Machine Learning for Differential Diagnosis Between Clinical Conditions With Social Difficulty: Autism Spectrum Disorder, Early Psychosis, and Social Anxiety Disorder

It is More Anxiousness than Role-playing: Social Camouflaging Conceptualization Among Adults on the Autism Spectrum Compared to Persons with Social Anxiety Disorder

PURPOSE

Autistic individuals consider social camouflaging, e.g., masking autistic traits or social skills compensation, as exhausting and effortful, often leading to diminished well-being or burnout, as well as adaptive for satisfying social interactions. Developing camouflaging may result in isolation, social avoidance, increased self-stigmatization, and misdiagnosis, including social anxiety disorder. The study's objective was to explore and conceptualize social camouflaging, with a particular focus on social anxiety symptoms, autistic burnout, and public stigma, among autistic individuals, with two comparative samples: with social anxiety disorder (SAD) and dual diagnoses (SAD + ASD).

METHODS

254 individuals participated in the study (including 186 females, 148 with ASD diagnosis). CAT-Q, AQ-10, AASPIRE's Autistic Burnout Scale, LSAS-SR, The Perceived Public Stigma Scale were used.

RESULTS

The findings suggest differences in the interrelation dynamics between the samples studied, with autistic burnout and social anxiety symptoms of essential significance in camouflaging strategies, and autistic traits being of secondary importance. Structural equation models showed that the proposed conceptualization, with camouflaging and autistic burnout as the outcome variables, exhibited acceptable fit, implying that this strategy is costly and may result in exhaustion.

CONCLUSION

The total score of camouflaging did not differ between the groups studied, suggesting that a tendency to camouflage is rather transdiagnostic, deriving from anxiousness and negative self-perception, not being autistic per se.

SADXAI: Predicting social anxiety disorder using multiple interpretable artificial intelligence techniques

Social anxiety disorder (SAD), also known as social phobia, is a psychological condition in which a person has a persistent and overwhelming fear of being negatively judged or observed by other individuals. This fear can affect them at work, in relationships and other social activities. The intricate combination of several environmental and biological factors is the reason for the onset of this mental condition. SAD is diagnosed using a test called the "Diagnostic and Statistical Manual of Mental Health Disorders (DSM-5), which is based on several physical, emotional and demographic symptoms. Artificial Intelligence has been a boon for medicine and is regularly used to diagnose various health conditions and diseases. Hence, this study used demographic, emotional, and physical symptoms and multiple machine learning (ML) techniques to diagnose SAD. A thorough descriptive and statistical analysis has been conducted before using the classifiers. Among all the models, the AdaBoost and logistic regression obtained the highest accuracy of 88 % each. Four eXplainable artificial techniques (XAI) techniques are utilized to make the predictions interpretable, transparent and understandable. According to XAI, the "Liebowitz Social Anxiety Scale questionnaire" and "The fear of speaking in public" are the most critical attributes in the diagnosis of SAD. This clinical decision support system framework could be utilized in various suitable locations such as schools, hospitals and workplaces to identify SAD in people.

A Review of and Roadmap for Data Science and Machine Learning for the Neuropsychiatric Phenotype of Autism

Autism spectrum disorder (autism) is a neurodevelopmental delay that affects at least 1 in 44 children. Like many neurological disorder phenotypes, the diagnostic features are observable, can be tracked over time, and can be managed or even eliminated through proper therapy and treatments. However, there are major bottlenecks in the diagnostic, therapeutic, and longitudinal tracking pipelines for autism and related neurodevelopmental delays, creating an opportunity for novel data science solutions to augment and transform existing workflows and provide increased access to services for affected families. Several efforts previously conducted by a multitude of research labs have spawned great progress toward improved digital diagnostics and digital therapies for children with autism. We review the literature on digital health methods for autism behavior quantification and beneficial therapies using data science. We describe both case-control studies and classification systems for digital phenotyping. We then discuss digital diagnostics and therapeutics that integrate machine learning models of autism-related behaviors, including the factors that must be addressed for translational use. Finally, we describe ongoing challenges and potential opportunities for the field of autism data science. Given the heterogeneous nature of autism and the complexities of the relevant behaviors, this review contains insights that are relevant to neurological behavior analysis and digital psychiatry more broadly.

A Machine Learning Approach to the Diagnosis of Autism Spectrum Disorder and Multi-Systemic Developmental Disorder Based on Retrospective Data and ADOS-2 Score

Early and accurate diagnosis of autism spectrum disorders (ASD) and tailored therapeutic interventions can improve prognosis. ADOS-2 is a standardized test for ASD diagnosis. However, owing to ASD heterogeneity, the presence of false positives remains a challenge for clinicians. In this study, retrospective data from patients with ASD and multi-systemic developmental disorder (MSDD), a term used to describe children under the age of 3 with impaired communication but with strong emotional attachments, were tested by machine learning (ML) models to assess the best predictors of disease development as well as the items that best describe these two autism spectrum disorder presentations. Maternal and infant data as well as ADOS-2 score were included in different ML testing models. Depending on the outcome to be estimated, a best-performing model was selected. RIDGE regression model showed that the best predictors for ADOS social affect score were gut disturbances, EEG retrievals, and sleep problems. Linear Regression Model showed that term pregnancy, psychomotor development status, and gut disturbances were predicting at best for the ADOS Repetitive and Restricted Behavior score. The LASSO regression model showed that EEG retrievals, sleep disturbances, age at diagnosis, term pregnancy, weight at birth, gut disturbances, and neurological findings were the best predictors for the overall ADOS score. The CART classification and regression model showed that age at diagnosis and weight at birth best discriminate between ASD and MSDD.

