Research & Writing

Peer-reviewed science, AI methodology, and public-facing writing. Over 100 publications, h-index 21, and 1,500+ citations.

Featured Work

The VALID Framework (JCO Clinical Cancer Informatics, 2025)

Validation of Accuracy for LLM/ML-Extracted Information and Data — a comprehensive framework for evaluating the quality of clinical data extracted by large language models, advancing industry standards for trustworthy AI-powered evidence generation in oncology.

Real-World Evidence from EHR in Germany (BMC Cancer, 2026)

Representativeness analysis and mortality endpoint validation in EHR-derived oncology cohorts from Germany, demonstrating 87.7% sensitivity and 91.7% specificity for vital status classification. First peer-reviewed validation of German EHR oncology data.

Approach to Machine Learning for Extraction of Real-World Data Variables from EHRs (Frontiers in Pharmacology, 2023)

Describes the general approach for applied NLP and ML methods used to extract data from unstructured EHR documents in oncology, developing 10 ML models outputting 20 distinct RWD variables. One of Blythe’s most cited first-author papers.

USA Today Op-Ed: “Schools need to reopen now. Here’s how to do it safely” (July 2020)

A public-facing policy argument for school reopening based on epidemiological evidence, published at the height of the pandemic debate. Demonstrates Blythe’s ability to translate complex science for a mass audience.

Nature Scientific Reports

HIV vaccination campaign strategy for South Africa.

ASCO Plenary Session

ACA Medicaid expansion eliminated racial disparities in timely cancer treatment — presented at plenary, covered by NPR, CNBC, and The Cancer Letter.

Peer-Reviewed Research

100+ publications across health economics, epidemiology, AI/ML, RWE, oncology, HIV and more. Citation metrics and full list auto-updated via Google Scholar:

View Google Scholar Profile