Machine learning approaches for prediction of bipolar disorder based on biological, clinical and neuropsychological markers: a systematic review and meta-analysis

Identifying neuroimaging biomarkers in major depressive disorder using machine learning algorithms and functional near-infrared spectroscopy (fNIRS) during verbal fluency task

One of the most prevalent psychiatric disorders is major depressive disorder (MDD), which increases the probability of suicidal ideation or untimely demise. Abnormal frontal hemodynamic changes detected by functional near-infrared spectroscopy (fNIRS) during verbal fluency task (VFT) have the potential to be used as an objective indicator for assessing clinical symptoms. However, comprehensive quantitative and objective assessment instruments for individuals who exhibit symptoms suggestive of depression remain undeveloped. Drawing from a total of 467 samples in a large-scale dataset comprising 289 MDD patients and 178 healthy controls, fNIRS measurements were obtained throughout the VFT. To identify unique MDD biomarkers, this research introduced a data representation approach for extracting spatiotemporal features from fNIRS signals, which were subsequently utilized as potential predictors. Machine learning classifiers (e.g., Gradient Boosted Decision Trees (GBDT) and Multilayer Perceptron) were implemented to assess the ability to predict selected features. The mean and standard deviation of the cross-validation indicated that the GBDT model, when combined with the 180-feature pattern, distinguishes patients with MDD from healthy controls in the most effective manner. The accuracy of correct classification for the test set was 0.829 ± 0.053, with an AUC of 0.895 (95 % CI: 0.864-0.925) and a sensitivity of 0.914 ± 0.051. Channels that made the most important contribution to the identification of MDD were identified using Shapley Additive Explanations method, located in the frontopolar area and the dorsolateral prefrontal cortex, as well as pars triangularis Broca's area. Assessment of abnormal prefrontal activity during the VFT in MDD serves as an objectively measurable biomarker that could be utilized to evaluate cognitive deficits and facilitate early screening for MDD. The model suggested in this research could be applied to large-scale case-control fNIRS datasets to detect unique characteristics of MDD and offer clinicians an objective biomarker-based analytical instrument to assist in the evaluation of suspicious cases.

Machine learning-based discrimination of unipolar depression and bipolar disorder with streamlined shortlist in adolescents of different ages

BACKGROUND

Variations in symptoms and indistinguishable depression episodes of unipolar depression (UD) and bipolar disorder (BD) make the discrimination difficult and time-consuming. For adolescents with high disease prevalence, an efficient diagnostic tool is important for the discrimination and treatment of BU and UD.

METHODS

This multi-center cross-sectional study involved 1587 UD and 246 BD adolescents aged 12-18. A combination of standard questionnaires and demographic information was collected for the construction of a full-item list. The unequal patient number was balanced with three data balancing algorithms, and 4 machine learning algorithms were compared for the discrimination ability of UD and BD in three age groups: all ages, 12-15 and 16-18. Random forest (RF) with the highest accuracy were used to rank the importance of features/items and construct the 25-item shortlist. A separate dataset was used for the final performance evaluation with the shortlist, and the discrimination ability for UD and BD was investigated.

RESULTS

RF performed the best for UD and BD discrimination in all 3 age groups (AUC 0.88-0.90). The most important features that differentiate UD from BD belong to Parental Bonding Instrument (PBI) and Loneliness Scale of the University of California at Los Angeles (UCLA). With RF and the 25-item shortlist, the diagnostic accuracy can still reach around 80 %, achieving 95 % of the accuracy levels obtained with all features.

CONCLUSIONS

Through machine learning algorithms, the most influencing factors for UD and BD classification were recombined and applied for rapid diagnosis. This highly feasible method holds the potential for convenient and accurate diagnosis of young patients in research and clinical practice.

Predicting remission after acute phase pharmacotherapy in patients with bipolar I depression: A machine learning approach with cross-trial and cross-drug replication

OBJECTIVES

Interpatient variability in bipolar I depression (BP-D) symptoms challenges the ability to predict pharmacotherapeutic outcomes. A machine learning workflow was developed to predict remission after 8 weeks of pharmacotherapy (total score of ≤8 on the Montgomery Åsberg Depression Rating Scale [MADRS]).

