Machine learning and neuroimaging in mood disorders: A promising path forward.

Can Machine Learning Decode Depression?

Differentiating between the diagnoses of mood disorders and other psychiatric disorders, and predicting treatment response in depression has long been a concern for clinicians. Machine learning (ML) is one part of artificial intelligence that focuses on instructing computers to mimic the cognitive abilities of the human brain through training. This study will review the research on the use of ML techniques to differentiate diagnoses and predict treatment responses in mood disorders based on electroencephalography (EEG) data. There have been several attempts to differentiate between the diagnoses of bipolar disorder and major depressive disorder , mood disorders, and other psychiatric disorders using ML techniques found on EEG markers. Previous studies have shown that accuracy varies depending on which EEG markers are used, the sample size, and the ML technique. Also, precise and improved ML approaches can be developed by adapting the various feature selection and validation methods that reflect each disease’s characteristics. Although ML faces some limitations and challenges in solving for consistent and improved accuracy in the diagnosis and treatment of mood disorders, it has a great potential to understand mood disorders better and provide valuable tools to personalize both identification and treatment.

Prior research has identified associations between social media activity and psychiatric diagnoses; however, diagnoses are rarely clinically confirmed. Toward the goal of applying novel approaches to improve outcomes, research using real patient data is necessary. We collected 3,404,959 Facebook messages and 142,390 images across 223 participants (mean age = 23.7; 41.7% male) with schizophrenia spectrum disorders (SSD), mood disorders (MD), and healthy volunteers (HV). We analyzed features uploaded up to 18 months before the first hospitalization using machine learning and built classifiers that distinguished SSD and MD from HV, and SSD from MD. Classification achieved AUC of 0.77 (HV vs. MD), 0.76 (HV vs. SSD), and 0.72 (SSD vs. MD). SSD used more (P < 0.01) perception words (hear, see, feel) than MD or HV. SSD and MD used more (P < 0.01) swear words compared to HV. SSD were more likely to express negative emotions compared to HV (P < 0.01). MD used more words related to biological processes (blood/pain) compared to HV (P < 0.01). The height and width of photos posted by SSD and MD were smaller (P < 0.01) than HV. MD photos contained more blues and less yellows (P < 0.01). Closer to hospitalization, use of punctuation increased (SSD vs HV), use of negative emotion words increased (MD vs. HV), and use of swear words increased (P < 0.01) for SSD and MD compared to HV. Machine-learning algorithms are capable of differentiating SSD and MD using Facebook activity alone over a year in advance of hospitalization. Integrating Facebook data with clinical information could one day serve to inform clinical decision-making.

BackgroundVirtually, all organisms on Earth have their own circadian rhythm, and humans are no exception. Circadian rhythms are associated with various human states, especially mood disorders, and disturbance of the circadian rhythm is known to be very closely related. Attempts have also been made to derive clinical implications associated with mood disorders using the vast amounts of digital log that is acquired by digital technologies develop and using computational analysis techniques.ObjectiveThis study was conducted to evaluate the mood state or episode, activity, sleep, light exposure, and heart rate during a period of about 2 years by acquiring various digital log data through wearable devices and smartphone apps as well as conventional clinical assessments. We investigated a mood prediction algorithm developed with machine learning using passive data phenotypes based on circadian rhythms.MethodsWe performed a prospective observational cohort study on 55 patients with mood disorders (major depressive disorder [MDD] and bipolar disorder type 1 [BD I] and 2 [BD II]) for 2 years. A smartphone app for self-recording daily mood scores and detecting light exposure (using the installed sensor) were provided. From daily worn activity trackers, digital log data of activity, sleep, and heart rate were collected. Passive digital phenotypes were processed into 130 features based on circadian rhythms, and a mood prediction algorithm was developed by random forest.ResultsThe mood state prediction accuracies for the next 3 days in all patients, MDD patients, BD I patients, and BD II patients were 65%, 65%, 64%, and 65% with 0.7, 0.69, 0.67, and 0.67 area under the curve (AUC) values, respectively. The accuracies of all patients for no episode (NE), depressive episode (DE), manic episode (ME), and hypomanic episode (HME) were 85.3%, 87%, 94%, and 91.2% with 0.87, 0.87, 0.958, and 0.912 AUC values, respectively. The prediction accuracy in BD II patients was distinctively balanced as high showing 82.6%, 74.4%, and 87.5% of accuracy (with generally good sensitivity and specificity) with 0.919, 0.868, and 0.949 AUC values for NE, DE, and HME, respectively.ConclusionsOn the basis of the theoretical basis of chronobiology, this study proposed a good model for future research by developing a mood prediction algorithm using machine learning by processing and reclassifying digital log data. In addition to academic value, it is expected that this study will be of practical help to improve the prognosis of patients with mood disorders by making it possible to apply actual clinical application owing to the rapid expansion of digital technology.

