Predicting Changes in Depression Severity Using the PSYCHE-D (Prediction of Severity Change-Depression) Model Involving Person-Generated Health Data: Longitudinal Case-Control Observational Study
BackgroundIn 2017, an estimated 17.3 million adults in the United States experienced at least one major depressive episode, with 35% of them not receiving any treatment. Underdiagnosis of depression has been attributed to many reasons, including stigma surrounding mental heal...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
JMIR Publications
2022-03-01
|
| Series: | JMIR mHealth and uHealth |
| Online Access: | https://mhealth.jmir.org/2022/3/e34148 |
| _version_ | 1797735191412736000 |
|---|---|
| author | Mariko Makhmutova Raghu Kainkaryam Marta Ferreira Jae Min Martin Jaggi Ieuan Clay |
| author_facet | Mariko Makhmutova Raghu Kainkaryam Marta Ferreira Jae Min Martin Jaggi Ieuan Clay |
| author_sort | Mariko Makhmutova |
| collection | DOAJ |
| description |
BackgroundIn 2017, an estimated 17.3 million adults in the United States experienced at least one major depressive episode, with 35% of them not receiving any treatment. Underdiagnosis of depression has been attributed to many reasons, including stigma surrounding mental health, limited access to medical care, and barriers due to cost.
ObjectiveThis study aimed to determine if low-burden personal health solutions, leveraging person-generated health data (PGHD), could represent a possible way to increase engagement and improve outcomes.
MethodsHere, we present the development of PSYCHE-D (Prediction of Severity Change-Depression), a predictive model developed using PGHD from more than 4000 individuals, which forecasts the long-term increase in depression severity. PSYCHE-D uses a 2-phase approach. The first phase supplements self-reports with intermediate generated labels, and the second phase predicts changing status over a 3-month period, up to 2 months in advance. The 2 phases are implemented as a single pipeline in order to eliminate data leakage and ensure results are generalizable.
ResultsPSYCHE-D is composed of 2 Light Gradient Boosting Machine (LightGBM) algorithm–based classifiers that use a range of PGHD input features, including objective activity and sleep, self-reported changes in lifestyle and medication, and generated intermediate observations of depression status. The approach generalizes to previously unseen participants to detect an increase in depression severity over a 3-month interval, with a sensitivity of 55.4% and a specificity of 65.3%, nearly tripling sensitivity while maintaining specificity when compared with a random model.
ConclusionsThese results demonstrate that low-burden PGHD can be the basis of accurate and timely warnings that an individual’s mental health may be deteriorating. We hope this work will serve as a basis for improved engagement and treatment of individuals experiencing depression. |
| first_indexed | 2024-03-12T12:55:30Z |
| format | Article |
| id | doaj.art-480208dbb4fb4049860d1e04b4e42211 |
| institution | Directory Open Access Journal |
| issn | 2291-5222 |
| language | English |
| last_indexed | 2024-03-12T12:55:30Z |
| publishDate | 2022-03-01 |
| publisher | JMIR Publications |
| record_format | Article |
| series | JMIR mHealth and uHealth |
| spelling | doaj.art-480208dbb4fb4049860d1e04b4e422112023-08-28T21:09:51ZengJMIR PublicationsJMIR mHealth and uHealth2291-52222022-03-01103e3414810.2196/34148Predicting Changes in Depression Severity Using the PSYCHE-D (Prediction of Severity Change-Depression) Model Involving Person-Generated Health Data: Longitudinal Case-Control Observational StudyMariko Makhmutovahttps://orcid.org/0000-0003-2127-5137Raghu Kainkaryamhttps://orcid.org/0000-0003-0811-1269Marta Ferreirahttps://orcid.org/0000-0002-8418-2141Jae Minhttps://orcid.org/0000-0003-4112-9583Martin Jaggihttps://orcid.org/0000-0003-1579-5558Ieuan Clayhttps://orcid.org/0000-0001-9722-8834 BackgroundIn 2017, an estimated 17.3 million adults in the United States experienced at least one major depressive episode, with 35% of them not receiving any treatment. Underdiagnosis of depression has been attributed to many reasons, including stigma surrounding mental health, limited access to medical care, and barriers due to cost. ObjectiveThis study aimed to determine if low-burden personal health