Exploring Digital Biomarkers of Illness Activity in Mood Episodes: Hypotheses Generating and Model Development Study

Gerard Anmella; Filippo Corponi; Bryan M. Li; Ariadna Mas; Miriam Sanabra; Isabella Pacchiarotti; Marc Valentí; Iria Grande; Antoni Benabarre; Anna Giménez-Palomo; Marina Garriga; Isabel Agasi; Anna Bastidas; Myriam Cavero; Tabatha Fernández-Plaza; Néstor Arbelo; Miquel Bioque; Clemente García-Rizo; Norma Verdolini; Santiago Madero; Andrea Murru; Silvia Amoretti; Anabel Martínez-Aran; Victoria Ruiz; Giovanna Fico; Michele De Prisco; Vincenzo Oliva; Aleix Solanes; Joaquim Radua; Ludovic Samalin; Allan H. Young; Eduard Vieta; Antonio Vergari; Diego Hidalgo-Mazzei

doi:10.2196/45405

Exploring Digital Biomarkers of Illness Activity in Mood Episodes: Hypotheses Generating and Model Development Study

Gerard Anmella, Filippo Corponi, Bryan M. Li, Ariadna Mas, Miriam Sanabra, Isabella Pacchiarotti, Marc Valentí, Iria Grande, Antoni Benabarre, Anna Giménez-Palomo, Marina Garriga, Isabel Agasi, Anna Bastidas, Myriam Cavero, Tabatha Fernández-Plaza, Néstor Arbelo, Miquel Bioque, Clemente García-Rizo, Norma Verdolini, Santiago MaderoAndrea Murru, Silvia Amoretti, Anabel Martínez-Aran, Victoria Ruiz, Giovanna Fico, Michele De Prisco, Vincenzo Oliva, Aleix Solanes, Joaquim Radua, Ludovic Samalin, Allan H. Young, Eduard Vieta, Antonio Vergari, Diego Hidalgo-Mazzei^*

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

18 Citations (Scopus)

Abstract

Background: Depressive and manic episodes within bipolar disorder (BD) and major depressive disorder (MDD) involve altered mood, sleep, and activity, alongside physiological alterations wearables can capture. Objective: Firstly, we explored whether physiological wearable data could predict (aim 1) the severity of an acute affective episode at the intra-individual level and (aim 2) the polarity of an acute affective episode and euthymia among different individuals. Secondarily, we explored which physiological data were related to prior predictions, generalization across patients, and associations between affective symptoms and physiological data. Methods: We conducted a prospective exploratory observational study including patients with BD and MDD on acute affective episodes (manic, depressed, and mixed) whose physiological data were recorded using a research-grade wearable (Empatica E4) across 3 consecutive time points (acute, response, and remission of episode). Euthymic patients and healthy controls were recorded during a single session (approximately 48 h). Manic and depressive symptoms were assessed using standardized psychometric scales. Physiological wearable data included the following channels: acceleration (ACC), skin temperature, blood volume pulse, heart rate (HR), and electrodermal activity (EDA). Invalid physiological data were removed using a rule-based filter, and channels were time aligned at 1-second time units and segmented at window lengths of 32 seconds, as best-performing parameters. We developed deep learning predictive models, assessed the channels’ individual contribution using permutation feature importance analysis, and computed physiological data to psychometric scales’ items normalized mutual information (NMI). We present a novel, fully automated method for the preprocessing and analysis of physiological data from a research-grade wearable device, including a viable supervised learning pipeline for time-series analyses. Results: Overall, 35 sessions (1512 hours) from 12 patients (manic, depressed, mixed, and euthymic) and 7 healthy controls (mean age 39.7, SD 12.6 years; 6/19, 32% female) were analyzed. The severity of mood episodes was predicted with moderate (62%-85%) accuracies (aim 1), and their polarity with moderate (70%) accuracy (aim 2). The most relevant features for the former tasks were ACC, EDA, and HR. There was a fair agreement in feature importance across classification tasks (Kendall W=0.383). Generalization of the former models on unseen patients was of overall low accuracy, except for the intra-individual models. ACC was associated with “increased motor activity” (NMI>0.55), “insomnia” (NMI=0.6), and “motor inhibition” (NMI=0.75). EDA was associated with “aggressive behavior” (NMI=1.0) and “psychic anxiety” (NMI=0.52). Conclusions: Physiological data from wearables show potential to identify mood episodes and specific symptoms of mania and depression quantitatively, both in BD and MDD. Motor activity and stress-related physiological data (EDA and HR) stand out as potential digital biomarkers for predicting mania and depression, respectively. These findings represent a promising pathway toward personalized psychiatry, in which physiological wearable data could allow the early identification and intervention of mood episodes.

