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.

Definition of early age at onset in bipolar disorder according to distinctive neurodevelopmental pathways: insights from the FACE-BD study.

BACKGROUND: Converging evidence suggests that a subgroup of bipolar disorder (BD) with an early age at onset (AAO) may develop from aberrant neurodevelopment. However, the definition of early AAO remains unprecise. We thus tested which age cut-off for early AAO best corresponds to distinguishable neurodevelopmental pathways. METHODS: We analyzed data from the FondaMental Advanced Center of Expertise-Bipolar Disorder cohort, a naturalistic sample of 4421 patients. First, a supervised learning framework was applied in binary classification experiments using neurodevelopmental history to predict early AAO, defined either with Gaussian mixture models (GMM) clustering or with each of the different cut-offs in the range 14 to 25 years. Second, an unsupervised learning approach was used to find clusters based on neurodevelopmental factors and to examine the overlap between such data-driven groups and definitions of early AAO used for supervised learning. RESULTS: A young cut-off, i.e. 14 up to 16 years, induced higher separability [mean nested cross-validation test AUROC = 0.7327 (± 0.0169) for ⩽16 years]. Predictive performance deteriorated increasing the cut-off or setting early AAO with GMM. Similarly, defining early AAO below 17 years was associated with a higher degree of overlap with data-driven clusters (Normalized Mutual Information = 0.41 for ⩽17 years) relatively to other definitions. CONCLUSIONS: Early AAO best captures distinctive neurodevelopmental patterns when defined as ⩽17 years. GMM-based definition of early AAO falls short of mapping to highly distinguishable neurodevelopmental pathways. These results should be used to improve patients' stratification in future studies of BD pathophysiology and biomarkers.

Lithium therapy and weight change in people with bipolar disorder: A systematic review and meta-analysis.

Lithium remains the gold standard maintenance treatment for Bipolar Disorder (BD). However, weight gain is a side effect of increasing relevance due to its metabolic implications. We conducted a systematic review and meta-analysis aimed at summarizing evidence on the use of lithium and weight change in BD. We followed the PRISMA methodology, searching Pubmed, Scopus and Web of Science. From 1003 screened references, 20 studies were included in the systematic review and 9 included in the meta-analysis. In line with the studies included in the systematic review, the meta-analysis revealed that weight gain with lithium was not significant, noting a weight increase of 0.462 Kg (p = 0158). A shorter duration of treatment was significantly associated with more weight gain. Compared to placebo, there were no significant differences in weight gain. Weight gain was significantly lower with lithium than with active comparators. This work reveals a low impact of lithium on weight change, especially compared to some of the most widely used active comparators. Our results could impact clinical decisions.

The biology of aggressive behavior in bipolar disorder: A systematic review.

Aggressive behavior (AB) represents a public health concern often associated with severe psychiatric disorders. Although most psychiatric patients are not aggressive, untreated psychiatric illness, including bipolar disorder (BD), may associate with an increased risk of AB. Accurate predictive models of AB are still lacking and it is crucial to delineate AB biomarkers state of the art in BD. We performed a systematic review according to PRISMA guidelines to identify biological correlates of AB in BD. Final results included 20 studies: 10 involving genetic and 10 other biological AB biomarkers (total sample size N = 5,181). Our results pointed to a serotoninergic hypoactivation in violent suicidal BD patients. Similarly, BD violent suicide attempters had a blunted hypothalamic-pituitary-adrenal (HPA) activity. Violent behavior in BD was associated with a chronic inflammatory state. While the role of lipids as biomarkers for AB remains equivocal, uric acid appears as a potential biomarker for hetero-AB in BD. Available data can be useful in the fulfill of specific biomarkers of AB in BD, ultimately leading to the development of accurate predictive models.

Deconstructing major depressive episodes across unipolar and bipolar depression by severity and duration: a cross-diagnostic cluster analysis on a large, international, observational study.

