Development of Machine Learning Systems to Predict Cancer-Related Symptoms With Validation Across a Health Care System
Open Access
- 1 September 2025
- journal article
- Published by American Society of Clinical Oncology (ASCO) in JCO Clinical Cancer Informatics
- Vol. 9 (9) , e2500073
Abstract
PURPOSE: Cancer and its treatment cause symptoms. In this study, we aimed to develop machine learning (ML) systems that predict future symptom deterioration among people receiving treatment for cancer and then validate the systems in a simulated deployment across an entire health care system. METHODS: We trained and tested ML systems that predict a deterioration in nine patient-reported symptoms within 30 days after treatments for aerodigestive cancers, using internal electronic health record (EHR) data at Princess Margaret Cancer Centre (3,229 patients; 20,267 treatments). The primary performance metric was the area under the receiver operating characteristic curve (AUROC). The best-performing systems in the held-out internal test set were then externally validated across 82 cancer centers in Ontario (12,079 patients; 77,003 treatments) by adapting techniques from meta-analysis. RESULTS: The best ML systems predicted symptom deterioration with AUROCs ranging from 0.66 (95% CI, 0.63 to 0.69) for dyspnea to 0.73 (95% CI, 0.71 to 0.75) for drowsiness in the internal test cohort. Treatments flagged as high-risk were significantly associated with future symptom deterioration (odds ratios [ORs], 2.53-6.56; all P < .001) and emergency department visits for dyspnea (OR, 1.85; P = .008), depression (OR, 1.84; P = .04), and anxiety (OR, 2.66; P < .001). In the external validation cohort, the AUROCs for different symptoms meta-analyzed across centers ranged from 0.67 (95% CI, 0.66 to 0.68) to 0.73 (95% CI, 0.72 to 0.74). Performance across centers displayed significant heterogeneity for six of nine symptoms (I 2 , 46.4%-66.9%; P = .004 for dyspnea, P < .001 for the rest). CONCLUSION: ML can predict future symptoms among people with cancer from routine EHR data, which could guide personalized interventions. Heterogeneous performance across centers must be considered when systems are deployed across a health care system.Keywords
This publication has 39 references indexed in Scilit:
- Health system-scale language models are all-purpose prediction enginesNature, 2023
- Factors Associated With Variability in the Performance of a Proprietary Sepsis Prediction Model Across 9 Networked Hospitals in the USJAMA Internal Medicine, 2023
- External Validation of a Widely Implemented Proprietary Sepsis Prediction Model in Hospitalized PatientsJAMA Internal Medicine, 2021
- Artificial neural networks for simultaneously predicting the risk of multiple co‐occurring symptoms among patients with cancerCancer Medicine, 2020
- The Integrated Calibration Index (ICI) and related metrics for quantifying the calibration of logistic regression modelsStatistics in Medicine, 2019
- Long-Term and Latent Side Effects of Specific Cancer TypesMedical Clinics of North America, 2017
- The Edmonton Symptom Assessment System 25 Years Later: Past, Present, and Future DevelopmentsJournal of Pain and Symptom Management, 2017
- Minimal clinically important differences in the Edmonton Symptom Assessment Scale in cancer patients: A prospective, multicenter studyCancer, 2015
- The symptom burden of cancer: Evidence for a core set of cancer‐related and treatment‐related symptoms from the Eastern Cooperative Oncology Group Symptom Outcomes and Practice Patterns studyCancer, 2013
- A Single Set of Numerical Cutpoints to Define Moderate and Severe Symptoms for the Edmonton Symptom Assessment SystemJournal of Pain and Symptom Management, 2010