Original language	English
Article number	e45405
Journal	JMIR mHealth and uHealth
Volume	11
DOIs	https://doi.org/10.2196/45405
Publication status	Published - 2023

Keywords

bipolar disorder
deep learning
depression
digital biomarker
Empatica E4
machine learning
major depressive disorder
mania
physiological data
wearable

Access to Document

10.2196/45405

Cite this

Anmella, G., Corponi, F., Li, B. M., Mas, A., Sanabra, M., Pacchiarotti, I., Valentí, M., Grande, I., Benabarre, A., Giménez-Palomo, A., Garriga, M., Agasi, I., Bastidas, A., Cavero, M., Fernández-Plaza, T., Arbelo, N., Bioque, M., García-Rizo, C., Verdolini, N., ... Hidalgo-Mazzei, D. (2023). Exploring Digital Biomarkers of Illness Activity in Mood Episodes: Hypotheses Generating and Model Development Study. JMIR mHealth and uHealth, 11, Article e45405. https://doi.org/10.2196/45405

@article{d5337895ae784810804ff10d68d63f99,

title = "Exploring Digital Biomarkers of Illness Activity in Mood Episodes: Hypotheses Generating and Model Development Study",

abstract = "Background: Depressive and manic episodes within bipolar disorder (BD) and major depressive disorder (MDD) involve altered mood, sleep, and activity, alongside physiological alterations wearables can capture. Objective: Firstly, we explored whether physiological wearable data could predict (aim 1) the severity of an acute affective episode at the intra-individual level and (aim 2) the polarity of an acute affective episode and euthymia among different individuals. Secondarily, we explored which physiological data were related to prior predictions, generalization across patients, and associations between affective symptoms and physiological data. Methods: We conducted a prospective exploratory observational study including patients with BD and MDD on acute affective episodes (manic, depressed, and mixed) whose physiological data were recorded using a research-grade wearable (Empatica E4) across 3 consecutive time points (acute, response, and remission of episode). Euthymic patients and healthy controls were recorded during a single session (approximately 48 h). Manic and depressive symptoms were assessed using standardized psychometric scales. Physiological wearable data included the following channels: acceleration (ACC), skin temperature, blood volume pulse, heart rate (HR), and electrodermal activity (EDA). Invalid physiological data were removed using a rule-based filter, and channels were time aligned at 1-second time units and segmented at window lengths of 32 seconds, as best-performing parameters. We developed deep learning predictive models, assessed the channels{\textquoteright} individual contribution using permutation feature importance analysis, and computed physiological data to psychometric scales{\textquoteright} items normalized mutual information (NMI). We present a novel, fully automated method for the preprocessing and analysis of physiological data from a research-grade wearable device, including a viable supervised learning pipeline for time-series analyses. Results: Overall, 35 sessions (1512 hours) from 12 patients (manic, depressed, mixed, and euthymic) and 7 healthy controls (mean age 39.7, SD 12.6 years; 6/19, 32% female) were analyzed. The severity of mood episodes was predicted with moderate (62%-85%) accuracies (aim 1), and their polarity with moderate (70%) accuracy (aim 2). The most relevant features for the former tasks were ACC, EDA, and HR. There was a fair agreement in feature importance across classification tasks (Kendall W=0.383). Generalization of the former models on unseen patients was of overall low accuracy, except for the intra-individual models. ACC was associated with “increased motor activity” (NMI>0.55), “insomnia” (NMI=0.6), and “motor inhibition” (NMI=0.75). EDA was associated with “aggressive behavior” (NMI=1.0) and “psychic anxiety” (NMI=0.52). Conclusions: Physiological data from wearables show potential to identify mood episodes and specific symptoms of mania and depression quantitatively, both in BD and MDD. Motor activity and stress-related physiological data (EDA and HR) stand out as potential digital biomarkers for predicting mania and depression, respectively. These findings represent a promising pathway toward personalized psychiatry, in which physiological wearable data could allow the early identification and intervention of mood episodes.",

