Machine learning in mental health: a scoping review of methods and applications

Predicting Symptoms of Depression and Anxiety Using Smartphone and Wearable Data

Background: Depression and anxiety are leading causes of disability worldwide but often remain undetected and untreated. Smartphone and wearable devices may offer a unique source of data to detect moment by moment changes in risk factors associated with mental disorders that overcome many of the limitations of traditional screening methods. Objective: The current study aimed to explore the extent to which data from smartphone and wearable devices could predict symptoms of depression and anxiety. Methods: A total of N = 60 adults (ages 24-68) who owned an Apple iPhone and Oura Ring were recruited online over a 2-week period. At the beginning of the study, participants installed the Delphi data acquisition app on their smartphone. The app continuously monitored participants' location (using GPS) and smartphone usage behavior (total usage time and frequency of use). The Oura Ring provided measures related to activity (step count and metabolic equivalent for task), sleep (total sleep time, sleep onset latency, wake after sleep onset and time in bed) and heart rate variability (HRV). In addition, participants were prompted to report their daily mood (valence and arousal). Participants completed self-reported assessments of depression, anxiety and stress (DASS-21) at baseline, midpoint and the end of the study. Results: Multilevel models demonstrated a significant negative association between the variability of locations visited and symptoms of depression (beta = -0.21, p = 0.037) and significant positive associations between total sleep time and depression (beta = 0.24, p = 0.023), time in bed and depression (beta = 0.26, p = 0.020), wake after sleep onset and anxiety (beta = 0.23, p = 0.035) and HRV and anxiety (beta = 0.26, p = 0.035). A combined model of smartphone and wearable features and self-reported mood provided the strongest prediction of depression. Conclusion: The current findings demonstrate that wearable devices may provide valuable sources of data in predicting symptoms of depression and anxiety, most notably data related to common measures of sleep.

Precision clinical trials: a framework for getting to precision medicine for neurobehavioural disorders

The goal of precision medicine (individually tailored treatments) is not being achieved for neurobehavioural conditions such as psychiatric disorders. Traditional randomized clinical trial methods are insufficient for advancing precision medicine because of the dynamic complexity of these conditions. We present a pragmatic solution: the precision clinical trial framework, encompassing methods for individually tailored treatments. This framework includes the following: (1) treatment-targeted enrichment, which involves measuring patients' response after a brief bout of an intervention, and then randomizing patients to a full course of treatment, using the acute response to predict long-term outcomes; (2) adaptive treatments, which involve adjusting treatment parameters during the trial to individually optimize the treatment; and (3) precise measurement, which involves measuring predictor and outcome variables with high accuracy and reliability using techniques such as ecological momentary assessment. This review summarizes precision clinical trials and provides a research agenda, including new biomarkers such as precision neuroimaging, transcranial magnetic stimulation-electroencephalogram digital phenotyping and advances in statistical and machine-learning models. Validation of these approaches - and then widespread incorporation of the precision clinical trial framework - could help achieve the vision of precision medicine for neurobehavioural conditions.

Accuracy of individual and combined risk-scale items in the prediction of repetition of self-harm: multicentre prospective cohort study

BACKGROUND

Individuals attending emergency departments following self-harm have increased risks of future self-harm. Despite the common use of risk scales in self-harm assessment, there is growing evidence that combinations of risk factors do not accurately identify those at greatest risk of further self-harm and suicide.

AIMS

To evaluate and compare predictive accuracy in prediction of repeat self-harm from clinician and patient ratings of risk, individual risk-scale items and a scale constructed with top-performing items.

METHOD

We conducted secondary analysis of data from a five-hospital multicentre prospective cohort study of participants referred to psychiatric liaison services following self-harm. We tested predictive utility of items from five risk scales: Manchester Self-Harm Rule, ReACT Self-Harm Rule, SAD PERSONS, Modified SAD PERSONS, Barratt Impulsiveness Scale and clinician and patient risk estimates. Area under the curve (AUC), sensitivity, specificity, predictive values and likelihood ratios were used to evaluate predictive accuracy, with sensitivity analyses using classification-tree regression.

RESULTS

A total of 483 self-harm episodes were included, and 145 (30%) were followed by a repeat presentation within 6 months. AUC of individual items ranged from 0.43-0.65. Combining best performing items resulted in an AUC of 0.56. Some individual items outperformed the scale they originated from; no items were superior to clinician or patient risk estimations.

CONCLUSIONS

No individual or combination of items outperformed patients' or clinicians' ratings. This suggests there are limitations to combining risk factors to predict risk of self-harm repetition. Risk scales should have little role in the management of people who have self-harmed.

Robust data-driven identification of risk factors and their interactions: A simulation and a study of parental and demographic risk factors for schizophrenia

OBJECTIVES

Few interactions between risk factors for schizophrenia have been replicated, but fitting all such interactions is difficult due to high-dimensionality. Our aims are to examine significant main and interaction effects for schizophrenia and the performance of our approach using simulated data.

