Sequence Modeling of Passive Sensing Data for Treatment Response Prediction in Major Depressive Disorder
Major depressive disorder (MDD) is a prevalent mental health condition and has become a pressing societal challenge. Early prediction of treatment response may aid in the rehabilitation engineering of depression, which is of great practical significance for the relief of suffering and burden of MDD....
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10078348/ |
| _version_ | 1797805146358415360 |
|---|---|
| author | Bochao Zou Xiaolong Zhang Le Xiao Ran Bai Xin Li Hui Liang Huimin Ma Gang Wang |
| author_facet | Bochao Zou Xiaolong Zhang Le Xiao Ran Bai Xin Li Hui Liang Huimin Ma Gang Wang |
| author_sort | Bochao Zou |
| collection | DOAJ |
| description | Major depressive disorder (MDD) is a prevalent mental health condition and has become a pressing societal challenge. Early prediction of treatment response may aid in the rehabilitation engineering of depression, which is of great practical significance for the relief of suffering and burden of MDD. In this paper, we present a sequence modeling approach that uses data collected by passive sensing techniques to predict patients with an outcome of treatment responded defined by the reduction in clinical administrated scales. Hundreds of patients with MDD have been recruited from outpatient clinics at 4 psychiatric sites. Each has been delivered with a self-developed app to passively record their daily phone usage and physical data with minimal human action. An unavoidable dilemma in passive sensing is missing values. To overcome that, the proposed approach combined feature extraction and sequence modeling methods to fully utilize the pattern of missing values from longitudinal data. With no treatment constraints, it enables us to predict the treatment response of MDD 8–10 weeks before the completion of the treatment course, leaving time for preventative measures. Our work explored the feasibility of treatment response prediction using longitudinal passive sensing data and sparse ground truth, and also has the potential for preventing depression by forecasting treatment outcomes weeks in advance. |
| first_indexed | 2024-03-13T05:47:38Z |
| format | Article |
| id | doaj.art-3bbc1e1c6a4f46e5ac19d3c41aeebee3 |
| institution | Directory Open Access Journal |
| issn | 1558-0210 |
| language | English |
| last_indexed | 2024-03-13T05:47:38Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| spelling | doaj.art-3bbc1e1c6a4f46e5ac19d3c41aeebee32023-06-13T20:07:06ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1558-02102023-01-01311786179510.1109/TNSRE.2023.326030110078348Sequence Modeling of Passive Sensing Data for Treatment Response Prediction in Major Depressive DisorderBochao Zou0https://orcid.org/0000-0002-2126-8159Xiaolong Zhang1https://orcid.org/0000-0003-2964-0485Le Xiao2Ran Bai3https://orcid.org/0000-0003-2964-7097Xin Li4Hui Liang5Huimin Ma6https://orcid.org/0000-0001-5383-5667Gang Wang7School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, ChinaNational Clinical Research Center for Mental Disorders & Beijing Key Laboratory of Mental Disorders, Beijing Anding Hospital, Capital Medical University, Beijing, ChinaNational Clinical Research Center for Mental Disorders & Beijing Key Laboratory of Mental Disorders, Beijing Anding Hospital, Capital Medical University, Beijing, ChinaNational Engineering Laboratory for Risk Perception and Prevention, Beijing, ChinaSchool of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, ChinaSchool of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, ChinaSchool of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, ChinaNational Clinical Research Center for Mental Disorders & Beijing Key Laboratory of Mental Disorders, Beijing Anding Hospital, Capital Medical University, Beijing, ChinaMajor depressive disorder (MDD) is a prevalent mental health condition and has become a pressing societal challenge. Early prediction of treatment response may aid in the rehabilitation engineering of depression, which is of great practical significance for the relief of suffering and burden of MDD. In this paper, we present a sequence modeling approach that uses data collected by passive sensing techniques to predict patients with an outcome of treatment responded defined by the reduction in clinical administrated scales. Hundreds of patients with MDD have been recruited from outpatient clinics at 4 psychiatric sites. Each has been delivered with a self-developed app to passively record their daily phone usage and physical data with minimal human action. An unavoidable dilemma in passive sensing is missing values. To overcome that, the proposed approach combined feature extraction and sequence modeling methods to fully utilize the pattern of missing values from longitudinal data. With no treatment constraints, it enables us to predict the treatment response of MDD 8–10 weeks before the completion of the treatment course, leaving time for preventative measures. Our work explored the feasibility of treatment response prediction using longitudinal passive sensing data and sparse ground truth, and also has the potential for preventing depression by forecasting treatment outcomes weeks in advance.https://ieeexplore.ieee.org/document/10078348/Major depressive disordertreatment response predictiondigital phenotypingsequence modeling |
| spellingShingle | Bochao Zou Xiaolong Zhang Le Xiao Ran Bai Xin Li Hui Liang Huimin Ma Gang Wang Sequence Modeling of Passive Sensing Data for Treatment Response Prediction in Major Depressive Disorder IEEE Transactions on Neural Systems and Rehabilitation Engineering Major depressive disorder treatment response prediction digital phenotyping sequence modeling |
| title | Sequence Modeling of Passive Sensing Data for Treatment Response Prediction in Major Depressive Disorder |
| title_full | Sequence Modeling of Passive Sensing Data for Treatment Response Prediction in Major Depressive Disorder |
| title_fullStr | Sequence Modeling of Passive Sensing Data for Treatment Response Prediction in Major Depressive Disorder |
| title_full_unstemmed | Sequence Modeling of Passive Sensing Data for Treatment Response Prediction in Major Depressive Disorder |
| title_short | Sequence Modeling of Passive Sensing Data for Treatment Response Prediction in Major Depressive Disorder |
| title_sort | sequence modeling of passive sensing data for treatment response prediction in major depressive disorder |
| topic | Major depressive disorder treatment response prediction digital phenotyping sequence modeling |
| url | https://ieeexplore.ieee.org/document/10078348/ |
| work_keys_str_mv | AT bochaozou sequencemodelingofpassivesensingdatafortreatmentresponsepredictioninmajordepressivedisorder AT xiaolongzhang sequencemodelingofpassivesensingdatafortreatmentresponsepredictioninmajordepressivedisorder AT lexiao sequencemodelingofpassivesensingdatafortreatmentresponsepredictioninmajordepressivedisorder AT ranbai sequencemodelingofpassivesensingdatafortreatmentresponsepredictioninmajordepressivedisorder AT xinli sequencemodelingofpassivesensingdatafortreatmentresponsepredictioninmajordepressivedisorder AT huiliang sequencemodelingofpassivesensingdatafortreatmentresponsepredictioninmajordepressivedisorder AT huiminma sequencemodelingofpassivesensingdatafortreatmentresponsepredictioninmajordepressivedisorder AT gangwang sequencemodelingofpassivesensingdatafortreatmentresponsepredictioninmajordepressivedisorder |