Panic Attack Prediction Using Wearable Devices and Machine Learning: Development and Cohort Study

Abstract

Background A 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). Objective This 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). Methods We 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. Results For 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. Conclusions It is possible to predict PAs using a combination of data from questionnaires and physiological and environmental data.

Wearable Artificial Intelligence for Anxiety and Depression: Scoping Review

“…Year of publication, n (%) [27,30,38,48,52,59,63,64,69,81] 10 ( 13) 2022 [19][20][21]23,25,28,41,45,49,54,61,62,68,73,74,77,78] 17 (25) 2021 [22,29,31,33,40,43,44,53,57,60,66,70,71,76,79] 15 (22) 2020 [26,32,34,42,46,47,51,56,…”

“…Type of publication, n (%) [19,21,23,[25][26][27][28][29][30]34,[38][39][40][41][42][43][44][45][46][48][49][50][51][52][53][54][56][57][58][59][60][61][64][65][66][69][70][71][73][74][75][77][78][79]81,82,84,86,87] 49 (71) Journal article [20,22,24,…”

“…Target condition [19,20,[23][24][25][26][27][28]30,32,[34][35][36][37][38]42,43,[46][47][48][49][50][51][52][53] 12) Wired [81] 1 (1) ANT+ (ANT Wireless) a The number of studies does not add up, as 1 (1%) study has both commercial and noncommercial wearable devices. b The number of studies does not add up, as several studies have used >1 wearable device.…”

“…AI category [19,20,23,25,26,31,33,34,37,39,40,42,46,[49][50][51][52][53][54][55][56][57][58][59][60][61][63][64][65][66][67][69][70][71]73,[75][76][77][78][79][80][81]83,84,86,87] 46 (67) ML a [24,29,32,44,47,62,82...…”

A Survey on Wearable Sensors for Mental Health Monitoring

“…Regarding the usage of ML in the context of physiological data, the literature is quite recent, and almost non-existent when taking into account the diseases and mental health monitoring using wearables. Nevertheless, we found usage of the generalized linear mode (GLM) [ 28 ], KNN, SVM [ 30 , 54 , 62 , 63 ], RF [ 30 , 32 , 62 , 63 ], logistic regression (LR) [ 30 ], extreme gradient boosting (XGBoost) [ 32 ], linear discriminant analysis (LDA) [ 32 ], AdaBoost [ 32 , 62 ], decision trees (DTs) [ 32 , 62 ], Bayesian networks (BNs) [ 62 ], and artificial neural networks (ANNs) [ 62 ].…”