Panic Attack Prediction Using Wearable Devices and Machine Learning: Development and Cohort Study
BackgroundA panic attack (PA) is an intense form of anxiety accompanied by multiple somatic presentations, leading to frequent emergency department visits and impairing the quality of life. A prediction model for PAs could help clinicians and patients monitor, control, and ca...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
JMIR Publications
2022-02-01
|
| Series: | JMIR Medical Informatics |
| Online Access: | https://medinform.jmir.org/2022/2/e33063 |
| _version_ | 1797735326670651392 |
|---|---|
| author | Chan-Hen Tsai Pei-Chen Chen Ding-Shan Liu Ying-Ying Kuo Tsung-Ting Hsieh Dai-Lun Chiang Feipei Lai Chia-Tung Wu |
| author_facet | Chan-Hen Tsai Pei-Chen Chen Ding-Shan Liu Ying-Ying Kuo Tsung-Ting Hsieh Dai-Lun Chiang Feipei Lai Chia-Tung Wu |
| author_sort | Chan-Hen Tsai |
| collection | DOAJ |
| description |
BackgroundA panic attack (PA) is an intense form of anxiety accompanied by multiple somatic presentations, leading to frequent emergency department visits and impairing the quality of life. A prediction model for PAs could help clinicians and patients monitor, control, and carry out early intervention for recurrent PAs, enabling more personalized treatment for panic disorder (PD).
ObjectiveThis study aims to provide a 7-day PA prediction model and determine the relationship between a future PA and various features, including physiological factors, anxiety and depressive factors, and the air quality index (AQI).
MethodsWe enrolled 59 participants with PD (Diagnostic and Statistical Manual of Mental Disorders, 5th edition, and the Mini International Neuropsychiatric Interview). Participants used smartwatches (Garmin Vívosmart 4) and mobile apps to collect their sleep, heart rate (HR), activity level, anxiety, and depression scores (Beck Depression Inventory [BDI], Beck Anxiety Inventory [BAI], State-Trait Anxiety Inventory state anxiety [STAI-S], State-Trait Anxiety Inventory trait anxiety [STAI-T], and Panic Disorder Severity Scale Self-Report) in their real life for a duration of 1 year. We also included AQIs from open data. To analyze these data, our team used 6 machine learning methods: random forests, decision trees, linear discriminant analysis, adaptive boosting, extreme gradient boosting, and regularized greedy forests.
ResultsFor 7-day PA predictions, the random forest produced the best prediction rate. Overall, the accuracy of the test set was 67.4%-81.3% for different machine learning algorithms. The most critical variables in the model were questionnaire and physiological features, such as the BAI, BDI, STAI, MINI, average HR, resting HR, and deep sleep duration.
ConclusionsIt is possible to predict PAs using a combination of data from questionnaires and physiological and environmental data. |
| first_indexed | 2024-03-12T12:57:25Z |
| format | Article |
| id | doaj.art-4ccc183e0713415883395b3965b89484 |
| institution | Directory Open Access Journal |
| issn | 2291-9694 |
| language | English |
| last_indexed | 2024-03-12T12:57:25Z |
| publishDate | 2022-02-01 |
| publisher | JMIR Publications |
| record_format | Article |
| series | JMIR Medical Informatics |
| spelling | doaj.art-4ccc183e0713415883395b3965b894842023-08-28T20:48:16ZengJMIR PublicationsJMIR Medical Informatics2291-96942022-02-01102e3306310.2196/33063Panic Attack Prediction Using Wearable Devices and Machine Learning: Development and Cohort StudyChan-Hen Tsaihttps://orcid.org/0000-0003-0205-497XPei-Chen Chenhttps://orcid.org/0000-0002-5692-8700Ding-Shan Liuhttps://orcid.org/0000-0001-7838-8963Ying-Ying Kuohttps://orcid.org/0000-0002-3450-8529Tsung-Ting Hsiehhttps://orcid.org/0000-0002-5082-4572Dai-Lun Chianghttps://orcid.org/0000-0001-6250-742XFeipei Laihttps://orcid.org/0000-0001-7147-8122Chia-Tung