METHODS

Supervised machine learning models were trained on data from BP-D patients treated with olanzapine (N = 168) and were externally validated on patients treated with olanzapine/fluoxetine combination (OFC; N = 131) and lamotrigine (LTG; N = 126). Top predictors were used to develop a prognosis rule informing how many symptoms should change and by how much within 4 weeks to increase the odds of achieving remission.

RESULTS

An AUC of 0.76 (NIR:0.59; p = 0.17) was established to predict remission in olanzapine-treated subjects. These trained models achieved AUCs of 0.70 with OFC (NIR:0.52; p < 0.03) and 0.73 with LTG (NIR:0.52; p < 0.003), demonstrating external replication of prediction performance. Week-4 changes in four MADRS symptoms (reported sadness, reduced sleep, reduced appetite, and concentration difficulties) were top predictors of remission. Across all pharmacotherapies, three or more of these symptoms needed to improve by ≥2 points at Week-4 to have a 65% chance of achieving remission at 8 weeks (OR: 3.74, 95% CI: 2.45-5.76; p < 9.3E-11).

CONCLUSION

Machine learning strategies achieved cross-trial and cross-drug replication in predicting remission after 8 weeks of pharmacotherapy for BP-D. Interpretable prognoses rules required only a limited number of depressive symptoms, providing a promising foundation for developing simple quantitative decision aids that may, in the future, serve as companions to clinical judgment at the point of care.

Machine learning applied to the prediction of relapse, hospitalization, and suicide in bipolar disorder using neuroimaging and clinical data: A systematic review

BACKGROUND

Bipolar disorder (BD) is associated with increased morbidity/mortality. Adverse outcome prediction might help with the management of patients with BD.

METHODS

We systematically reviewed the performance of machine learning (ML) studies in predicting adverse outcomes (relapse or recurrence, hospital admission, and suicide-related events) in patients with BD. Demographic, clinical, and neuroimaging-related poor outcome predictors were also reviewed. Three databases (PubMed, Scopus, and Web of Science) were explored from inception to July 2023.

RESULTS

Eighteen studies, accounting for >30,000 patients, were included. Support vector machine, decision trees, random forest, and logistic regression were the most frequently used ML algorithms. ML models' area under the receiver operating characteristic (ROC) curve (AUC), sensitivity, and specificity ranged from 0.71 to 0.98, 72.7-92.8 %, and 59.0-95.2 % for relapse/recurrence prediction (4 studies (3 on relapses and 1 on recurrences). The corresponding values were 0.78-0.88, 21.4-100 %, and 77.0-99.7 % for hospital admissions (3 studies, 21,266 patients), and 0.71-0.99, 44.4-97.9 %, and 38.9-95.0 % for suicide-related events (10 studies, 5558 patients). Also, one study addressed a combination of the interest outcomes. Adverse outcome predictors included early onset BD, BD type I, comorbid psychiatric or substance use disorder, circadian rhythm disruption, hospitalization characteristics, and neuroimaging parameters, including increased dynamic amplitude of low-frequency fluctuation, decreased frontolimbic functional connectivity and aberrant dynamic functional connectivity in corticostriatal circuitry.

CONCLUSIONS

ML models can predict adverse outcomes of BD with relatively acceptable performance measures. Future studies with larger samples and nested cross-validation validation should be conducted to reach more reliable results.

A generalizable normative deep autoencoder for brain morphological anomaly detection: application to the multi-site StratiBip dataset on bipolar disorder in an external validation framework

The heterogeneity of psychiatric disorders makes researching disorder-specific neurobiological markers an ill-posed problem. Here, we face the need for disease stratification models by presenting a generalizable multivariate normative modelling framework for characterizing brain morphology, applied to bipolar disorder (BD). We employed deep autoencoders in an anomaly detection framework, combined with a confounder removal step integrating training and external validation. The model was trained with healthy control (HC) data from the human connectome project and applied to multi-site external data of HC and BD individuals. We found that brain deviating scores were greater, more heterogeneous, and with increased extreme values in the BD group, with volumes prominently from the basal ganglia, hippocampus and adjacent regions emerging as significantly deviating. Similarly, individual brain deviating maps based on modified z scores expressed higher abnormalities occurrences, but their overall spatial overlap was lower compared to HCs. Our generalizable framework enabled the identification of subject- and group-level brain normative-deviating patterns, a step forward towards the development of more effective and personalized clinical decision support systems and patient stratification in psychiatry.

