable medical insights

For Clinical Researchers

Access advanced datasets and cutting-edge analytics to power innovation in healthcare and life sciences.

For Data Scientists

nSights turns complex healthcare data into actionable insights, driving innovation and smarter decision-making in medical research and development.

Revolutionize drug development through AI-driven insights, accelerating timelines and improving clinical trial outcomes.

For Bio Pharma

Unlock actionable insights to improve patient outcomes and optimize healthcare delivery with data-driven solutions.

For Health Systems

Our AI-driven solutions empower clinical trial design, enhance innovation in product development and streamline regulatory submissions.

GLP-1 receptor agonists (GLP-1RAs) such as semaglutide and tirzepatide have transformed obesity care and weight management, delivering unprecedented levels of weight loss in real-world practice.

What happens to weight after we stop prescribing GLP-1 therapies?

Characterization of Patients With Narcolepsy Treated vs Not Treated With Sodium Oxybate: A Propensity Score–Matched Cohort Study

Associations of the Fibrosis-4 Index With Rates of Cardiac Events and Liver Decompensation, and the Potential Implications on Risk Stratification in Patients With Nonalcoholic Steatohepatitis.

nference's extensive library of publications showcase cutting-edge research and healthcare advancements.

Blogs

nference Establishes AI Initiative with Takeda to Advance Precision Medicine in Inflammatory Bowel Disease

News

Our latest blogs and insights cover industry trends, technological breakthroughs, and expert insights, to keep you updated on the forefront of healthcare innovation.

Cutting-edge AI solutions to transform cardiac care

Empowering digital pathology with a new WSI paradigm

Navbar v2

New-onset alopecia was more common with tirzepatide than with semaglutide

Hair loss with GLP-1 drugs is rare, but real, studies find

nference study suggest that some people can keep the weight off.

Does stopping a GLP-1 really doom you to regain all the weight?

Eli Lilly's (LLY.N), opens new tab GLP-1 drug tirzepatide yields greater weight loss on average than Novo ‌Nordisk's (NOVOb.CO), opens new tab semaglutide, but at a greater expense to muscles and connective tissues, according to a study published this week ahead of peer review.

April 16 (Reuters) - Eli Lilly's (LLY.N), opens new tab GLP-1 drug tirzepatide yields greater weight loss on average than Novo ‌Nordisk's (NOVOb.CO), opens new tab semaglutide, but at a greater expense to muscles and connective tissues, according to a study published this week ahead of peer review.

Novo weight-loss drug may preserve lean body mass better than Lilly's, study finds

Real-world data suggested the dual GLP-1/GIP receptor agonist tirzepatide (Mounjaro, Zepbound) was associated with greater weight loss,

GLP-1s and Muscle Loss; 'Ozempic Personality'

While Eli Lilly’s tirzepatide helps patients drop more weight than Novo Nordisk’s semaglutide, this might come with greater loss in lean body mass, according to …

Lilly’s tirzepatide sheds lean muscle harder than Novo’s semaglutide, study suggests

nference announced a series of publications from the Metabolic Agentic Intelligence Atlas initiative, or MAIA, a federated AI program that enables real-time synthesis of biomedical knowledge from the de-identified care patterns of over 30 million patients. The studies provide collectively, for the first-time, a high-resolution precision map of the impact of GLP-1, GIP, and other incretin therapies on the whole human body beyond weight-loss and glucose measurements that have been the primary endpoints of clinical studies thus far.

Federated network of 30 million patients powers first-series of 15 foundational studies from Metabolism Agentic Intelligence Atlas (MAIA) toward novel diagnostics, therapeutics, and surgical interventions.

CAMBRIDGE, Mass., June 9, 2026 /PRNewswire/ -- nference today announced a series of publications from the Metabolic Agentic Intelligence Atlas initiative, or MAIA, a federated AI program that enables real-time synthesis of biomedical knowledge from the de-identified care patterns of over 30 million patients. The studies provide collectively, for the first-time, a high-resolution precision map of the impact of GLP-1, GIP, and other incretin therapies on the whole human body beyond weight-loss and glucose measurements that have been the primary endpoints of clinical studies thus far. Across these studies, the nference MAIA team leveraged physician-validated Large Language Models (LLMs) and other AI technologies to derive deep insights into longitudinal clinical notes, medication exposure and adherence patterns, serial laboratory measurements, body weight and body-composition trajectories, radiology and pathology imaging, and electrophysiology waveforms to quantify healthy longevity outcomes.

"GLP-1 medicines are no longer just obesity drugs. They are therapeutic lenses into healthy longevity and evolution of diverse disease pathologies at a resolution that was unimaginable until recently," said Dr. Venky Soundararajan, PhD, Founder & Chief Scientific Officer of nference. "The consistent signal from the first set of MAIA studies is that next-generation clinical trials and decision-support systems should be designed with whole-body spatial intelligence."

Across the portfolio, MAIA is intended to go beyond what gold-standard randomized clinical trials (RCTs) have contributed, addressing a central blind spot in modern cardiometabolism: the field has measured pounds lost far more precisely than organs protected, disease trajectories redirected, or durability retained after therapy stops. MAIA turns routine care into a longitudinal discovery engine, connecting dose, adherence, discontinuation, tissue remodeling, infection resilience, immune modulation, neuropsychiatric outcomes, cancer progression, surgical risk, and healthy longevity into a single computable map. The result is not a replacement for RCTs, but a hypothesis-generating operating system for powering the next-generation of innovation.

"These studies from nference signal that longitudinal, AI-curated evidence can inform prospective studies in profound ways," said Dr. C. Michael Gibson, MD, Professor of Medicine at Harvard and CEO of the Baim Institute for Clinical Research. "The broad spectrum of weight-loss-independent benefits revealed by the first series of MAIA publications challenges long-held cardiometabolism assumptions that place glucose lowering and total body weight reduction at the center of therapeutic value. These findings reinforce that incretin biology is organ-specific, durable, and multidimensional.

The emerging blueprint for cardiometabolism trial design

The first wave of peer-reviewed MAIA publications reframes obesity pharmacotherapy from an average-weight-loss field into a response-architecture field. Across these studies, nference advances a new organizing principle for cardiometabolism: weight-change velocity is not merely an endpoint, but a longitudinal signal of metabolic memory, incretin responsiveness, behavioral context, and therapeutic durability. The findings illuminate the questions that conventional obesity trials have not been designed to answer at scale: which patients enter distinct response trajectories, how quickly those trajectories separate, what biological and behavioral signals precede them, and which patients continue to benefit after GLP-1/GIP receptor agonist treatment stops.

In the peer-reviewed study "Decoding the hallmarks of GLP-1RA weight-loss super-responders," published in Biology Methods and Protocols by Oxford University Press1, the MAIA team analyzed 135,349 individuals treated with semaglutide and tirzepatide formulations and classified patients into weight-loss super-responders, moderate responders, minimal-weight-loss patients, and weight regainers. Most provocatively, among super-responders, one year of treatment returned average body weight to levels approximating 20 years before therapy initiation; moderate responders approximated a 10-year reversal. This finding suggests that GLP-1RA response is not merely a treatment effect measured at one year, but a window into decades of accumulated metabolic history.

In the peer-reviewed study "Weight Loss Dynamics and Health Burden Changes with Tirzepatide versus Semaglutide," accepted by the journal PNAS Nexus (published by U.S. National Academy of Sciences)2, the MAIA team compared 10,339 tirzepatide-treated and 10,339 semaglutide-treated propensity-matched patients. An important trial-design signal unearthed was heterogeneity in weight-loss response: female and white patients on either tirzepatide or semaglutide more frequently achieved significant weight loss than male, black, and Hispanic patients, who were more likely to lose less than 5% of their body weight in a year. These differences in weight-loss response outcomes for both the currently marketed GLP1RA therapies highlights the need for the next-generation of clinical studies to advance obesity solutions that cater to the broader-spectrum of patients with continued clinical unmet needs.

In the peer-reviewed study "Weight trajectories after last tirzepatide or semaglutide prescription across a federated health network" published by the journal Biology Methods and Protocols (Oxford University Press)3, the MAIA team assessed 4,182 patients in the six months after their last documented semaglutide or tirzepatide prescription. Contrary to the assumption that GLP-1RA cessation inevitably leads to immediate rebound, approximately two-thirds of patients showed stable weight or continued weight loss. In an LLM-curated subset with clinician-documented discontinuation, 72% did not show the expected weight regain. Exercise counseling appeared significantly more frequently among patients with durable weight loss than among those with regain, suggesting that post-GLP-1RA durability may be shaped by a combination of pharmacology, patient behavior, clinical follow-up, and care-delivery context.