Wuhttps://orcid.org/0000-0002-5612-8607 BackgroundA panic attack (PA) is an intense form of anxiety accompanied by multiple somatic presentations, leading to frequent emergency department visits and impairing the quality of life. A prediction model for PAs could help clinicians and patients monitor, control, and carry out early intervention for recurrent PAs, enabling more personalized treatment for panic disorder (PD). ObjectiveThis study aims to provide a 7-day PA prediction model and determine the relationship between a future PA and various features, including physiological factors, anxiety and depressive factors, and the air quality index (AQI). MethodsWe enrolled 59 participants with PD (Diagnostic and Statistical Manual of Mental Disorders, 5th edition, and the Mini International Neuropsychiatric Interview). Participants used smartwatches (Garmin Vívosmart 4) and mobile apps to collect their sleep, heart rate (HR), activity level, anxiety, and depression scores (Beck Depression Inventory [BDI], Beck Anxiety Inventory [BAI], State-Trait Anxiety Inventory state anxiety [STAI-S], State-Trait Anxiety Inventory trait anxiety [STAI-T], and Panic Disorder Severity Scale Self-Report) in their real life for a duration of 1 year. We also included AQIs from open data. To analyze these data, our team used 6 machine learning methods: random forests, decision trees, linear discriminant analysis, adaptive boosting, extreme gradient boosting, and regularized greedy forests. ResultsFor 7-day PA predictions, the random forest produced the best prediction rate. Overall, the accuracy of the test set was 67.4%-81.3% for different machine learning algorithms. The most critical variables in the model were questionnaire and physiological features, such as the BAI, BDI, STAI, MINI, average HR, resting HR, and deep sleep duration. ConclusionsIt is possible to predict PAs using a combination of data from questionnaires and physiological and environmental data.https://medinform.jmir.org/2022/2/e33063 |
| spellingShingle | Chan-Hen Tsai Pei-Chen Chen Ding-Shan Liu Ying-Ying Kuo Tsung-Ting Hsieh Dai-Lun Chiang Feipei Lai Chia-Tung Wu Panic Attack Prediction Using Wearable Devices and Machine Learning: Development and Cohort Study JMIR Medical Informatics |
| title | Panic Attack Prediction Using Wearable Devices and Machine Learning: Development and Cohort Study |
| title_full | Panic Attack Prediction Using Wearable Devices and Machine Learning: Development and Cohort Study |
| title_fullStr | Panic Attack Prediction Using Wearable Devices and Machine Learning: Development and Cohort Study |
| title_full_unstemmed | Panic Attack Prediction Using Wearable Devices and Machine Learning: Development and Cohort Study |
| title_short | Panic Attack Prediction Using Wearable Devices and Machine Learning: Development and Cohort Study |
| title_sort | panic attack prediction using wearable devices and machine learning development and cohort study |
| url | https://medinform.jmir.org/2022/2/e33063 |
| work_keys_str_mv | AT chanhentsai panicattackpredictionusingwearabledevicesandmachinelearningdevelopmentandcohortstudy AT peichenchen panicattackpredictionusingwearabledevicesandmachinelearningdevelopmentandcohortstudy AT dingshanliu panicattackpredictionusingwearabledevicesandmachinelearningdevelopmentandcohortstudy AT yingyingkuo panicattackpredictionusingwearabledevicesandmachinelearningdevelopmentandcohortstudy AT tsungtinghsieh panicattackpredictionusingwearabledevicesandmachinelearningdevelopmentandcohortstudy AT dailunchiang panicattackpredictionusingwearabledevicesandmachinelearningdevelopmentandcohortstudy AT feipeilai panicattackpredictionusingwearabledevicesandmachinelearningdevelopmentandcohortstudy AT chiatungwu panicattackpredictionusingwearabledevicesandmachinelearningdevelopmentandcohortstudy |