keywords = "bipolar disorder, deep learning, depression, digital biomarker, Empatica E4, machine learning, major depressive disorder, mania, physiological data, wearable",

author = "Gerard Anmella and Filippo Corponi and Li, {Bryan M.} and Ariadna Mas and Miriam Sanabra and Isabella Pacchiarotti and Marc Valent{\'i} and Iria Grande and Antoni Benabarre and Anna Gim{\'e}nez-Palomo and Marina Garriga and Isabel Agasi and Anna Bastidas and Myriam Cavero and Tabatha Fern{\'a}ndez-Plaza and N{\'e}stor Arbelo and Miquel Bioque and Clemente Garc{\'i}a-Rizo and Norma Verdolini and Santiago Madero and Andrea Murru and Silvia Amoretti and Anabel Mart{\'i}nez-Aran and Victoria Ruiz and Giovanna Fico and {De Prisco}, Michele and Vincenzo Oliva and Aleix Solanes and Joaquim Radua and Ludovic Samalin and Young, {Allan H.} and Eduard Vieta and Antonio Vergari and Diego Hidalgo-Mazzei",

note = "Funding Information: GA is supported by a Rio Hortega 2021 grant (CM21/00017) from the Spanish Ministry of Health financed by the Instituto de Salud Carlos III (ISCIII) and cofinanced by Fondo Social Europeo Plus (FSE+). FC and BML are supported by the United Kingdom Research and Innovation (grant EP/S02431X/1), UK Research and Innovation (UKRI) Centre for Doctoral Training in Biomedical AI at the University of Edinburgh, School of Informatics. A Mas is supported by an Ag{\`e}ncia de Gesti{\'o} d{\textquoteright}Ajudes Universit{\`a}ries i de Investigaci{\'o} (AGAUR)—PAND{\`E}MIES 2020 grant (PI047003) from the Generalitat de Catalunya. MS is supported by a grant from the Baszucki Brain Research Fund. IG thanks the support of the Spanish Ministry of Science and Innovation (PI19/00954) integrated into the Plan Nacional de I+D+I and cofinanced by the ISCIII-Subdirecci{\'o}n General de Evaluaci{\'o}n y el Fondos Europeos de la Uni{\'o}n Europea (FEDER, FSE, Next Generation EU/Plan de Recuperaci{\'o}n Transformaci{\'o}n y Resiliencia_PRTR); the ISCIII; the CIBER of Mental Health (CIBERSAM); and the Secretaria d{\textquoteright}Universitats i Recerca del Departament d{\textquoteright}Economia i Coneixement (2017 SGR 1365), Centres de Recerca de Catalunya (CERCA) Programme or Generalitat de Catalunya as well as the Fundaci{\'o} Cl{\'i}nic per la Recerca Biom{\`e}dica (Pons Bartran 2022-FRCB_PB1_2022). AG-P is supported by a Rio Hortega 2021 grant (CM21/00094) from the Spanish Ministry of Health financed by ISCIII and cofinanced by Fondo Social Europeo Plus (FSE+). MB thanks the Spanish Ministry of Health and ISCIII (PI20/01066). NV thanks the Biomedicine International Training Research Programme for Excellent Clinician-Scientists (BITRECS) project, which has received funding from the European Union{\textquoteright}s Horizon 2020 research and innovation programme under the Marie Sk{\l}odowska-Curie grant agreement No 754550 and from “La Caixa” Foundation (ID 100010434), under the agreement LCF/PR/GN18/50310006. SM is supported by the grant “Contracte de Recerca Emili Letang-Josep Font” provided by Hospital Cl{\'i}nic de Barcelona. A Murru thanks the support of the Spanish Ministry of Science and Innovation (PI19/00672) integrated into the Plan Nacional de I+D+I and cofinanced by the ISCIII-Subdirecci{\'o}n General de Evaluaci{\'o}n and the Fondo Europeo de Desarrollo Regional (FEDER). SA has been supported by a Sara Borrell contract (CD20/00177), funded by ISCIII and cofunded by the European Social Fund “Investing in your future.” AM-A thanks the