Journal article
Using real-world electronic health record data to predict the development of 12 cancer-related symptoms in the context of multimorbidity
JAMIA open, Vol.7(3), ooae082
10/01/2024
DOI: 10.1093/jamiaopen/ooae082
PMCID: PMC11397936
PMID: 39282082
Abstract
Abstract Objective This study uses electronic health record (EHR) data to predict 12 common cancer symptoms, assessing the efficacy of machine learning (ML) models in identifying symptom influencers. Materials and Methods We analyzed EHR data of 8156 adults diagnosed with cancer who underwent cancer treatment from 2017 to 2020. Structured and unstructured EHR data were sourced from the Enterprise Data Warehouse for Research at the University of Iowa Hospital and Clinics. Several predictive models, including logistic regression, random forest (RF), and XGBoost, were employed to forecast symptom development. The performances of the models were evaluated by F1-score and area under the curve (AUC) on the testing set. The SHapley Additive exPlanations framework was used to interpret these models and identify the predictive risk factors associated with fatigue as an exemplar. Results The RF model exhibited superior performance with a macro average AUC of 0.755 and an F1-score of 0.729 in predicting a range of cancer-related symptoms. For instance, the RF model achieved an AUC of 0.954 and an F1-score of 0.914 for pain prediction. Key predictive factors identified included clinical history, cancer characteristics, treatment modalities, and patient demographics depending on the symptom. For example, the odds ratio (OR) for fatigue was significantly influenced by allergy (OR = 2.3, 95% CI: 1.8-2.9) and colitis (OR = 1.9, 95% CI: 1.5-2.4). Discussion Our research emphasizes the critical integration of multimorbidity and patient characteristics in modeling cancer symptoms, revealing the considerable influence of chronic conditions beyond cancer itself. Conclusion We highlight the potential of ML for predicting cancer symptoms, suggesting a pathway for integrating such models into clinical systems to enhance personalized care and symptom management.
Details
- Title: Subtitle
- Using real-world electronic health record data to predict the development of 12 cancer-related symptoms in the context of multimorbidity
- Creators
- Anindita Bandyopadhyay - University of IowaAlaa Albashayreh - University of IowaNahid Zeinali - University of IowaWeiguo Fan - University of IowaStephanie Gilbertson-White
- Resource Type
- Journal article
- Publication Details
- JAMIA open, Vol.7(3), ooae082
- Publisher
- OXFORD UNIV PRESS
- DOI
- 10.1093/jamiaopen/ooae082
- PMID
- 39282082
- PMCID
- PMC11397936
- ISSN
- 2574-2531
- eISSN
- 2574-2531
- Grant note
- NINR (National Institute for Nursing Research): P20 1P20NR018081 National Cancer Institute (NCI): P30 P30CA086862 Institute for Clinical and Translational Science, CTSA University of Iowa: UL1TR002537
This work was supported by the Betty Irene Moore Fellowship for Nurse Leaders and Innovators; College of Nursing, University of Iowa; Center for Advancing Multimorbidity Science (CAMS); NINR (National Institute for Nursing Research) grant number P20 1P20NR018081; Holden Comprehensive Cancer Center, University of Iowa, National Cancer Institute (NCI) grant number P30 P30CA086862; Iowa Health Data Resource (IHDR), University of Iowa; and Institute for Clinical and Translational Science, CTSA University of Iowa grant number UL1TR002537.
- Language
- English
- Date published
- 10/01/2024
- Academic Unit
- Nursing; Business Analytics; Internal Medicine
- Record Identifier
- 9984705606802771
Metrics
14 Record Views