Together, these studies define a new blueprint for cardiometabolism development: enrich trials by response phenotype, measure weight velocity rather than only endpoint weight change, treat durability after discontinuation as a first-class endpoint, and design maintenance and tapering strategies prospectively.

"This may be the first time that decades of body-weight history have been reconstructed from routine patient records at this scale," said Dr. Marcelo Montorzi, MD, an Internal Medicine physician scientist at Southcoast Health. "The finding that GLP-1 super-responders are often the same patients who experienced the most recent acceleration in weight gain is a fundamental observation. It suggests that future cardiometabolism trials should not only ask how much weight a drug reduces, but whether the patient's prior weight-gain velocity predicts the magnitude, durability, and clinical meaning of response."

From Weight Loss to Longevity: The Whole-Body Biology of GLP-1 Therapies

Across cardiovascular, hepatic, neuropsychiatric, neurodegenerative, renal, and infection-resilience studies, nference identified associations suggesting that dose exposure, treatment trajectory, and tissue-specific outcomes may provide additional insight into patient benefit. Collectively, these findings support a next-generation trial-design framework for the incretin era — one that evaluates GLP-1 biology across organs, exposure patterns, and longitudinal disease trajectories, not solely through the magnitude of weight loss.

In the study "Semaglutide cardiovascular outcomes align more closely with attained dose than achieved weight loss," published as a preprint with peer-review ongoing at npj Cardiovascular Health (Springer Nature)4, the MAIA team analyzed 47,199 patients with baseline cardiovascular disease. Higher attained semaglutide dose was associated with lower post-landmark risk of all-cause mortality, composite cardiovascular events, cerebrovascular disease, heart failure, and valvular or rheumatic heart disease. In contrast, achieved weight loss did not show the same monotonic association with later cardiovascular risk. Notably, many patients had their peak semaglutide exposure during the two years before the subsequent cardiovascular outcome window, raising a provocative hypothesis: the heart may retain a therapeutic benefit legacy of prior incretin exposure even after active treatment stops.

"The weighing scale may be the loudest biomarker of GLP-1 therapy effectiveness, but the heart may be reading a distinct signal of therapeutic benefit," said Dr. Kalyanam Shivkumar, MD PhD, Distinguished Professor of Cardiology, Radiology, and Bioengineering at the University of California, Los Angeles (UCLA). "If confirmed prospectively, this finding argues that cardiovascular trials should treat dose exposure, persistence, and organ endpoints as first-class variables rather than assuming weight loss is the major mediator."

In the study "Semaglutide is associated with stiffness improvement and broad liver benefits with distinct dose- and weight-linked patterns", the MAIA team analyzed 6,734 patients with baseline liver disease burden and a complementary elastography cohort of 326 adults with paired noninvasive liver stiffness measurements from radiology imaging before and after semaglutide initiation5. Median liver stiffness decreased after semaglutide initiation; 59.5% of patients had lower follow-up stiffness, 40.8% achieved at least 20% stiffness reduction, and 21.2% shifted to a lower fibrosis stage by prespecified elastography thresholds. These liver imaging-based findings point to potential tissue-level remodeling benefits of semaglutide. While prospective validation is needed, the results support inclusion of organ-specific endpoints in future incretin trials and position liver health as an important dimension of whole-body cardiometabolic benefit.

In the study "Legacy neuropsychiatric benefit after semaglutide is linked to maximum achieved dose and independent of the maximum weight lost", the MAIA team evaluated 63,215 semaglutide-treated patients with baseline neuropsychiatric conditions across 24 incident outcomes6. Higher attained dose during the first two years of semaglutide therapy, but not body weight lost during that period, was associated with significantly lower subsequent 2–4-year incidence of several neuropsychiatric outcome groups. The semaglutide-associated incident risk reduction includes substance disorders, mood-, anxiety- and stress-related conditions, central nervous system (CNS) atrophy, neuromuscular diseases, sleep disturbances, behavioral disorders, and impulse control diseases. By extending beyond one or two neuropsychiatric endpoints, this MAIA study suggests that semaglutide's long-term neuropsychiatric associations may reflect more than weight reduction alone. In patients with prior neuropsychiatric burden, attained dose appeared more informative than maximum weight lost for subsequent incident risk across a broad spectrum of brain and behavior outcomes.

In the study "Functional-vs-Cognitive Decline Heterogeneity in Alzheimer's Disease Revealed by LLM-curation of Decades of Clinical Notes has Implications for Semaglutide Trial Design", the MAIA team recovered clinical outcome scores from decades of routine clinical notes7. Among 131,824 patients with structured Alzheimer's disease diagnoses, 42,242 had at least one LLM-derived outcome assessment, and semaglutide-treated AD patients showed more favorable paired MMSE and MoCA changes than matched controls. This study advances a trajectory-aware framework for Alzheimer's disease trial design by showing that decades of routine clinical notes can be transformed into standardized cognitive, functional, global severity, and neuropsychiatric trajectories at scale. By revealing distinct patterns of functional-first decline versus cognitive-first decline, and by linking semaglutide exposure to more favorable observed MMSE and MoCA trajectories versus matched controls, the study identifies disease phase, functional reserve, multimorbidity, APOE context, and the temporal ordering of decline as variables that may be critical for designing future incretin trials in Alzheimer's disease.

In the study "Semaglutide use linked to lower COVID-19 and influenza severity with better cardiovascular, pulmonary, renal outcomes after pandemic or seasonal infection", the MAIA team compared 11,238 COVID-19 patients and 3,409 influenza infection (flu) patients with their respective matched standard-of-care cohorts8. Prior semaglutide exposure was associated with lower 30-day COVID-19 mortality, hospitalization, ICU admission, mechanical ventilation, and composite severity, and with lower influenza hospitalization, ICU admission, mechanical ventilation, and composite severity. The study also reported lower acute coronary syndrome, pulmonary complication, and renal complication signals during sub-acute post-infection windows.

"These findings raise a host-resilience hypothesis," said Dr. AJ Venkatakrishnan, PhD, Senior Vice President for Strategic AI Partnerships at nference. "The next generation of incretin studies may focus not only on chronic disease, but also evaluate how incretin interventions could reshape how vulnerable hosts respond to acute infection, organ stress, and inflammatory injury."

Together, these MAIA studies move GLP-1 medicine from a weight-loss paradigm toward a Whole-Body Spatial Intelligence framework. The emerging question is whether the heart, liver, brain, lung, kidney, immune system, and functional reserve each carry distinct, measurable signatures of incretin exposure — and whether those signatures can be prospectively tested to advance healthy longevity. The MAIA framework now extends naturally to complex, chronic conditions with immunologic dysregulation mechanisms and substantial unmet need, including cancer and type 1 diabetes, where metabolic state intersects in intricate ways with the human immune system.

Cancer Metabotypes: Extending MAIA from Breast Cancer Survival Signals to Solid Cancer Immunotherapy and Hematologic Malignancies

In the study "Semaglutide is associated with improved breast cancer survival, lower metastatic burden, and a dose–survival relationship uncoupled from weight-loss magnitude", the MAIA team analyzed real-world outcomes from large cohorts with multimodal clinical data9. Semaglutide exposure was associated with more favorable overall survival, lower metastatic burden, and a dose-associated survival gradient in breast cancer that was not explained by weight-loss magnitude alone. Across multiple cancer types, GLP-1 receptor agonist exposure was associated with lower rates of metastatic progression and more favorable cancer trajectories. These findings raise the possibility that incretin therapies may influence cancer biology beyond their metabolic effects and support prospective studies.

At the American Society of Clinical Oncology (ASCO) 2026 Meeting10,11, the nference MAIA team presented "Metabotypes of Pembrolizumab and Lung Cancer" and "Associations between early on-treatment weight change and overall survival across targeted therapies in chronic lymphocytic leukemia (CLL)". In the lung cancer study, early on-treatment weight gain was a favorable survival association, with each 1% increase in body weight after pembrolizumab initiation consistently associated with lower subsequent mortality risk. In the CLL study of 3,542 patients initiating targeted therapies, on-treatment weight gain was associated with improved overall survival for venetoclax and ibrutinib. These studies, published in the Journal of Clinical Oncology10,11, suggest that early body-weight trajectory may serve as a pragmatic metabotype signal across both solid-tumor immunotherapy and hematologic malignancy treatment settings.