A cross-diagnostic, post-hoc analysis of the BRIDGE-II-MIX study was performed to investigate how unipolar and bipolar patients suffering from an acute major depressive episode (MDE) cluster according to severity and duration. Duration of index episode, Clinical Global Impression-Bipolar Version-Depression (CGI-BP-D) and Global Assessment of Functioning (GAF) were used as clustering variables. MANOVA and post-hoc ANOVAs examined between-group differences in clustering variables. A stepwise backward regression model explored the relationship with the 56 clinical-demographic variables available. Agglomerative hierarchical clustering with two clusters was shown as the best fit and separated the study population (n = 2314) into 65.73% (Cluster 1 (C1)) and 34.26% (Cluster 2 (C2)). MANOVA showed a significant main effect for cluster group (p < 0.001) but ANOVA revealed that significant between-group differences were restricted to CGI-BP-D (p < 0.001) and GAF (p < 0.001), showing greater severity in C2. Psychotic features and a minimum of three DSM-5 criteria for mixed features (DSM-5-3C) had the strongest association with C2, that with greater disease burden, while non-mixed depression in bipolar disorder (BD) type II had negative association. Mixed affect defined as DSM-5-3C associates with greater acute severity and overall impairment, independently of the diagnosis of bipolar or unipolar depression. In this study a pure, non-mixed depression in BD type II significantly associates with lesser burden of clinical and functional severity. The lack of association for less restrictive, researched-based definitions of mixed features underlines DSM-5-3C specificity. If confirmed in further prospective studies, these findings would warrant major revisions of treatment algorithms for both unipolar and bipolar depression.

Symptom networks in acute depression across bipolar and major depressive disorders: A network analysis on a large, international, observational study.

Major Depressive Episode (MDE) is a transdiagnostic nosographic construct straddling Major Depressive (MDD) and Bipolar Disorder (BD). Prognostic and treatment implications warrant a differentiation between these two disorders. Network analysis is a novel approach that outlines symptoms interactions in psychopathological networks. We investigated the interplay among depressive and mixed symptoms in acutely depressed MDD/BD patients, using a data-driven approach. We analyzed 7 DSM-IV-TR criteria for MDE and 14 researched-based criteria for mixed features (RBDC) in 2758 acutely depressed MDD/BD patients from the BRIDGE-II-Mix study. The global network was described in terms of symptom thresholds and symptom centrality. Symptom endorsement rates were compared across diagnostic subgroups. Subsequently, MDD/BD differences in symptom-network structure were examined using permutation-based network comparison test. Mixed symptoms were the most central and highly interconnected nodes in the network, particularly agitation followed by irritability. Despite mixed symptoms, appetite gain and hypersomnia were significantly more endorsed in BD patients, associations between symptoms were highly correlated across MDD/BD (Spearman's r = 0.96, p<0.001). Network comparison tests showed no significant differences among MDD/BD in network strength, structure, or specific edges, with strong edges correlations (0.66-0.78). Upstream differences in MDD/BD may produce similar symptoms networks downstream during acute depression. Yet, mixed symptoms, appetite gain and hypersomnia are associated to BD rather than MDD. Symptoms during mixed-MDE might aggregate according to 2 different clusters, suggesting a possible stratification within mixed states. Future symptom-based studies should implement clinical, longitudinal, and biological factors, in order to establish tailored therapeutic strategies for acute depression.

Genetics of resilience: Implications from genome-wide association studies and candidate genes of the stress response system in posttraumatic stress disorder and depression.

Resilience is the ability to cope with critical situations through the use of personal and socially mediated resources. Since a lack of resilience increases the risk of developing stress-related psychiatric disorders such as posttraumatic stress disorder (PTSD) and major depressive disorder (MDD), a better understanding of the biological background is of great value to provide better prevention and treatment options. Resilience is undeniably influenced by genetic factors, but very little is known about the exact underlying mechanisms. A recently published genome-wide association study (GWAS) on resilience has identified three new susceptibility loci, DCLK2, KLHL36, and SLC15A5. Further interesting results can be found in association analyses of gene variants of the stress response system, which is closely related to resilience, and PTSD and MDD. Several promising genes, such as the COMT (catechol-O-methyltransferase) gene, the serotonin transporter gene (SLC6A4), and neuropeptide Y (NPY) suggest gene × environment interaction between genetic variants, childhood adversity, and the occurrence of PTSD and MDD, indicating an impact of these genes on resilience. GWAS on PTSD and MDD provide another approach to identifying new disease-associated loci and, although the functional significance for disease development for most of these risk genes is still unknown, they are potential candidates due to the overlap of stress-related psychiatric disorders and resilience. In the future, it will be important for genetic studies to focus more on resilience than on pathological phenotypes, to develop reasonable concepts for measuring resilience, and to establish international cooperations to generate sufficiently large samples.

