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

Machine learning-based risk predictive models for diabetic kidney disease in type 2 diabetes mellitus patients: a systematic review and meta-analysis

Background

Machine learning (ML) models are being increasingly employed to predict the risk of developing and progressing diabetic kidney disease (DKD) in patients with type 2 diabetes mellitus (T2DM). However, the performance of these models still varies, which limits their widespread adoption and practical application. Therefore, we conducted a systematic review and meta-analysis to summarize and evaluate the performance and clinical applicability of these risk predictive models and to identify key research gaps.

Methods

We conducted a systematic review and meta-analysis to compare the performance of ML predictive models. We searched PubMed, Embase, the Cochrane Library, and Web of Science for English-language studies using ML algorithms to predict the risk of DKD in patients with T2DM, covering the period from database inception to April 18, 2024. The primary performance metric for the models was the area under the receiver operating characteristic curve (AUC) with a 95% confidence interval (CI). The risk of bias was assessed using the Prediction Model Risk of Bias Assessment Tool (PROBAST) checklist.

Results

26 studies that met the eligibility criteria were included into the meta-analysis. 25 studies performed internal validation, but only 8 studies conducted external validation. A total of 94 ML models were developed, with 81 models evaluated in the internal validation sets and 13 in the external validation sets. The pooled AUC was 0.839 (95% CI 0.787-0.890) in the internal validation and 0.830 (95% CI 0.784-0.877) in the external validation sets. Subgroup analysis based on the type of ML showed that the pooled AUC for traditional regression ML was 0.797 (95% CI 0.777-0.816), for ML was 0.811 (95% CI 0.785-0.836), and for deep learning was 0.863 (95% CI 0.825-0.900). A total of 26 ML models were included, and the AUCs of models that were used three or more times were pooled. Among them, the random forest (RF) models demonstrated the best performance with a pooled AUC of 0.848 (95% CI 0.785-0.911).

Conclusion

This meta-analysis demonstrates that ML exhibit high performance in predicting DKD risk in T2DM patients. However, challenges related to data bias during model development and validation still need to be addressed. Future research should focus on enhancing data transparency and standardization, as well as validating these models' generalizability through multicenter studies.

Systematic Review Registration

https://inplasy.com/inplasy-2024-9-0038/, identifier INPLASY202490038.

Support Vector Machine for Stratification of Cognitive Impairment Using 3D T1WI in Patients with Type 2 Diabetes Mellitus

Purpose

To explore the potential of MRI-based radiomics in predicting cognitive dysfunction in patients with diagnosed type 2 diabetes mellitus (T2DM).

Patients and Methods

In this study, data on 158 patients with T2DM were retrospectively collected between September 2019 and December 2020. The participants were categorized into a normal cognitive function (N) group (n=30), a mild cognitive impairment (MCI) group (n=90), and a dementia (DM) group (n=38) according to the Chinese version of the Montréal Cognitive Assessment Scale-B (MoCA-B). Radiomics features were extracted from the brain tissue except ventricles and sulci in the 3D T1WI images, support vector machine (SVM) model was then established to identify the CI and N groups, and the MCI and DM groups, respectively. The models were evaluated based on their area under the receiver operating characteristic curve (AUC), Precision (P), Recall rate (Recall, R), F1-score, and Support. Finally, ROC curves were plotted for each model.

Results

The study consisted of 68 cases in the N and CI group, with 54 cases in the training set and 14 in the verification set, and 128 cases were included in the MCI and DM groups, with 90 training sets and 38 verification sets. The consistency for inter-group and intra-group of radiomics features in two physicians were 0.86 and 0.90, respectively. After features selection, there were 11 optimal features to distinguish N and CI and 12 optimal features to MCI and DM. In the test set, the AUC for the SVM classifier was 0.857 and the accuracy was 0.830 in distinguishing CI and N, while AUC was 0.821 and the accuracy was 0.830 in distinguishing MCI and DM.

Conclusion

The SVM model based on MRI radiomics exhibits high efficacy in the diagnosis of cognitive dysfunction and evaluation of its severity among patients with T2DM.

Continuous remote monitoring of neurophysiologic Immersion accurately predicts mood

Mental health professionals have relied primarily on clinical evaluations to identify in vivo pathology. As a result, mental health is largely reactive rather than proactive. In an effort to proactively assess mood, we collected continuous neurophysiologic data for ambulatory individuals 8-10 h a day at 1 Hz for 3 weeks (N = 24). Data were obtained using a commercial neuroscience platform (Immersion Neuroscience) that quantifies the neural value of social-emotional experiences. These data were related to self-reported mood and energy to assess their predictive accuracy. Statistical analyses quantified neurophysiologic troughs by the length and depth of social-emotional events with low values and neurophysiologic peaks as the complement. Participants in the study had an average of 2.25 (SD = 3.70, Min = 0, Max = 25) neurophysiologic troughs per day and 3.28 (SD = 3.97, Min = 0, Max = 25) peaks. The number of troughs and peaks predicted daily mood with 90% accuracy using least squares regressions and machine learning models. The analysis also showed that women were more prone to low mood compared to men. Our approach demonstrates that a simple count variable derived from a commercially-available platform is a viable way to assess low mood and low energy in populations vulnerable to mood disorders. In addition, peak Immersion events, which are mood-enhancing, may be an effective measure of thriving in adults.

Assistive tools for classifying neurological disorders using fMRI and deep learning: A guide and example

BACKGROUND

Deep-learning (DL) methods are rapidly changing the way researchers classify neurological disorders. For example, combining functional magnetic resonance imaging (fMRI) and DL has helped researchers identify functional biomarkers of neurological disorders (e.g., brain activation and connectivity) and pilot innovative diagnostic models. However, the knowledge required to perform DL analyses is often domain-specific and is not widely taught in the brain sciences (e.g., psychology, neuroscience, and cognitive science). Conversely, neurological diagnoses and neuroimaging training (e.g., fMRI) are largely restricted to the brain and medical sciences. In turn, these disciplinary knowledge barriers and distinct specializations can act as hurdles that prevent the combination of fMRI and DL pipelines. The complexity of fMRI and DL methods also hinders their clinical adoption and generalization to real-world diagnoses. For example, most current models are not designed for clinical settings or use by nonspecialized populations such as students, clinicians, and healthcare workers. Accordingly, there is a growing area of assistive tools (e.g., software and programming packages) that aim to streamline and increase the accessibility of fMRI and DL pipelines for the diagnoses of neurological disorders.

