Ensemble Approach to Combining Episode Prediction Models Using Sequential Circadian Rhythm Sensor Data from Mental Health Patients
Managing mood disorders poses challenges in counseling and drug treatment, owing to limitations. Counseling is the most effective during hospital visits, and the side effects of drugs can be burdensome. Patient empowerment is crucial for understanding and managing these triggers. The daily monitorin...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-10-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/23/20/8544 |
_version_ | 1797572257984282624 |
---|---|
author | Taek Lee Heon-Jeong Lee Jung-Been Lee Jeong-Dong Kim |
author_facet | Taek Lee Heon-Jeong Lee Jung-Been Lee Jeong-Dong Kim |
author_sort | Taek Lee |
collection | DOAJ |
description | Managing mood disorders poses challenges in counseling and drug treatment, owing to limitations. Counseling is the most effective during hospital visits, and the side effects of drugs can be burdensome. Patient empowerment is crucial for understanding and managing these triggers. The daily monitoring of mental health and the utilization of episode prediction tools can enable self-management and provide doctors with insights into worsening lifestyle patterns. In this study, we test and validate whether the prediction of future depressive episodes in individuals with depression can be achieved by using lifelog sequence data collected from digital device sensors. Diverse models such as random forest, hidden Markov model, and recurrent neural network were used to analyze the time-series data and make predictions about the occurrence of depressive episodes in the near future. The models were then combined into a hybrid model. The prediction accuracy of the hybrid model was 0.78; especially in the prediction of rare episode events, the F1-score performance was approximately 1.88 times higher than that of the dummy model. We explored factors such as data sequence size, train-to-test data ratio, and class-labeling time slots that can affect the model performance to determine the combinations of parameters that optimize the model performance. Our findings are especially valuable because they are experimental results derived from large-scale participant data analyzed over a long period of time. |
first_indexed | 2024-03-10T20:54:42Z |
format | Article |
id | doaj.art-6bcc2ddf81384b658f67e1b4205d5ecb |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-10T20:54:42Z |
publishDate | 2023-10-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-6bcc2ddf81384b658f67e1b4205d5ecb2023-11-19T18:04:31ZengMDPI AGSensors1424-82202023-10-012320854410.3390/s23208544Ensemble Approach to Combining Episode Prediction Models Using Sequential Circadian Rhythm Sensor Data from Mental Health PatientsTaek Lee0Heon-Jeong Lee1Jung-Been Lee2Jeong-Dong Kim3Division of Computer Science and Engineering, College of Software and Convergence, Sun Moon University, Asan 31460, Republic of KoreaDepartment of Psychiatry, Korea University College of Medicine, Seoul 02841, Republic of KoreaDivision of Computer Science and Engineering, College of Software and Convergence, Sun Moon University, Asan 31460, Republic of KoreaDivision of Computer Science and Engineering, College of Software and Convergence, Sun Moon University, Asan 31460, Republic of KoreaManaging mood disorders poses challenges in counseling and drug treatment, owing to limitations. Counseling is the most effective during hospital visits, and the side effects of drugs can be burdensome. Patient empowerment is crucial for understanding and managing these triggers. The daily monitoring of mental health and the utilization of episode prediction tools can enable self-management and provide doctors with insights into worsening lifestyle patterns. In this study, we test and validate whether the prediction of future depressive episodes in individuals with depression can be achieved by using lifelog sequence data collected from digital device sensors. Diverse models such as random forest, hidden Markov model, and recurrent neural network were used to analyze the time-series data and make predictions about the occurrence of depressive episodes in the near future. The models were then combined into a hybrid model. The prediction accuracy of the hybrid model was 0.78; especially in the prediction of rare episode events, the F1-score performance was approximately 1.88 times higher than that of the dummy model. We explored factors such as data sequence size, train-to-test data ratio, and class-labeling time slots that can affect the model performance to determine the combinations of parameters that optimize the model performance. Our findings are especially valuable because they are experimental results derived from large-scale participant data analyzed over a long period of time.https://www.mdpi.com/1424-8220/23/20/8544episode predictionhidden Markov modelrecurrent neural networkrandom forestmood disorderdigital healthcare |
spellingShingle | Taek Lee Heon-Jeong Lee Jung-Been Lee Jeong-Dong Kim Ensemble Approach to Combining Episode Prediction Models Using Sequential Circadian Rhythm Sensor Data from Mental Health Patients Sensors episode prediction hidden Markov model recurrent neural network random forest mood disorder digital healthcare |
title | Ensemble Approach to Combining Episode Prediction Models Using Sequential Circadian Rhythm Sensor Data from Mental Health Patients |
title_full | Ensemble Approach to Combining Episode Prediction Models Using Sequential Circadian Rhythm Sensor Data from Mental Health Patients |
title_fullStr | Ensemble Approach to Combining Episode Prediction Models Using Sequential Circadian Rhythm Sensor Data from Mental Health Patients |
title_full_unstemmed | Ensemble Approach to Combining Episode Prediction Models Using Sequential Circadian Rhythm Sensor Data from Mental Health Patients |
title_short | Ensemble Approach to Combining Episode Prediction Models Using Sequential Circadian Rhythm Sensor Data from Mental Health Patients |
title_sort | ensemble approach to combining episode prediction models using sequential circadian rhythm sensor data from mental health patients |
topic | episode prediction hidden Markov model recurrent neural network random forest mood disorder digital healthcare |
url | https://www.mdpi.com/1424-8220/23/20/8544 |
work_keys_str_mv | AT taeklee ensembleapproachtocombiningepisodepredictionmodelsusingsequentialcircadianrhythmsensordatafrommentalhealthpatients AT heonjeonglee ensembleapproachtocombiningepisodepredictionmodelsusingsequentialcircadianrhythmsensordatafrommentalhealthpatients AT jungbeenlee ensembleapproachtocombiningepisodepredictionmodelsusingsequentialcircadianrhythmsensordatafrommentalhealthpatients AT jeongdongkim ensembleapproachtocombiningepisodepredictionmodelsusingsequentialcircadianrhythmsensordatafrommentalhealthpatients |