1
|
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. Exploring digital biomarkers of illness activity in mood episodes: hypotheses generating and model development study. JMIR Mhealth Uhealth 2023; 11:e45405. [PMID: 36939345 DOI: 10.2196/45405] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/29/2022] [Revised: 02/20/2023] [Accepted: 03/07/2023] [Indexed: 03/21/2023] Open
Abstract
BACKGROUND Depressive and manic episodes within bipolar disorder (BD) and major depressive disorder (MDD) involve altered mood, sleep, and activity alongside physiological alterations that wearables can capture. OBJECTIVE We explored whether physiological wearable data could predict: (aim 1) the severity of an acute affective episode at the intra-individual level, (aim 2) the polarity of an acute affective episode and euthymia among different individuals. Secondarily, we explored which physiological data were related to the 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 with a research-grade wearable (Empatica E4) across three consecutive timepoints (acute, response, and remission of episode). Euthymic patients and healthy controls (HC) were recorded during a single session (∼48 hours). Manic and depressive symptoms were assessed with standardized psychometric scales. Physiological wearable data included the following channels: acceleration (ACC), temperature (TEMP), blood volume pulse (BVP), heart rate (HR), and electrodermal activity (EDA). For data pre-processing, invalid physiological data were removed using a rule-based filter, channels were time-aligned at 1 second time units and then segmented window lengths of 32 seconds, since those parameters showed the best performances. We developed deep learning predictive models, assessed 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 analysis of physiological data from a research-grade wearable device, including a rule-based filter for invalid data and a viable supervised learning pipeline for time-series analyses. RESULTS 35 sessions (1,512 hours) from 12 patients (manic, depressed, mixed, and euthymic) and 7 HC (age 39.7±12.6; 31.6% female) were analyzed. (aim 1) The severity of mood episodes was predicted with moderate (62%-85%) accuracies. (aim 2) The polarity of episodes was predicted with moderate (70%) accuracy. The most relevant features for the former tasks were ACC, EDA, and HR. Kendall W showed fair agreement (0.383) in feature importance across classification tasks. Generalization of the former models were of overall low accuracy, with better results for the intra-individual models. "Increased motor activity" was associated with ACC (NMI>0.55), "aggressive behavior" with EDA (NMI=1.0), "insomnia" with ACC (NMI∼0.6), "motor inhibition" with ACC (NMI∼0.75), and "psychic anxiety" with EDA (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 towards personalized psychiatry, in which physiological wearable data could allow early identification and intervention of mood episodes. CLINICALTRIAL
Collapse
Affiliation(s)
- Gerard Anmella
- Hospital Clínic de Barcelona, Villarroel St., 170, 08036 Barcelona, Spain., Barcelona, ES
| | - Filippo Corponi
- School of informatics, University of Edinburgh, UK., Edinburgh, GB
| | - Bryan M Li
- School of informatics, University of Edinburgh, UK., Edinburgh, GB
| | - Ariadna Mas
- Hospital Clínic de Barcelona, Villarroel St., 170, 08036 Barcelona, Spain., Barcelona, ES
| | - Miriam Sanabra
- Hospital Clínic de Barcelona, Villarroel St., 170, 08036 Barcelona, Spain., Barcelona, ES
| | - Isabella Pacchiarotti
- Hospital Clínic de Barcelona, Villarroel St., 170, 08036 Barcelona, Spain., Barcelona, ES
| | - Marc Valentí
- Hospital Clínic de Barcelona, Villarroel St., 170, 08036 Barcelona, Spain., Barcelona, ES
| | - Iria Grande
- Hospital Clínic de Barcelona, Villarroel St., 170, 08036 Barcelona, Spain., Barcelona, ES
| | - Antoni Benabarre
- Hospital Clínic de Barcelona, Villarroel St., 170, 08036 Barcelona, Spain., Barcelona, ES
| | - Anna Giménez-Palomo
- Hospital Clínic de Barcelona, Villarroel St., 170, 08036 Barcelona, Spain., Barcelona, ES
| | - Marina Garriga
- Hospital Clínic de Barcelona, Villarroel St., 170, 08036 Barcelona, Spain., Barcelona, ES
| | - Isabel Agasi
- Hospital Clínic de Barcelona, Villarroel St., 170, 08036 Barcelona, Spain., Barcelona, ES
| | - Anna Bastidas
- Hospital Clínic de Barcelona, Villarroel St., 170, 08036 Barcelona, Spain., Barcelona, ES
| | - Myriam Cavero