support of the Spanish Ministry of Science and Innovation (PI18/00789, PI21/00787) integrated into the Plan Nacional de I+D+I and cofinanced by ISCIII-Subdirecci{\'o}n General de Evaluaci{\'o}n and the FEDER; the ISCIII; the CIBERSAM; the Secretaria d{\textquoteright}Universitats i Recerca del Departament d{\textquoteright}Economia i Coneixement (2017 SGR 1365), the CERCA Programme, and the Departament de Salut de la Generalitat de Catalunya for the PERIS grant SLT006/17/00177. GF is supported by a fellowship from “La Caixa” Foundation (ID 100010434)—fellowship code—LCF/BQ/DR21/11880019. JR is supported by a Miguel Servet II contract (CPII19/00009), funded by ISCIII and cofunded by the European Social Fund “Investing in your future.” EV thanks the support of the Spanish Ministry of Science, Innovation and Universities (PI15/00283, PI18/00805, PI19/00394, CPII19/00009) integrated into the Plan Nacional de I+D+I and cofinanced by the ISCIII-Subdirecci{\'o}n General de Evaluaci{\'o}n and the FEDER; the ISCIII; the CIBERSAM; the Secretaria d{\textquoteright}Universitats i Recerca del Departament d{\textquoteright}Economia i Coneixement (2017 SGR 1365), and the CERCA Programme or Generalitat de Catalunya. The authors would like to thank the Departament de Salut de la Generalitat de Catalunya for the PERIS grant SLT006/17/00357. DH-M is supported by a Juan Rod{\'e}s JR18/00021 granted by the ISCIII. Funding Information: This project was funded by the ISCIII (FIS PI21/00340, TIMEBASE Study), cofunded by the Euopean Union, as well as a Baszucki Brain Research Fund grant (PI046998) from the Milken Foundation. The ISCIII or the Milken Foundation had no further role in study design; in the collection, analysis, and interpretation of data; in the writing of the report; and in the decision to submit the paper for publication. Publisher Copyright: {\textcopyright} Gerard Anmella, Filippo Corponi, Bryan M Li, Ariadna Mas, Miriam Sanabra, Isabella Pacchiarotti, Marc Valent{\'i}, Iria Grande, Antoni Benabarre, Anna Gim{\'e}nez-Palomo, Marina Garriga, Isabel Agasi, Anna Bastidas, Myriam Cavero, Tabatha Fern{\'a}ndez-Plaza, N{\'e}stor Arbelo, Miquel Bioque, Clemente Garc{\'i}a-Rizo, Norma Verdolini, Santiago Madero, Andrea Murru, Silvia Amoretti, Anabel Mart{\'i}nez-Aran, Victoria Ruiz, Giovanna Fico, Michele De Prisco, Vincenzo Oliva, Aleix Solanes, Joaquim Radua, Ludovic Samalin, Allan H Young, Eduard Vieta, Antonio Vergari, Diego Hidalgo-Mazzei.",

year = "2023",

doi = "10.2196/45405",

language = "English",

volume = "11",

journal = "JMIR mHealth and uHealth",

issn = "2291-5222",

publisher = "JMIR Publications",

}

Anmella, G, Corponi, F, Li, BM, Mas, A, Sanabra, M, Pacchiarotti, I, Valentí, M, Grande, I, Benabarre, A, Giménez-Palomo, A, Garriga, M, Agasi, I, Bastidas, A, Cavero, M, Fernández-Plaza, T, Arbelo, N, Bioque, M, García-Rizo, C, Verdolini, N, Madero, S, Murru, A, Amoretti, S, Martínez-Aran, A, Ruiz, V, Fico, G, De Prisco, M, Oliva, V, Solanes, A, Radua, J, Samalin, L, Young, AH, Vieta, E, Vergari, A & Hidalgo-Mazzei, D 2023, 'Exploring Digital Biomarkers of Illness Activity in Mood Episodes: Hypotheses Generating and Model Development Study', JMIR mHealth and uHealth, vol. 11, e45405. https://doi.org/10.2196/45405

TY - JOUR

T1 - Exploring Digital Biomarkers of Illness Activity in Mood Episodes

T2 - Hypotheses Generating and Model Development Study

AU - Anmella, Gerard

AU - Corponi, Filippo

AU - Li, Bryan M.

