Christopher M Hatton1, Lewis W Paton2, Dean McMillan3, James Cussens4, Simon Gilbody5, Paul A Tiffin6. 1. Department of Health Sciences, University of York, UK; Hull York Medical School, University of York, UK. Electronic address: hych2@hyms.ac.uk. 2. Department of Health Sciences, University of York, UK. Electronic address: lewis.paton@york.ac.uk. 3. Department of Health Sciences, University of York, UK; Hull York Medical School, University of York, UK. Electronic address: dean.mcmillan@york.ac.uk. 4. Department of Computer Science & York Centre for Complex Systems Analysis, University of York, UK. Electronic address: james.cussens@york.ac.uk. 5. Department of Health Sciences, University of York, UK; Hull York Medical School, University of York, UK. Electronic address: simon.gilbody@york.ac.uk. 6. Department of Health Sciences, University of York, UK; Hull York Medical School, University of York, UK. Electronic address: paul.tiffin@york.ac.uk.
Abstract
BACKGROUND: Depression causes significant physical and psychosocial morbidity. Predicting persistence of depressive symptoms could permit targeted prevention, and lessen the burden of depression. Machine learning is a rapidly expanding field, and such approaches offer powerful predictive abilities. We investigated the utility of a machine learning approach to predict the persistence of depressive symptoms in older adults. METHOD: Baseline demographic and psychometric data from 284 patients were used to predict the likelihood of older adults having persistent depressive symptoms after 12 months, using a machine learning approach ('extreme gradient boosting'). Predictive performance was compared to a conventional statistical approach (logistic regression). Data were drawn from the 'treatment-as-usual' arm of the CASPER (CollAborative care and active surveillance for Screen-Positive EldeRs with subthreshold depression) trial. RESULTS: Predictive performance was superior using machine learning compared to logistic regression (mean AUC 0.72 vs. 0.67, p < 0.0001). Using machine learning, an average of 89% of those predicted to have PHQ-9 scores above threshold at 12 months actually did, compared to 78% using logistic regression. However, mean negative predictive values were somewhat lower for the machine learning approach (45% vs. 35%). LIMITATIONS: A relatively small sample size potentially limited the predictive power of the algorithm. In addition, PHQ-9 scores were used as an indicator of persistent depressive symptoms, and whilst well validated, a clinical interview would have been preferable. CONCLUSIONS: Overall, our findings support the potential application of machine learning in personalised mental healthcare.
BACKGROUND:Depression causes significant physical and psychosocial morbidity. Predicting persistence of depressive symptoms could permit targeted prevention, and lessen the burden of depression. Machine learning is a rapidly expanding field, and such approaches offer powerful predictive abilities. We investigated the utility of a machine learning approach to predict the persistence of depressive symptoms in older adults. METHOD: Baseline demographic and psychometric data from 284 patients were used to predict the likelihood of older adults having persistent depressive symptoms after 12 months, using a machine learning approach ('extreme gradient boosting'). Predictive performance was compared to a conventional statistical approach (logistic regression). Data were drawn from the 'treatment-as-usual' arm of the CASPER (CollAborative care and active surveillance for Screen-Positive EldeRs with subthreshold depression) trial. RESULTS: Predictive performance was superior using machine learning compared to logistic regression (mean AUC 0.72 vs. 0.67, p < 0.0001). Using machine learning, an average of 89% of those predicted to have PHQ-9 scores above threshold at 12 months actually did, compared to 78% using logistic regression. However, mean negative predictive values were somewhat lower for the machine learning approach (45% vs. 35%). LIMITATIONS: A relatively small sample size potentially limited the predictive power of the algorithm. In addition, PHQ-9 scores were used as an indicator of persistent depressive symptoms, and whilst well validated, a clinical interview would have been preferable. CONCLUSIONS: Overall, our findings support the potential application of machine learning in personalised mental healthcare.
Authors: Seyul Kwak; Dae Jong Oh; Yeong-Ju Jeon; Da Young Oh; Su Mi Park; Hairin Kim; Jun-Young Lee Journal: J Alzheimers Dis Date: 2022 Impact factor: 4.472