Using machine learning analyses of speech to classify levels of expressed emotion in parents of youth with mood disorders

Mood disorders often are diagnosed by clinical interview, yet many cases are missed or misdiagnosed. Mood disorders increase the risk of suicide, making it imperative to diagnose and treat these disorders quickly. Artificial intelligence (AI) has been investigated for diagnosing mood disorders, but the merits of the literature have not been evaluated. This systematic review aims to understand and explain AI methods and evaluate their use in augmenting clinical diagnosis of mood disorders as well as identifying individuals at increased suicide risk. We conducted a systematic literature review of all studies until August 1, 2020 examining the efficacy of different AI techniques for diagnosing mood disorders and identifying individuals at increased suicide risk because of a mood disorder. Our literature search generated 13 studies (10 of mood disorders and 3 describing suicide risk) where AI techniques were used. Machine learning and artificial neural networks were most commonly used; both showed merit in helping to diagnose mood disorders and assess suicide risk. The data shows that AI methods have merit in improving the diagnosis of mood disorders as well as identifying suicide risk. More research is needed for bipolar disorder because only 2 studies explored this condition, and it is often misdiagnosed. Although only a few AI techniques are discussed in detail in this review, there are many more that can be employed, and should be evaluated in future studies.

Identifying a clinical signature of suicidality among patients with mood disorders: A pilot study using a machine learning approach

Application of machine learning classification for structural brain MRI in mood disorders: Critical review from a clinical perspective

Comparisons of deep learning and machine learning while using text mining methods to identify suicide attempts of patients with mood disorders

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.

Construction and verification of risk prediction model for suicidal attempts of mood disorder based on machine learning.

Traditional medicine and biomedical sciences are reaching a turning point because of the constantly growing impact and volume of Big Data. Machine Learning (ML) techniques and related algorithms play a central role as diagnostic, prognostic, and decision-making tools in this field. Another promising area becoming part of everyday clinical practice is personalized therapy and pharmacogenomics. Applying ML to pharmacogenomics opens new frontiers to tailored therapeutical strategies to help clinicians choose drugs with the best response and fewer side effects, operating with genetic information and combining it with the clinical profile. This systematic review aims to draw up the state-of-the-art ML applied to pharmacogenomics in psychiatry. Our research yielded fourteen papers; most were published in the last three years. The sample comprises 9,180 patients diagnosed with mood disorders, psychoses, or autism spectrum disorders. Prediction of drug response and prediction of side effects are the most frequently considered domains with the supervised ML technique, which first requires training and then testing. The random forest is the most used algorithm; it comprises several decision trees, reduces the training set's overfitting, and makes precise predictions. ML proved effective and reliable, especially when genetic and biodemographic information were integrated into the algorithm. Even though ML and pharmacogenomics are not part of everyday clinical practice yet, they will gain a unique role in the next future in improving personalized treatments in psychiatry.

Simple SummaryDepression and related mood disorders, such as seasonal affective disorder (SAD), affect nearly one-fifth of the global population and have substantial economic and personal costs. Mutations in circadian clock genes are associated with mood disorders, suggesting that molecular pathways affecting mood are influenced by the circadian clock, but the molecular mechanisms underlying this link are poorly understood. We use machine learning and statistical analyses to determine the circadian gene variants and clinical features most highly associated with symptoms of seasonality and SAD. Our results support previous links between CRY2, PER2, and ZBTB20 genes and identify novel links for CLOCK and PER3 with symptoms of seasonality and SAD. Our findings reinforce the sex-specific influences of circadian genes on seasonality and SAD and highlight the multiple pathways by which clock variants affect downstream mood pathways via direct and indirect mechanisms. These results enhance our understanding of the molecular mechanisms underlying seasonality in mood and may elucidate new therapeutic targets for circadian-related mood disorders, including SAD, depression, and anxiety.Molecular pathways affecting mood are associated with circadian clock gene variants and are influenced, in part, by the circadian clock, but the molecular mechanisms underlying this link are poorly understood. We use machine learning and statistical analyses to determine the circadian gene variants and clinical features most highly associated with symptoms of seasonality and seasonal affective disorder (SAD) in a deeply phenotyped population sample. We report sex-specific clock gene effects on seasonality and SAD symptoms; genotypic combinations of CLOCK3111/ZBTB20 and PER2/PER3B were significant genetic risk factors for males, and CRY2/PER3C and CRY2/PER3-VNTR were significant risk factors for females. Anxiety, eveningness, and increasing age were significant clinical risk factors for seasonality and SAD for females. Protective factors for SAD symptoms (in females only) included single gene variants: CRY1-GG and PER3-VNTR-4,5. Clock gene effects were partially or fully mediated by diurnal preference or chronotype, suggesting multiple indirect effects of clock genes on seasonality symptoms. Interestingly, protective effects of CRY1-GG, PER3-VNTR-4,5, and ZBTB20 genotypes on seasonality and depression were not mediated by chronotype, suggesting some clock variants have direct effects on depressive symptoms related to SAD. Our results support previous links between CRY2, PER2, and ZBTB20 genes and identify novel links for CLOCK and PER3 with symptoms of seasonality and SAD. Our findings reinforce the sex-specific nature of circadian clock influences on seasonality and SAD and underscore the multiple pathways by which clock variants affect downstream mood pathways via direct and indirect mechanisms.