METHODS

We apply the machine learning technique elastic net to a high-dimensional logistic regression model to produce a sparse set of predictors, and then assess the significance of odds ratios (OR) with Bonferroni-corrected p-values and confidence intervals (CI). We introduce a simulation model that resembles a Finnish nested case-control study of schizophrenia which uses national registers to identify cases (n = 1,468) and controls (n = 2,975). The predictors include nine sociodemographic factors and all interactions (31 predictors).

RESULTS

In the simulation, interactions with OR = 3 and prevalence = 4% were identified with <5% false positive rate and ≥80% power. None of the studied interactions were significantly associated with schizophrenia, but main effects of parental psychosis (OR = 5.2, CI 2.9-9.7; p < .001), urbanicity (1.3, 1.1-1.7; p = .001), and paternal age ≥35 (1.3, 1.004-1.6; p = .04) were significant.

CONCLUSIONS

We have provided an analytic pipeline for data-driven identification of main and interaction effects in case-control data. We identified highly replicated main effects for schizophrenia, but no interactions.

A comparison of penalised regression methods for informing the selection of predictive markers

Background

Penalised regression methods are a useful atheoretical approach for both developing predictive models and selecting key indicators within an often substantially larger pool of available indicators. In comparison to traditional methods, penalised regression models improve prediction in new data by shrinking the size of coefficients and retaining those with coefficients greater than zero. However, the performance and selection of indicators depends on the specific algorithm implemented. The purpose of this study was to examine the predictive performance and feature (i.e., indicator) selection capability of common penalised logistic regression methods (LASSO, adaptive LASSO, and elastic-net), compared with traditional logistic regression and forward selection methods.

Design

Data were drawn from the Australian Temperament Project, a multigenerational longitudinal study established in 1983. The analytic sample consisted of 1,292 (707 women) participants. A total of 102 adolescent psychosocial and contextual indicators were available to predict young adult daily smoking.

Findings

Penalised logistic regression methods showed small improvements in predictive performance over logistic regression and forward selection. However, no single penalised logistic regression model outperformed the others. Elastic-net models selected more indicators than either LASSO or adaptive LASSO. Additionally, more regularised models included fewer indicators, yet had comparable predictive performance. Forward selection methods dismissed many indicators identified as important in the penalised logistic regression models.

Conclusions

Although overall predictive accuracy was only marginally better with penalised logistic regression methods, benefits were most clear in their capacity to select a manageable subset of indicators. Preference to competing penalised logistic regression methods may therefore be guided by feature selection capability, and thus interpretative considerations, rather than predictive performance alone.

Spectral features based convolutional neural network for accurate and prompt identification of schizophrenic patients

Schizophrenia is a fatal mental disorder, which affects millions of people globally by the disturbance in their thinking, feeling and behaviour. In the age of the internet of things assisted with cloud computing and machine learning techniques, the computer-aided diagnosis of schizophrenia is essentially required to provide its patients with an opportunity to own a better quality of life. In this context, the present paper proposes a spectral features based convolutional neural network (CNN) model for accurate identification of schizophrenic patients using spectral analysis of multichannel EEG signals in real-time. This model processes acquired EEG signals with filtering, segmentation and conversion into frequency domain. Then, given frequency domain segments are divided into six distinct spectral bands like delta, theta-1, theta-2, alpha, beta and gamma. The spectral features including mean spectral amplitude, spectral power and Hjorth descriptors (Activity, Mobility and Complexity) are extracted from each band. These features are independently fed to the proposed spectral features-based CNN and long short-term memory network (LSTM) models for classification. This work also makes use of raw time-domain and frequency-domain EEG segments for classification using temporal CNN and spectral CNN models of same architectures respectively. The overall analysis of simulation results of all models exhibits that the proposed spectral features based CNN model is an efficient technique for accurate and prompt identification of schizophrenic patients among healthy individuals with average classification accuracies of 94.08% and 98.56% for two different datasets with optimally small classification time.

Application of deep learning in detecting neurological disorders from magnetic resonance images: a survey on the detection of Alzheimer's disease, Parkinson's disease and schizophrenia

Neuroimaging, in particular magnetic resonance imaging (MRI), has been playing an important role in understanding brain functionalities and its disorders during the last couple of decades. These cutting-edge MRI scans, supported by high-performance computational tools and novel ML techniques, have opened up possibilities to unprecedentedly identify neurological disorders. However, similarities in disease phenotypes make it very difficult to detect such disorders accurately from the acquired neuroimaging data. This article critically examines and compares performances of the existing deep learning (DL)-based methods to detect neurological disorders-focusing on Alzheimer's disease, Parkinson's disease and schizophrenia-from MRI data acquired using different modalities including functional and structural MRI. The comparative performance analysis of various DL architectures across different disorders and imaging modalities suggests that the Convolutional Neural Network outperforms other methods in detecting neurological disorders. Towards the end, a number of current research challenges are indicated and some possible future research directions are provided.