OBJECTIVES AND METHODS

In this study, we present an introductory guide to some popular DL and fMRI assistive tools. We also create an example autism spectrum disorder (ASD) classification model using assistive tools (e.g., Optuna, GIFT, and the ABIDE preprocessed repository), fMRI, and a convolutional neural network.

RESULTS

In turn, we provide researchers with a guide to assistive tools and give an example of a streamlined fMRI and DL pipeline.

CONCLUSIONS

We are confident that this study can help more researchers enter the field and create accessible fMRI and deep-learning diagnostic models for neurological disorders.

The application of machine learning techniques in posttraumatic stress disorder: a systematic review and meta-analysis

Posttraumatic stress disorder (PTSD) recently becomes one of the most important mental health concerns. However, no previous study has comprehensively reviewed the application of big data and machine learning (ML) techniques in PTSD. We found 873 studies meet the inclusion criteria and a total of 31 of those in a sample of 210,001 were included in quantitative analysis. ML algorithms were able to discriminate PTSD with an overall accuracy of 0.89. Pooled estimates of classification accuracy from multi-dimensional data (0.96) are higher than single data types (0.86 to 0.90). ML techniques can effectively classify PTSD and models using multi-dimensional data perform better than those using single data types. While selecting optimal combinations of data types and ML algorithms to be clinically applied at the individual level still remains a big challenge, these findings provide insights into the classification, identification, diagnosis and treatment of PTSD.

One size does not fit all: notable individual variation in brain activity correlates of antidepressant treatment response

Introduction

To date, no robust electroencephalography (EEG) markers of antidepressant treatment response have been identified. Variable findings may arise from the use of group analyses, which neglect individual variation. Using a combination of group and single-participant analyses, we explored individual variability in EEG characteristics of treatment response.

Methods

Resting-state EEG data and Montgomery-Åsberg Depression Rating Scale (MADRS) symptom scores were collected from 43 patients with depression before, at 1 and 12 weeks of pharmacotherapy. Partial least squares (PLS) was used to: 1) identify group differences in EEG connectivity (weighted phase lag index) and complexity (multiscale entropy) between eventual medication responders and non-responders, and 2) determine whether group patterns could be identified in individual patients.

Results

Responders showed decreased alpha and increased beta connectivity, and early, widespread decreases in complexity over treatment. Non-responders showed an opposite connectivity pattern, and later, spatially confined decreases in complexity. Thus, as in previous studies, our group analyses identified significant differences between groups of patients with different treatment outcomes. These group-level EEG characteristics were only identified in ~40-60% of individual patients, as assessed quantitatively by correlating the spatiotemporal brain patterns between groups and individual results, and by independent raters through visualization.

Discussion

Our single-participant analyses suggest that substantial individual variation exists, and needs to be considered when investigating characteristics of antidepressant treatment response for potential clinical applicability.

Clinical trial registration

https://clinicaltrials.gov, identifier NCT00519428.

Abnormal stability of spontaneous neuronal activity as a predictor of diagnosis conversion from major depressive disorder to bipolar disorder

OBJECTIVE

Bipolar disorder (BD) is often misdiagnosed as major depressive disorder (MDD) in the early stage, which may lead to inappropriate treatment. This study aimed to characterize the alterations of spontaneous neuronal activity in patients with depressive episodes whose diagnosis transferred from MDD to BD.

METHODS

532 patients with MDD and 132 healthy controls (HCs) were recruited over 10 years. During the follow-up period, 75 participants with MDD transferred to BD (tBD), and 157 participants remained with the diagnosis of unipolar depression (UD). After excluding participants with poor image quality and excessive head movement, 68 participants with the diagnosis of tBD, 150 participants with the diagnosis of UD, and 130 HCs were finally included in the analysis. The dynamic amplitude of low-frequency fluctuations (dALFF) of spontaneous neuronal activity was evaluated in tBD, UD and HC using functional magnetic resonance imaging at study inclusion. Receiver operating characteristic (ROC) analysis was performed to evaluate sensitivity and specificity of the conversion prediction from MDD to BD based on dALFF.

RESULTS

Compared to HC, tBD exhibited elevated dALFF at left premotor cortex (PMC_L), right lateral temporal cortex (LTC_R) and right early auditory cortex (EAC_R), and UD showed reduced dALFF at PMC_L, left paracentral lobule (PCL_L), bilateral medial prefrontal cortex (mPFC), right orbital frontal cortex (OFC_R), right dorsolateral prefrontal cortex (DLPFC_R), right posterior cingulate cortex (PCC_R) and elevated dALFF at LTC_R. Furthermore, tBD exhibited elevated dALFF at PMC_L, PCL_L, bilateral mPFC, bilateral OFC, DLPFC_R, PCC_R and LTC_R than UD. In addition, ROC analysis based on dALFF in differential areas obtained an area under the curve (AUC) of 72.7%.

CONCLUSIONS

The study demonstrated the temporal dynamic abnormalities of tBD and UD in the critical regions of the somatomotor network (SMN), default mode network (DMN), and central executive network (CEN). The differential abnormal patterns of temporal dynamics between the two diseases have the potential to predict the diagnosis transition from MDD to BD.