Pharmacogenetics and Depression: A Critical Perspective.

Depression leads the higher personal and socio-economical burden within psychiatric disorders. Despite the fact that over 40 antidepressants (ADs) are available, suboptimal response still poses a major challenge and is thought to be partially a result of genetic variation. Pharmacogenetics studies the effects of genetic variants on treatment outcomes with the aim of providing tailored treatments, thereby maximizing efficacy and tolerability. After two decades of pharmacogenetic research, variants in genes coding for the cytochromes involved in ADs metabolism (CYP2D6 and CYP2C19) are now considered biomarkers with sufficient scientific support for clinical application, despite the lack of conclusive cost/effectiveness evidence. The effect of variants in genes modulating ADs mechanisms of action (pharmacodynamics) is still controversial, because of the much higher complexity of ADs pharmacodynamics compared to ADs metabolism. Considerable progress has been made since the era of candidate gene studies: the genomic revolution has made possible to assess genetic variance on an unprecedented scale, throughout the whole genome, and to analyze the cumulative effect of different variants. The results have revealed key information on the biological mechanisms mediating ADs effect and identified hypothetical new pharmacological targets. They also paved the way for future availability of polygenic pharmacogenetic panels to predict treatment outcome, which are expected to explain much higher variance in ADs response compared to CYP2D6 and CYP2C19 only. As the demand and availability of AD pharmacogenetic testing is projected to increase, it is important for clinicians to keep abreast of this evolving area to facilitate informed discussions with their patients.

Novel antipsychotics specificity profile: A clinically oriented review of lurasidone, brexpiprazole, cariprazine and lumateperone.

Second generation antipsychotics (SGAs) are effective options in the treatment of schizophrenia and mood disorders, each with characteristic efficacy and safety features. In order to optimize the balance between efficacy and side effects, it is of upmost importance to match compound specificity against patient clinical profile. As the number of SGAs increased, this review can assist physicians in the prescription of three novel SGAs already on the market, namely lurasidone, brexpiprazole, cariprazine, and lumateperone, which is in the approval phase for schizophrenia treatment at the FDA. Besides schizophrenia, EMA and/or FDA approved lurasidone for bipolar depression, brexpiprazole as augmentation in major depressive disorder and cariprazine for the acute treatment of manic or mixed episodes associated with bipolar I disorder. These new antipsychotics were developed with the aim of improving efficacy on negative and depressive symptoms and reducing metabolic and cardiovascular side effects compared to prior SGAs, while keeping the risk of extrapyramidal symptoms low. They succeeded quite well in containing these side effects, despite weight gain during acute treatment remains a possible concern for brexpiprazole, while cariprazine and lurasidone show higher risk of akathisia compared to placebo and other SGAs such as olanzapine. The available studies support the expected benefits on negative symptoms, cognitive dysfunction and depressive symptoms, while the overall effect on acute psychotic symptoms may be similar to other SGAs such as quetiapine, aripiprazole and ziprasidone. The discussed new antipsychotics represent useful therapeutic options but their efficacy and side effect profiles should be considered to personalize prescription.

Corrected QT Interval Prolongation in Psychopharmacological Treatment and Its Modulation by Genetic Variation.