Deep neural networks detect suicide risk from textual facebook posts

Detection of suicide risk is a highly prioritized, yet complicated task. Five decades of research have produced predictions slightly better than chance (AUCs = 0.56–0.58). In this study, Artificial Neural Network (ANN) models were constructed to predict suicide risk from everyday language of social media users. The dataset included 83,292 postings authored by 1002 authenticated Facebook users, alongside valid psychosocial information about the users. Using Deep Contextualized Word Embeddings for text representation, two models were constructed: A Single Task Model (STM), to predict suicide risk from Facebook postings directly (Facebook texts → suicide) and a Multi-Task Model (MTM), which included hierarchical, multilayered sets of theory-driven risk factors (Facebook texts → personality traits → psychosocial risks → psychiatric disorders → suicide). Compared with the STM predictions (0.621 ≤ AUC ≤ 0.629), the MTM produced significantly improved prediction accuracy (0.697 ≤ AUC ≤ 0.746), with substantially larger effect sizes (0.729 ≤ d ≤ 0.936). Subsequent content analyses suggested that predictions did not rely on explicit suicide-related themes, but on a range of text features. The findings suggest that machine learning based analyses of everyday social media activity can improve suicide risk predictions and contribute to the development of practical detection tools.

Illuminating the dark spaces of healthcare with ambient intelligence

Advances in machine learning and contactless sensors have given rise to ambient intelligence-physical spaces that are sensitive and responsive to the presence of humans. Here we review how this technology could improve our understanding of the metaphorically dark, unobserved spaces of healthcare. In hospital spaces, early applications could soon enable more efficient clinical workflows and improved patient safety in intensive care units and operating rooms. In daily living spaces, ambient intelligence could prolong the independence of older individuals and improve the management of individuals with a chronic disease by understanding everyday behaviour. Similar to other technologies, transformation into clinical applications at scale must overcome challenges such as rigorous clinical validation, appropriate data privacy and model transparency. Thoughtful use of this technology would enable us to understand the complex interplay between the physical environment and health-critical human behaviours.

Social Media and Mental Health: Benefits, Risks, and Opportunities for Research and Practice

Social media platforms are popular venues for sharing personal experiences, seeking information, and offering peer-to-peer support among individuals living with mental illness. With significant shortfalls in the availability, quality, and reach of evidence-based mental health services across the United States and globally, social media platforms may afford new opportunities to bridge this gap. However, caution is warranted, as numerous studies highlight risks of social media use for mental health. In this commentary, we consider the role of social media as a potentially viable intervention platform for offering support to persons with mental disorders, promoting engagement and retention in care, and enhancing existing mental health services. Specifically, we summarize current research on the use of social media among mental health service users, and early efforts using social media for the delivery of evidence-based programs. We also review the risks, potential harms, and necessary safety precautions with using social media for mental health. To conclude, we explore opportunities using data science and machine learning, for example by leveraging social media for detecting mental disorders and developing predictive models aimed at characterizing the aetiology and progression of mental disorders. These various efforts using social media, as summarized in this commentary, hold promise for improving the lives of individuals living with mental disorders.

[Quality psychiatry and destigmatization : Can quality psychiatry and psychotherapy contribute to destigmatization of mental illnesses?]

BACKGROUND

Among the many reasons for the stigmatization of mental illnesses and those affected by it, the supposedly insufficient treatability plays a central role. In fact, treatability is not worse compared to various somatic diseases, although different factors impair the use and thus the effect of optimal treatment options. This is where measures to optimize treatment and care within the framework of quality psychiatry and psychotherapy come into play, whose resource-backed systematic introduction and implementation can contribute to overcoming stigma.

OBJECTIVE

This article examines whether and how the quality of psychiatric treatment and care can contribute to reducing stigmatizing attitudes in the general public and the stigma experienced or anticipated by persons with mental illnesses.

METHODS

Components of quality assured psychiatric treatment and care were identified at the conceptual level, which can hypothetically contribute to the destigmatization of persons with mental illnesses.

RESULTS AND CONCLUSION

The components of quality psychiatry that can contribute to the destigmatization of persons with mental illnesses include the implementation of regularly updated evidence-based treatment guidelines, the individualization of psychiatric treatment (precision psychiatry) and the application of quality indicators within the framework of comprehensive quality management. The postulated relationships must be empirically verified, further analyzed and communicated to the public to be made systematically useful for the destigmatization of mental illnesses.

Supervised Machine Learning: A Brief Primer

Machine learning is increasingly used in mental health research and has the potential to advance our understanding of how to characterize, predict, and treat mental disorders and associated adverse health outcomes (e.g., suicidal behavior). Machine learning offers new tools to overcome challenges for which traditional statistical methods are not well-suited. This paper provides an overview of machine learning with a specific focus on supervised learning (i.e., methods that are designed to predict or classify an outcome of interest). Several common supervised learning methods are described, along with applied examples from the published literature. We also provide an overview of supervised learning model building, validation, and performance evaluation. Finally, challenges in creating robust and generalizable machine learning algorithms are discussed.