Mood Disorder Severity and Subtype Classification Using Multimodal Deep Neural Network Models

The subtype diagnosis and severity classification of mood disorder have been made through the judgment of verified assistance tools and psychiatrists. Recently, however, many studies have been conducted using biomarker data collected from subjects to assist in diagnosis, and most studies use heart rate variability (HRV) data collected to understand the balance of the autonomic nervous system on statistical analysis methods to perform classification through statistical analysis. In this research, three mood disorder severity or subtype classification algorithms are presented through multimodal analysis of data on the collected heart-related data variables and hidden features from the variables of time and frequency domain of HRV. Comparing the classification performance of the statistical analysis widely used in existing major depressive disorder (MDD), anxiety disorder (AD), and bipolar disorder (BD) classification studies and the multimodality deep neural network analysis newly proposed in this study, it was confirmed that the severity or subtype classification accuracy performance of each disease improved by 0.118, 0.231, and 0.125 on average. Through the study, it was confirmed that deep learning analysis of biomarker data such as HRV can be applied as a primary identification and diagnosis aid for mental diseases, and that it can help to objectively diagnose psychiatrists in that it can confirm not only the diagnosed disease but also the current mood status.

An experimental machine learning study investigating the decision-making process of students and qualified radiographers when interpreting radiographic images

AI is becoming more prevalent in healthcare and is predicted to be further integrated into workflows to ease the pressure on an already stretched service. The National Health Service in the UK has prioritised AI and Digital health as part of its Long-Term Plan. Few studies have examined the human interaction with such systems in healthcare, despite reports of biases being present with the use of AI in other technologically advanced fields, such as finance and aviation. Understanding is needed of how certain user characteristics may impact how radiographers engage with AI systems in use in the clinical setting to mitigate against problems before they arise. The aim of this study is to determine correlations of skills, confidence in AI and perceived knowledge amongst student and qualified radiographers in the UK healthcare system. A machine learning based AI model was built to predict if the interpreter was either a student (n = 67) or a qualified radiographer (n = 39) in advance, using important variables from a feature selection technique named Boruta. A survey, which required the participant to interpret a series of plain radiographic examinations with and without AI assistance, was created on the Qualtrics survey platform and promoted via social media (Twitter/LinkedIn), therefore adopting convenience, snowball sampling This survey was open to all UK radiographers, including students and retired radiographers. Pearson's correlation analysis revealed that males who were proficient in their profession were more likely than females to trust AI. Trust in AI was negatively correlated with age and with level of experience. A machine learning model was built, the best model predicted the image interpreter to be qualified radiographers with 0.93 area under curve and a prediction accuracy of 93%. Further testing in prospective validation cohorts using a larger sample size is required to determine the clinical utility of the proposed machine learning model.

Detecting individuals with severe mental illness using artificial intelligence applied to magnetic resonance imaging

BACKGROUND

Identifying individuals at risk for severe mental illness (SMI) is crucial for prevention and early intervention strategies. While MRI shows potential for case identification even before illness onset, no practical model for mental health risk monitoring has been developed. This study aims to develop an initial version of an efficient and practical model for mental health screening among at-risk populations.

METHODS

A deep learning model known as Multiple Instance Learning (MIL) was adopted to train and test a SMI detection model with clinical MRI scans of 14,915 patients with SMI (age 32.98 ± 12.01 years, 9102 women) and 4538 healthy controls (age 40.60 ± 10.95 years, 2424 women) in the primary dataset. Validation analysis was conducted in an independent dataset with 290 patients (age 28.08 ± 10.95 years, 169 women) and 310 healthy participants (age 33.55 ± 11.09 years, 165 women). Another three machine learning models of ResNet, DenseNet and EfficientNet were used for comparison. We also recruited 148 individuals receiving high-stress medical school education to characterize the potential real-world utility of the MIL model in detecting risk of mental illness.

FINDINGS

Similar performance of successful differentiation of individuals with SMI and healthy controls was observed for the MIL model (AUC: 0.82) and other models (ResNet, DenseNet, EfficientNet, 0.83, 0.81, and 0.80 respectively). MIL had better generalization in the validation test than other models (AUC: 0.82 vs 0.59, 0.66 and 0.59), and less drop-off in performance from 3.0T to 1.5T scanners. The MIL model did better in predicting clinician ratings of distress than self-ratings with questionnaires (84% vs 22%) in the medical student sample. Brain regions that contributed to SMI identification were mainly neocortical, including right precuneus, bilateral temporal regions, left precentral/postcentral gyrus, bilateral medial prefrontal cortex and right cerebellum.

INTERPRETATION

Our digital model based on brief clinical MRI protocols identified individual SMI patients with good accuracy and high sensitivity, suggesting that with incremental improvements the approach may offer potentially useful aid for early identification and intervention to prevent illness onset in vulnerable at-risk populations.

FUNDING

This study was supported by the National Natural Science Foundation of China, National Key Technologies R&D Program of China, and Sichuan Science and Technology Program.

From promise to practice: towards the realisation of AI-informed mental health care

In this Series paper, we explore the promises and challenges of artificial intelligence (AI)-based precision medicine tools in mental health care from clinical, ethical, and regulatory perspectives. The real-world implementation of these tools is increasingly considered the prime solution for key issues in mental health, such as delayed, inaccurate, and inefficient care delivery. Similarly, machine-learning-based empirical strategies are becoming commonplace in psychiatric research because of their potential to adequately deconstruct the biopsychosocial complexity of mental health disorders, and hence to improve nosology of prognostic and preventive paradigms. However, the implementation steps needed to translate these promises into practice are currently hampered by multiple interacting challenges. These obstructions range from the current technology-distant state of clinical practice, over the lack of valid real-world databases required to feed data-intensive AI algorithms, to model development and validation considerations being disconnected from the core principles of clinical utility and ethical acceptability. In this Series paper, we provide recommendations on how these challenges could be addressed from an interdisciplinary perspective to pave the way towards a framework for mental health care, leveraging the combined strengths of human intelligence and AI.

