Automated Speech Analysis in Bipolar Disorder: The CALIBER Study Protocol and Preliminary Results.

Background: Bipolar disorder (BD) involves significant mood and energy shifts reflected in speech patterns. Detecting these patterns is crucial for diagnosis and monitoring, currently assessed subjectively. Advances in natural language processing offer opportunities to objectively analyze them. Aims: To (i) correlate speech features with manic-depressive symptom severity in BD, (ii) develop predictive models for diagnostic and treatment outcomes, and (iii) determine the most relevant speech features and tasks for these analyses. Methods: This naturalistic, observational study involved longitudinal audio recordings of BD patients at euthymia, during acute manic/depressive phases, and after-response. Patients participated in clinical evaluations, cognitive tasks, standard text readings, and storytelling. After automatic diarization and transcription, speech features, including acoustics, content, formal aspects, and emotionality, will be extracted. Statistical analyses will (i) correlate speech features with clinical scales, (ii) use lasso logistic regression to develop predictive models, and (iii) identify relevant speech features. Results: Audio recordings from 76 patients (24 manic, 21 depressed, 31 euthymic) were collected. The mean age was 46.0 ± 14.4 years, with 63.2% female. The mean YMRS score for manic patients was 22.9 ± 7.1, reducing to 5.3 ± 5.3 post-response. Depressed patients had a mean HDRS-17 score of 17.1 ± 4.4, decreasing to 3.3 ± 2.8 post-response. Euthymic patients had mean YMRS and HDRS-17 scores of 0.97 ± 1.4 and 3.9 ± 2.9, respectively. Following data pre-processing, including noise reduction and feature extraction, comprehensive statistical analyses will be conducted to explore correlations and develop predictive models. Conclusions: Automated speech analysis in BD could provide objective markers for psychopathological alterations, improving diagnosis, monitoring, and response prediction. This technology could identify subtle alterations, signaling early signs of relapse. Establishing standardized protocols is crucial for creating a global speech cohort, fostering collaboration, and advancing BD understanding.

Identifying digital biomarkers of illness activity and treatment response in bipolar disorder with a novel wearable device (TIMEBASE): protocol for a pragmatic observational clinical study.

BACKGROUND: Bipolar disorder is highly prevalent and consists of biphasic recurrent mood episodes of mania and depression, which translate into altered mood, sleep and activity alongside their physiological expressions. AIMS: The IdenTifying dIgital bioMarkers of illnEss activity and treatment response in BipolAr diSordEr with a novel wearable device (TIMEBASE) project aims to identify digital biomarkers of illness activity and treatment response in bipolar disorder. METHOD: We designed a longitudinal observational study including 84 individuals. Group A comprises people with acute episode of mania (n = 12), depression (n = 12 with bipolar disorder and n = 12 with major depressive disorder (MDD)) and bipolar disorder with mixed features (n = 12). Physiological data will be recorded during 48 h with a research-grade wearable (Empatica E4) across four consecutive time points (acute, response, remission and episode recovery). Group B comprises 12 people with euthymic bipolar disorder and 12 with MDD, and group C comprises 12 healthy controls who will be recorded cross-sectionally. Psychopathological symptoms, disease severity, functioning and physical activity will be assessed with standardised psychometric scales. Physiological data will include acceleration, temperature, blood volume pulse, heart rate and electrodermal activity. Machine learning models will be developed to link physiological data to illness activity and treatment response. Generalisation performance will be tested in data from unseen patients. RESULTS: Recruitment is ongoing. CONCLUSIONS: This project should contribute to understanding the pathophysiology of affective disorders. The potential digital biomarkers of illness activity and treatment response in bipolar disorder could be implemented in a real-world clinical setting for clinical monitoring and identification of prodromal symptoms. This would allow early intervention and prevention of affective relapses, as well as personalisation of treatment.

Wearable Data From Subjects Playing Super Mario, Taking University Exams, or Performing Physical Exercise Help Detect Acute Mood Disorder Episodes via Self-Supervised Learning: Prospective, Exploratory, Observational Study.