A broader implication of these oncology studies is that body-weight trajectory may be an underused clinical signal in cancer care. Many oncology trials do not systematically decode the relationship between on-treatment weight change and long-term outcomes such as survival, metastatic progression, treatment tolerance, or supportive-care need. The MAIA findings suggest that routine weight measurements, when linked to longitudinal EHR context and treatment exposure, could become a scalable, low-burden metabotype biomarker to complement immunotherapy and targeted therapy studies, while supporting earlier risk stratification, supportive-care intervention, and value-based oncology management.

"For decades, oncology has studied tumor metabolism, but we have not fully leveraged the patient's own metabolic trajectory as a clinical signal," said Dr. Manish Kohli, MD, Presidential Endowed Chair in Cancer Research at the University of Utah-Huntsman Cancer Institute. "These cancer metabotyping studies point to a common hypothesis: host metabolism may influence cancer progression, treatment tolerance, immune response, drug efficacy, and survival in ways that are measurable in routine care. If validated prospectively, weight trajectory and metabolic context could become practical tools for stratifying patients across solid tumors and hematologic malignancies."

Type-1 Diabetes with GLP-1: From Insulin Dependence to Insulin Deintensification

Type 1 diabetes (T1D) remains an insulin-dependent autoimmune disease with substantial unmet need, particularly for adults facing high insulin requirements, weight gain, glycemic variability, and long-term cardiometabolic risk. In the study, "Semaglutide and Tirzepatide in Type 1 Diabetes: Real-World Insulin Deintensification, Cardiovascular Outcomes and Safety Assessment," the MAIA team analyzed 2,002 adults with T1D exposed to semaglutide or tirzepatide versus propensity-score matched T1D control patients without GLP-1RA exposure12. The central signal was sustained insulin deintensification: at 12 months, insulin total daily dose (TDD) declined by 22.0% with semaglutide and 19.7% with tirzepatide, compared with a 10.3% increase in matched controls. By 24 months, insulin TDD reductions widened to 27.4% and 25.9% with semaglutide and tirzepatide respectively, compared with 10.4% increase in controls.

At 12 months, HbA1c declined by 4.2% with semaglutide and 3.0% with tirzepatide versus 0.3% in controls, while body weight declined by 4.0% and 6.8%, respectively, versus 0.5% in controls. Among semaglutide-treated patients, mean 12-month insulin TDD reduction was 34.5% in those losing at least 10% of body weight versus 19.6% in those losing less than 5%, and higher semaglutide dose tiers were associated with greater TDD reduction. By contrast, tirzepatide dose escalation was not significantly associated with TDD reduction in this analysis. These findings suggest that future T1D trials should jointly model insulin dose reduction, achieved incretin dose, weight change, HbA1c, and safety signals to distinguish patients who can safely de-intensify insulin from those who require closer monitoring.

The observed safety profile was gastrointestinal-predominant, with increases in nausea or vomiting, constipation, diarrhea, decreased appetite, hypoglycemia, and acute kidney injury, while diabetic ketoacidosis, severe hypoglycemia, pancreatitis, gallbladder disease, gastroparesis, and retinopathy progression did not change significantly in the paired pre/post analysis. However, patients with greater than 30% insulin TDD reduction at 6 months had higher diabetic ketoacidosis incidence, suggesting that insulin deintensification should be supported by structured safety monitoring rather than simple dose reduction.

The MAIA study also showed that across 24 prespecified cardiovascular and renal time-to-event endpoints, semaglutide or tirzepatide exposure was associated with lower 2-year all-cause mortality and major adverse cardiovascular events (MACE), while no renal endpoint remained significant after multiple-testing correction.

"The recent publications from nference provide a new roadmap of AI-curated evidence that will  almost certainly be used to inform gold standard randomized clinical trials for disorders beyond obesity and type 2 diabetes mellitus," said Dr. Clifford Rosen, MD, Director of the Center for Clinical & Translational Research at Maine Health and Professor at Tufts Medicine.

Physician-adjudicated LLM Curation of Longitudinal Clinical Notes Reveals the Hidden Landscape of Treatment adherence and Compounded GLP-1 Use

In the study "Auditable LLM curation of clinical notes refines GLP-1 initiation, persistence ascertainment and compounding use beyond prescription records," the MAIA team exposed a central vulnerability in GLP-1 real-world evidence: a prescription is not the same as a patient taking the drug13. Across 553,073 adults with semaglutide or tirzepatide prescriptions, structured prescription records were noted to miss salient information that an LLM pipeline on clinical notes captured, such as delayed starts, access barriers, early interruptions, true persistence, and compounded GLP-1 exposure. Prescription-based persistence was found to substantially overestimate note-confirmed active use at 18 months, while insurance and cost barriers, perioperative holds, and gastrointestinal adverse events emerged as major drivers of discontinuation or treatment friction. This study demonstrates that clinical notes are not ancillary evidence, but essential infrastructure for GLP-1 trial design, payer strategy, safety surveillance, compounding-risk monitoring, and interventions that improve sustained access to peptide therapies whose benefits depend on starting and staying on treatment.

"Structured prescriptions record intent, whereas longitudinal clinical notes reveal reality," said Karthik Murugadoss, Vice President of AI Research at nference. "For GLP-1 therapies, critical signals such as exposure, adherence, compounding, weight dynamics, and clinician judgment often live beyond structured EHR fields. This study shows how LLMs with physician validation turn fragmented health system encounters into auditable AI infrastructure for the incretin era."

Semaglutide Microdosing Linked to Cardiometabolic Benefit with Minimal Weight Loss; Head-to-Head Comparison Shows Favorable Tolerability Over Low-Intensity Tirzepatide

In the study "Sustained low-dose semaglutide is linked to broad-spectrum cardiometabolic benefits, and better tolerability profile over low-dose tirzepatide, motivating semaglutide microdosing studies," the MAIA team analyzed real-world outcomes among patients who remained on initiation-dose semaglutide (0.25 mg) or initiation-dose tirzepatide (2.5 mg) for prolonged periods14. Despite only modest weight change, sustained initiation-dose semaglutide was associated with lower 24-month event probabilities for mortality, composite cardiovascular events, heart failure, arrhythmias, ischemic heart disease, and venous thromboembolism versus matched patients receiving metformin, DPP-4 inhibitors, or SGLT-2 inhibitors, with the strongest signals observed among patients with baseline cardiovascular burden. In head-to-head comparisons, sustained initiation-dose semaglutide also demonstrated a more favorable tolerability profile than sustained initiation-dose tirzepatide, with lower rates of diverse gastrointestinal, renal, musculoskeletal, and respiratory adverse events. These findings suggest that clinically meaningful cardiometabolic benefits may be achievable at substantially lower doses than currently studied in RCTs and support prospective evaluation of semaglutide microdosing strategies. Particularly, low-intensity semaglutide exposure may represent a distinct opportunity for prevention, maintenance, and longevity-oriented cardiometabolism trials.

"The very promising  link of microdose levels of these agents to lower 24-month event-rates for a broad array of cardiovascular endpoints despite very modest weight loss, when taken together with evidence of disproportionate lean muscle loss at higher doses of some agents, only emphasizes the reality that the magnitude and scope of the many and varied impacts of these agents are well beyond their effectiveness at overall weight loss," said Dr. Joseph Smith, MD PhD, Cardiologist/Electrophysiologist, AI interventions expert and Adjunct Professor of Johns Hopkins.

Body-composition digital phenotyping reveals that the future of GLP-1 longevity medicine must optimize fat loss without sacrificing lean-tissue reserve

In the study "Greater lean-body-mass decline with tirzepatide than semaglutide in routine care, revealed by body-composition digital phenotyping," the MAIA team showed that the next frontier in GLP-1 medicine is not simply how much weight is lost, but what kind of weight is lost15. Across 670,422 first-episode GLP-1RA users, including 456,742 semaglutide-treated and 213,680 tirzepatide-treated patients, 7,965 individuals had paired pre- and post-initiation body-composition measurements. Tirzepatide was associated with greater relative lean-body-mass (LBM) loss than semaglutide at every measured timepoint, with excess LBM losses of 1.1%, 1.5%, 1.3%, and 2.0% at 3, 6, 9, and 12 months, respectively. Tirzepatide also produced greater total body weight (TBW) loss, suggesting that its superior weight-loss efficacy may come with a greater LBM tradeoff. A "Depletive GLP-1 Metabotype," defined as >20% TBW loss with >5% LBM loss, was significantly more frequent with tirzepatide than semaglutide (10.3% versus 6.7%), while the "Prime GLP-1 Metabotype," defined as >10% TBW loss with <5% LBM loss was 11.8% versus 12.3%, respectively.