Machine learning for autism spectrum disorder diagnosis using structural magnetic resonance imaging: Promising but challenging

Autism spectrum disorder (ASD) is a complex neurodevelopmental disorder that affects approximately 1% of the population and causes significant burdens. ASD's pathogenesis remains elusive; hence, diagnosis is based on a constellation of behaviors. Structural magnetic resonance imaging (sMRI) studies have shown several abnormalities in volumetric and geometric features of the autistic brain. However, inconsistent findings prevented most contributions from being translated into clinical practice. Establishing reliable biomarkers for ASD using sMRI is crucial for the correct diagnosis and treatment. In recent years, machine learning (ML) and specifically deep learning (DL) have quickly extended to almost every sector, notably in disease diagnosis. Thus, this has led to a shift and improvement in ASD diagnostic methods, fulfilling most clinical diagnostic requirements. However, ASD discovery remains difficult. This review examines the ML-based ASD diagnosis literature over the past 5 years. A literature-based taxonomy of the research landscape has been mapped, and the major aspects of this topic have been covered. First, we provide an overview of ML's general classification pipeline and the features of sMRI. Next, representative studies are highlighted and discussed in detail with respect to methods, and biomarkers. Finally, we highlight many common challenges and make recommendations for future directions. In short, the limited sample size was the main obstacle; Thus, comprehensive data sets and rigorous methods are necessary to check the generalizability of the results. ML technologies are expected to advance significantly in the coming years, contributing to the diagnosis of ASD and helping clinicians soon.

Personalized Diagnosis and Treatment for Neuroimaging in Depressive Disorders

Depressive disorders are highly heterogeneous in nature. Previous studies have not been useful for the clinical diagnosis and prediction of outcomes of major depressive disorder (MDD) at the individual level, although they provide many meaningful insights. To make inferences beyond group-level analyses, machine learning (ML) techniques can be used for the diagnosis of subtypes of MDD and the prediction of treatment responses. We searched PubMed for relevant studies published until December 2021 that included depressive disorders and applied ML algorithms in neuroimaging fields for depressive disorders. We divided these studies into two sections, namely diagnosis and treatment outcomes, for the application of prediction using ML. Structural and functional magnetic resonance imaging studies using ML algorithms were included. Thirty studies were summarized for the prediction of an MDD diagnosis. In addition, 19 studies on the prediction of treatment outcomes for MDD were reviewed. We summarized and discussed the results of previous studies. For future research results to be useful in clinical practice, ML enabling individual inferences is important. At the same time, there are important challenges to be addressed in the future.

Performances of whole-brain dynamic and static functional connectivity fingerprinting in machine learning-based classification of major depressive disorder

BACKGROUND

Alterations in static and dynamic functional connectivity during resting state have been widely reported in major depressive disorder (MDD). The objective of this study was to compare the performances of whole-brain dynamic and static functional connectivity combined with machine learning approach in differentiating MDD patients from healthy controls at the individual subject level. Given the dynamic nature of brain activity, we hypothesized that dynamic connectivity would outperform static connectivity in the classification.

METHODS

Seventy-one MDD patients and seventy-one well-matched healthy controls underwent resting-state functional magnetic resonance imaging scans. Whole-brain dynamic and static functional connectivity patterns were calculated and utilized as classification features. Linear kernel support vector machine was employed to design the classifier and a leave-one-out cross-validation strategy was used to assess classifier performance.

RESULTS

Experimental results of dynamic functional connectivity-based classification showed that MDD patients could be discriminated from healthy controls with an excellent accuracy of 100% irrespective of whether or not global signal regression (GSR) was performed (permutation test with P < 0.0002). Brain regions with the most discriminating dynamic connectivity were mainly and reliably located within the default mode network, cerebellum, and subcortical network. In contrast, the static functional connectivity-based classifiers exhibited unstable classification performances, i.e., a low accuracy of 38.0% without GSR (P = 0.9926) while a high accuracy of 96.5% with GSR (P < 0.0002); moreover, there was a considerable variability in the distribution of brain regions with static connectivity most informative for classification.

CONCLUSION

These findings suggest the superiority of dynamic functional connectivity in machine learning-based classification of depression, which may be helpful for a better understanding of the neural basis of MDD as well as for the development of effective computer-aided diagnosis tools in clinical settings.

Potential applications and performance of machine learning techniques and algorithms in clinical practice: A systematic review

PURPOSE

The advent of clinically adapted machine learning algorithms can solve numerous problems ranging from disease diagnosis and prognosis to therapy recommendations. This systematic review examines the performance of machine learning (ML) algorithms and evaluates the progress made to date towards their implementation in clinical practice.

METHODS

Systematic searching of databases (PubMed, MEDLINE, Scopus, Google Scholar, Cochrane Library and WHO Covid-19 database) to identify original articles published between January 2011 and October 2021. Studies reporting ML techniques in clinical practice involving humans and ML algorithms with a performance metric were considered.

RESULTS

Of 873 unique articles identified, 36 studies were eligible for inclusion. The XGBoost (extreme gradient boosting) algorithm showed the highest potential for clinical applications (n = 7 studies); this was followed jointly by random forest algorithm, logistic regression, and the support vector machine, respectively (n = 5 studies). Prediction of outcomes (n = 33), in particular Inflammatory diseases (n = 7) received the most attention followed by cancer and neuropsychiatric disorders (n = 5 for each) and Covid-19 (n = 4). Thirty-three out of the thirty-six included studies passed more than 50% of the selected quality assessment criteria in the TRIPOD checklist. In contrast, none of the studies could achieve an ideal overall bias rating of 'low' based on the PROBAST checklist. In contrast, only three studies showed evidence of the deployment of ML algorithm(s) in clinical practice.

CONCLUSIONS

ML is potentially a reliable tool for clinical decision support. Although advocated widely in clinical practice, work is still in progress to validate clinically adapted ML algorithms. Improving quality standards, transparency, and interpretability of ML models will further lower the barriers to acceptability.