A scoping review of machine learning in psychotherapy research

Machine learning (ML) offers robust statistical and probabilistic techniques that can help to make sense of large amounts of data. This scoping review paper aims to broadly explore the nature of research activity using ML in the context of psychological talk therapies, highlighting the scope of current methods and considerations for clinical practice and directions for future research. Using a systematic search methodology, fifty-one studies were identified. A narrative synthesis indicates two types of studies, those who developed and tested an ML model (k=44), and those who reported on the feasibility of a particular treatment tool that uses an ML algorithm (k=7). Most model development studies used supervised learning techniques to classify or predict labeled treatment process or outcome data, whereas others used unsupervised techniques to identify clusters in the unlabeled patient or treatment data. Overall, the current applications of ML in psychotherapy research demonstrated a range of possible benefits for indications of treatment process, adherence, therapist skills and treatment response prediction, as well as ways to accelerate research through automated behavioral or linguistic process coding. Given the novelty and potential of this research field, these proof-of-concept studies are encouraging, however, do not necessarily translate to improved clinical practice (yet).

Embracing the positive: an examination of how well resilience factors at age 14 can predict distress at age 17

One-in-two people suffering from mental health problems develop such distress before or during adolescence. Research has shown that distress can predict itself well over time. Yet, little is known about how well resilience factors (RFs), i.e. those factors that decrease mental health problems, predict subsequent distress. Therefore, we investigated which RFs are the best indicators for subsequent distress and with what accuracy RFs predict subsequent distress. We examined three interpersonal (e.g. friendships) and seven intrapersonal RFs (e.g. self-esteem) and distress in 1130 adolescents, at age 14 and 17. We estimated the RFs and a continuous distress-index using factor analyses, and ordinal distress-classes using factor mixture models. We then examined how well age-14 RFs and age-14 distress predict age-17 distress, using stepwise linear regressions, relative importance analyses, as well as ordinal and linear prediction models. Low brooding, low negative and high positive self-esteem RFs were the most important indicators for age-17 distress. RFs and age-14 distress predicted age-17 distress similarly. The accuracy was acceptable for ordinal (low/moderate/high age-17 distress-classes: 62-64%), but low for linear models (37-41%). Crucially, the accuracy remained similar when only self-esteem and brooding RFs were used instead of all ten RFs (ordinal = 62%; linear = 37%); correctly predicting for about two-in-three adolescents whether they have low, moderate or high distress 3 years later. RFs, and particularly brooding and self-esteem, seem to predict subsequent distress similarly well as distress can predict itself. As assessing brooding and self-esteem can be strength-focussed and is time-efficient, those RFs may be promising for risk-detection and translational intervention research.

Efficacy of a Smartphone App Intervention for Reducing Caregiver Stress: Randomized Controlled Trial

BACKGROUND

Caregivers play a pivotal role in maintaining an economically viable health care system, yet they are characterized by low levels of psychological well-being and consistently report unmet needs for psychological support. Mobile app-based (mobile health [mHealth]) interventions present a novel approach to both reducing stress and improving well-being.

OBJECTIVE

This study aims to evaluate the effectiveness of a self-guided mobile app-based psychological intervention for people providing care to family or friends with a physical or mental disability.

METHODS

In a randomized, single-blind, controlled trial, 183 caregivers recruited through the web were randomly allocated to either an intervention (n=73) or active control (n=110) condition. The intervention app contained treatment modules combining daily self-monitoring with third-wave (mindfulness-based) cognitive-behavioral therapies, whereas the active control app contained only self-monitoring features. Both programs were completed over a 5-week period. It was hypothesized that intervention app exposure would be associated with decreases in depression, anxiety, and stress, and increases in well-being, self-esteem, optimism, primary and secondary control, and social support. Outcomes were assessed at baseline, postintervention, and 3-4 months postintervention. App quality was also assessed.

RESULTS

In total, 25% (18/73) of the intervention participants were lost to follow-up at 3 months, and 30.9% (34/110) of the participants from the wait-list control group dropped out before the postintervention survey. The intervention group experienced reductions in stress (b=-2.07; P=.04) and depressive symptoms (b=-1.36; P=.05) from baseline to postintervention. These changes were further enhanced from postintervention to follow-up, with the intervention group continuing to report lower levels of depression (b=-1.82; P=.03) and higher levels of emotional well-being (b=6.13; P<.001), optimism (b=0.78; P=.007), self-esteem (b=-0.84; P=.005), support from family (b=2.15; P=.001), support from significant others (b=2.66; P<.001), and subjective well-being (b=4.82; P<.001). On average, participants completed 2.5 (SD 1.05) out of 5 treatment modules. The overall quality of the app was also rated highly, with a mean score of 3.94 out of a maximum score of 5 (SD 0.58).