The implications are clinically important for U.S. adults with Medicare coverage (65+ years), patients with frailty risk, adults seeking longevity-oriented long-term metabolic optimization, and patients with sports injuries, chronic knee or neck pain, reduced mobility, or other conditions where preserving lean mass is central to function. Indeed, in this MAIA study15, baseline musculoskeletal pain emerged as a major correlate of greater LBM loss, with cervicalgia and knee pain showing especially large LBM loss, and higher LBM loss was linked to reduced exercise tolerance. These findings argue that future cardiometabolism trials should incorporate whole body composition-aware endpoints that maximize fat loss while preserving strength, function, and the lifelong reserve needed for the quest for longevity.

Toward Autonomous AI Agents for Healthy Longevity

The first series of MAIA publications highlights a larger quest at nference: engineering autonomous AI agents that continuously learn from de-identified routine care, convert multimodal patient trajectories into computable hypotheses, and help design the next generation of prospective cardiometabolism studies. Within MAIA, these agents operate with physician and scientist checkpoints, generating prompts, challenging and validating one another's hypotheses, and mapping incretin therapies, concomitant medicines, and real-world interventions to their molecular mechanisms of action. This enables systematic assessment of potential synergy, antagonism, and signaling-pathway interactions across routine care. MAIA represents an early step toward a future in which cardiometabolism is interpreted as a living system of biomedical knowledge, and real-world evidence becomes a translational intelligence layer for advancing AI diagnostics, precision peptide therapeutics, surgical interventions, clinical decision support, and healthy longevity.

AJ Venkatakrishnan, Karthik Murugadoss, Venky Soundararajan, Decoding the hallmarks of GLP-1RA weight-loss super-responders, Biology Methods and Protocols, Volume 11, Issue 1, 2026, bpag021, https://doi.org/10.1093/biomethods/bpag021

AJ Venkatakrishnan, Karthik Murugadoss, Venky Soundararajan, Weight Loss Dynamics with Tirzepatide versus Semaglutide, PNAS Nexus, Accepted for publication, June 2026, medRxiv preprint: https://www.medrxiv.org/content/10.64898/2025.11.30.25341294v1

Karthik Murugadoss, Gowtham Varma, AJ Venkatakrishnan, C Michael Gibson, Venky Soundararajan, Weight trajectories after last tirzepatide or semaglutide prescription across a federated health network, Biology Methods and Protocols, Volume 11, Issue 1, 2026, bpag020, https://doi.org/10.1093/biomethods/bpag020

Karthik Murugadoss, AJ Venkatakrishnan, Christopher Gregg, Venky Soundararajan, Semaglutide cardiovascular outcomes align more closely with attained dose than achieved weight loss, npj Cardiovascular Health - under review. Preprint in Research Square (Springer Nature), https://doi.org/10.21203/rs.3.rs-9407045/v1

AJ Venkatakrishnan, K Purushotham, Gowtham Kumar Varma, Avinash Aman, Karthik Murugadoss, Venky Soundararajan, Semaglutide is associated with stiffness improvement and broad liver benefits with distinct dose- and weight-linked patterns. Under review. Preprint: https://www.medrxiv.org/content/10.64898/2026.04.14.26350891v1

Karthik Murugadoss, AJ Venkatakrishnan, Venky Soundararajan, Legacy neuropsychiatric benefit after semaglutide is linked to maximum achieved dose and independent of the maximum weight lost. Under review. Preprint: https://www.medrxiv.org/content/10.64898/2026.04.16.26351060v1

Karthik Murugadoss, AJ Venkatakrishnan, Gowtham Kumar Varma, Ravi Sunil Kumar, Gourab Saha, Venky Soundararajan, Functional-vs-Cognitive Decline Heterogeneity in Alzheimer's Disease Revealed by LLM-Curation of Decades of Clinical Notes has Implications for Semaglutide Trial Design. SSRN (Preprints with The Lancet): http://dx.doi.org/10.2139/ssrn.6841482

Robert Matson, Karthik Murugadoss, AJ Venkatakrishnan, Venky Soundararajan. Semaglutide use linked to lower COVID-19 and influenza severity with better cardiovascular, pulmonary, renal outcomes after pandemic or seasonal infection. Submitted to Preprints.org.

Karthik Murugadoss, AJ Venkatakrishnan, Venky Soundararajan. Semaglutide is associated with improved breast cancer survival, lower metastatic burden, and a dose–survival relationship uncoupled from weight-loss magnitude. Under review. Preprint: https://www.medrxiv.org/content/10.64898/2026.04.23.26351609v1

Venky Soundararajan, Karthik Murugadoss. Metabotyping using early body weight velocity in lung cancer patients treated with pembrolizumab. J Clin Oncol 44, e20527-e20527(2026). https://ascopubs.org/doi/10.1200/JCO.2026.44.16_suppl.e20527

Venky Soundararajan, Karthik Murugadoss. Associations between early on-treatment weight change and overall survival across targeted therapies in chronic lymphocytic leukemia. J Clin Oncol 44, e19001(2026). https://ascopubs.org/doi/10.1200/JCO.2026.44.16_suppl.e19001

Robert Matson, Karthik Murugadoss, AJ Venkatakrishnan, Venky Soundararajan. Semaglutide and Tirzepatide in Type 1 Diabetes: Real-World Insulin Deintensification, Cardiovascular Outcomes and Safety Assessment. Preprints.org. https://www.preprints.org/manuscript/202606.0638

Gowtham Varma, Karthik Murugadoss, Mathews E Kurian, Jerin Varghese, AJ Venkatakrishnan, Venky Soundararajan. Auditable LLM curation of clinical notes refines GLP-1 initiation, persistence ascertainment and compounding use beyond prescription records. Submitted to Preprints.org.

Karthik Murugadoss, AJ Venkatakrishnan, Venky Soundararajan. Sustained low-dose semaglutide is linked to broad-spectrum cardiometabolic benefits, and better tolerability profile over low-dose tirzepatide, motivating semaglutide microdosing studies. Preprints.org. https://www.preprints.org/manuscript/202606.0636

Karthik Murugadoss, AJ Venkatakrishnan, Venky Soundararajan. Greater lean-body-mass decline with tirzepatide than semaglutide in routine care, revealed by body-composition digital phenotyping. Under review. Preprint in Research Square (Springer Nature), https://www.researchsquare.com/article/rs-9407186/v1

The Metabolism Agentic Intelligence Atlas (MAIA) is an nference strategic initiative focused on making cardiometabolism computable across therapies, diseases, organs, and patient trajectories. By integrating federated real-world data with AI-enabled clinical phenotyping, MAIA maps how metabolic interventions influence health outcomes across the body and throughout the lifespan. The platform combines electronic health records, clinical notes, treatment exposure, laboratory measurements, imaging-derived biomarkers, body-composition assessments, and other AI-derived phenotypes to generate biologically grounded, clinically testable insights. These insights are intended to inform clinical trial design, patient stratification, dose optimization, safety evaluation, organ-specific endpoint discovery, and AI-enabled decision support. Unless otherwise specified, MAIA studies are retrospective and observational. Associations should not be interpreted as proof of causality or used to guide clinical care without prospective validation. Preprints have not completed peer review. nference intends MAIA to serve as a hypothesis-generating translational engine that can inform rigorous prospective studies, including randomized trials, pragmatic trials, active-comparator observational analyses, mechanistic studies, diagnostic development studies, and future AI-enabled clinical decision-support frameworks.

nference is an Agentic Intelligence company making biomedical knowledge computable from multimodal healthcare data. The company builds federated AI systems that transform the language of routine care into privacy-preserving, computable knowledge for discovery, development, and care transformation. The data includes clinical notes, lab tests, medication records, radiology and pathology imaging, electrophysiology signals, body-composition data, wearables, genomes, and longitudinal patient trajectories. nference is building the infrastructure for a future in which biomedical knowledge is continuously learned from routine care, responsibly validated, and translated into better strategies for prevention, treatment, and healthy longevity.

