Machine Learning Research Fellow (Health Economics Dataset)

We're looking for a researcher to produce an original, TRIPOD+AI-compliant finding using the Medical Expenditure Panel Survey (MEPS), a nationally representative US health-economics dataset. This is an invited submission to JPMedAI (Journal of Precision Medicine and Artificial Intelligence), a new, open-access, peer-reviewed journal currently assembling its inaugural issue. Article processing charges are waived during this launch phase, meaning there is no cost to you to publish. This suits researchers who value a genuine, citable publication and hands-on methodological support as much as (or more than) the cash fee, which reflects that context. THE DATASET - Training dataset: Medical Expenditure Panel Survey (MEPS), AHRQ. Household Component, ≈10,000–35,000 individuals per panel-year, pooled files available back to 1996, with linked Medical Conditions and Prescribed Medicines files. - External validation: Temporal external validation using non-overlapping, more recent MEPS panel years (e.g. train 2016–2019, validate 2021–2023). - The angle: something in identifying individuals or population segments at high risk of costly, potentially avoidable health events. The rationale is moving past standard retrospective cost-trend reporting toward a prospective, explainable model useful for care-management targeting. We have a specific direction in mind, but haven't fixed it here. Propose your own take in your application. GENERAL EXPECTATIONS FOR THE RESEARCH FELLOW - Use a large, freely or quick-access public dataset for model development (training) and at least one genuinely independent dataset for external validation. - Report according to TRIPOD+AI (2024), the AI/ML-specific extension of TRIPOD, citing the original TRIPOD statement as the foundational reference. Grad-CAM should be used for convolutional-image attention-map / saliency-based explainability; SHAP or an equivalent feature-attribution method should be used otherwise. - Report discrimination (AUC/C-index, with time-dependent AUC for survival endpoints), calibration (plots, not just calibration slope/intercept in text), and decision-curve analysis against a clinically meaningful comparator (an existing risk score, guideline threshold, or current standard practice), not against "no model" alone. - Explicitly test and report subgroup performance (by sex, race/ethnicity, socioeconomic proxy, or income/insurance type) rather than a single pooled metric. - Before finalising the research question, complete a focused, dated literature search on the exact proposed endpoint/model combination and document the closest 2–3 prior papers and the specific point of difference. - Write up the work as a scientific manuscript, 3,000–6,000 words, up to 8 figures, in this structure: Abstract (≤300 words, structured), Keywords (3–6), Introduction, Methods (including ethics-approval statement if applicable), Results, Discussion, Conclusion, References (Vancouver style). JPMedAI provides free academic writing support to any author who needs it, separate from the project-specific editorial guidance described below. WHAT YOU'LL GET - An invited submission pathway to JPMedAI, a new, open-access, peer-reviewed journal building its inaugural issue. Early submissions get direct editorial engagement, not a slot in a large backlog. - Hands-on editorial and methodological support, beyond the journal's own free academic-writing service noted above. We'll personally guide you on statistical reporting, clinical framing, and endpoint interpretation to bring your first draft to publishable, TRIPOD+AI-compliant standard. - Named byline, full citation credit, ORCID-compatible publication metadata, and a PDF for your portfolio, CV, or dissertation appendix. - A $100 honorarium on completion/acceptance. The primary value on offer here is the invited, mentored publication itself. - First-mover advantage: be among the first researchers to publish on this specific dataset and question. WHAT THIS IS NOT - This is not content writing. You are not ghost-writing. You are an independent researcher producing original work under your own name. - The peer-review and editorial process exists to enforce scientific governance standards, not to change your conclusions or direct your inquiry. IDEAL CANDIDATE PROFILE We expect interest from two kinds of applicants, and both are genuinely welcome: - Early-career researchers (PhD students, postdocs, recent graduates) who already have at least one preprint or publication and want a fast, well-supported second one. - Strong ML / data science practitioners without a formal clinical or health-publication track record who want to break into applied health research. For this group, our editorial support specifically includes guidance on clinical framing, endpoint selection, and TRIPOD+AI reporting norms. Also useful (but not required): background in health economics, biostatistics, or survey-weighted analysis (MEPS uses a complex survey design of strata/PSU/weights); familiarity with calibration plots, decision-curve analysis, or explainability methods. Sharing workload with one or two collaborators who will be coauthors is welcome. IF YOU ARE INTERESTED Answer the questions below and submit with your cover letter.