CONCLUSIONS

This study demonstrates that mHealth psychological interventions are an effective treatment option for caregivers experiencing high levels of stress. Recommendations for improving mHealth interventions for caregivers include offering flexibility and customization in the treatment design.

TRIAL REGISTRATION

Australian New Zealand Clinical Trial Registry ACTRN12616000996460; https://www.anzctr.org.au/Trial/Registration/TrialReview.aspx?id=371170.

A scoping review of the use of Twitter for public health research

Public health practitioners and researchers have used traditional medical databases to study and understand public health for a long time. Recently, social media data, particularly Twitter, has seen some use for public health purposes. Every large technological development in history has had an impact on the behaviour of society. The advent of the internet and social media is no different. Social media creates public streams of communication, and scientists are starting to understand that such data can provide some level of access into the people's opinions and situations. As such, this paper aims to review and synthesize the literature on Twitter applications for public health, highlighting current research and products in practice. A scoping review methodology was employed and four leading health, computer science and cross-disciplinary databases were searched. A total of 755 articles were retreived, 92 of which met the criteria for review. From the reviewed literature, six domains for the application of Twitter to public health were identified: (i) Surveillance; (ii) Event Detection; (iii) Pharmacovigilance; (iv) Forecasting; (v) Disease Tracking; and (vi) Geographic Identification. From our review, we were able to obtain a clear picture of the use of Twitter for public health. We gained insights into interesting observations such as how the popularity of different domains changed with time, the diseases and conditions studied and the different approaches to understanding each disease, which algorithms and techniques were popular with each domain, and more.

Machine learning and natural language processing in psychotherapy research: Alliance as example use case

Artificial intelligence generally and machine learning specifically have become deeply woven into the lives and technologies of modern life. Machine learning is dramatically changing scientific research and industry and may also hold promise for addressing limitations encountered in mental health care and psychotherapy. The current paper introduces machine learning and natural language processing as related methodologies that may prove valuable for automating the assessment of meaningful aspects of treatment. Prediction of therapeutic alliance from session recordings is used as a case in point. Recordings from 1,235 sessions of 386 clients seen by 40 therapists at a university counseling center were processed using automatic speech recognition software. Machine learning algorithms learned associations between client ratings of therapeutic alliance exclusively from session linguistic content. Using a portion of the data to train the model, machine learning algorithms modestly predicted alliance ratings from session content in an independent test set (Spearman's ρ = .15, p < .001). These results highlight the potential to harness natural language processing and machine learning to predict a key psychotherapy process variable that is relatively distal from linguistic content. Six practical suggestions for conducting psychotherapy research using machine learning are presented along with several directions for future research. Questions of dissemination and implementation may be particularly important to explore as machine learning improves in its ability to automate assessment of psychotherapy process and outcome. (PsycInfo Database Record (c) 2020 APA, all rights reserved).

Utilization of machine learning to test the impact of cognitive processing and emotion recognition on the development of PTSD following trauma exposure

BACKGROUND

Though lifetime exposure to traumatic events is significant, only a minority of individuals develops symptoms of posttraumatic stress disorder (PTSD). Post-trauma alterations in neurocognitive and affective functioning are likely to reflect changes in underlying brain networks that are predictive of PTSD. These constructs are assumed to interact in a highly complex way. The aim of this exploratory study was to apply machine learning models to investigate the contribution of these interactions on PTSD symptom development and identify measures indicative of circuit related dysfunction.

METHODS

N = 94 participants admitted to the emergency room of an inner-city hospital after trauma exposure completed a battery of neurocognitive and emotional tests 1 month after the incident. Different machine learning algorithms were applied to predict PTSD symptom severity and clusters after 3 months based.

RESULTS

Overall, model accuracy did not differ between PTSD clusters, though the importance of cognitive and emotional domains demonstrated both key differences and overlap. Alterations in higher-order executive functioning, speed of information processing, and processing of emotionally incongruent cues were the most important predictors.

CONCLUSIONS

Data-driven approaches are a powerful tool to investigate complex interactions and can enhance the mechanistic understanding of PTSD. The study identifies important relationships between cognitive processing and emotion recognition that may be valuable to predict and understand mechanisms of risk and resilience responses to trauma prospectively.