June 9 (PR Newswire) - nference announced a series of publications from the Metabolic Agentic Intelligence Atlas initiative, or MAIA, a federated AI program that enables real-time synthesis of biomedical knowledge from the de-identified care patterns of over 30 million patients. The studies provide collectively, for the first-time, a high-resolution precision map of the impact of GLP-1, GIP, and other incretin therapies on the whole human body beyond weight-loss and glucose measurements that have been the primary endpoints of clinical studies thus far.

Weight-loss: nference Advances Cardiometabolism Moat for Precision Peptide Medicines and Healthy Longevity

Whole-Body Spatial Intelligence Beyond Weight-loss: nference Advances Cardiometabolism Moat for Precision Peptide Medicines and Healthy Longevity

Banner Health and nference, a science-first software company transforming healthcare by making biomedical data computable, today announced a partnership to accelerate scientific discovery to improve treatment, diagnosis, and care.

CAMBRIDGE, Mass., Aug. 22, 2023 – Banner Health and nference, a science-first software company transforming healthcare by making biomedical data computable, today announced a partnership to accelerate scientific discovery to improve treatment, diagnosis, and care.

By incorporating nference’s state-of-the-art analytics capabilities, Banner Health and its researchers can gain valuable insight into diseases and treatments, adapting the practice of medicine to meet the needs of its communities. 

“We’re excited to embark on this innovative partnership that will unlock the insights from our data to further personalize the ways we deliver care to our patients,” said Scott Nordlund, Executive Vice President Chief Strategy and Growth Officer at Banner Health. “This partnership will support our own efforts to improve the care patients receive in our diverse clinical settings and benefit other researchers with global impact on diagnosis and treatment.” 

nference’s Federated Analytics Platform enables researchers and clinicians to derive meaningful insights from proprietary longitudinal clinical datasets, transforming discovery and accelerating development while preserving patient privacy. The platform provides insights from the deepest, de-identified, multimodal (electronic health record, imaging, electrocardiogram) dataset available across therapeutic areas. These include cardiology, oncology, immunology, neuroscience, metabolic diseases, and infectious diseases by leveraging the company’s Federated AI network.

“Our collaboration with Banner Health is an exciting addition to our unique federated network,” said Murali Aravamudan, co-founder and CEO of nference. “Banner Health brings comprehensive, multimodal data from a geographically and ethnically diverse patient population to our network that will provide more potent insight generation, offering researchers the option to examine more inclusive data.”

nference’s agreement with Banner Health builds on recent collaborations with other leading academic medical centers, accelerating nference’s mission to expand its federated network, which is scalable and structured to encourage and facilitate collaboration among healthcare systems and biopharmaceutical researchers.

Through its powerful technology platform and software, nference is transforming healthcare by making biomedical knowledge computable. Its partnerships with major academic medical centers empower nference to synthesize decades of institutional knowledge, producing real-world evidence (RWE) in real time by converting large amounts of de-identified data into deep insights to advance discovery and development of diagnostics and therapeutics. Its proprietary AI-enabled software platform, nSights, harnesses the power of federated learning to accelerate life sciences research, development, and clinical care in significant ways, including biomarker discovery and validation, RWE generation leveraging real-world data, early disease detection, public health policy generation and validation, and more. nference is headquartered in Cambridge, Mass. Follow nference on LinkedIn and Twitter. Visit us at www.nference.com.

Banner Health is one of the largest, secular nonprofit health care systems in the country. In addition to 30 acute-care hospitals, Banner also operates an academic medicine division, Banner – University Medicine, and Banner MD Anderson Cancer Center, a partnership with one of the world’s leading cancer programs, MD Anderson Cancer Center. Banner’s array of services includes a health insurance division, employed physician groups, outpatient surgery centers, urgent care locations, home care and hospice services, retail pharmacies, stand-alone imaging centers, physical therapy and rehabilitation, behavioral health services, a research division and a nursing registry. To make health care easier, 100% of Banner-employed doctors are available for virtual visits and patients may also reserve spots at Banner Urgent Care locations and can book appointments online with many Banner-employed doctors. Headquartered in Arizona, Banner Health also has locations in California, Colorado, Nebraska, Nevada and Wyoming. For more information, visit bannerhealth.com.

Andrea Sampson, Sampson Public Relations Group

Banner Health Partners with nference to Accelerate Scientific Discovery for Patient Care

Research collaboration expedites innovation by leveraging synergies between Valo Health's Opal Computational PlatformTM and the nference Agentic AI platform

CAMBRIDGE and LEXINGTON, Mass., March 18, 2025 – Valo Health, Inc. (“Valo”), a biotechnology company focused on transforming the drug discovery and development process using human-centric data and artificial intelligence (AI), today announced a multi-year collaboration with nference, a company dedicated to transforming healthcare by making biomedical knowledge computable. The research collaboration will leverage decades of comprehensive, HIPAA-compliant, fully de-identified patient-level data from the nference federated AI network to enhance the capabilities of Valo’s Opal Computational Platform™, enabling advances in the discovery and development of drug targets and precision medicines.

“We are entering a new era of medicine made possible by abundant clinical data and an enhanced ability to analyze it,” said Brett Blackman, Ph.D., chief operating officer at Valo Health. “Our collaboration gives us access to nference's deep multimodal, longitudinal data and AI software platform, which will allow us to learn through observation while accelerating and widening the scope of experimentation. Together, with nference and our other ecosystem partners, we aim to shorten the drug development timeline and bring critical treatment options to the patients who need them the most.”

The collaboration grants Valo the ability to use the nference AI platform, the industry’s most comprehensive multimodal biomedical knowledge base, incorporating deep, de-identified insights from top-ranked academic medical centers that are part of the nference federated AI network. Use of the nference AI platform provides Valo with real-time access to a wide range of data modes, including insights from physicians’ notes, medical imaging and outcomes data, patients’ diagnostic and treatment information, and lab results.

The partnership’s unique collaboration model supports Valo’s novel, human-centric approaches to target discovery, clinical translation, and biomarker discovery. As nference brings onboard additional data modalities, Valo will have access to an expanding pool of rich data and advanced analytics tools that will yield deeper insights to support its translational research programs.

“Our partnership with Valo demonstrates how the nference Agentic AI platform can deliver clinical knowledge and de-identified, real-world patient insights to accelerate drug discovery and development,” said Venky Soundararajan, Ph.D., co-founder and chief scientific officer at nference. “In combination with Valo’s digital-native drug discovery process and human-centric data platform, our collaboration will expedite biomedical discovery for those patient populations who have the most unmet clinical needs.”

Valo Health, Inc is leveraging artificial intelligence (AI) and advanced analytics to better learn from the patient experience to discover and develop better medicines at greater speed and scale. The company’s Opal Platform™ is a human-centric, AI-driven drug development engine that uses AI to identify and validate novel drug targets, using real-world data and human models to rapidly discover and develop small molecule therapies against those targets with more predictable safety and efficacy. Founded by Flagship Pioneering and headquartered in Lexington, Mass., Valo also has offices in New York, N.Y. and Tel Aviv, Israel. To learn more, visit valo​health​.com.

nference is unlocking the potential of healthcare data with Agentic AI, delivering real-world evidence, insights, and solutions informed by the most comprehensive multimodal data across all therapeutic areas. Our extensive de-identified, longitudinal data includes decades of clinical notes along with rich patient histories, vitals, lab tests, radiology images, digital pathology, genomics, and electrophysiology waveforms. Our federated data platform, comprised of premier healthcare organizations, enables advanced research and custom AI model development. With unprecedented access to data from over 40 million patient journeys, our partners can target discovery, accelerate clinical trial design, and optimize lifecycle management. Follow nference on LinkedIn. Visit us at www.nference.com.

nference:
Matthew Hurchik
mhurchik@nference.net

Valo Health and nference Announce Long-term Partnership to Accelerate Human-Centric Drug Discovery and Development

Retrospective analysis reveals no significant differences in comorbidities in narcolepsy patients treated vs. not treated with sodium oxybate

One third of patients taking immediate-release, twice-nightly sodium oxybate discontinued treatment, most often due to lack of efficacy; inability to wake up was most common reason for missing second nightly dose

DUBLIN, April 17, 2025 (GLOBE NEWSWIRE) -- Avadel Pharmaceuticals plc (Nasdaq: AVDL), a biopharmaceutical company focused on transforming medicines to transform lives, and nference, a health tech company dedicated to making biomedical data computable, today announced the publication of real-world data on comorbidities and treatment patterns of people with narcolepsy treated versus not treated with immediate-release sodium oxybate. The paper, titled “Characterization and Treatment Patterns of Patients Treated With Immediate-Release Sodium Oxybate for Narcolepsy: A Propensity-Matched Cohort Study,” was published online in the Journal of Clinical Neuroscience. 