Mood Disorders are a group of mental health conditions characterized by a disruption of the emotional state that affects the quality of life of the people living with them. Mental Disorders are difficult to diagnose and treat due to the complex processes involved and limitations of the healthcare system. Digital biomarkers have created accessible, long-term, non-invasive, and user-friendly alternatives for the diagnosis, treatment, and monitoring of these conditions. The use of everyday devices like smartphones and smartwatches and specialized tools like actigraphy, in conjunction with powerful statistical tools, artificial intelligence, and machine learning, represents a promising avenue for the implementation of personalized strategies to monitor and treat Mood Disorders, and potentially higher adherence to treatment. We conducted several studies that implement a variety of methodologies and tools to better understand Mood Disorders, using a patient-focused approach with the ultimate goal of identifying better strategies to improve their quality of life.

Mood disorders, including depression and anxiety, affect almost one-fifth of the world’s adult population and are becoming increasingly prevalent. Mutations in circadian clock genes have previously been associated with mood disorders both directly and indirectly through alterations in circadian phase, suggesting that the circadian clock influences multiple molecular pathways involved in mood. By targeting previously identified single nucleotide polymorphisms (SNPs) that have been implicated in anxiety and depressive disorders, we use a combination of statistical and machine learning techniques to investigate associations with the generalized anxiety disorder assessment (GAD-7) scores in a UK Biobank sample of 90,882 individuals. As in previous studies, we observed that females exhibited higher GAD-7 scores than males regardless of genotype. Interestingly, we found no significant effects on anxiety from individual circadian gene variants; only circadian genotypes with multiple SNP variants showed significant associations with anxiety. For both sexes, severe anxiety is associated with a 120-fold increase in odds for individuals with CRY2_AG(rs1083852)/ZBTB20_TT(rs1394593) genotypes and is associated with a near 40-fold reduction in odds for individuals with PER3-A_CG(rs228697)/ZBTB20_TT(rs1394593) genotypes. We also report several sex-specific associations with anxiety. In females, the CRY2/ZBTB20 genotype combination showed a > 200-fold increase in odds of anxiety and PER3/ZBTB20 and CRY1 /PER3-A genotype combinations also appeared as female risk factors. In males, CRY1/PER3-A and PER3-B/ZBTB20 genotype combinations were associated with anxiety risk. Mediation analysis revealed direct associations of CRY2/ZBTB20 variant genotypes with moderate anxiety in females and CRY1/PER3-A variant genotypes with severe anxiety in males. The association of CRY1/PER3-A variant genotypes with severe anxiety in females was partially mediated by extreme evening chronotype. Our results reinforce existing findings that females exhibit stronger anxiety outcomes than males, and provide evidence for circadian gene associations with anxiety, particularly in females. Our analyses only identified significant associations using two-gene combinations, underscoring the importance of combined gene effects on anxiety risk. We describe novel, robust associations between gene combinations involving the ZBTB20 SNP (rs1394593) and risk of anxiety symptoms in a large population sample. Our findings also support previous findings that the ZBTB20 SNP is an important factor in mood disorders, including seasonal affective disorder. Our results suggest that reduced expression of this gene significantly modulates the risk of anxiety symptoms through direct influences on mood-related pathways. Together, these observations provide novel links between the circadian clockwork and anxiety symptoms and identify potential molecular pathways through which clock genes may influence anxiety risk.