AU - Mas, Ariadna

AU - Sanabra, Miriam

AU - Pacchiarotti, Isabella

AU - Valentí, Marc

AU - Grande, Iria

AU - Benabarre, Antoni

AU - Giménez-Palomo, Anna

AU - Garriga, Marina

AU - Agasi, Isabel

AU - Bastidas, Anna

AU - Cavero, Myriam

AU - Fernández-Plaza, Tabatha

AU - Arbelo, Néstor

AU - Bioque, Miquel

AU - García-Rizo, Clemente

AU - Verdolini, Norma

AU - Madero, Santiago

AU - Murru, Andrea

AU - Amoretti, Silvia

AU - Martínez-Aran, Anabel

AU - Ruiz, Victoria

AU - Fico, Giovanna

AU - De Prisco, Michele

AU - Oliva, Vincenzo

AU - Solanes, Aleix

AU - Radua, Joaquim

AU - Samalin, Ludovic

AU - Young, Allan H.

AU - Vieta, Eduard

AU - Vergari, Antonio

AU - Hidalgo-Mazzei, Diego

N1 - Funding Information: GA is supported by a Rio Hortega 2021 grant (CM21/00017) from the Spanish Ministry of Health financed by the Instituto de Salud Carlos III (ISCIII) and cofinanced by Fondo Social Europeo Plus (FSE+). FC and BML are supported by the United Kingdom Research and Innovation (grant EP/S02431X/1), UK Research and Innovation (UKRI) Centre for Doctoral Training in Biomedical AI at the University of Edinburgh, School of Informatics. A Mas is supported by an Agència de Gestió d’Ajudes Universitàries i de Investigació (AGAUR)—PANDÈMIES 2020 grant (PI047003) from the Generalitat de Catalunya. MS is supported by a grant from the Baszucki Brain Research Fund. IG thanks the support of the Spanish Ministry of Science and Innovation (PI19/00954) integrated into the Plan Nacional de I+D+I and cofinanced by the ISCIII-Subdirección General de Evaluación y el Fondos Europeos de la Unión Europea (FEDER, FSE, Next Generation EU/Plan de Recuperación Transformación y Resiliencia_PRTR); the ISCIII; the CIBER of Mental Health (CIBERSAM); and the Secretaria d’Universitats i Recerca del Departament d’Economia i Coneixement (2017 SGR 1365), Centres de Recerca de Catalunya (CERCA) Programme or Generalitat de Catalunya as well as the Fundació Clínic per la Recerca Biomèdica (Pons Bartran 2022-FRCB_PB1_2022). AG-P is supported by a Rio Hortega 2021 grant (CM21/00094) from the Spanish Ministry of Health financed by ISCIII and cofinanced by Fondo Social Europeo Plus (FSE+). MB thanks the Spanish Ministry of Health and ISCIII (PI20/01066). NV thanks the Biomedicine International Training Research Programme for Excellent Clinician-Scientists (BITRECS) project, which has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No 754550 and from “La Caixa” Foundation (ID 100010434), under the agreement LCF/PR/GN18/50310006. SM is supported by the grant “Contracte de Recerca Emili Letang-Josep Font” provided by Hospital Clínic de Barcelona. A Murru thanks the support of the Spanish Ministry of Science and Innovation (PI19/00672) integrated into the Plan Nacional de I+D+I and cofinanced by the ISCIII-Subdirección General de Evaluación and the Fondo Europeo de Desarrollo Regional (FEDER). SA has been supported by a Sara Borrell contract (CD20/00177), funded by ISCIII and cofunded by the European Social Fund “Investing in your future.” AM-A thanks the support of the Spanish Ministry of Science and Innovation (PI18/00789, PI21/00787) integrated into the Plan Nacional de I+D+I and cofinanced by ISCIII-Subdirección General de Evaluación and the FEDER; the ISCIII; the CIBERSAM; the Secretaria d’Universitats i Recerca del Departament d’Economia i Coneixement (2017 SGR 1365), the CERCA Programme, and the Departament de Salut de la Generalitat de Catalunya for the PERIS grant SLT006/17/00177. GF is supported by a fellowship from “La Caixa” Foundation (ID 100010434)—fellowship code—LCF/BQ/DR21/11880019. JR is supported by a Miguel Servet II contract (CPII19/00009), funded by ISCIII and cofunded by the European Social Fund “Investing in your future.” EV thanks the support of the Spanish Ministry of Science, Innovation and Universities (PI15/00283, PI18/00805, PI19/00394, CPII19/00009) integrated into the Plan Nacional de I+D+I and cofinanced by the ISCIII-Subdirección General de Evaluación and the FEDER; the ISCIII; the CIBERSAM; the Secretaria d’Universitats i Recerca del Departament d’Economia i Coneixement (2017 SGR 1365), and the CERCA Programme or Generalitat de Catalunya. The authors would like to thank the Departament de Salut de la Generalitat de Catalunya for the PERIS grant SLT006/17/00357. DH-M is supported by a Juan Rodés JR18/00021 granted by the ISCIII. Funding Information: This project was funded by the ISCIII (FIS PI21/00340, TIMEBASE Study), cofunded by the Euopean Union, as well as a Baszucki Brain Research Fund grant (PI046998) from the Milken Foundation. The ISCIII or the Milken Foundation had no further role in study design; in the collection, analysis, and interpretation of data; in the writing of the report; and in the decision to submit the paper for publication. Publisher Copyright: © Gerard Anmella, Filippo Corponi, Bryan M Li, Ariadna Mas, Miriam Sanabra, Isabella Pacchiarotti, Marc Valentí, Iria Grande, Antoni Benabarre, Anna Giménez-Palomo, Marina Garriga, Isabel Agasi, Anna Bastidas, Myriam Cavero, Tabatha Fernández-Plaza, Néstor Arbelo, Miquel Bioque, Clemente García-Rizo, Norma Verdolini, Santiago Madero, Andrea Murru, Silvia Amoretti, Anabel Martínez-Aran, Victoria Ruiz, Giovanna Fico, Michele De Prisco, Vincenzo Oliva, Aleix Solanes, Joaquim Radua, Ludovic Samalin, Allan H Young, Eduard Vieta, Antonio Vergari, Diego Hidalgo-Mazzei.