The Role of Machine Learning in Diagnosing Bipolar Disorder: Scoping Review

BACKGROUND

Bipolar disorder (BD) is the 10th most common cause of frailty in young individuals and has triggered morbidity and mortality worldwide. Patients with BD have a life expectancy 9 to 17 years lower than that of normal people. BD is a predominant mental disorder, but it can be misdiagnosed as depressive disorder, which leads to difficulties in treating affected patients. Approximately 60% of patients with BD are treated for depression. However, machine learning provides advanced skills and techniques for better diagnosis of BD.

OBJECTIVE

This review aims to explore the machine learning algorithms used for the detection and diagnosis of bipolar disorder and its subtypes.

METHODS

The study protocol adopted the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. We explored 3 databases, namely Google Scholar, ScienceDirect, and PubMed. To enhance the search, we performed backward screening of all the references of the included studies. Based on the predefined selection criteria, 2 levels of screening were performed: title and abstract review, and full review of the articles that met the inclusion criteria. Data extraction was performed independently by all investigators. To synthesize the extracted data, a narrative synthesis approach was followed.

RESULTS

We retrieved 573 potential articles were from the 3 databases. After preprocessing and screening, only 33 articles that met our inclusion criteria were identified. The most commonly used data belonged to the clinical category (19, 58%). We identified different machine learning models used in the selected studies, including classification models (18, 55%), regression models (5, 16%), model-based clustering methods (2, 6%), natural language processing (1, 3%), clustering algorithms (1, 3%), and deep learning-based models (3, 9%). Magnetic resonance imaging data were most commonly used for classifying bipolar patients compared to other groups (11, 34%), whereas microarray expression data sets and genomic data were the least commonly used. The maximum ratio of accuracy was 98%, whereas the minimum accuracy range was 64%.

CONCLUSIONS

This scoping review provides an overview of recent studies based on machine learning models used to diagnose patients with BD regardless of their demographics or if they were compared to patients with psychiatric diagnoses. Further research can be conducted to provide clinical decision support in the health industry.

Machine Learning for Predicting Individual Severity of Blepharospasm Using Diffusion Tensor Imaging

Accumulating diffusion tensor imaging (DTI) evidence suggests that white matter abnormalities evaluated by local diffusion homogeneity (LDH) or fractional anisotropy (FA) occur in patients with blepharospasm (BSP), both of which are significantly correlated with disease severity. However, whether the individual severity of BSP can be identified using these DTI metrics remains unknown. We aimed to investigate whether a combination of machine learning techniques and LDH or FA can accurately identify the individual severity of BSP. Forty-one patients with BSP were assessed using the Jankovic Rating Scale and DTI. The patients were assigned to non-functionally and functionally limited groups according to their Jankovic Rating Scale scores. A machine learning scheme consisting of beam search and support vector machines was designed to identify non-functionally versus functionally limited outcomes, with the input features being LDH or FA in 68 white matter regions. The proposed machine learning scheme with LDH or FA yielded an overall accuracy of 88.67 versus 85.19% in identifying non-functionally limited versus functionally limited outcomes. The scheme also identified a sensitivity of 91.40 versus 85.87% in correctly identifying functionally limited outcomes, a specificity of 83.33 versus 83.67% in accurately identifying non-functionally limited outcomes, and an area under the curve of 93.7 versus 91.3%. These findings suggest that a combination of LDH or FA measurements and a sophisticated machine learning scheme can accurately and reliably identify the individual disease severity in patients with BSP.

The Role of Machine Learning in Diagnosing Bipolar Disorder: Scoping Review (Preprint).. [DOI: 10.2196/preprints.29749] [Citation(s) in RCA: 0] [Impact Index Per Article: 0]

BACKGROUND

Bipolar disorder (BD) is the 10th most common cause of frailty in young individuals and has triggered morbidity and mortality worldwide. Patients with BD have a life expectancy 9 to 17 years lower than that of normal people. BD is a predominant mental disorder, but it can be misdiagnosed as depressive disorder, which leads to difficulties in treating affected patients. Approximately 60% of patients with BD are treated for depression. However, machine learning provides advanced skills and techniques for better diagnosis of BD.

OBJECTIVE

This review aims to explore the machine learning algorithms used for the detection and diagnosis of bipolar disorder and its subtypes.

METHODS

The study protocol adopted the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. We explored 3 databases, namely Google Scholar, ScienceDirect, and PubMed. To enhance the search, we performed backward screening of all the references of the included studies. Based on the predefined selection criteria, 2 levels of screening were performed: title and abstract review, and full review of the articles that met the inclusion criteria. Data extraction was performed independently by all investigators. To synthesize the extracted data, a narrative synthesis approach was followed.

RESULTS

We retrieved 573 potential articles were from the 3 databases. After preprocessing and screening, only 33 articles that met our inclusion criteria were identified. The most commonly used data belonged to the clinical category (19, 58%). We identified different machine learning models used in the selected studies, including classification models (18, 55%), regression models (5, 16%), model-based clustering methods (2, 6%), natural language processing (1, 3%), clustering algorithms (1, 3%), and deep learning–based models (3, 9%). Magnetic resonance imaging data were most commonly used for classifying bipolar patients compared to other groups (11, 34%), whereas microarray expression data sets and genomic data were the least commonly used. The maximum ratio of accuracy was 98%, whereas the minimum accuracy range was 64%.

CONCLUSIONS

This scoping review provides an overview of recent studies based on machine learning models used to diagnose patients with BD regardless of their demographics or if they were compared to patients with psychiatric diagnoses. Further research can be conducted to provide clinical decision support in the health industry.