solutions, leveraging person-generated health data (PGHD), could represent a possible way to increase engagement and improve outcomes. MethodsHere, we present the development of PSYCHE-D (Prediction of Severity Change-Depression), a predictive model developed using PGHD from more than 4000 individuals, which forecasts the long-term increase in depression severity. PSYCHE-D uses a 2-phase approach. The first phase supplements self-reports with intermediate generated labels, and the second phase predicts changing status over a 3-month period, up to 2 months in advance. The 2 phases are implemented as a single pipeline in order to eliminate data leakage and ensure results are generalizable. ResultsPSYCHE-D is composed of 2 Light Gradient Boosting Machine (LightGBM) algorithm–based classifiers that use a range of PGHD input features, including objective activity and sleep, self-reported changes in lifestyle and medication, and generated intermediate observations of depression status. The approach generalizes to previously unseen participants to detect an increase in depression severity over a 3-month interval, with a sensitivity of 55.4% and a specificity of 65.3%, nearly tripling sensitivity while maintaining specificity when compared with a random model. ConclusionsThese results demonstrate that low-burden PGHD can be the basis of accurate and timely warnings that an individual’s mental health may be deteriorating. We hope this work will serve as a basis for improved engagement and treatment of individuals experiencing depression.https://mhealth.jmir.org/2022/3/e34148 |
| spellingShingle | Mariko Makhmutova Raghu Kainkaryam Marta Ferreira Jae Min Martin Jaggi Ieuan Clay Predicting Changes in Depression Severity Using the PSYCHE-D (Prediction of Severity Change-Depression) Model Involving Person-Generated Health Data: Longitudinal Case-Control Observational Study JMIR mHealth and uHealth |
| title | Predicting Changes in Depression Severity Using the PSYCHE-D (Prediction of Severity Change-Depression) Model Involving Person-Generated Health Data: Longitudinal Case-Control Observational Study |
| title_full | Predicting Changes in Depression Severity Using the PSYCHE-D (Prediction of Severity Change-Depression) Model Involving Person-Generated Health Data: Longitudinal Case-Control Observational Study |
| title_fullStr | Predicting Changes in Depression Severity Using the PSYCHE-D (Prediction of Severity Change-Depression) Model Involving Person-Generated Health Data: Longitudinal Case-Control Observational Study |
| title_full_unstemmed | Predicting Changes in Depression Severity Using the PSYCHE-D (Prediction of Severity Change-Depression) Model Involving Person-Generated Health Data: Longitudinal Case-Control Observational Study |
| title_short | Predicting Changes in Depression Severity Using the PSYCHE-D (Prediction of Severity Change-Depression) Model Involving Person-Generated Health Data: Longitudinal Case-Control Observational Study |
| title_sort | predicting changes in depression severity using the psyche d prediction of severity change depression model involving person generated health data longitudinal case control observational study |
| url | https://mhealth.jmir.org/2022/3/e34148 |
| work_keys_str_mv | AT marikomakhmutova predictingchangesindepressionseverityusingthepsychedpredictionofseveritychangedepressionmodelinvolvingpersongeneratedhealthdatalongitudinalcasecontrolobservationalstudy AT raghukainkaryam predictingchangesindepressionseverityusingthepsychedpredictionofseveritychangedepressionmodelinvolvingpersongeneratedhealthdatalongitudinalcasecontrolobservationalstudy AT martaferreira predictingchangesindepressionseverityusingthepsychedpredictionofseveritychangedepressionmodelinvolvingpersongeneratedhealthdatalongitudinalcasecontrolobservationalstudy AT jaemin predictingchangesindepressionseverityusingthepsychedpredictionofseveritychangedepressionmodelinvolvingpersongeneratedhealthdatalongitudinalcasecontrolobservationalstudy AT martinjaggi predictingchangesindepressionseverityusingthepsychedpredictionofseveritychangedepressionmodelinvolvingpersongeneratedhealthdatalongitudinalcasecontrolobservationalstudy AT ieuanclay predictingchangesindepressionseverityusingthepsychedpredictionofseveritychangedepressionmodelinvolvingpersongeneratedhealthdatalongitudinalcasecontrolobservationalstudy |