Several antipsychotics and antidepressants have been associated with electrocardiogram alterations, the most clinically relevant of which is the heart rate-corrected QT interval (QTc) prolongation, a risk factor for sudden cardiac death. Genetic variants influence drug-induced QTc prolongation and can provide valuable information for precision medicine. The effect of genetic variants on QTc prolongation as well as the possible interaction between polymorphisms and risk medications in determining QTc prolongation were investigated. Medications were classified according to their known risk of inducing QTc prolongation (high-to-moderate, low, and no risk). QTc duration and risk of QTc > median value were investigated in a sample of 77 patients with mood or psychotic disorders being treated with antidepressants and antipsychotics, and who had at least 1 ECG recording. A secondary analysis considered QTc percentage change in patients (n = 25) with 2 ECG recordings. Single-nucleotide polymorphisms previously associated with QTc prolongation during treatment with psychotropic medications were investigated. No association survived after multiple-testing correction. The best results for modulation of QTc duration were identified for rs10808071 (the ABCB1 gene, nominal p = 0.007) when at least 1 medication with a moderate-to-high risk was prescribed, and for rs12029454 (the NOS1AP gene) in patients taking at least 1 medication with a cardiovascular risk (nominal p = 0.008). In the secondary analysis, rs2072413 (the KCNH2 gene) was the top finding for the modulation of QTc percentage change (nominal p = 0.001) when 1 drug with a moderate-to-high risk was added compared to baseline. Despite the limited power of this study, our results suggest that ABCB1, NOS1AP, and KCNH2 may play a role in QTc duration/prolongation during treatment with psychotropic drugs.

Genetic basis of psychopathological dimensions shared between schizophrenia and bipolar disorder.

Shared genetic vulnerability between schizophrenia (SCZ) and bipolar disorder (BP) was demonstrated, but the genetic underpinnings of specific symptom domains are unclear. This study investigated which genes and gene sets may modulate specific psychopathological domains and if genome-wide significant loci previously associated with SCZ or BP may play a role. Genome-wide data were available in patients with SCZ (n = 226) or BP (n = 228). Phenotypes under investigation were depressive and positive symptoms severity, suicidal ideation, onset age and substance use disorder comorbidity. Genome-wide analyses were performed at gene and gene set level, while 148 genome-wide significant loci previously associated with SCZ and/or BP were investigated. Each sample was analyzed separately then a meta-analysis was performed. SH3GL2 and CLVS1 genes were associated with suicidal ideation in SCZ (p = 5.62e-08 and 0.01, respectively), the former also in the meta-analysis (p = .01). SHC4 gene was associated with depressive symptoms severity in BP (p = .003). A gene set involved in cellular differentiation (GO:0048661) was associated with substance disorder comorbidity in the meta-analysis (p = .03). Individual loci previously associated with SCZ or BP did not modulate the phenotypes of interest. This study provided confirmatory and new findings. SH3GL2 (endophilin A1) showed a role in suicidal ideation that may be due to its relevance to the glutamate system. SHC4 regulates BDNF-induced MAPK activation and was previously associated with depression. CLVS1 is involved in lysosome maturation and was for the first time associated with a psychiatric trait. GO:0048661 may mediate the risk of substance disorder through an effect on neurodevelopment/neuroplasticity.

The Genetics of Treatment-Resistant Depression: A Critical Review and Future Perspectives.

Background: One-third of depressed patients develop treatment-resistant depression with the related sequelae in terms of poor functionality and worse prognosis. Solid evidence suggests that genetic variants are potentially valid predictors of antidepressant efficacy and could be used to provide personalized treatments. Methods: The present review summarizes genetic findings of treatment-resistant depression including results from candidate gene studies and genome-wide association studies. The limitations of these approaches are discussed, and suggestions to improve the design of future studies are provided. Results: Most studies used the candidate gene approach, and few genes showed replicated associations with treatment-resistant depression and/or evidence obtained through complementary approaches (e.g., gene expression studies). These genes included GRIK4, BDNF, SLC6A4, and KCNK2, but confirmatory evidence in large cohorts was often lacking. Genome-wide association studies did not identify any genome-wide significant association at variant level, but pathways including genes modulating actin cytoskeleton, neural plasticity, and neurogenesis may be associated with treatment-resistant depression, in line with results obtained by genome-wide association studies of antidepressant response. The improvement of aggregated tests (e.g., polygenic risk scores), possibly using variant/gene prioritization criteria, the increase in the covering of genetic variants, and the incorporation of clinical-demographic predictors of treatment-resistant depression are proposed as possible strategies to improve future pharmacogenomic studies. Conclusions: Genetic biomarkers to identify patients with higher risk of treatment-resistant depression or to guide treatment in these patients are not available yet. Methodological improvements of future studies could lead to the identification of genetic biomarkers with clinical validity.