Individual prediction of symptomatic converters in youth offspring of bipolar parents using proton magnetic resonance spectroscopy

Children of individuals with bipolar disorder (bipolar offspring) are at increased risk for developing mood disorders, but strategies to predict mood episodes are unavailable. In this study, we used support vector machine (SVM) to characterize the potential of proton magnetic resonance spectroscopy (¹H-MRS) in predicting the first mood episode in youth bipolar offspring. From a longitudinal neuroimaging study, 19 at-risk youth who developed their first mood episode (converters), and 19 without mood episodes during follow-up (non-converters) were selected and matched for age, sex and follow-up time. Baseline ¹H-MRS data were obtained from anterior cingulate cortex (ACC) and bilateral ventrolateral prefrontal cortex (VLPFC). Glutamate (Glu), myo-inositol (mI), choline (Cho), N-acetyl aspartate (NAA), and phosphocreatine plus creatine (PCr + Cr) levels were calculated. SVM with a linear kernel was adopted to classify converters and non-converters based on their baseline metabolites. SVM allowed the significant classification of converters and non-converters across all regions for Cho (accuracy = 76.0%), but not for other metabolites. Considering all metabolites within each region, SVM allowed the significant classification of converters and non-converters for left VLPFC (accuracy = 76.5%), but not for right VLPFC or ACC. The combined mI, PCr + Cr, and Cho from left VLPFC achieved the highest accuracy differentiating converters from non-converters (79.0%). Our findings from this exploratory study suggested that ¹H-MRS levels of mI, Cho, and PCr + Cr from left VLPFC might be useful to predict the development of first mood episode in youth bipolar offspring using machine learning. Future studies that prospectively examine and validate these metabolites as predictors of mood episodes in high-risk individuals are necessary.

Automated classification of depression from structural brain measures across two independent community-based cohorts

Major depressive disorder (MDD) has been the subject of many neuroimaging case-control classification studies. Although some studies report accuracies ≥80%, most have investigated relatively small samples of clinically-ascertained, currently symptomatic cases, and did not attempt replication in larger samples. We here first aimed to replicate previously reported classification accuracies in a small, well-phenotyped community-based group of current MDD cases with clinical interview-based diagnoses (from STratifying Resilience and Depression Longitudinally cohort, 'STRADL'). We performed a set of exploratory predictive classification analyses with measures related to brain morphometry and white matter integrity. We applied three classifier types-SVM, penalised logistic regression or decision tree-either with or without optimisation, and with or without feature selection. We then determined whether similar accuracies could be replicated in a larger independent population-based sample with self-reported current depression (UK Biobank cohort). Additional analyses extended to lifetime MDD diagnoses-remitted MDD in STRADL, and lifetime-experienced MDD in UK Biobank. The highest cross-validation accuracy (75%) was achieved in the initial current MDD sample with a decision tree classifier and cortical surface area features. The most frequently selected decision tree split variables included surface areas of bilateral caudal anterior cingulate, left lingual gyrus, left superior frontal, right precentral and paracentral regions. High accuracy was not achieved in the larger samples with self-reported current depression (53.73%), with remitted MDD (57.48%), or with lifetime-experienced MDD (52.68-60.29%). Our results indicate that high predictive classification accuracies may not immediately translate to larger samples with broader criteria for depression, and may not be robust across different classification approaches.

Identifying resting-state effective connectivity abnormalities in drug-naïve major depressive disorder diagnosis via graph convolutional networks

Major depressive disorder (MDD) is a leading cause of disability; its symptoms interfere with social, occupational, interpersonal, and academic functioning. However, the diagnosis of MDD is still made by phenomenological approach. The advent of neuroimaging techniques allowed numerous studies to use resting-state functional magnetic resonance imaging (rs-fMRI) and estimate functional connectivity for brain-disease identification. Recently, attempts have been made to investigate effective connectivity (EC) that represents causal relations among regions of interest. In the meantime, to identify meaningful phenotypes for clinical diagnosis, graph-based approaches such as graph convolutional networks (GCNs) have been leveraged recently to explore complex pairwise similarities in imaging/nonimaging features among subjects. In this study, we validate the use of EC for MDD identification by estimating its measures via a group sparse representation along with a structured equation modeling approach in a whole-brain data-driven manner from rs-fMRI. To distinguish drug-naïve MDD patients from healthy controls, we utilize spectral GCNs based on a population graph to successfully integrate EC and nonimaging phenotypic information. Furthermore, we devise a novel sensitivity analysis method to investigate the discriminant connections for MDD identification in our trained GCNs. Our experimental results validated the effectiveness of our method in various scenarios, and we identified altered connectivities associated with the diagnosis of MDD.

Association between personality traits and suicidality by age groups in a nationally representative Korean sample

Suicide is a leading health issue, which substantially contributes to the causes of death worldwide. Personality traits are some of the major risk factors for suicidality. We sought to identify the relationships between personality traits and suicidality by age group.The Big-Five Inventory-10 traits were measured in community-dwelling individuals in a nationally representative sample in the Republic of Korea. Because personality traits are long-standing patterns throughout one's lifetime, suicidality was measured based on lifetime history, rather than in a recent period. To comprehensively examine independent influences of personality traits on suicidality, psychiatric comorbidity and sociodemographic data were adjusted for.A total of 6022 subjects (3714 females and 2308 males) were included. Agreeableness (odds ratio (OR) [95% confidential intervals (CI)] = 0.79 [0.64-0.98]) was negatively associated with suicidal ideation, whereas neuroticism (1.27 [1.05-1.54]) and openness (1.36 [1.11-1.67]) were positively associated with suicidal ideation among young adults. Openness (1.25 [1.10-1.43]) had a positive association, and conscientiousness (0.86 [0.75-0.98]) had a negative association with suicidal ideation among the middle-aged group. Neuroticism is the only influencing factor for suicidal attempts among the young adult (1.88 [1.24-2.86]) and older (1.65 [1.24-2.20]) groups.Given the differential associations between personality traits and suicidality by age groups, future studies are needed to comprehensively identify possible roles of personality in suicide by age.