PY - 2023

Y1 - 2023

N2 - Background: Depressive and manic episodes within bipolar disorder (BD) and major depressive disorder (MDD) involve altered mood, sleep, and activity, alongside physiological alterations wearables can capture. Objective: Firstly, we explored whether physiological wearable data could predict (aim 1) the severity of an acute affective episode at the intra-individual level and (aim 2) the polarity of an acute affective episode and euthymia among different individuals. Secondarily, we explored which physiological data were related to prior predictions, generalization across patients, and associations between affective symptoms and physiological data. Methods: We conducted a prospective exploratory observational study including patients with BD and MDD on acute affective episodes (manic, depressed, and mixed) whose physiological data were recorded using a research-grade wearable (Empatica E4) across 3 consecutive time points (acute, response, and remission of episode). Euthymic patients and healthy controls were recorded during a single session (approximately 48 h). Manic and depressive symptoms were assessed using standardized psychometric scales. Physiological wearable data included the following channels: acceleration (ACC), skin temperature, blood volume pulse, heart rate (HR), and electrodermal activity (EDA). Invalid physiological data were removed using a rule-based filter, and channels were time aligned at 1-second time units and segmented at window lengths of 32 seconds, as best-performing parameters. We developed deep learning predictive models, assessed the channels’ individual contribution using permutation feature importance analysis, and computed physiological data to psychometric scales’ items normalized mutual information (NMI). We present a novel, fully automated method for the preprocessing and analysis of physiological data from a research-grade wearable device, including a viable supervised learning pipeline for time-series analyses. Results: Overall, 35 sessions (1512 hours) from 12 patients (manic, depressed, mixed, and euthymic) and 7 healthy controls (mean age 39.7, SD 12.6 years; 6/19, 32% female) were analyzed. The severity of mood episodes was predicted with moderate (62%-85%) accuracies (aim 1), and their polarity with moderate (70%) accuracy (aim 2). The most relevant features for the former tasks were ACC, EDA, and HR. There was a fair agreement in feature importance across classification tasks (Kendall W=0.383). Generalization of the former models on unseen patients was of overall low accuracy, except for the intra-individual models. ACC was associated with “increased motor activity” (NMI>0.55), “insomnia” (NMI=0.6), and “motor inhibition” (NMI=0.75). EDA was associated with “aggressive behavior” (NMI=1.0) and “psychic anxiety” (NMI=0.52). Conclusions: Physiological data from wearables show potential to identify mood episodes and specific symptoms of mania and depression quantitatively, both in BD and MDD. Motor activity and stress-related physiological data (EDA and HR) stand out as potential digital biomarkers for predicting mania and depression, respectively. These findings represent a promising pathway toward personalized psychiatry, in which physiological wearable data could allow the early identification and intervention of mood episodes.

