Predicting Depression Risk in Patients With Cancer Using Multimodal Data: Algorithm Development Study (Preprint)
Preprint
- 17 August 2023
- preprint
- Published by JMIR Publications Inc. in JMIR Preprints
Abstract
BACKGROUND Patients with cancer starting systemic treatment programs, such as chemotherapy, often develop depression. A prediction model may assist physicians and health care workers in the early identification of these vulnerable patients. OBJECTIVE This study aimed to develop a prediction model for depression risk within the first month of cancer treatment. METHODS We included 16,159 patients diagnosed with cancer starting chemo- or radiotherapy treatment between 2008 and 2021. Machine learning models (eg, least absolute shrinkage and selection operator [LASSO] logistic regression) and natural language processing models (Bidirectional Encoder Representations from Transformers [BERT]) were used to develop multimodal prediction models using both electronic health record data and unstructured text (patient emails and clinician notes). Model performance was assessed in an independent test set (n=5387, 33%) using area under the receiver operating characteristic curve (AUROC), calibration curves, and decision curve analysis to assess initial clinical impact use. RESULTS Among 16,159 patients, 437 (2.7%) received a depression diagnosis within the first month of treatment. The LASSO logistic regression models based on the structured data (AUROC 0.74, 95% CI 0.71-0.78) and structured data with email classification scores (AUROC 0.74, 95% CI 0.71-0.78) had the best discriminative performance. The BERT models based on clinician notes and structured data with email classification scores had AUROCs around 0.71. The logistic regression model based on email classification scores alone performed poorly (AUROC 0.54, 95% CI 0.52-0.56), and the model based solely on clinician notes had the worst performance (AUROC 0.50, 95% CI 0.49-0.52). Calibration was good for the logistic regression models, whereas the BERT models produced overly extreme risk estimates even after recalibration. There was a small range of decision thresholds for which the best-performing model showed promising clinical effectiveness use. The risks were underestimated for female and Black patients. CONCLUSIONS The results demonstrated the potential and limitations of machine learning and multimodal models for predicting depression risk in patients with cancer. Future research is needed to further validate these models, refine the outcome label and predictors related to mental health, and address biases across subgroups.Keywords
All Related Versions
- Published version: JMIR Medical Informatics, 12 (1), e51925.
This publication has 53 references indexed in Scilit:
- Anxiety and depression after cancer diagnosis: Prevalence rates by cancer type, gender, and ageJournal of Affective Disorders, 2012
- Using electronic medical records to determine the diagnosis of clinical depressionInternational Journal of Medical Informatics, 2011
- Decrease in Depression Symptoms Is Associated With Longer Survival in Patients With Metastatic Breast Cancer: A Secondary AnalysisJournal of Clinical Oncology, 2011
- Prevalence of depression, anxiety, and adjustment disorder in oncological, haematological, and palliative-care settings: a meta-analysis of 94 interview-based studiesThe Lancet Oncology, 2011
- Early discontinuation and non-adherence to adjuvant hormonal therapy are associated with increased mortality in women with breast cancerBreast Cancer Research and Treatment, 2010
- Assessing the Performance of Prediction ModelsEpidemiology, 2010
- Healthcare resource utilization and costs associated with non-adherence to imatinib treatment in chronic myeloid leukemia patientsCurrent Medical Research and Opinion, 2009
- Insomnia and depressionSleep Medicine, 2008
- Depressive symptoms and quality of life in home-care-assisted cancer patientsJournal of Pain and Symptom Management, 1996
- A new method of classifying prognostic comorbidity in longitudinal studies: Development and validationJournal of Chronic Diseases, 1987