Neuroimaging Biomarkers for Predicting Treatment Response and Recurrence of Major Depressive Disorder

The acute treatment duration for major depressive disorder (MDD) is 8 weeks or more. Treatment of patients with MDD without predictors of treatment response and future recurrence presents challenges and clinical problems to patients and physicians. Recently, many neuroimaging studies have been published on biomarkers for treatment response and recurrence of MDD using various methods such as brain volumetric magnetic resonance imaging (MRI), functional MRI (resting-state and affective tasks), diffusion tensor imaging, magnetic resonance spectroscopy, near-infrared spectroscopy, and molecular imaging (i.e., positron emission tomography and single photon emission computed tomography). The results have been inconsistent, and we hypothesize that this could be due to small sample size; different study design, including eligibility criteria; and differences in the imaging and analysis techniques. In the future, we suggest a more sophisticated research design, larger sample size, and a more comprehensive integration including genetics to establish biomarkers for the prediction of treatment response and recurrence of MDD.

An investigation of cortical thickness and antidepressant response in major depressive disorder: A CAN-BIND study report

Major depressive disorder (MDD) is considered a highly heterogeneous clinical and neurobiological mental disorder. We employed a novel layered treatment design to investigate whether cortical thickness features at baseline differentiated treatment responders from non-responders after 8 and 16 weeks of a standardized sequential antidepressant treatment. Secondary analyses examined baseline differences between MDD and controls as a replication analysis and longitudinal changes in thickness after 8 weeks of escitalopram treatment. 181 MDD and 95 healthy comparison (HC) participants were studied. After 8 weeks of escitalopram treatment (10-20 mg/d, flexible dosage), responders (>50% decrease in Montgomery-Åsberg Depression Scale score) were continued on escitalopram; non-responders received adjunctive aripiprazole (2-10 mg/d, flexible dosage). MDD participants were classified into subgroups according to their response profiles at weeks 8 and 16. Baseline group differences in cortical thickness were analyzed with FreeSurfer between HC and MDD groups as well as between response groups. Two-stage longitudinal processing was used to investigate 8-week escitalopram treatment-related changes in cortical thickness. Compared to HC, the MDD group exhibited thinner cortex in the left rostral middle frontal cortex [MNI(X,Y,Z=-29,9,54.5,-7.7); CWP=0.0002]. No baseline differences in cortical thickness were observed between responders and non-responders based on week-8 or week-16 response profile. No changes in cortical thickness was observed after 8 weeks of escitalopram monotherapy. In a two-step 16-week sequential clinical trial we found that baseline cortical thickness does not appear to be associated to clinical response to pharmacotherapy at 8 or 16 weeks.

Image Based Brain Segmentation: From Multi-Atlas Fusion to Deep Learning

Background:

This review aims to identify the development of the algorithms for brain tissue and structure segmentation in MRI images.

Discussion:

Starting from the results of the Grand Challenges on brain tissue and structure segmentation held in Medical Image Computing and Computer-Assisted Intervention (MICCAI), this review analyses the development of the algorithms and discusses the tendency from multi-atlas label fusion to deep learning. The intrinsic characteristics of the winners’ algorithms on the Grand Challenges from the year 2012 to 2018 are analyzed and the results are compared carefully.

Conclusion:

Although deep learning has got higher rankings in the challenge, it has not yet met the expectations in terms of accuracy. More effective and specialized work should be done in the future.

Classifying major depression patients and healthy controls using EEG, eye tracking and galvanic skin response data

OBJECTIVE

Major depression disorder (MDD) is one of the most prevalent mental disorders worldwide. Diagnosing depression in the early stage is crucial to treatment process. However, due to depression's comorbid nature and the subjectivity in diagnosis, an early diagnosis could be challenging. Recently, machine learning approaches have been used to process Electroencephalography (EEG) and neuroimaging data to facilitate the diagnosis. In the present study, we used a multimodal machine learning approach involving EEG, eye tracking and galvanic skin response data as input to classify depression patients and healthy controls.

METHODS

One hundred and forty-four MDD depression patients and 204 matched healthy controls were recruited. They were required to watch a series of affective and neutral stimuli while EEG, eye tracking information and galvanic skin response were recorded via a set of low-cost, portable devices. Three machine learning algorithms including Random Forests, Logistic Regression and Support Vector Machine (SVM) were trained to build dichotomous classification model.

RESULTS

The results showed that the highest classification f1 score was obtained by Logistic Regression algorithms, with accuracy = 79.63%, precision = 76.67%, recall = 85.19% and f1 score = 80.70% LIMITATIONS: No hospitalized patients were available; only outpatients were included in the present study. The sample consisted mostly of young adult, and no elder patients were included.

CONCLUSIONS

The machine learning approach can be a useful tool for classifying MDD patients and healthy controls and may help for diagnostic processes.

Differentiating between bipolar and unipolar depression in functional and structural MRI studies

Distinguishing depression in bipolar disorder (BD) from unipolar depression (UD) solely based on clinical clues is difficult, which has led to the exploration of promising neural markers in neuroimaging measures for discriminating between BD depression and UD. In this article, we review structural and functional magnetic resonance imaging (MRI) studies that directly compare UD and BD depression based on neuroimaging modalities including functional MRI studies on regional brain activation or functional connectivity, structural MRI on gray or white matter morphology, and pattern classification analyses using a machine learning approach. Numerous studies have reported distinct functional and structural alterations in emotion- or reward-processing neural circuits between BD depression and UD. Different activation patterns in neural networks including the amygdala, anterior cingulate cortex (ACC), prefrontal cortex (PFC), and striatum during emotion-, reward-, or cognition-related tasks have been reported between BD and UD. A stronger functional connectivity pattern in BD was pronounced in default mode and in frontoparietal networks and brain regions including the PFC, ACC, parietal and temporal regions, and thalamus compared to UD. Gray matter volume differences in the ACC, hippocampus, amygdala, and dorsolateral prefrontal cortex (DLPFC) have been reported between BD and UD, along with a thinner DLPFC in BD compared to UD. BD showed reduced integrity in the anterior part of the corpus callosum and posterior cingulum compared to UD. Several studies performed pattern classification analysis using structural and functional MRI data to distinguish between UD and BD depression using a supervised machine learning approach, which yielded a moderate level of accuracy in classification.