Bipolar disorder staging and the impact it has on its management: an update

INTRODUCTION

The longitudinal course of bipolar disorder (BD) is associated with an active process of neuroprogression, characterized by structural brain alterations and progressive functional impairment. In the last decades, a growing need of a standardized staging model for BD arose, with the aim of a more appropriate definition of stage-specific clinical manifestations and the identification of more customized therapeutic tools.

AREAS COVERED

The authors review the literature on clinical aspects, neurobiological correlates and treatment issues related to BD progression. Thereafter, they address the definition, constructs, and evolution of the staging concept, focusing on the clinical applications of BD staging models available in literature.

EXPERT OPINION

Although several staging models for BD have been proposed to date, their application in clinical practice is still relatively scant. This may have a detrimental impact on the clinical and therapeutic management of BD, in terms of early and proper diagnosis as well as tailored treatment interventions according to the different stages of illness. Future research efforts should tend to the integration of recent insights on neuroimaging and epigenetic markers, toward a standardized and multidimensional staging model.

Individualized prediction models in ADHD: a systematic review and meta-regression

There have been increasing efforts to develop prediction models supporting personalised detection, prediction, or treatment of ADHD. We overviewed the current status of prediction science in ADHD by: (1) systematically reviewing and appraising available prediction models; (2) quantitatively assessing factors impacting the performance of published models. We did a PRISMA/CHARMS/TRIPOD-compliant systematic review (PROSPERO: CRD42023387502), searching, until 20/12/2023, studies reporting internally and/or externally validated diagnostic/prognostic/treatment-response prediction models in ADHD. Using meta-regressions, we explored the impact of factors affecting the area under the curve (AUC) of the models. We assessed the study risk of bias with the Prediction Model Risk of Bias Assessment Tool (PROBAST). From 7764 identified records, 100 prediction models were included (88% diagnostic, 5% prognostic, and 7% treatment-response). Of these, 96% and 7% were internally and externally validated, respectively. None was implemented in clinical practice. Only 8% of the models were deemed at low risk of bias; 67% were considered at high risk of bias. Clinical, neuroimaging, and cognitive predictors were used in 35%, 31%, and 27% of the studies, respectively. The performance of ADHD prediction models was increased in those models including, compared to those models not including, clinical predictors (β = 6.54, p = 0.007). Type of validation, age range, type of model, number of predictors, study quality, and other type of predictors did not alter the AUC. Several prediction models have been developed to support the diagnosis of ADHD. However, efforts to predict outcomes or treatment response have been limited, and none of the available models is ready for implementation into clinical practice. The use of clinical predictors, which may be combined with other type of predictors, seems to improve the performance of the models. A new generation of research should address these gaps by conducting high quality, replicable, and externally validated models, followed by implementation research.

A systematic review of the biomarkers associated with cognition and mood state in bipolar disorder

BACKGROUND

Bipolar disorder (BD) is a severe psychiatric disorder characterized by changes in mood that alternate between (hypo) mania or depression and mixed states, often associated with functional impairment and cognitive dysfunction. But little is known about biomarkers that contribute to the development and sustainment of cognitive deficits. The aim of this study was to review the association between neurocognition and biomarkers across different mood states.

METHOD

Search databases were Web of Science, Scopus and PubMed. A systematic review was carried out following the PRISMA guidelines. Risk of bias was assessed with the Newcastle-Ottawa Scale. Studies were selected that focused on the correlation between neuroimaging, physiological, genetic or peripheral biomarkers and cognition in at least two phases of BD: depression, (hypo)mania, euthymia or mixed. PROSPERO Registration No.: CRD42023410782.

