Background: FOLFIRINOX is a cornerstone regimen for eligible patients with pancreatic ductal adenocarcinoma (PDAC), but its clinical benefit is limited by substantial toxicity and frequent dose modification. In real-world practice, dose modifications are often individualized, and the clinical factors associated with these decisions remain incompletely characterized. Objective: To develop and evaluate an electronic medical record (EMR)-based machine-learning framework for modeling cycle-specific FOLFIRINOX dose modification decisions in patients with PDAC. Methods: We included patients with PDAC who received FOLFIRINOX at UCSF oncology clinics between November 2011 and December 2023. Predictors included demographic, clinical, laboratory, and treatment variables derived from the EMR. Logistic regression, random forest, and XGBoost models were trained using group-based 5-fold cross-validation to predict cycle-specific dose modifications for 5-fluorouracil, irinotecan, and oxaliplatin. Model performance was evaluated using area under the receiver operating characteristic curve. Results: The cohort included 514 patients receiving FOLFIRINOX across 5,041 treatment cycles. The mean age was 59 years, 60% of patients were White, 41% had a history of smoking, and patients received a median of 6 chemotherapy cycles. More than 60% of patients required at least one dose modification during treatment. XGBoost demonstrated the highest performance across component drugs, with AUCs ranging from 0.53 to 0.70. Clinically plausible predictors of irinotecan and oxaliplatin dose modification included hepatic and renal function markers, cumulative drug exposure, treatment-related symptoms, and demographic or behavioral characteristics. Conclusion: We developed an EMR-based machine-learning framework to model real-world FOLFIRINOX dose modification and identified clinically plausible, routinely available predictors, particularly for irinotecan and oxaliplatin. Variable model performance suggests that dosing decisions are only partially captured by structured EMR data, highlighting both the limitations of current data-driven approaches and clinical domains where ML-based models may support individualized dosing and toxicity surveillance. Future informatics efforts should incorporate dose-modification rationale, patient-reported and functional outcomes, and validation across diverse practice settings.

Atul Butte reports being a co-founder and consultant to Personalis and NuMedii; and a consultant or advisor to NIH, JAMA, Mango Tree Corporation, Samsung, Geisinger Health, Washington University in Saint Louis, and the University of Utah, and previously to 10x Genomics, Helix, Pathway Genomics, and Verinata (Illumina). He has served on paid advisory boards or panels for Regenstrief Institute, Gerson Lehman Group, AlphaSights, Covance, Novartis, Genentech, Merck, and Roche. He is a shareholder in Personalis and NuMedii, and a minor shareholder in multiple publicly traded companies, including Apple, Meta (Facebook), Alphabet (Google), Microsoft, Amazon, NVIDIA, AMD, Snap, 10x Genomics, Doximity, Regeneron, Sanofi, Pfizer, Royalty Pharma, Moderna, BioNTech, Invitae, Pacific Biosciences, Editas Medicine, Eli Lilly, Nuna Health, Assay Depot (Scientist.com), Vet24seven, Snowflake, and Sophia Genetics. He has received honoraria and travel reimbursement for invited talks from multiple organizations, including Johnson and Johnson, Roche, Genentech, Pfizer, Merck, Eli Lilly, Takeda, Varian, Mars, Siemens, Optum, Abbott, Celgene, AstraZeneca, AbbVie, Westat, Applied Research Works, Acentrus, and ALDA, as well as academic institutions and foundations. He receives royalty payments through Stanford University for intellectual property licensed to NuMedii and Personalis. His research has been funded by NIH, FDA, Peraton, the Chan Zuckerberg Initiative, the Barbara and Gerson Bakar Foundation, Genentech, Johnson and Johnson, the Robert Wood Johnson Foundation, the Leon Lowenstein Foundation, and the Intervalien Foundation, and previously by the March of Dimes, Juvenile Diabetes Research Foundation, the California Governor Office of Planning and Research, the California Institute for Regenerative Medicine, LOreal, and Progenity. None of these entities had any role in the design, conduct, or reporting of this study. Travis Zack is Chief Medical Officer of OpenEvidence, a medical AI platform. Dr. Atul Butte is deceased. Conflict of interest disclosures are based on the most recent information available. Travis Zack is Chief Medical Officer of OpenEvidence, a medical AI platform.

This study did not receive any funding.

I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.

Yes

The details of the IRB/oversight body that provided approval or exemption for the research described are given below:

Data used in this study were drawn from UCSF Information Commons, including de-identified UCSF Health electronic health record data made available for research use through UCSF governed research data infrastructure. Access to these data is governed by UCSF data access, privacy, compliance, and institutional review processes. Research use of de-identified UCSF Information Commons data is considered non-human subjects research and does not require study-specific IRB approval. No direct patient identifiers were available to the study team.

I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.

Yes

I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).

Yes

I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable.

Yes

The data that support the findings of this study are derived from electronic health records and are not publicly available due to patient privacy and institutional restrictions. Access may be considered upon reasonable request and with appropriate institutional approvals.