Data Creation
Digitizing pathology and generating sequencing
Pathology
Historically, pathology slides are collected and stored in physical form. Though our partners have 10M+ physical pathology slides collected over decades, digitization is the first step required to enable downstream analysis and applications, including training AI models to detect pathologic features. We use high-throughput scanning systems that are state-of-the-art in both hardware and software, allowing us to digitize archival slides.
Selecting drug target-disease pairs to try in the clinic can be highly subjective and subject-matter driven.
Sequencing
Sequencing has already been clinically impactful for disease areas such as oncology. We provide clinical-grade sequencing for patients at our partner medical centers. Unlike others that focus on sequencing panels of genes already known to be clinically relevant, we prioritize data generation through whole exome and transcriptome sequencing to support platform development and discovery of novel molecular phenotypes associated with diseases across therapeutic areas.
Selecting drug target-disease pairs to try in the clinic can be highly subjective and subject-matter driven.
Augmented Curation
Making healthcare data consumable
By transforming unstructured clinical notes data into structured form through the extraction of key sentiments and relationships from text, our “augmented curation” uses neural networks to effectively automaticlaly transform unstructured text from the EMR into labeled patient datasets.
Data Harmonization
Making healthcare data consumable
Due to the long and varied history of EMRs, even the structured data is complex. For example, the same lab test may be represented with multiple distinct codes and use different units of measurement. We use software-aided processes to transform this semi-structured patient data consisting of distinct data points into common unified data variables, which can then be consumed for downstream applications and analyses.
Triangulating your data
Improving your data connectivity
Triangulation with public and proprietary data
Integrating additional data sources with labeled, curated and harmonized EMR data can strengthen the insights derived from downstream data analysis. This data includes biomedical literature (ex. PubMed), clinical trials (ex. clinicaltrials.gov) and molecular data (ex. Gene Expression Omnibus).
State of the art algorithms
The labeled, curated and harmonized EMR data serves as a starting point that enables training state-of-the-art AI algorithms. We develop these algorithms as solutions to some of the major challenges in healthcare, including early detection and diagnosis of disease, identification of biomarkers for disease progression and more.
We integrate your processed EMR data with additional public and proprietary data sources to provide additional insights through the connections made across additional data sources and types.
Compute Solutions
The most secure storage available for healthcare
We provide differentiated compute and storage solutions that address the unique needs of healthcare data, with improved security and performance advantages over traditional providers.
NFERENCE PRODUCTS
Software product access
Medical centers we partner with have access to nference developed software built on EMR data
Nfer Clinical NSights Software | Our EMR Data Product
Powered by the largest set of deep, longitudinal de-identified clinical data in the world, this suite of sophisticated applications and tools unlocks the ability to realize insights from both structured and unstructured records of more than 11M+ patients from our health system partners, including the Mayo Clinic and Duke Health.
Learn more
© 2024 nference, Inc. All rights reserved.