RESULTS

A total of 1824 references were screened, identifying 1023 published articles, of which 336 were considered eligible. Only 16 provided information on the association between biomarkers and cognition in the different affective states of BD. The included studies found: (i) Differences in levels of total cholesterol and C reactive protein depending on mood state; (ii) There is no association found between cognition and peripheral biomarkers; (iii) Neuroimaging biomarkers highlighted hypoactivation of frontal areas as distinctive of acute state of BD; (iv) A deactivation failure has been reported in the ventromedial prefrontal cortex (vmPFC), potentially serving as a trait marker of BD.

CONCLUSION

Only a few recent articles have investigated biomarker-cognition associations in BD mood phases. Our findings underline that there appear to be central regions involved in BD that are observed in all mood states. However, there appear to be underlying mechanisms of cognitive dysfunction that may vary across different mood states in BD. This review highlights the importance of standardizing the data and the assessment of cognition, as well as the need for biomarkers to help prevent acute symptomatic phases of the disease, and the associated functional and cognitive impairment.

Identifying predictive factors for mood recurrence in early-onset major mood disorders: A 4-year, multicenter, prospective cohort study

We investigate the predictive factors of the mood recurrence in patients with early-onset major mood disorders from a prospective observational cohort study from July 2015 to December 2019. A total of 495 patients were classified into three groups according to recurrence during the cohort observation period: recurrence group with (hypo)manic or mixed features (MMR), recurrence group with only depressive features (ODR), and no recurrence group (NR). As a result, the baseline diagnosis of bipolar disorder type 1 (BDI) and bipolar disorder type 2 (BDII), along with a familial history of BD, are strong predictors of the MMR. The discrepancies in wake-up times between weekdays and weekends, along with disrupted circadian rhythms, are identified as a notable predictor of ODR. Our findings confirm that we need to be aware of different predictors for each form of mood recurrences in patients with early-onset mood disorders. In clinical practice, we expect that information obtained from the initial assessment of patients with mood disorders, such as mood disorder type, family history of BD, regularity of wake-up time, and disruption of circadian rhythms, can help predict the risk of recurrence for each patient, allowing for early detection and timely intervention.

Distinguishing bipolar depression, bipolar mania, and major depressive disorder by gut microbial characteristics

BACKGROUND

Gut microbial disturbance has been widely confirmed in mood disorders. However, little is known about whether gut microbial characteristics can distinguish major depressive disorder (MDD), bipolar depression (BP-D), and bipolar mania (BP-M).

METHODS

This was a prospective case-control study. The composition of gut microbiota was profiled using 16S ribosomal RNA (rRNA) gene sequencing of fecal samples and compared between healthy controls (HC; n = 46), MDD (n = 51), BP-D (n = 44), and patients with BP-M (n = 45).

RESULTS

Gut microbial compositions were remarkably changed in the patients with MDD, BP-D, and BP-M. Compared to HC, distinct gut microbiome signatures were found in MDD, BP-D, and BP-M, and some gut microbial changes were overlapping between the three mood disorders. Furthermore, we identified a signature of 7 operational taxonomic units (OUT; Prevotellaceae-related OUT22, Prevotellaceae-related OUT31, Prevotellaceae-related OTU770, Ruminococcaceae-related OUT70, Bacteroidaceae-related OTU1536, Propionibacteriaceae-related OTU97, Acidaminococcaceae-related OTU34) that can distinguish patients with MDD from those with BP-D, BP-M, or HC, with area under the curve (AUC) values ranging from 0.910 to 0.996.

CONCLUSION

Our results provide the clinical rationale for the discriminative diagnosis of MDD, BP-D, and BP-M by characteristic gut microbial features.

Can diffusion tensor imaging have a diagnostic utility to differentiate early-onset forms of bipolar disorder and schizophrenia: A neuroimaging study with explainable machine learning algorithms

BACKGROUND/AIM

Accurate diagnosis of early-onset psychotic disorders is crucial to improve clinical outcomes. This study aimed to differentiate patients with early-onset schizophrenia (EOS) from early-onset bipolar disorder (EBD) with machine learning (ML) algorithms using white matter tracts (WMT).