- Hospital Clínic de Barcelona, Villarroel St., 170, 08036 Barcelona, Spain., Barcelona, ES
| | | | - Néstor Arbelo
- Hospital Clínic de Barcelona, Villarroel St., 170, 08036 Barcelona, Spain., Barcelona, ES
| | - Miquel Bioque
- Hospital Clínic de Barcelona, Villarroel St., 170, 08036 Barcelona, Spain., Barcelona, ES
| | - Clemente García-Rizo
- Hospital Clínic de Barcelona, Villarroel St., 170, 08036 Barcelona, Spain., Barcelona, ES
| | - Norma Verdolini
- Hospital Clínic de Barcelona, Villarroel St., 170, 08036 Barcelona, Spain., Barcelona, ES
| | - Santiago Madero
- Hospital Clínic de Barcelona, Villarroel St., 170, 08036 Barcelona, Spain., Barcelona, ES
| | - Andrea Murru
- Hospital Clínic de Barcelona, Villarroel St., 170, 08036 Barcelona, Spain., Barcelona, ES
| | - Silvia Amoretti
- Hospital Clínic de Barcelona, Villarroel St., 170, 08036 Barcelona, Spain., Barcelona, ES
| | - Anabel Martínez-Aran
- Hospital Clínic de Barcelona, Villarroel St., 170, 08036 Barcelona, Spain., Barcelona, ES
| | - Victoria Ruiz
- Hospital Clínic de Barcelona, Villarroel St., 170, 08036 Barcelona, Spain., Barcelona, ES
| | - Giovanna Fico
- Hospital Clínic de Barcelona, Villarroel St., 170, 08036 Barcelona, Spain., Barcelona, ES
| | - Michele De Prisco
- Hospital Clínic de Barcelona, Villarroel St., 170, 08036 Barcelona, Spain., Barcelona, ES
| | - Vincenzo Oliva
- Hospital Clínic de Barcelona, Villarroel St., 170, 08036 Barcelona, Spain., Barcelona, ES
| | - Aleix Solanes
- Imaging of Mood- and Anxiety-Related Disorders (IMARD) group, Barcelona, ES
| | - Joaquim Radua
- Imaging of Mood- and Anxiety-Related Disorders (IMARD) group, Barcelona, ES
| | - Ludovic Samalin
- Department of Psychiatry, CHU Clermont-Ferrand, University of Clermont Auvergne, CNRS, Clermont Auvergne INP, Institut Pascal (UMR 6602), Clermont-Ferrand, France., Clermont-Ferrand, FR
| | - Allan H Young
- Centre for Affective Disorders, Institute of Psychiatry, Psychology & Neuroscience, King's College London, London, United Kingdom., London, GB
| | - Eduard Vieta
- Hospital Clínic de Barcelona, Villarroel St., 170, 08036 Barcelona, Spain., Barcelona, ES
| | - Antonio Vergari
- School of informatics, University of Edinburgh, UK., Edinburgh, GB
| | - Diego Hidalgo-Mazzei
- Hospital Clínic de Barcelona, Villarroel St., 170, 08036 Barcelona, Spain., Barcelona, ES
| |
Collapse
|
4
|
Bach V, Abbiss CR, Libert JP, McCabe SM. Skin Temperatures of Back or Neck Are Better Than Abdomen for Indication of Average Proximal Skin Temperature During Sleep of School-Aged Children. Front Psychiatry 2020; 11:494528. [PMID: 33061911 PMCID: PMC7530240 DOI: 10.3389/fpsyt.2020.494528] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/29/2019] [Accepted: 08/31/2020] [Indexed: 11/16/2022] Open
Abstract
PURPOSE The tight association between sleep, body temperature regulation, and patterns of skin temperature change highlights the necessity for accurate and valid assessment of skin temperatures during sleep. With increased interest in this functional relationship in infants and children, it is important to identify where to best measure proximal skin temperature and whether it is possible to reduce the number of sites of measures, in order to limit the experimental effects in natural settings. Thus, the aim of this study was to determine the most suitable single skin temperature sites for representation of average proximal skin temperature during sleep of school aged children. METHODS Statistical analyses were applied to skin temperature data of 22 children, aged 6 to 12 years, measured over four consecutive school nights in their home settings, to compare single site measures of abdomen, back, neck, forehead and subclavicular skin temperatures (local temperatures) with average proximal skin temperatures. RESULTS Abdomen and forehead skin temperatures were significantly different (respectively higher and lower) to the other local proximal temperatures and to average proximal skin temperatures. Moreover, the time pattern of forehead temperature was very different from that of the other local temperatures. CONCLUSIONS Local forehead and abdomen skin temperatures are least suitable as single site representations of average proximal skin temperatures in school aged children when considering both the level and the time course pattern of the temperature across the night. Conversely, back and neck temperatures provide most fitting representation of average proximal skin temperatures.