AB - Background: Depressive and manic episodes within bipolar disorder (BD) and major depressive disorder (MDD) involve altered mood, sleep, and activity, alongside physiological alterations wearables can capture. Objective: Firstly, we explored whether physiological wearable data could predict (aim 1) the severity of an acute affective episode at the intra-individual level and (aim 2) the polarity of an acute affective episode and euthymia among different individuals. Secondarily, we explored which physiological data were related to prior predictions, generalization across patients, and associations between affective symptoms and physiological data. Methods: We conducted a prospective exploratory observational study including patients with BD and MDD on acute affective episodes (manic, depressed, and mixed) whose physiological data were recorded using a research-grade wearable (Empatica E4) across 3 consecutive time points (acute, response, and remission of episode). Euthymic patients and healthy controls were recorded during a single session (approximately 48 h). Manic and depressive symptoms were assessed using standardized psychometric scales. Physiological wearable data included the following channels: acceleration (ACC), skin temperature, blood volume pulse, heart rate (HR), and electrodermal activity (EDA). Invalid physiological data were removed using a rule-based filter, and channels were time aligned at 1-second time units and segmented at window lengths of 32 seconds, as best-performing parameters. We developed deep learning predictive models, assessed the channels’ individual contribution using permutation feature importance analysis, and computed physiological data to psychometric scales’ items normalized mutual information (NMI). We present a novel, fully automated method for the preprocessing and analysis of physiological data from a research-grade wearable device, including a viable supervised learning pipeline for time-series analyses. Results: Overall, 35 sessions (1512 hours) from 12 patients (manic, depressed, mixed, and euthymic) and 7 healthy controls (mean age 39.7, SD 12.6 years; 6/19, 32% female) were analyzed. The severity of mood episodes was predicted with moderate (62%-85%) accuracies (aim 1), and their polarity with moderate (70%) accuracy (aim 2). The most relevant features for the former tasks were ACC, EDA, and HR. There was a fair agreement in feature importance across classification tasks (Kendall W=0.383). Generalization of the former models on unseen patients was of overall low accuracy, except for the intra-individual models. ACC was associated with “increased motor activity” (NMI>0.55), “insomnia” (NMI=0.6), and “motor inhibition” (NMI=0.75). EDA was associated with “aggressive behavior” (NMI=1.0) and “psychic anxiety” (NMI=0.52). Conclusions: Physiological data from wearables show potential to identify mood episodes and specific symptoms of mania and depression quantitatively, both in BD and MDD. Motor activity and stress-related physiological data (EDA and HR) stand out as potential digital biomarkers for predicting mania and depression, respectively. These findings represent a promising pathway toward personalized psychiatry, in which physiological wearable data could allow the early identification and intervention of mood episodes.

KW - bipolar disorder

KW - deep learning

KW - depression

KW - digital biomarker

KW - Empatica E4

KW - machine learning

KW - major depressive disorder

KW - mania

KW - physiological data

KW - wearable

UR - http://www.scopus.com/inward/record.url?scp=85152131859&partnerID=8YFLogxK

U2 - 10.2196/45405

DO - 10.2196/45405

M3 - Article

C2 - 36939345

AN - SCOPUS:85152131859

SN - 2291-5222

VL - 11

JO - JMIR mHealth and uHealth

JF - JMIR mHealth and uHealth

M1 - e45405

ER -

Exploring Digital Biomarkers of Illness Activity in Mood Episodes: Hypotheses Generating and Model Development Study

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this