METHOD

Diffusion tensor imaging was obtained from adolescents with either EOS (n = 43) or EBD (n = 32). Global probabilistic tractography using an automated tract-based TRACULA software was performed to analyze the fractional anisotropy (FA) of forty-two WMT. The nested cross-validation was performed in feature selection and model construction. EXtreme Gradient Boosting (XGBoost) was applied to select the features that can give the best performance in the ML model. The interpretability of the model was explored with the SHApley Additive exPlanations (SHAP).

FINDINGS

The XGBoost algorithm identified nine out of the 42 major WMTs with significant predictive power. Among ML models, Support Vector Machine-Linear showed the best performance. Higher SHAP values of left acoustic radiation, bilateral anterior thalamic radiation, and the corpus callosum were associated with a higher likelihood of EOS.

CONCLUSIONS

Our findings suggested that ML models based on the FA values of major WMT reconstructed by global probabilistic tractography can unveil hidden microstructural aberrations to distinguish EOS from EBD.

Artificial intelligence in psychiatry research, diagnosis, and therapy

Psychiatric disorders are now responsible for the largest proportion of the global burden of disease, and even more challenges have been seen during the COVID-19 pandemic. Artificial intelligence (AI) is commonly used to facilitate the early detection of disease, understand disease progression, and discover new treatments in the fields of both physical and mental health. The present review provides a broad overview of AI methodology and its applications in data acquisition and processing, feature extraction and characterization, psychiatric disorder classification, potential biomarker detection, real-time monitoring, and interventions in psychiatric disorders. We also comprehensively summarize AI applications with regard to the early warning, diagnosis, prognosis, and treatment of specific psychiatric disorders, including depression, schizophrenia, autism spectrum disorder, attention-deficit/hyperactivity disorder, addiction, sleep disorders, and Alzheimer's disease. The advantages and disadvantages of AI in psychiatry are clarified. We foresee a new wave of research opportunities to facilitate and improve AI technology and its long-term implications in psychiatry during and after the COVID-19 era.

A voting-based machine learning approach for classifying biological and clinical datasets

BACKGROUND

Different machine learning techniques have been proposed to classify a wide range of biological/clinical data. Given the practicability of these approaches accordingly, various software packages have been also designed and developed. However, the existing methods suffer from several limitations such as overfitting on a specific dataset, ignoring the feature selection concept in the preprocessing step, and losing their performance on large-size datasets. To tackle the mentioned restrictions, in this study, we introduced a machine learning framework consisting of two main steps. First, our previously suggested optimization algorithm (Trader) was extended to select a near-optimal subset of features/genes. Second, a voting-based framework was proposed to classify the biological/clinical data with high accuracy. To evaluate the efficiency of the proposed method, it was applied to 13 biological/clinical datasets, and the outcomes were comprehensively compared with the prior methods.

RESULTS

The results demonstrated that the Trader algorithm could select a near-optimal subset of features with a significant level of p-value < 0.01 relative to the compared algorithms. Additionally, on the large-sie datasets, the proposed machine learning framework improved prior studies by ~ 10% in terms of the mean values associated with fivefold cross-validation of accuracy, precision, recall, specificity, and F-measure.

CONCLUSION

Based on the obtained results, it can be concluded that a proper configuration of efficient algorithms and methods can increase the prediction power of machine learning approaches and help researchers in designing practical diagnosis health care systems and offering effective treatment plans.

