Alternative data datasets
Browse by provider, category, marketplace, access, delivery and license
A healthcare claims dataset containing detailed records on patients, care providers, and the medical services rendered.
View source information and access options.
View source information and access options.
View source information and access options.
An AI-driven solution that automates and refines the process of matching patients to suitable clinical trials.
Track healthy organs in medical scans to improve cancer treatment
View source information and access options.
A Snowflake-native solution that converts patient records into population health indicators, quality reporting measures, and AI-generated clinical intelligence.
View source information and access options.
View source information and access options.
View source information and access options.
View source information and access options.
View source information and access options.
Carefully selected patient data collections enhanced with key clinical context, obtained from the BCDA platform.
A broad resource designed to assess and examine the clinical trial environment across therapeutic areas and study types.
An organized compilation of records intended to review and interpret the global clinical trials ecosystem.
A detailed offering aimed at benchmarking and investigating clinical research activities across regions and phases.
Country-level healthcare claims platform that traces patient pathways and results across hundreds of millions of records.
Research and intelligence covering pharmaceutical products, clinical trials, patent filings and regulatory progress.
Population-level data on people, schooling, migration patterns, public health, labor markets, quality of life, and related areas.
Thirteen years of structured analytics on Exchange plan pricing, coverage features, and benefit mappings.
Information on more than 95,000 healthcare providers in Canada's three most populous provinces, refreshed on a weekly basis.
Up-to-date CDC records prepared for analytical use.
Maintained CMS Medicare and Medicaid information packaged for analytics and refreshed on an ongoing basis.
Research-oriented CMS data sourced from cms.data.gov/data-research with records extending back to 2001.
Medicaid claim expenditures attributed at the provider level using National Provider Identifiers, covering more than 200 million claims across over fifty states from 2018 onward.
Relational provider information refreshed weekly with multiple attributes per record.
Complete listing of CMS prior authorization requirements and timelines organized by entity and linked to Federal Register sources.
Over twenty million adverse event reports covering drugs and medical devices are consolidated, refreshed daily, and structured for analysis.
Normalized extracts from the FDA FAERS system enable evaluation of drug adverse event reports and related safety signals.
Structured records of FDA medical device adverse event reports, formatted to support safety monitoring and risk evaluation workflows.
Three decades of measurements covering heavy metals, pesticide residues, and nutritional content in roughly 280 food items available in the United States, prepped for analysis.
Continuously refreshed, query-ready dataset covering county employment figures, medically underserved regions, and Federally Qualified Health Center locations.
Directory of American healthcare practitioners that has been verified, duplicates removed, registered in PECOS, checked against the OIG exclusion list, supplemented with location data, and prepared for FHIR compatibility.
View source information and access options.
View source information and access options.
Principal economic indicators and statistical products covering the early 1980s baseline.
Mid-1980s socio-economic data focused on household-level measurements and income distributions.
Population dynamics, public health metrics, and broader social welfare indicators from the early-to-mid 1980s.
Commercial healthcare dataset profiling practitioners, care sites, organizational relationships and medical procedures.
A publication covering the field of orthodontics and dentofacial orthopedics.
A curated, well-organized collection of documents formatted for straightforward ingestion into retrieval-augmented generation systems.
Content structured to serve as a retrieval-augmented knowledge foundation for a domain-specific research tool.
Source material for developing or refining language models aimed at answering questions about past public health issues, disease patterns, and the history of medicine.
A collection examining surgical practice during a period of technological and medical advancement.
Records documenting medical practices and treatments at the height of the Victorian period.
Materials on public health, sanitation, and disease patterns in Canada during the early 1900s.
A leading Canadian medical publication covering the years 1911 through 1930.
A prominent trade publication serving pharmacists across the United Kingdom.
A curated collection drawn from five leading dental journals, comprising 95,763 processed rows prepared for machine learning, with bias reviews and source lineage documentation.
Pre-1930 textual material on genetics and inheritance that has been cleaned and formatted for machine learning use.
Organized text collection well suited for retrieval-augmented generation, longitudinal language modeling, and dialogue-based data exploration.
Curated and audited corpus drawing from two leading obstetrics and gynecology journals, formatted for artificial intelligence workflows.
Curated historical clinical text that has been cleaned and checked for bias to support better model reasoning and factual grounding.
A leading peer-reviewed publication focused on otolaryngology, covering ear, nose, and throat clinical practice.
Structured corpus optimized for retrieval-augmented generation and semantic similarity tasks, featuring duplicate removal, complete data fields, and substantial record counts.
Refined surgical records with documented bias review, released under public domain terms and available through a 30-day evaluation access.
Ready-to-use collection suited for retrieval-augmented question answering on historical medical topics.
Dataset focused on early-stage multiple sclerosis studies and clinical neurology.
Well-suited for embedding-based search and retrieval-augmented generation across a unified historical text collection.