Machine Learning Risk Stratification for Older Breast Cancer Survivors: Clinical Care Implications
- 16 July 2025
- journal article
- Published by Wiley in Health Services Research
- Vol. 61 (2) , e70005
Abstract
Objective: To develop and validate a clinical risk prediction algorithm to identify breast cancer survivors at high risk for adverse outcomes. Study Setting and Design: Our national retrospective analysis used cross‐validated random forest machine learning models to separately predict the risk of all‐cause death, cancer‐specific death, claims‐derived risk of recurrence, and other adverse health outcomes within 3 and 5 years following treatment completion. Data Sources and Analytic Sample: Our study used the Surveillance and Epidemiology End Results (SEER) registry—Consumer Assessment of Healthcare Providers and Systems (CAHPS) survey (SEER‐CAHPS) linked data for survivors diagnosed between 2003 and 2011, with follow‐up claims data to 2017. Principal Findings: Within the 3‐year follow‐up period, 372/4516 survivors (mean age 75.1; 81.7% white) in the primary cohort (8.2%) died, 111 from cancer (2.5%), 665 (14.7%) experienced cancer recurrence, and 488 (10.8%) were hospitalized for adverse health outcomes. The algorithm's prediction resulted in 91.9% out‐of‐sample accuracy (the percent of observations classified correctly) and a 37.6% Cohen's Kappa (i.e., improvement over an uninformed model). Out‐of‐sample accuracy was 97.5% (44% improvement) for predicting cancer‐specific death, 85% (26% improvement) for recurrence, and 89% (28% improvement) for other adverse health outcomes. Important predictors across outcomes included geographic region, age, frailty, comorbidity, time since diagnosis, and out‐of‐pocket cost responsibility. Conclusions: Machine learning models accurately predicted relevant adverse survivorship outcomes, driven primarily by non‐cancer specific factors. Breast cancer survivors at high risk for adverse outcomes may benefit from more intensive care, whereas those at low risk may be more appropriately managed by primary care.Keywords
Funding Information
- American Cancer Society (ACS5113568)
This publication has 40 references indexed in Scilit:
- Development of a Multilevel Model to Identify Patients at Risk for Delay in Starting Cancer TreatmentJAMA Network Open, 2023
- Developing personalized survivorship care pathways in the United States: Existing resources and remaining challengesCancer, 2020
- Survivorship care for cancer patients in primary versus secondary care: a systematic reviewJournal of Cancer Survivorship, 2020
- Association of Treatment Delays With Survival for Patients With Head and Neck CancerJAMA Otolaryngology–Head & Neck Surgery, 2019
- Unveiling SEER-CAHPS®: A New Data Resource for Quality of Care ResearchJournal of General Internal Medicine, 2015
- Current unmet needs of cancer survivors: Analysis of open‐ended responses to the American Cancer Society Study of Cancer Survivors IICancer, 2015
- Using claims data to predict dependency in activities of daily living as a proxy for frailtyPharmacoepidemiology and Drug Safety, 2014
- The complex health profile of long-term cancer survivors: prevalence and predictors of comorbid conditionsJournal of Cancer Survivorship, 2014
- Towards a personalised approach to aftercare: a review of cancer follow-up in the UKJournal of Cancer Survivorship, 2011
- Trends in Follow-up and Preventive Care for Colorectal Cancer SurvivorsJournal of General Internal Medicine, 2008