Cortical thickness in major depressive disorder: A systematic review and meta-analysis

Neuroimaging studies assessing neurobiological differences between patients with major depressive disorder (MDD) and healthy controls (HC) are often hindered by small sample sizes and heterogeneity of the patient sample. We performed a comprehensive literature search for studies assessing cortical thickness between patient and control groups, including studies investigating treatment effects on cortical thickness. We identified 34 studies meeting criteria for the systematic review and used Seed-based d Mapping to meta-analyze 24 of those that met additional criteria. Analysis of the full sample of subjects (MDD = 1073; HC = 936) revealed significant thinning in the MDD group in the bilateral orbitofrontal gyrus (BA 11), left pars opercularis (BA 45) and left calcarine fissure/lingual gyrus (BA 17), as well as an area of significant thickening in the left supramarginal gyrus (BA 40). These results support other imaging modalities that report disruptions in various frontal and temporal areas in MDD and identify additional areas in all major cerebral lobes likely to be significant when parsing for biomarkers of treatment or relapse.

Development of Neuroimaging-Based Biomarkers in Psychiatry

This chapter presents an overview of accumulating neuroimaging data with emphasis on translational potential. The subject will be described in the context of three disease states, i.e., schizophrenia, bipolar disorder, and major depressive disorder, and for three clinical goals, i.e., disease risk assessment, subtyping, and treatment decision.

Neuroimaging in Psychiatric Disorders: A Bibliometric Analysis of the 100 Most Highly Cited Articles

BACKGROUND AND PURPOSE

Extensive research has been conducted to find neuroimaging biomarkers for psychiatric disorders. This study aimed at identifying trends of the 100 most highly cited articles on neuroimaging in primary psychiatric disorders.

METHODS

The most highly cited original research articles were identified and analyzed, following searches of MEDLINE and Web of Science All Databases.

RESULTS

The top 100 articles ranked by yearly citation (from 137.5 to 31.1) were published between 1989 and 2017. Depressive disorders (30 articles), schizophrenia spectrum and other psychotic disorders (27), autism spectrum disorder (17), substance-related and addictive disorders (7), and post-traumatic stress disorder (7) were among the most studied conditions. Functional magnetic resonance imaging (42), structural magnetic resonance imaging (30), and positron emission tomography (22) were the most utilized neuroimaging modalities. While 85 articles investigated the pathophysiology of psychiatric disorders (including 7 focusing on developmental changes and 1 on genetic susceptibility), 15 articles studied the impact of treatment, including antidepressants (6), deep brain stimulation (4), antipsychotics (3), behavior therapy (3), and exercise (1). The analysis also identified the most contributing authors, countries (the United States: 71 articles, the United Kingdom: 8, Canada: 5, and China: 5), and journals (JAMA Psychiatry: 20 articles and Biological Psychiatry: 17). Ninety-eight studies were prospective, and two were retrospective. The sample size ranged from 3 to 1,188 (median: 21).

CONCLUSIONS

Our study identified intellectual milestones in the utility of neuroimaging in investigating primary psychiatric disorders. The historic trends could help guide future research in this field.

Towards enhanced metabolomic data analysis of mass spectrometry image: Multivariate Curve Resolution and Machine Learning

Large amounts of data are generally produced from mass spectrometry imaging (MSI) experiments in obtaining the molecular and spatial information of biological samples. Traditionally, MS images are constructed using manually selected ions, and it is very challenging to comprehensively analyze MSI results due to their large data sizes and highly complex data structures. To overcome these barriers, it is obligatory to develop advanced data analysis approaches to handle the increasingly large MSI data. In the current study, we focused on the method development of using Multivariate Curve Resolution (MCR) and Machine Learning (ML) approaches. We aimed to effectively extract the essential information present in the large and complex MSI data and enhance the metabolomic data analysis of biological tissues. Multivariate Curve Resolution-Alternating Least Squares (MCR-ALS) algorithm was used to obtain major patterns of spatial distribution and grouped metabolites with the same spatial distribution patterns. In addition, both supervised and unsupervised ML methods were established to analyze the MSI data. In the supervised ML approach, Random Forest method was selected, and the model was trained using the selected datasets based on the distribution pattern obtained from MCR-ALS analyses. In the unsupervised ML approach, both DBSCAN (Density-based Spatial Clustering of Applications with Noise) and CLARA (Clustering Large Applications) were applied to cluster the MSI datasets. It is worth noting that similar patterns of spatial distribution were discovered through MSI data analysis using MCR-ALS, supervised ML, and unsupervised ML. Our protocols of data analysis can be applied to process the data acquired using many other types of MSI techniques, and to extract the overall features present in MSI results that are intractable using traditional data analysis approaches.

Neurobiological support to the diagnosis of ADHD in stimulant-naïve adults: pattern recognition analyses of MRI data

OBJECTIVE

In adulthood, the diagnosis of attention-deficit/hyperactivity disorder (ADHD) has been subject of recent controversy. We searched for a neuroanatomical signature associated with ADHD spectrum symptoms in adults by applying, for the first time, machine learning-based pattern classification methods to structural MRI and diffusion tensor imaging (DTI) data obtained from stimulant-naïve adults with childhood-onset ADHD and healthy controls (HC).

METHOD

Sixty-seven ADHD patients and 66 HC underwent high-resolution T1-weighted and DTI acquisitions. A support vector machine (SVM) classifier with a non-linear kernel was applied on multimodal image features extracted on regions of interest placed across the whole brain.

RESULTS

The discrimination between a mixed-gender ADHD subgroup and individually matched HC (n = 58 each) yielded area-under-the-curve (AUC) and diagnostic accuracy (DA) values of up to 0.71% and 66% (P = 0.003) respectively. AUC and DA values increased to 0.74% and 74% (P = 0.0001) when analyses were restricted to males (52 ADHD vs. 44 HC).

CONCLUSION

Although not at the level of clinically definitive DA, the neuroanatomical signature identified herein may provide additional, objective information that could influence treatment decisions in adults with ADHD spectrum symptoms.