EUVIMEDEUVIMED entdecken
Crossref

Machine Learning Risk Stratification Approach Using Patient-Reported Outcomes for Forecasting Unplanned Health Care Use and Symptom Burden in Cancer Survivors

Akina Natori iD, Jerry R Bonnell iD, Vasileios Stathias iD, Sara E Fleszar-Pavlovic, Mitsunori Ogihara iD, Andrew Wang iD, Ravi Vadapalli iD, Blanca Silvia Noriega Esquives iD, Tracy E Crane iD, Frank J Penedo iD

JCO Clinical Cancer Informatics · 2026-04 · 10 (2)

DOI: 10.1200/cci-25-00389 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JCO Clinical Cancer Informatics, 2026-04. Verfasst von Akina Natori und 9 weiteren Autor:innen. Beteiligte Einrichtung: Division of Medical Oncology, Department of Medicine, University of Miami Miller School of Medicine, Sylvester Comprehensive Cancer Center, Coral Gab…. Hauptthemen laut MEDLINE: Patient Reported Outcome Measures, Machine Learning, Cancer Survivors, Patient Acceptance of Health Care. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 39 Literaturangaben. Gefördert von: NCI NIH HHS, NCATS NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PURPOSE Effective risk stratification in cancer survivorship requires handling longitudinal data characterized by multimodal inputs, irregular follow-up, and recurrent clinical events. This study evaluated the incremental value of integrating patient-reported outcomes (PROs) with electronic health record (EHR) data and identified optimal windowing strategies for machine learning–based prediction of adverse survivorship outcomes. PATIENTS AND METHODS This study used a cohort of 25,592 cancer survivors followed for 36 months. Data from four domains were integrated: baseline measures, treatments, PROs, and health care utilization (emergency room visits and hospitalizations). Two classification models, LASSO and CATBOOST, were applied across modality combinations and five temporal representations of patient history: static early-phase (0-6 months), cumulative history, sliding windows (4- and 12-month), and a most-recent baseline. Performance was evaluated for predicting monthly health care utilization and patient-reported symptom burden using average precision (AP). SHapley Additive exPlanations (SHAP) analysis identified key predictors and characterized their evolving influence. RESULTS For health care utilization, CATBOOST models trained on the full multimodal data set with time-windowed predictors achieved strong discrimination (AP = 0.207), outperforming static baselines by 27%. SHAP analyses emphasized dynamic contributions from recent utilization and treatment toxicity. For symptom burden, PRO integration was crucial, nearly doubling clinical-only performance (AP = 0.132 v 0.071), with longer historical context improving characterization of progressive functional decline and symptom severity. Flagging the top 10% of patients by predicted risk captured 51.7% of health care utilizations and 46.7% of symptom burden events. CONCLUSION Adverse survivorship risk is dynamic and outcome-specific: acute health care utilization is best predicted by recent clinical momentum, while longitudinal patient-reported trends drive symptom burden. Implementing decoupled, dynamic windows provides a flexible framework for risk stratification and risk prediction beyond standard clinical heuristics, facilitating proactive, precision-based survivorship care.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Patient Reported Outcome MeasuresMachine LearningCancer SurvivorsPatient Acceptance of Health CareNeoplasmsHumansFemaleRisk AssessmentSymptom BurdenMaleMiddle AgedAgedPredictive Learning ModelsElectronic Health RecordsBoosting Machine Learning AlgorithmsClassification AlgorithmsPrediction Algorithms

Autor:innen und Institutionen

  • Division of Medical Oncology, Department of Medicine, University of Miami Miller School of Medicine, Sylvester Comprehensive Cancer Center, Coral Gables, FL.
  • Frost Institute for Data Science and Computing, University of Miami, Coral Gables, FL.
  • Department of Molecular and Cellular Pharmacology, University of Miami Miller School of Medicine, Coral Gables, FL.
  • Data Science, Sylvester Comprehensive Cancer Center, Coral Gables, FL.
  • Department of Computer Science, University of Miami, Coral Gables, FL.
  • Sylvester Comprehensive Cancer Center, Coral Gables, FL.

ORCID-Profile: Akina Natori, Jerry R Bonnell, Vasileios Stathias, Mitsunori Ogihara, Andrew Wang, Ravi Vadapalli, Blanca Silvia Noriega Esquives, Tracy E Crane, Frank J Penedo

Förderung

  • NCI NIH HHS
  • NCATS NIH HHS

Zitieren

APA

Natori, A., Bonnell, J. R., Stathias, V., Fleszar-Pavlovic, S. E., Ogihara, M., Wang, A., Vadapalli, R., Noriega Esquives, B. S., Crane, T. E., & Penedo, F. J. (2026). Machine Learning Risk Stratification Approach Using Patient-Reported Outcomes for Forecasting Unplanned Health Care Use and Symptom Burden in Cancer Survivors. JCO Clinical Cancer Informatics, 10(2). https://doi.org/10.1200/cci-25-00389

Vancouver

Natori A, Bonnell JR, Stathias V, Fleszar-Pavlovic SE, Ogihara M, Wang A, et al. Machine Learning Risk Stratification Approach Using Patient-Reported Outcomes for Forecasting Unplanned Health Care Use and Symptom Burden in Cancer Survivors. JCO Clinical Cancer Informatics. 2026;10(2). doi:10.1200/cci-25-00389

BibTeX
@article{Natori2026,
  author = {Natori, Akina and Bonnell, Jerry R and Stathias, Vasileios and Fleszar-Pavlovic, Sara E and Ogihara, Mitsunori and Wang, Andrew and Vadapalli, Ravi and Noriega Esquives, Blanca Silvia and Crane, Tracy E and Penedo, Frank J},
  title = {Machine Learning Risk Stratification Approach Using Patient-Reported Outcomes for Forecasting Unplanned Health Care Use and Symptom Burden in Cancer Survivors},
  journal = {JCO Clinical Cancer Informatics},
  year = {2026},
  volume = {10},
  number = {2},
  doi = {10.1200/cci-25-00389}
}
Kostenlos starten →