BACKGROUND: Personal sensing, leveraging data passively and near-continuously collected with wearables from patients in their ecological environment, is a promising paradigm to monitor mood disorders (MDs), a major determinant of the worldwide disease burden. However, collecting and annotating wearable data is resource intensive. Studies of this kind can thus typically afford to recruit only a few dozen patients. This constitutes one of the major obstacles to applying modern supervised machine learning techniques to MD detection. OBJECTIVE: In this paper, we overcame this data bottleneck and advanced the detection of acute MD episodes from wearables' data on the back of recent advances in self-supervised learning (SSL). This approach leverages unlabeled data to learn representations during pretraining, subsequently exploited for a supervised task. METHODS: We collected open access data sets recording with the Empatica E4 wristband spanning different, unrelated to MD monitoring, personal sensing tasks-from emotion recognition in Super Mario players to stress detection in undergraduates-and devised a preprocessing pipeline performing on-/off-body detection, sleep/wake detection, segmentation, and (optionally) feature extraction. With 161 E4-recorded subjects, we introduced E4SelfLearning, the largest-to-date open access collection, and its preprocessing pipeline. We developed a novel E4-tailored transformer (E4mer) architecture, serving as the blueprint for both SSL and fully supervised learning; we assessed whether and under which conditions self-supervised pretraining led to an improvement over fully supervised baselines (ie, the fully supervised E4mer and pre-deep learning algorithms) in detecting acute MD episodes from recording segments taken in 64 (n=32, 50%, acute, n=32, 50%, stable) patients. RESULTS: SSL significantly outperformed fully supervised pipelines using either our novel E4mer or extreme gradient boosting (XGBoost): n=3353 (81.23%) against n=3110 (75.35%; E4mer) and n=2973 (72.02%; XGBoost) correctly classified recording segments from a total of 4128 segments. SSL performance was strongly associated with the specific surrogate task used for pretraining, as well as with unlabeled data availability. CONCLUSIONS: We showed that SSL, a paradigm where a model is pretrained on unlabeled data with no need for human annotations before deployment on the supervised target task of interest, helps overcome the annotation bottleneck; the choice of the pretraining surrogate task and the size of unlabeled data for pretraining are key determinants of SSL success. We introduced E4mer, which can be used for SSL, and shared the E4SelfLearning collection, along with its preprocessing pipeline, which can foster and expedite future research into SSL for personal sensing.

Sleep-wake variations of electrodermal activity in bipolar disorder.

BACKGROUND: Affective states influence the sympathetic nervous system, inducing variations in electrodermal activity (EDA), however, EDA association with bipolar disorder (BD) remains uncertain in real-world settings due to confounders like physical activity and temperature. We analysed EDA separately during sleep and wakefulness due to varying confounders and potential differences in mood state discrimination capacities. METHODS: We monitored EDA from 102 participants with BD including 35 manic, 29 depressive, 38 euthymic patients, and 38 healthy controls (HC), for 48 h. Fifteen EDA features were inferred by mixed-effect models for repeated measures considering sleep state, group and covariates. RESULTS: Thirteen EDA feature models were significantly influenced by sleep state, notably including phasic peaks (p < 0.001). During wakefulness, phasic peaks showed different values for mania (M [SD] = 6.49 [5.74, 7.23]), euthymia (5.89 [4.83, 6.94]), HC (3.04 [1.65, 4.42]), and depression (3.00 [2.07, 3.92]). Four phasic features during wakefulness better discriminated between HC and mania or euthymia, and between depression and euthymia or mania, compared to sleep. Mixed symptoms, average skin temperature, and anticholinergic medication affected the models, while sex and age did not. CONCLUSION: EDA measured from awake recordings better distinguished between BD states than sleep recordings, when controlled by confounders.

Lithium response in bipolar disorder: Epigenome-wide DNA methylation signatures and epigenetic aging.

Lithium (Li) is the first-line treatment for bipolar disorder (BD) even though only 30 % of BD patients are considered excellent responders. The mechanisms by which Li exerts its action are not clearly understood, but it has been suggested that specific epigenetic mechanisms, such as methylation processes, may play a role. In this regard, DNA methylation patterns can be used to estimate epigenetic age (EpiAge), which is accelerated in BD patients and reversed by Li treatment. Our first aim was to compare the DNA methylation profile in peripheral blood between BD patients categorized as excellent responders to Li (Ex-Rp) and non-responders (N-Rp). Secondly, EpiAge was estimated to detect differential age acceleration between the two groups. A total of 130 differentially methylated positions (DMPs) and 16 differentially methylated regions (DMRs) between Ex-Rp (n = 26) and N-Rp (n = 37) were identified (FDR adjusted p-value < 0.05). We found 122 genes mapping the DMPs and DMRs, nine of which (HOXB6, HOXB3, HOXB-AS3, TENM2, CACNA1B, ANK3, EEF2K, CYP1A1, and SORCS2) had previously been linked to Li response. We found genes related to the GSK3ß pathway to be highly represented. Using FUMA, we found enrichment in Gene Ontology Cell Component for the synapse. Gene network analysis highlighted functions related to the cell cycle, nervous system development and function, and gene expression. No significant differences in age acceleration were found between Ex-Rp and N-Rp for any of the epigenetic clocks analysed. Our findings indicate that a specific methylation pattern could determine the response to Li in BD patients. We also found that a significant portion of the differentially methylated genes are closely associated with the GSK3ß pathway, reinforcing the role of this system in Li response. Future longitudinal studies with larger samples will help to elucidate the epigenetic mechanisms underlying Li response.