Collapse
Affiliation(s)
- Véronique Bach
- Peritox, UMR_I 01, University of Picardy Jules Verne, Amiens, France
| | - Chris R Abbiss
- School of Medical and Health Sciences, Edith Cowan University, Joondalup, WA, Australia
| | | | - Susan M McCabe
- School of Medical and Health Sciences, Edith Cowan University, Joondalup, WA, Australia
| |
Collapse
|
6
|
Papolos D, Frei M, Rossignol D, Mattis S, Hernandez-Garcia LC, Teicher MH. Clinical experience using intranasal ketamine in the longitudinal treatment of juvenile bipolar disorder with fear of harm phenotype. J Affect Disord 2018; 225:545-551. [PMID: 28866299 DOI: 10.1016/j.jad.2017.08.081] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/01/2017] [Revised: 08/21/2017] [Accepted: 08/27/2017] [Indexed: 10/19/2022]
Abstract
OBJECTIVES Fear of Harm (FOH) is a pediatric onset phenotype of bipolar disorder (BD) characterized by BD plus treatment resistance, separation anxiety, aggressive obsessions, parasomnias, and thermal dysregulation. Intranasal ketamine (InK) in 12 youths with BD-FOH produced marked improvement during a two-week trial. Here we report on the open effectiveness and safety of InK in maintenance treatment of BD-FOH from the private practice of one author. METHODS As part of a chart review, patients 18 years or older and parents of younger children responded to a clinical effectiveness and safety survey. Effectiveness was assessed from analysis of responses to 49 questions on symptomatology plus qualitative content analyses of written reports and chart review. Adverse events (AEs) were analyzed by frequency, duration and severity. Peak InK doses ranged from 20 to 360mg per administration. RESULTS Surveys were completed on 45 patients treated with InK for 3 months to 6.5 years. Almost all patients were "much" to "very much" improved clinically and in ratings of social function and academic performance. Significant reductions were reported in all symptom categories. There were 13 reports of persistent AEs, none of which resulted in discontinuation. Acute emergence reactions were sporadically observed in up to 75%, but were mild and of brief duration. LIMITATIONS Retrospective review from a single practice without placebo control with potential for response and recall bias. CONCLUSIONS InK every 3-4 days at sub-anesthetic doses appeared to be a beneficial and well-tolerated treatment. Use of InK may be considered as a tertiary alternative in treatment refractory cases. Randomized control trials are warranted.
Collapse
Affiliation(s)
- Demitri Papolos
- Juvenile Bipolar Research Foundation, 277 Martine Avenue, Suite 226 White Plains, NY 10601, United States; Department of Psychiatry, Albert Einstein College of Medicine, New York, United States.
| | - Mark Frei
- Advanced Signal Analysis and Processing, 2360 Sterling Creek Pkwy, Oviedo, FL 32766, United States
| | - Daniel Rossignol
- Juvenile Bipolar Research Foundation, 277 Martine Avenue, White Plains, NY 10601, United States
| | - Steven Mattis
- Department of Psychiatry Cornell-Weil Medical College of Medicine, United States
| | - Laura C Hernandez-Garcia
- Developmental Biopsychiatry Research Program, McLean Hospital, Department of Psychiatry, Harvard Medical School, United States
| | - Martin H Teicher
- Developmental Biopsychiatry Research Program, McLean Hospital, Department of Psychiatry, Harvard Medical School, United States
| |
Collapse
|