A review of de-identified electronic health records (EHR) from patients at Mayo Clinic identified 4,387 individuals living with narcolepsy, of whom 351 had received immediate-release sodium oxybate treatment. This cohort of 351 patients with narcolepsy treated with sodium oxybate was age/sex matched with a cohort of 351 patients with narcolepsy without sodium oxybate treatment. The retrospective analysis was conducted through Mayo Clinic’s Clinical Data Analytics Platform, which leverages nference’s AI software to provide access to curated, deidentified electronic health data in a secure, privacy-protected environment. These types of data provide a more comprehensive view of patient information than claims data alone.

No differences between the sodium oxybate treated group and the matched cohort in the rates of the top 10 overall comorbidities (unadjusted analysis), except for idiopathic hypersomnia and fatigue. After adjusting the analysis to reduce the risk of a false positive result, there were no significant differences in the rates of comorbidities between the sodium oxybate cohort and the matched cohortIdiopathic hypersomnia was reported in 22.8% of the sodium oxybate treated group versus 33.0% of the matched cohort; as IH and narcolepsy are mutually exclusive disorders, these results reflect the frequent diagnostic change with repeat testing

The rate of hypertension in the sodium oxybate treated group was 21.1% compared to the matched cohort group of 21.4% (adjusted P>0.9)

The rate of coronary artery disease was 7.1% in both groups (adjusted P>0.9)

Additional findings from the cohort of 351 patients with narcolepsy treated with twice-nightly sodium oxybate revealed that:

Approximately 1/3 had documented clinical notes for discontinuation, with lack of efficacy being most common

Chart review confirmed instances of missing the second doseInability to wake up was the most frequently cited reasonNext-day consequences of the missed second dose (e.g., cataplexy, lower daytime alertness) were documented  

“In this real-world study of de-identified Mayo Clinic EHR data comparing patients treated with sodium oxybate to a matched narcolepsy cohort without sodium oxybate, we see comparable rates of comorbidities, including hypertension and coronary artery disease. Other relevant findings included high rates of insomnia in both groups (approximately 43%), reflecting the frequent disruptive nighttime sleep inherent in narcolepsy,” said Melissa Lipford, M.D., a neurologist at the Center for Sleep Medicine at Mayo Clinic and lead author of the published paper. “The high rate of idiopathic hypersomnia (IH) diagnosis underscores the challenges with distinguishing between narcolepsy and IH based upon current testing. These findings also revealed insights into challenges with middle-of-the-night sodium oxybate dosing and lessened efficacy when the second dose was omitted.”

“This is the second study for which we have collaborated with nference to generate real-world de-identified data from patients with narcolepsy,” said Jennifer Gudeman, Pharm.D., Senior Vice President, Medical and Clinical Affairs of Avadel. “Despite sodium oxybate being FDA approved for more than 20 years, these findings reflect the underutilization of sodium oxybate therapy, some of which may be due to the necessity of first-generation oxybates requiring chronic, middle-of-the-night dosing. These data provide further reassurance into the lack of a signal for sodium oxybate utilization and cardiovascular risk.”

About Avadel Pharmaceuticals plc
Avadel Pharmaceuticals plc (Nasdaq: AVDL) is a biopharmaceutical company focused on transforming medicines to transform lives. Our approach includes applying innovative solutions to the development of medications that address the challenges patients face with current treatment options. Avadel’s commercial product, LUMRYZ™, was approved by the U.S. Food & Drug Administration (FDA) as the first and only once-at-bedtime oxybate for the treatment of cataplexy or EDS in patients 7 years of age and older with narcolepsy. For more information, please visit www.avadel.com.

About nference
nference is unlocking the potential of healthcare data with AI, delivering real-world evidence, insights, and solutions informed by the most comprehensive multimodal data across all therapeutic areas. Our extensive de-identified, longitudinal data includes decades of clinical notes along with rich patient histories, vitals, lab tests, radiology images, digital pathology, genomics, and electrophysiology waveforms. Our federated data platform, comprised of premier healthcare organizations, including Banner Health, Duke Health, Emory Healthcare, Mayo Clinic, and Vanderbilt University Medical Center, enables advanced research and custom AI model development. With unprecedented access to data from over 40 million patient journeys, our partners can accelerate target discovery, optimize clinical trial design, and enhance lifecycle management. Follow nference on LinkedIn. Visit us at www.nference.com.

Avadel
Investor Contact:
Austin Murtagh
Precision AQ
Austin.Murtagh@precisionaq.com
(212) 698-8696

Media Contact:
Lesley Stanley
Real Chemistry
lestanley@realchemistry.com 
(609) 273-3162

nference
Media Contact:
Matt Hurchik
info@nference.net

Retrospective analysis reveals no significant differences in comorbidities in narcolepsy patients treated vs. not treated with sodium oxybate

Avadel and nference Announce Publication of Real-World Data on Sodium Oxybate Treatment Patterns in the Journal of Clinical Neuroscience

Real-world data study aims to improve treatment options for chronic lymphocytic leukemia and small lymphocytic lymphoma patients

CAMBRIDGE, Mass., April 16, 2024 – nference, a company dedicated to transforming healthcare by making biomedical data computable, today announced a collaboration with BeiGene, Ltd, a global oncology company that intends to change its name to BeOne Medicines Ltd., to unlock new insights in treating B-cell cancers. The collaboration will leverage nference’s proprietary Agentic AI platform to deepen understanding of chronic lymphocytic leukemia (CLL) and small lymphocytic lymphoma (SLL) treatment patterns.

B-cell cancers, including CLL and SLL, are a group of malignancies affecting lymphocytes, a type of white blood cell crucial to immune function. These cancers impact thousands, with CLL being the most common adult leukemia in the U.S. This retrospective descriptive analysis will review more than 700 patient charts to identify real-world treatment patterns.

“Through this collaboration with BeiGene, we aim to uncover valuable real-world insights into treatment patterns and outcomes, helping refine clinical practices,” said Dr. Venky Soundararajan, Co-founder and Chief Scientific Officer at nference. “Our goal is to generate a comprehensive view of real-world outcomes that enhances clinical decisions, leading to more effective, personalized care for patients with CLL, SLL, and other B-cell malignancies.”

About nference
nference is unlocking the potential of healthcare data with AI, delivering real-world evidence, insights, and solutions informed by the most comprehensive multimodal data across all therapeutic areas. Our extensive de-identified, longitudinal data includes decades of clinical notes along with rich patient histories, vitals, lab tests, radiology images, digital pathology, genomics, and electrophysiology waveforms. Our federated data platform, comprised of premier healthcare organizations, including Mayo Clinic, Duke Health, Banner Health, Vanderbilt University Medical Center, and Emory Healthcare, enables advanced research and custom AI model development. With unprecedented access to data from over 40 million patient journeys, our partners can accelerate target discovery, optimize clinical trial design, and enhance lifecycle management. Follow nference on LinkedIn. Visit us at www.nference.com.

nference and BeiGene Collaborate to Drive New B-Cell Cancer Research

Powered by nference’s advanced machine learning models, the nSights platform will help to contextualize Parabilis’ single arm clinical trial data and inform target ID and clinical biomarker identification.

CAMBRIDGE, Mass., Nov. 12, 2024 – nference today announced a strategic research and data science partnership with Parabilis Medicines, Inc. (“Parabilis”) focused on supporting the clinical development of Parabilis’ lead program, FOG-001, in colorectal cancer. This collaboration will provide Parabilis’ researchers with access to a vast repository of longitudinal, multimodal clinical data from millions of cancer patients sourced from top-tier medical institutions.