Automated mood disorder symptoms monitoring from multivariate time-series sensory data: getting the full picture beyond a single number.

Mood disorders (MDs) are among the leading causes of disease burden worldwide. Limited specialized care availability remains a major bottleneck thus hindering pre-emptive interventions. MDs manifest with changes in mood, sleep, and motor activity, observable in ecological physiological recordings thanks to recent advances in wearable technology. Therefore, near-continuous and passive collection of physiological data from wearables in daily life, analyzable with machine learning (ML), could mitigate this problem, bringing MDs monitoring outside the clinician's office. Previous works predict a single label, either the disease state or a psychometric scale total score. However, clinical practice suggests that the same label may underlie different symptom profiles, requiring specific treatments. Here we bridge this gap by proposing a new task: inferring all items in HDRS and YMRS, the two most widely used standardized scales for assessing MDs symptoms, using physiological data from wearables. To that end, we develop a deep learning pipeline to score the symptoms of a large cohort of MD patients and show that agreement between predictions and assessments by an expert clinician is clinically significant (quadratic Cohen's κ and macro-average F1 score both of 0.609). While doing so, we investigate several solutions to the ML challenges associated with this task, including multi-task learning, class imbalance, ordinal target variables, and subject-invariant representations. Lastly, we illustrate the importance of testing on out-of-distribution samples.

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

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.

Association of Polygenic Score and the involvement of Cholinergic and Glutamatergic Pathways with Lithium Treatment Response in Patients with Bipolar Disorder.

Lithium is regarded as the first-line treatment for bipolar disorder (BD), a severe and disabling mental disorder that affects about 1% of the population worldwide. Nevertheless, lithium is not consistently effective, with only 30% of patients showing a favorable response to treatment. To provide personalized treatment options for bipolar patients, it is essential to identify prediction biomarkers such as polygenic scores. In this study, we developed a polygenic score for lithium treatment response (Li+PGS) in patients with BD. To gain further insights into lithium's possible molecular mechanism of action, we performed a genome-wide gene-based analysis. Using polygenic score modeling, via methods incorporating Bayesian regression and continuous shrinkage priors, Li+PGS was developed in the International Consortium of Lithium Genetics cohort (ConLi+Gen: N=2,367) and replicated in the combined PsyCourse (N=89) and BipoLife (N=102) studies. The associations of Li+PGS and lithium treatment response - defined in a continuous ALDA scale and a categorical outcome (good response vs. poor response) were tested using regression models, each adjusted for the covariates: age, sex, and the first four genetic principal components. Statistical significance was determined at P<����������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������.

Emotional intelligence: a comparison between patients after first episode mania and those suffering from chronic bipolar disorder type I.

BACKGROUND: Deficits in emotional intelligence (EI) were detected in patients with bipolar disorder (BD), but little is known about whether these deficits are already present in patients after presenting a first episode mania (FEM). We sought (i) to compare EI in patients after a FEM, chronic BD and healthy controls (HC); (ii) to examine the effect exerted on EI by socio-demographic, clinical and neurocognitive variables in FEM patients. METHODS: The Emotional Intelligence Quotient (EIQ) was calculated with the Mayer-Salovey-Caruso Emotional Intelligence Test (MSCEIT). Performance on MSCEIT was compared among the three groups using generalized linear models. In patients after a FEM, the influence of socio-demographic, clinical and neurocognitive variables on the EIQ was examined using a linear regression model. RESULTS: In total, 184 subjects were included (FEM n = 48, euthymic chronic BD type I n = 75, HC n = 61). BD patients performed significantly worse than HC on the EIQ [mean difference (MD) = 10.09, standard error (s.e.) = 3.14, p = 0.004] and on the understanding emotions branch (MD = 7.46, s.e. = 2.53, p = 0.010). FEM patients did not differ from HC and BD on other measures of MSCEIT. In patients after a FEM, EIQ was positively associated with female sex (ß = -0.293, p = 0.034) and verbal memory performance (ß = 0.374, p = 0.008). FEM patients performed worse than HC but better than BD on few neurocognitive domains. CONCLUSIONS: Patients after a FEM showed preserved EI, while patients in later stages of BD presented lower EIQ, suggesting that impairments in EI might result from the burden of disease and neurocognitive decline, associated with the chronicity of the illness.