Psychosis, vulnerability, and the moral significance of biomedical innovation in psychiatry. Why ethicists should join efforts

The study of the neuroscience and genomics of mental illness are increasingly intertwined. This is mostly due to the translation of medical technologies into psychiatry and to technological convergence. This article focuses on psychosis. I argue that the convergence of neuroscience and genomics in the context of psychosis is morally problematic, and that ethics scholarship should go beyond the identification of a number of ethical, legal, and social issues. My argument is composed of two strands. First, I argue that we should respond to technological convergence by developing an integrated, patient-centred approach focused on the assessment of individual vulnerabilities. Responding to technological convergence requires that we (i) integrate insights from several areas of ethics, (ii) translate bioethical principles into the mental health context, and (iii) proactively try to anticipate future ethical concerns. Second, I argue that a nuanced understanding of the concept of vulnerability might help us to accomplish this task. I borrow Florencia Luna's notion of 'layers of vulnerability' to show how potential harms or wrongs to individuals who experience psychosis can be conceptualised as stemming from different sources, or layers, of vulnerability. I argue that a layered notion of vulnerability might serve as a common ground to achieve the ethical integration needed to ensure that biomedical innovation can truly benefit, and not harm, individuals who suffer from psychosis.

Automated MRI-Based Deep Learning Model for Detection of Alzheimer’s Disease Process

In the context of neuro-pathological disorders, neuroimaging has been widely accepted as a clinical tool for diagnosing patients with Alzheimer’s disease (AD) and mild cognitive impairment (MCI). The advanced deep learning method, a novel brain imaging technique, was applied in this study to evaluate its contribution to improving the diagnostic accuracy of AD. Three-dimensional convolutional neural networks (3D-CNNs) were applied with magnetic resonance imaging (MRI) to execute binary and ternary disease classification models. The dataset from the Alzheimer’s disease neuroimaging initiative (ADNI) was used to compare the deep learning performances across 3D-CNN, 3D-CNN-support vector machine (SVM) and two-dimensional (2D)-CNN models. The outcomes of accuracy with ternary classification for 2D-CNN, 3D-CNN and 3D-CNN-SVM were [Formula: see text]%, [Formula: see text]% and [Formula: see text]% respectively. The 3D-CNN-SVM yielded a ternary classification accuracy of 93.71%, 96.82% and 96.73% for NC, MCI and AD diagnoses, respectively. Furthermore, 3D-CNN-SVM showed the best performance for binary classification. Our study indicated that ‘NC versus MCI’ showed accuracy, sensitivity and specificity of 98.90%, 98.90% and 98.80%; ‘NC versus AD’ showed accuracy, sensitivity and specificity of 99.10%, 99.80% and 98.40%; and ‘MCI versus AD’ showed accuracy, sensitivity and specificity of 89.40%, 86.70% and 84.00%, respectively. This study clearly demonstrates that 3D-CNN-SVM yields better performance with MRI compared to currently utilized deep learning methods. In addition, 3D-CNN-SVM proved to be efficient without having to manually perform any prior feature extraction and is totally independent of the variability of imaging protocols and scanners. This suggests that it can potentially be exploited by untrained operators and extended to virtual patient imaging data. Furthermore, owing to the safety, noninvasiveness and nonirradiative properties of the MRI modality, 3D-CNN-SMV may serve as an effective screening option for AD in the general population. This study holds value in distinguishing AD and MCI subjects from normal controls and to improve value-based care of patients in clinical practice.

Knowing me, knowing you: theory of mind in AI

Artificial intelligence has dramatically changed the world as we know it, but is yet to fully embrace 'hot' cognition, i.e., the way an intelligent being's thinking is affected by their emotional state. Artificial intelligence encompassing hot cognition will not only usher in enhanced machine-human interactions, but will also promote a much needed ethical approach. Theory of Mind, the ability of the human mind to attribute mental states to others, is a key component of hot cognition. To endow machines with (limited) Theory of Mind capabilities, computer scientists will need to work closely with psychiatrists, psychologists and neuroscientists. They will need to develop new models, but also to formally define what problems need to be solved and how the results should be assessed.

Machine Learning Models for the Prediction of Postpartum Depression: Application and Comparison Based on a Cohort Study

Background

Postpartum depression (PPD) is a serious public health problem. Building a predictive model for PPD using data during pregnancy can facilitate earlier identification and intervention.

Objective

The aims of this study are to compare the effects of four different machine learning models using data during pregnancy to predict PPD and explore which factors in the model are the most important for PPD prediction.

Methods

Information on the pregnancy period from a cohort of 508 women, including demographics, social environmental factors, and mental health, was used as predictors in the models. The Edinburgh Postnatal Depression Scale score within 42 days after delivery was used as the outcome indicator. Using two feature selection methods (expert consultation and random forest-based filter feature selection [FFS-RF]) and two algorithms (support vector machine [SVM] and random forest [RF]), we developed four different machine learning PPD prediction models and compared their prediction effects.

Results

There was no significant difference in the effectiveness of the two feature selection methods in terms of model prediction performance, but 10 fewer factors were selected with the FFS-RF than with the expert consultation method. The model based on SVM and FFS-RF had the best prediction effects (sensitivity=0.69, area under the curve=0.78). In the feature importance ranking output by the RF algorithm, psychological elasticity, depression during the third trimester, and income level were the most important predictors.

Conclusions

In contrast to the expert consultation method, FFS-RF was important in dimension reduction. When the sample size is small, the SVM algorithm is suitable for predicting PPD. In the prevention of PPD, more attention should be paid to the psychological resilience of mothers.