Powered by nference’s advanced machine learning models, the nSights platform will help to contextualize Parabilis’ single arm clinical trial data and inform target ID and clinical biomarker identification. The platform will help to accurately identify and characterize real world outcomes in patient cohorts that could benefit from Parabilis’ lead program, FOG-001, a beta-catenin inhibitor which is being investigated in a Phase 1/2 clinical trial for colorectal cancer, one of the most prevalent and challenging cancers worldwide.

“At nference, we are committed to advancing cancer care by harnessing AI and real-world patient journeys to unlock valuable insights that can drive better treatment outcomes,” said Dr. AJ Venkatakrishnan, SVP of Strategic AI Partnerships at nference.

“By leveraging our nSights platform and biomedical research capabilities, we aim to accelerate Parabilis’ groundbreaking work in developing Helicon™ therapeutics, offering new hope for patients with difficult-to-treat cancers,” said Aaron Mathias, VP of Business Development & Corporate Strategy at nference.

“We are excited about this collaboration with nference,” said Dr. Brandon Allgood, Chief Data Science Officer at Parabilis. “The nSights platform will enable us to tap into a large depth of real-world, multimodal clinical data, helping us identify optimal patient populations and improve the targeting of our programs. By combining advanced AI, robust computational methods, and a continuous learning system built on our growing data repository, we are creating a transformative platform that not only accelerates drug discovery and development but also increases the precision and success of our therapeutic programs.”

About Parabilis Medicines (Formerly FogPharma)
Parabilis Medicines™ is a clinical-stage biopharmaceutical company dedicated to creating extraordinary medicines for people living with cancer. Through its pioneering Helicon™ discovery platform, Parabilis is engineering precisely tuned, stabilized helical peptide therapeutics that have the potential to unlock a large number of traditionally undruggable targets. FOG-001, the company’s first-in-class TCF-blocking β-catenin inhibitor and lead clinical program, is being evaluated in a Phase 1/2 study for patients with colorectal cancer and other solid tumors and is proof of the applicability of the platform to address undruggable intracellular protein-protein targets. The company is additionally advancing a pipeline of other first-in-class programs that target proteins known to be relevant to numerous cancers but considered intractable with traditional drug modalities. The versatility of the Helicon approach allows for the discovery of multiple targeting mechanisms, including functional protein-protein interaction inhibitors, bifunctional degraders, and radioligand therapeutics. Parabilis is headquartered in Cambridge, Mass., and is well-capitalized, with more than $500 million raised to date from leading life sciences investors. For more information, please visit: www.parabilismed.com.


nference Establishes AI Research Partnership with Parabilis Medicines in Colorectal Cancer

Data demonstrated people with narcolepsy were significantly more likely to have sleep, mood and pain disorders

DUBLIN, Oct. 24, 2024 (GLOBE NEWSWIRE) -- Avadel Pharmaceuticals plc (Nasdaq: AVDL), a biopharmaceutical company focused on transforming medicines to transform lives, and nference, a health tech company dedicated to making biomedical data computable, today announced the publication of real-world data that identified the demographic characteristics and the top 20 most prevalent comorbidities of people living with narcolepsy.

The paper, titled “Demographic Characteristics and Comorbidities of Patients With Narcolepsy: A Propensity-Matched Cohort Study,” was published online in Sleep Advances. These real-world findings were previously presented at the American Neurological Association (ANA) Annual Meeting in October 2022.

Results describing demographic characteristics and the top 20 comorbidities were based on a review of deidentified electronic health data from more than 2,000 people with narcolepsy and 2,000 matched controls. The retrospective analysis was conducted through Mayo Clinic Platform, which leverages nference’s AI software to provide access to curated, deidentified electronic health data in a secure, privacy-protected environment. These types of data provide a more comprehensive view of patient information than claims data alone.

“This is the first real-world study in narcolepsy to use aggregate electronic health record data,” said Melissa Lipford, M.D., a neurologist at the Center for Sleep Medicine at Mayo Clinic and lead author of the published paper. “We found that people with narcolepsy were more likely to have psychiatric, sleep and pain disorders. Understanding which comorbid conditions are most common should help clinicians better understand the challenges faced by patients with narcolepsy and help them optimize the management of their symptoms with the most appropriate treatment.” 

“We were proud to collaborate with Mayo Clinic Platform and nference to generate these real-world deidentified data from patients seen at the Mayo Clinic Health System. Narcolepsy is a chronic and complex neurological disorder and understanding the most prevalent comorbidities increased in this patient population may help to inform optimal management,” said Jennifer Gudeman, Pharm.D., Senior Vice President, Medical and Clinical Affairs of Avadel. “In contrast to claims-based studies, cardiovascular disease was not among the top 20 co-morbidities found to be increased in the narcolepsy cohort compared to the matched cohort.”

About Avadel Pharmaceuticals plc
Avadel Pharmaceuticals plc (Nasdaq: AVDL) is a biopharmaceutical company focused on transforming medicines to transform lives. Our approach includes applying innovative solutions to the development of medications that address the challenges patients face with current treatment options. Avadel’s commercial product, LUMRYZ, was approved by the U.S. Food & Drug Administration (FDA) as the first and only once-at-bedtime oxybate for the treatment of cataplexy or EDS in patients seven years and older with narcolepsy. For more information, please visit www.avadel.com.

Cautionary Disclosure Regarding Forward-Looking Statements
This press release includes “forward-looking statements” within the meaning of Section 27A of the Securities Act of 1933 and Section 21E of the Securities Exchange Act of 1934. These forward-looking statements relate to our future expectations, beliefs, plans, strategies, objectives, results, conditions, financial performance, prospects or other events. Such forward-looking statements include, but are not limited to, expectations regarding the potential impact of the study on helping clinicians optimize the management of patients’ symptoms with the most appropriate treatment. In some cases, forward-looking statements can be identified by the use of words such as “will,” “may,” “could,” “believe,” “expect,” “look forward,” “on track,” “guidance,” “anticipate,” “estimate,” “project,” “next steps” and similar expressions and the negatives thereof (if applicable).

The Company’s forward-looking statements are based on estimates and assumptions that are made within the bounds of our knowledge of our business and operations and that we consider reasonable. However, the Company’s business and operations are subject to significant risks, and, as a result, there can be no assurance that actual results and the results of the company’s business and operations will not differ materially from the results contemplated in such forward-looking statements. Factors that could cause actual results to differ from expectations in the Company’s forward-looking statements include the risks and uncertainties described in the “Risk Factors” section of Part I, Item 1A of the Company’s Annual Report on Form 10-K for the year ended December 31, 2023, which was filed with the Securities and Exchange Commission (SEC) on February 29, 2024, and subsequent SEC filings. Forward-looking statements speak only as of the date they are made and are not guarantees of future performance. Accordingly, you should not place undue reliance on forward-looking statements. The Company does not undertake any obligation to publicly update or revise our forward-looking statements, except as required by law.

Avadel
Investor Contact:
Courtney Mogerley
Precision AQ
Courtney.Mogerley@precisionAQ.com
(212) 698-8687

nference
Media Contact:
Andrea Sampson
President/CEO, Sampson Public Relations Group
asampson@sampsonprgroup.com

Avadel Pharmaceuticals and nference Announce Publication of Real-World Data in Sleep Advances

Collaboration aims to identify personalized treatment approaches and improve care for patients with IBD

nference today announced a strategic research alliance with Takeda aimed at harnessing artificial intelligence (AI) to optimize patient care in inflammatory bowel disease (IBD), a chronic gastrointestinal disorder affecting millions globally.

The collaboration, known as Project SUCCINCT (Systematic UC & Crohn’s INformatics Clinical Toolkit), will utilize nference’s advanced machine learning models to analyze de-identified electronic health records. By harnessing AI to identify patients who could benefit from advanced medical interventions, the initiative aims to personalize treatment options and improve care for those living with IBD.

“Takeda is at the forefront of gastroenterology, especially in the area of IBD, and we are honored to collaborate with them on this critical research,” said Maulik Nanavaty, President of Ventures at nference & CEO at Anumana. “Project SUCCINCT seeks to fill a void by more effectively managing treatment of patients early in their IBD journey, which persists as an area of significant unmet medical need due to its intricate and diverse nature. This initiative will leverage our state-of-the-art, AI-enabled platform to unlock previously undiscovered insights and information that will help facilitate more precise and targeted interventions with the disease.”