Pharmacogenetics in Psychiatry.

Mental illness represents a major health issue both at the individual and at the socioeconomical level. This is partly due to the current suboptimal treatment options: existing psychotropic medications, including antidepressants, antipsychotics, and mood stabilizers, are effective only in a subset of patients or produce partial response and they are often associated with debilitating side effects that discourage adherence. Pharmacogenetics is the study of how genetic information impacts on drug response/side effects with the goal to provide tailored treatments, thereby maximizing efficacy and tolerability. The first pharmacogenetic studies focused on candidate genes, previously known to be relevant to the pharmacokinetics and pharmacodynamics of psychotropic drugs. Results were mainly inconclusive, but some replicated candidates were identified and included as pharmacogenetic biomarkers in drug labeling and in some commercial kits. With the advent of the genomic revolution, it became possible to study the genetic variation on an unprecedented scale, throughout the whole genome with no need of a priori hypothesis. This may lead to the personalized prescription of existing medications and potentially to the development of innovative ones, thanks to new insights into the genetics of mental illness. Promising findings were obtained, but methods for the generation and analysis of genome-wide and sequencing data are still in evolution. Future pharmacogenetic tests may consist of hundreds/thousands of polymorphisms throughout the genome or selected pathways in order to take into account the complex interactions across variants in a number of genes.

Pleiotropic genes in psychiatry: Calcium channels and the stress-related FKBP5 gene in antidepressant resistance.

A candidate gene and a genome-wide approach were combined to study the pharmacogenetics of antidepressant response and resistance. Investigated genes were selected on the basis of pleiotropic effect across psychiatric phenotypes in previous genome-wide association studies and involvement in antidepressant response. Three samples with major depressive disorder (total=671) were genotyped for 44 SNPs in 8 candidate genes (CACNA1C, CACNB2, ANK3, GRM7, TCF4, ITIH3, SYNE1, FKBP5). Phenotypes were response/remission after 4weeks of treatment and treatment-resistant depression (TRD). Genome-wide data from STAR*D were used to replicate findings for response/remission (n=1409) and TRD (n=620). Pathways including the most promising candidate genes were investigated in STAR*D for involvement in TRD. FKBP5 polymorphisms showed replicated but nominal associations with response, remission or TRD. CACNA1C rs1006737 and rs10848635 were the only polymorphisms that survived multiple-testing correction. In STAR*D the best pathway associated with TRD included CACNA1C (GO:0006942, permutated p=0.15). Machine learning models showed that independent SNPs in this pathway predicted TRD with a mean sensitivity of 0.83 and specificity of 0.56 after 10-fold cross validation repeated 100 times. FKBP5 polymorphisms appear good candidates for inclusion in antidepressant pharmacogenetic tests. Pathways including the CACNA1C gene may be involved in TRD and they may provide the base for developing multi-marker predictors of TRD.

Cariprazine specificity profile in the treatment of acute schizophrenia: a meta-analysis and meta-regression of randomized-controlled trials.

Cariprazine is a new dopamine D2 and D3 receptor partial agonist antipsychotic. Meta-analytic evidence of efficacy in acute schizophrenia and specific groups of patients is lacking. We carried out a meta-analysis in patients with acute schizophrenia to evaluate the efficacy of cariprazine over placebo and active comparators in overall symptoms, positive and negative symptoms and quality of life. Low and high (≥6 mg/day) doses were tested separately. The possible effect of clinical-demographic modulators was also tested. Four studies (2144 patients) were included. Both high and low cariprazine doses proved superior to placebo in all symptom domains. The standardized mean difference (SMD) to placebo showed a modest impact on overall symptoms compared with meta-analytic results for other antipsychotics (SMD was similar to lurasidone, asenapine, ziprasidone and aripiprazole, but lower than risperidone, quetiapine and olanzapine). The SMD to placebo on negative symptoms was superior to many antipsychotics including aripiprazole, with a slightly more relevant effect of cariprazine low doses. This effect was probably on secondary negative symptoms since the short-term follow-up of the studies included. Meta-regression data further refined the compound clinical profile, suggesting that cariprazine may be particularly useful in young patients with a relatively short duration of disease.