Improving Diagnosis of Depression With XGBOOST Machine Learning Model and a Large Biomarkers Dutch Dataset (n = 11,081)

Machine Learning has been on the rise and healthcare is no exception to that. In healthcare, mental health is gaining more and more space. The diagnosis of mental disorders is based upon standardized patient interviews with defined set of questions and scales which is a time consuming and costly process. Our objective was to apply the machine learning model and to evaluate to see if there is predictive power of biomarkers data to enhance the diagnosis of depression cases. In this research paper, we aimed to explore the detection of depression cases among the sample of 11,081 Dutch citizen dataset. Most of the earlier studies have balanced datasets wherein the proportion of healthy cases and unhealthy cases are equal but in our study, the dataset contains only 570 cases of self-reported depression out of 11,081 cases hence it is a class imbalance classification problem. The machine learning model built on imbalance dataset gives predictions biased toward majority class hence the model will always predict the case as no depression case even if it is a case of depression. We used different resampling strategies to address the class imbalance problem. We created multiple samples by under sampling, over sampling, over-under sampling and ROSE sampling techniques to balance the dataset and then, we applied machine learning algorithm “Extreme Gradient Boosting” (XGBoost) on each sample to classify the mental illness cases from healthy cases. The balanced accuracy, precision, recall and F1 score obtained from over-sampling and over-under sampling were more than 0.90.

Grant Report on SCH: Personalized Depression Treatment Supported by Mobile Sensor Analytics

We report on the newly started project "SCH: Personalized Depression Treatment Supported by Mobile Sensor Analytics". The current best practice guidelines for treating depression call for close monitoring of patients, and periodically adjusting treatment as needed. This project will advance personalized depression treatment by developing a system, DepWatch, that leverages mobile health technologies and machine learning tools. The objective of DepWatch is to assist clinicians with their decision making process in the management of depression. The project comprises two studies. Phase I collects sensory data and other data, e.g., clinical data, ecological momentary assessments (EMA), tolerability and safety data from 250 adult participants with unstable depression symptomatology initiating depression treatment. The data thus collected will be used to develop and validate assessment and prediction models, which will be incorporated into DepWatch system. In Phase II, three clinicians will use DepWatch to support their clinical decision making process. A total of 128 participants under treatment by the three participating clinicians will be recruited for the study. A number of new machine learning techniques will be developed.

schema: an open-source, distributed mobile platform for deploying mHealth research tools and interventions

Background

Mobile applications for health, also known as ‘mHealth apps’, have experienced increasing popularity over the past ten years. However, most publicly available mHealth apps are not clinically validated, and many do not utilise evidence-based strategies. Health researchers wishing to develop and evaluate mHealth apps may be impeded by cost and technical skillset barriers. As traditionally lab-based methods are translated onto mobile platforms, robust and accessible tools are needed to enable the development of quality, evidence-based programs by clinical experts.

Results

This paper introduces schema, an open-source, distributed, app-based platform for researchers to deploy behavior monitoring and health interventions onto mobile devices. The architecture and design features of the platform are discussed, including flexible scheduling, randomisation, a wide variety of survey and media elements, and distributed storage of data. The platform supports a range of research designs, including cross-sectional surveys, ecological momentary assessment, randomised controlled trials, and micro-randomised just-in-time adaptive interventions. Use cases for both researchers and participants are considered to demonstrate the flexibility and usefulness of the platform for mHealth research.

Conclusions

The paper concludes by considering the strengths and limitations of the platform, and a call for support from the research community in areas of technical development and evaluation. To get started with schema, please visit the GitHub repository: https://github.com/schema-app/schema.

Deep learning in mental health outcome research: a scoping review

Mental illnesses, such as depression, are highly prevalent and have been shown to impact an individual's physical health. Recently, artificial intelligence (AI) methods have been introduced to assist mental health providers, including psychiatrists and psychologists, for decision-making based on patients' historical data (e.g., medical records, behavioral data, social media usage, etc.). Deep learning (DL), as one of the most recent generation of AI technologies, has demonstrated superior performance in many real-world applications ranging from computer vision to healthcare. The goal of this study is to review existing research on applications of DL algorithms in mental health outcome research. Specifically, we first briefly overview the state-of-the-art DL techniques. Then we review the literature relevant to DL applications in mental health outcomes. According to the application scenarios, we categorize these relevant articles into four groups: diagnosis and prognosis based on clinical data, analysis of genetics and genomics data for understanding mental health conditions, vocal and visual expression data analysis for disease detection, and estimation of risk of mental illness using social media data. Finally, we discuss challenges in using DL algorithms to improve our understanding of mental health conditions and suggest several promising directions for their applications in improving mental health diagnosis and treatment.