“AI-driven innovation represents a promising new frontier in medicine. We’re pleased to join forces with nference on this vital research endeavor seeking to improve the diagnostic and treatment journey for patients around the world living with IBD,” said Vijay Yajnik, MD, PhD, Vice President, Head of U.S. Medical in Gastroenterology at Takeda, a biopharmaceutical leader headquartered in Japan with a global hub in Cambridge, Mass.“ By harnessing AI, we can push beyond the boundaries of what is possible today to empower healthcare providers with information to help tailor treatment selection for patients, precisely when needed.”

nference's federated AI platform, nSights, introduced in 2021, provides researchers with access to insights from a curated, de-identified dataset spanning all therapeutic areas, including gastroenterology, cardiology, oncology, metabolic diseases, immunology, and infectious diseases.

nference is unlocking the potential of healthcare data with AI, delivering real-world evidence, insights, and solutions informed by the most comprehensive multimodal data across all therapeutic areas. Our extensive de-identified, longitudinal data includes decades of clinical notes along with rich patient histories, vitals, lab tests, radiology images, digital pathology, genomics, and electrophysiology waveforms. Our federated data platform, comprised of premier healthcare organizations, including Mayo Clinic, Duke Health, Banner Health, Vanderbilt University Medical Center, and Emory Healthcare, enables advanced research and custom AI model development. With unprecedented access to data from over 40 million patient journeys, our partners can accelerate target discovery, optimize clinical trial design, and enhance lifecycle management. Follow nference on LinkedIn. Visit us at www.nference.com.


Andrea Sampson
President/CEO, Sampson Public Relations Group
asampson@sampsonprgroup.com

Based on pioneering research from Mayo Clinic, ECG-AI LEF aims to aid physicians in identifying low ejection fraction in patients at risk of heart failure.

CAMBRIDGE, Mass. – Oct. 2, 2023 – Anumana, Inc., a leading AI-driven health technology and nference portfolio company working in collaboration with Mayo Clinic, today announced U.S. Food and Drug Administration (FDA) 510(k) clearance for ECG-AI LEF, a breakthrough artificial intelligence (AI)-powered medical device to detect low ejection fraction (LEF) in patients at risk of heart failure.

LEF, or a weak heart pump, is a significant, at times asymptomatic, and commonly undiagnosed indicator of heart failure.1 The increasing prevalence of heart failure and its associated morbidity, mortality, rehospitalizations, and societal costs2,3 underscores the need to identify and manage patients with LEF.

“Anumana’s ECG-AI LEF fills an important unmet need – the lack of an easily accessible point-of-care, noninvasive, and inexpensive tool to screen for a weak heart pump,” said Paul Friedman, M.D., chair of the Department of Cardiovascular Medicine at Mayo Clinic in Rochester, Minn. and chair of Anumana’s Board of Advisors. “It allows identification of otherwise hidden disease, for which many effective, lifesaving treatments are available – once the presence of the disease is known.”

Developed in partnership with Mayo Clinic, Anumana’s ECG-AI LEF is an innovative software-as-a-medical device (SaMD) designed to screen for LEF in adults at risk for heart failure using data from a routine 12-lead electrocardiogram (ECG), a rapid and common test used in both primary and specialty care. Based on pioneering research from Mayo Clinic,4 the algorithm has been developed utilizing over 100,000 ECG and echocardiogram data pairs from unique patients and has been clinically tested in more than 25 studies involving more than 40,000 patients in the U.S. and internationally.5

Anumana’s ECG-AI LEF was clinically validated in a multi-site, retrospective clinical study of 16,000 racially diverse patients, achieving its primary endpoint with an 84.5% sensitivity and 83.6% specificity.6 ECG-AI LEF achieved an AUROC7 of 0.932, demonstrating an ability to differentiate between LEF and ejection fraction (EF) >40% extremely well (a score ≥0.90 is considered excellent8) and better than most tests currently used in heart failure standard of care.9

Additionally, the EAGLE study, a groundbreaking prospective, randomized, controlled clinical trial by Mayo Clinic evaluated the use of an investigational version of the algorithm in routine clinical care of 22,641 adults by 120 primary care teams from 45 clinics or hospitals, demonstrating that ECG-AI LEF implementation improved clinician’s ability to diagnosis of LEF by 31% versus standard of care without increasing the overall rate of echocardiogram usage.10

ECG-AI LEF is one of Anumana’s broad pipeline of algorithms, including three additional FDA breakthrough device designation algorithms (pulmonary hypertension, cardiac amyloidosis, and hyperkalemia), and is founded on more than six years of pioneering ECG-AI research and development at Mayo Clinic, including nearly 100 peer-reviewed publications to date.

“Anumana was established in 2021 by nference in partnership with Mayo Clinic to unlock the electrical language of the heart through deep learning and improve disease diagnosis and patient care,” said Murali Aravamudan, co-founder and CEO of Anumana and nference. “In the short time of two years we have secured multiple FDA breakthrough device designations, entered multi-year agreements with three pharma partners, successfully established two new medical procedure codes for ECG AI technology, and now achieved our first FDA breakthrough medical device clearance. This is a significant milestone, and we are excited about the next phase of the journey, deploying our technology in the U.S. and globally to empower clinicians and enhance real-world clinical care.”

Anumana is focused on driving fast-paced adoption of the new ECG-AI category, clinically developing and commercializing its novel technologies in healthcare. The newly FDA-cleared ECG-AI LEF can be easily integrated with various ECG information management systems or directly with a patient’s electronic health record via Anumana’s web-based ECG Viewer to support clinical decision-making.

Anumana spearheaded the effort to bring reimbursement to ECG-AI, receiving approval for two Category III CPT® codes from the American Medical Association in 2022. These codes are now available and designed to facilitate the use, adoption, and potential reimbursement of emerging technologies in clinical workflows.

To learn more about ECG-AI LEF and schedule a demo, visit us at ECG-AI LEF.

Anumana is a leading AI-driven health technology company leveraging cutting-edge AI and industry-leading translational science to unlock the electrical language of the heart as never before. The company was founded by nference in partnership with Mayo Clinic to leverage the clinical and technical expertise of both organizations to develop innovative ECG-AI technology from an investigational resource to a clinically meaningful tool for clinicians to advance patient care. Anumana’s software-as-a-medical device (SaMD) solutions aim to detect hidden diseases using ECG-AI algorithms to enhance and improve interventional procedures through real-time AI insights.

Anumana was named one of Fierce MedTech’s Fierce 15 companies for 2022. Follow Anumana at anumana.ai and on LinkedIn and Twitter.

Dr. Friedman and Mayo Clinic have a financial interest in the technology referenced in this press release. Mayo Clinic will use any revenue it receives to support its not-for-profit mission in patient care, education, and research.

1.     Jaskanwal D Sara, Takumi Toya, Riad Taher, Amir Lerman, Bernard J Gersh, Nandan S Anavekar. Asymptomatic Left Ventricle Systolic Dysfunction. European Cardiology Review 2020, 15:e13; https://doi.org/10.15420/ecr.2019.14.

2.     Tsao, C.W., Aday, A.W., Almarzooq Z.I., et al. Heart Disease and Stroke Statistics—2023 Update: A Report From the American Heart Association. Circulation Vol. 147, No. 8; https://www.ahajournals.org/doi/10.1161/CIR.0000000000001123#d330256e1.

3.     Khazanie P, Allen LA. Systematizing Heart Failure Population Health. Heart Fail Clin. 2020 Oct;16(4):457-466. Doi: 10.1016/j.hfc.2020.06.006. Epub 2020 Jul 21. PMID: 32888640; PMCID: PMC7737815; https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7737815/.

4.     Attia, Z.I., Kapa, S., Lopez-Jimenez, F. et al. Screening for cardiac contractile dysfunction using an artificial intelligence–enabled electrocardiogram. Nat Med 25, 70–74 (2019); https://doi.org/10.1038/s41591-018-0240-2.

5.     Anumana data on file and published studies.

6.     Anumana data on file (NCT04963218).

7.     Area Under the Receiving Operating Characteristic curve (AUROC) is a performance metric commonly used to evaluate the ability of a model to distinguish between two classes. An AUROC of 0.5 suggests that the model is no better than random and an AUROC of 1.0 indicates a perfect classifier; https://en.wikipedia.org/wiki/Receiver_operating_characteristic.

Featured News

April 16, 2026