Predictive modelling of deliberate self-harm and suicide attempts in young people accessing primary care: a machine learning analysis of a longitudinal study

PURPOSE

Machine learning (ML) has shown promise in modelling future self-harm but is yet to be applied to key questions facing clinical services. In a cohort of young people accessing primary mental health care, this study aimed to establish (1) the performance of models predicting deliberate self-harm (DSH) compared to suicide attempt (SA), (2) the performance of models predicting new-onset or repeat behaviour, and (3) the relative importance of factors predicting these outcomes.

METHODS

802 young people aged 12-25 years attending primary mental health services had detailed social and clinical assessments at baseline and 509 completed 12-month follow-up. Four ML algorithms, as well as logistic regression, were applied to build four distinct models.

RESULTS

The mean performance of models predicting SA (AUC: 0.82) performed better than the models predicting DSH (AUC: 0.72), with mean positive predictive values (PPV) approximately twice that of the prevalence (SA prevalence 14%, PPV: 0.32, DSH prevalence 22%, PPV: 0.40). All ML models outperformed standard logistic regression. The most frequently selected variable in both models was a history of DSH via cutting.

CONCLUSION

History of DSH and clinical symptoms of common mental disorders, rather than social and demographic factors, were the most important variables in modelling future behaviour. The performance of models predicting outcomes in key sub-cohorts, those with new-onset or repetition of DSH or SA during follow-up, was poor. These findings may indicate that the performance of models of future DSH or SA may depend on knowledge of the individual's recent history of either behaviour.

Predicting social anxiety in young adults with machine learning of resting-state brain functional radiomic features

Social anxiety is a symptom widely prevalent among young adults, and when present in excess, can lead to maladaptive patterns of social behavior. Recent approaches that incorporate brain functional radiomic features and machine learning have shown potential for predicting certain phenotypes or disorders from functional magnetic resonance images. In this study, we aimed to predict the level of social anxiety in young adult participants by training machine learning models with resting-state brain functional radiomic features including the regional homogeneity, fractional amplitude of low-frequency fluctuation, fractional resting-state physiological fluctuation amplitude, and degree centrality. Among the machine learning models, the XGBoost model achieved the best performance with balanced accuracy of 77.7% and F1 score of 0.815. Analysis of input feature importance demonstrated that the orbitofrontal cortex and the degree centrality were most relevant to predicting the level of social anxiety among the input brain regions and the input type of radiomic features, respectively. These results suggest potential validity for predicting social anxiety with machine learning of the resting-state brain functional radiomic features and provide further understanding of the neural basis of the symptom.

Machine Learning-Based Behavioral Diagnostic Tools for Depression: Advances, Challenges, and Future Directions

The psychiatric diagnostic procedure is currently based on self-reports that are subject to personal biases. Therefore, the diagnostic process would benefit greatly from data-driven tools that can enhance accuracy and specificity. In recent years, many studies have achieved promising results in detecting and diagnosing depression based on machine learning (ML) analysis. Despite these favorable results in depression diagnosis, which are primarily based on ML analysis of neuroimaging data, most patients do not have access to neuroimaging tools. Hence, objective assessment tools are needed that can be easily integrated into the routine psychiatric diagnostic process. One solution is to use behavioral data, which can be easily collected while still maintaining objectivity. The current paper summarizes the main ML-based approaches that use behavioral data in diagnosing depression and other psychiatric disorders. We classified these studies into two main categories: (a) laboratory-based assessments and (b) data mining, the latter of which we further divided into two sub-groups: (i) social media usage and movement sensors data and (ii) demographic and clinical information. The paper discusses the advantages and challenges in this field and suggests future research directions and implementations. The paper's overarching aim is to serve as a first step in synthetizing existing knowledge about ML-based behavioral diagnosis studies in order to develop interventions and individually tailored treatments in the future.

Predicting self-harm within six months after initial presentation to youth mental health services: A machine learning study

BACKGROUND

A priority for health services is to reduce self-harm in young people. Predicting self-harm is challenging due to their rarity and complexity, however this does not preclude the utility of prediction models to improve decision-making regarding a service response in terms of more detailed assessments and/or intervention. The aim of this study was to predict self-harm within six-months after initial presentation.

METHOD

The study included 1962 young people (12-30 years) presenting to youth mental health services in Australia. Six machine learning algorithms were trained and tested with ten repeats of ten-fold cross-validation. The net benefit of these models were evaluated using decision curve analysis.

RESULTS

Out of 1962 young people, 320 (16%) engaged in self-harm in the six months after first assessment and 1642 (84%) did not. The top 25% of young people as ranked by mean predicted probability accounted for 51.6% - 56.2% of all who engaged in self-harm. By the top 50%, this increased to 82.1%-84.4%. Models demonstrated fair overall prediction (AUROCs; 0.744-0.755) and calibration which indicates that predicted probabilities were close to the true probabilities (brier scores; 0.185-0.196). The net benefit of these models were positive and superior to the 'treat everyone' strategy. The strongest predictors were (in ranked order); a history of self-harm, age, social and occupational functioning, sex, bipolar disorder, psychosis-like experiences, treatment with antipsychotics, and a history of suicide ideation.

CONCLUSION

Prediction models for self-harm may have utility to identify a large sub population who would benefit from further assessment and targeted (low intensity) interventions. Such models could enhance health service approaches to identify and reduce self-harm, a considerable source of distress, morbidity, ongoing health care utilisation and mortality.