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.
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.
ASCO 2019 Plenary
ACA Medicaid expansion eliminated racial disparities in timely cancer treatment — presented at plenary, covered by NPR, CNBC, and The Cancer Letter.
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.
Real-World Evidence from 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.
Advancing Breast Cancer Research in Japan Using EHR-Derived Real-World Data (ISPOR 2025 Poster)
Characterization of a novel Japanese breast cancer cohort derived from deidentified EHRs with technology-enabled abstraction in Japanese-language clinical documentation — demonstrating cross-country RWE capability.
Nature Scientific Reports
HIV vaccination campaign strategy for South Africa.
Insights
Thought leadership and analysis on health economics, AI in medicine, and evidence-based policy. Previously published as a blog — now curated as a collection of perspectives.
- ‘The Last of Us’ Epidemiologists: How to Survive Zombies
When a zombie apocalypse hits, who’s left to calculate how to survive? In HBO’s The Last of Us, society… - MPOX Vaccine Dose-Sparing Strategy Evaluated
Our math model found tradeoffs in MPOX vaccination strategies and supports smaller doses to protect a larger population at risk… - Real World Accuracy of Rapid Antigen vs PCR Tests for Infectious Omicron
Real world data from occupational safety programs revealed most Omicron cases were infectious for several days before being detectable by rapid antigen tests. - Better Health Policy for Successful Live Theater in COVID-19
The best health and economic policies for safe, successful, live theater in 2021-2023 will be dynamic – adapting protocols quickly… - Major League Sports Lessons in COVID-19
It’s been an honor to serve and learn as a member of the COVID-19 Sports and Society Working Group, co-chaired… - Fall 2020 Scientific Speaking
Effective scientific communication is really hard This summer I met a few cast members from Saturday Night Live, including the…
Full Publication List
Peer-Reviewed Research
100+ publications across health economics, epidemiology, AI/ML, and oncology. Citation metrics and full list auto-updated via Google Scholar:
Op-Eds & Public Writing
- USA Today: “Schools need to reopen now. Here’s how to do it safely” (July 2020)
- Additional op-eds and public-facing articles as published