Restoring the missing person to personalized medicine and precision psychiatry

Precision psychiatry has emerged as part of the shift to personalized medicine and builds on frameworks such as the U.S. National Institute of Mental Health Research Domain Criteria (RDoC), multilevel biological "omics" data and, most recently, computational psychiatry. The shift is prompted by the realization that a one-size-fits all approach is inadequate to guide clinical care because people differ in ways that are not captured by broad diagnostic categories. One of the first steps in developing this personalized approach to treatment was the use of genetic markers to guide pharmacotherapeutics based on predictions of pharmacological response or non-response, and the potential risk of adverse drug reactions. Advances in technology have made a greater degree of specificity or precision potentially more attainable. To date, however, the search for precision has largely focused on biological parameters. Psychiatric disorders involve multi-level dynamics that require measures of phenomenological, psychological, behavioral, social structural, and cultural dimensions. This points to the need to develop more fine-grained analyses of experience, self-construal, illness narratives, interpersonal interactional dynamics, and social contexts and determinants of health. In this paper, we review the limitations of precision psychiatry arguing that it cannot reach its goal if it does not include core elements of the processes that give rise to psychopathological states, which include the agency and experience of the person. Drawing from contemporary systems biology, social epidemiology, developmental psychology, and cognitive science, we propose a cultural-ecosocial approach to integrating precision psychiatry with person-centered care.

Depression and bipolar disorder subtypes differ in their genetic correlations with biological rhythms

Major Depression and Bipolar Disorder Type I (BIP-I) and Type II (BIP-II), are characterized by depressed, manic, and hypomanic episodes in which specific changes of physical activity, circadian rhythm, and sleep are observed. It is known that genetic factors contribute to variation in mood disorders and biological rhythms, but unclear to what extent there is an overlap between their underlying genetics. In the present study, data from genome-wide association studies were used to examine the genetic relationship between mood disorders and biological rhythms. We tested the genetic correlation of depression, BIP-I, and BIP-II with physical activity (overall physical activity, moderate activity, sedentary behaviour), circadian rhythm (relative amplitude), and sleep features (sleep duration, daytime sleepiness). Genetic correlations of depression, BIP-I, and BIP-II with biological rhythms were compared to discover commonalities and differences. A gene-based analysis tested for associations of single genes and common circadian genes with mood disorders. Depression was negatively correlated with overall physical activity and positively with sedentary behaviour, while BIP-I showed associations in the opposite direction. Depression and BIP-II had negative correlations with relative amplitude. All mood disorders were positively correlated with daytime sleepiness. Overall, we observed both genetic commonalities and differences across mood disorders in their relationships with biological rhythms: depression and BIP-I differed the most, while BIP-II was in an intermediate position. Gene-based analysis suggested potential targets for further investigation. The present results suggest shared genetic underpinnings for the clinically observed associations between mood disorders and biological rhythms. Research considering possible joint mechanisms may offer avenues for improving disease detection and treatment.

Distinguish bipolar and major depressive disorder in adolescents based on multimodal neuroimaging: Results from the Adolescent Brain Cognitive Development study®

Background

Major depressive disorder and bipolar disorder in adolescents are prevalent and are associated with cognitive impairment, executive dysfunction, and increased mortality. Early intervention in the initial stages of major depressive disorder and bipolar disorder can significantly improve personal health.

Methods

We collected 309 samples from the Adolescent Brain Cognitive Development study, including 116 adolescents with bipolar disorder, 64 adolescents with major depressive disorder, and 129 healthy adolescents, and employed a support vector machine to develop classification models for identification. We developed a multimodal model, which combined functional connectivity of resting-state functional magnetic resonance imaging and four anatomical measures of structural magnetic resonance imaging (cortical thickness, area, volume, and sulcal depth). We measured the performances of both multimodal and single modality classifiers.

Results

The multimodal classifiers showed outstanding performance compared with all five single modalities, and they are 100% for major depressive disorder versus healthy controls, 100% for bipolar disorder versus healthy control, 98.5% (95% CI: 95.4–100%) for major depressive disorder versus bipolar disorder, 100% for major depressive disorder versus depressed bipolar disorder and the leave-one-site-out analysis results are 77.4%, 63.3%, 79.4%, and 81.7%, separately.

Conclusions

The study shows that multimodal classifiers show high classification performances. Moreover, cuneus may be a potential biomarker to differentiate major depressive disorder, bipolar disorder, and healthy adolescents. Overall, this study can form multimodal diagnostic prediction workflows for clinically feasible to make more precise diagnose at the early stage and potentially reduce loss of personal pain and public society.