Ethical dilemmas posed by mobile health and machine learning in psychiatry research

The application of digital technology to psychiatry research is rapidly leading to new discoveries and capabilities in the field of mobile health. However, the increase in opportunities to passively collect vast amounts of detailed information on study participants coupled with advances in statistical techniques that enable machine learning models to process such information has raised novel ethical dilemmas regarding researchers' duties to: (i) monitor adverse events and intervene accordingly; (ii) obtain fully informed, voluntary consent; (iii) protect the privacy of participants; and (iv) increase the transparency of powerful, machine learning models to ensure they can be applied ethically and fairly in psychiatric care. This review highlights emerging ethical challenges and unresolved ethical questions in mobile health research and provides recommendations on how mobile health researchers can address these issues in practice. Ultimately, the hope is that this review will facilitate continued discussion on how to achieve best practice in mobile health research within psychiatry.

Prevalence of Machine Learning in Craniofacial Surgery

Machine learning (ML) revolves around the concept of using experience to teach computer-based programs to reliably perform specific tasks. Healthcare setting is an ideal environment for adaptation of ML applications given the multiple specific tasks that could be allocated to computer programs to perform. There have been several scoping reviews published in literature looking at the general acceptance and adaptability of surgical specialities to ML applications, but very few focusing on the application towards craniofacial surgery. This study aims to present a detailed scoping review regarding the use of ML applications in craniofacial surgery.

An Autoencoder and Machine Learning Model to Predict Suicidal Ideation with Brain Structural Imaging

It is estimated that at least one million people die by suicide every year, showing the importance of suicide prevention and detection. In this study, an autoencoder and machine learning model was employed to predict people with suicidal ideation based on their structural brain imaging. The subjects in our generalized q-sampling imaging (GQI) dataset consisted of three groups: 41 depressive patients with suicidal ideation (SI), 54 depressive patients without suicidal thoughts (NS), and 58 healthy controls (HC). In the GQI dataset, indices of generalized fractional anisotropy (GFA), isotropic values of the orientation distribution function (ISO), and normalized quantitative anisotropy (NQA) were separately trained in different machine learning models. A convolutional neural network (CNN)-based autoencoder model, the supervised machine learning algorithm extreme gradient boosting (XGB), and logistic regression (LR) were used to discriminate SI subjects from NS and HC subjects. After five-fold cross validation, separate data were tested to obtain the accuracy, sensitivity, specificity, and area under the curve of each result. Our results showed that the best pattern of structure across multiple brain locations can classify suicidal ideates from NS and HC with a prediction accuracy of 85%, a specificity of 100% and a sensitivity of 75%. The algorithms developed here might provide an objective tool to help identify suicidal ideation risk among depressed patients alongside clinical assessment.

Using machine learning to explain the heterogeneity of schizophrenia. Realizing the promise and avoiding the hype

Despite extensive research and prodigious advances in neuroscience, our comprehension of the nature of schizophrenia remains rudimentary. Our failure to make progress is attributed to the extreme heterogeneity of this condition, enormous complexity of the human brain, limitations of extant research paradigms, and inadequacy of traditional statistical methods to integrate or interpret increasingly large amounts of multidimensional information relevant to unravelling brain function. Fortunately, the rapidly developing science of machine learning appears to provide tools capable of addressing each of these impediments. Enthusiasm about the potential of machine learning methods to break the current impasse is reflected in the steep increase in the number of scientific publication about the application of machine learning to the study of schizophrenia. Machine learning approaches are, however, poorly understood by schizophrenia researchers and clinicians alike. In this paper, we provide a simple description of the nature and techniques of machine learning and their application to the study of schizophrenia. We then summarize its potential and constraints with illustrations from six studies of machine learning in schizophrenia and address some common misconceptions about machine learning. We suggest some guidelines for researchers, readers, science editors and reviewers of the burgeoning machine learning literature in schizophrenia. In order to realize its enormous promise, we suggest the need for the disciplined application of machine learning methods to the study of schizophrenia with a clear recognition of its capability and challenges accompanied by a concurrent effort to improve machine learning literacy among neuroscientists and mental health professionals.

Digital Innovations for Global Mental Health: Opportunities for Data Science, Task Sharing, and Early Intervention

PURPOSE

Globally, individuals living with mental disorders are more likely to have access to a mobile phone than mental health care. In this commentary, we highlight opportunities for expanding access to and use of digital technologies to advance research and intervention in mental health, with emphasis on the potential impact in lower resource settings.

RECENT FINDINGS

Drawing from empirical evidence, largely from higher income settings, we considered three emerging areas where digital technology will potentially play a prominent role: supporting methods in data science to further our understanding of mental health and inform interventions, task sharing for building workforce capacity by training and supervising non-specialist health workers, and facilitating new opportunities for early intervention for young people in lower resource settings. Challenges were identified related to inequities in access, threats of bias in big data analyses, risks to users, and need for user involvement to support engagement and sustained use of digital interventions.

SUMMARY

For digital technology to achieve its potential to transform the ways we detect, treat, and prevent mental disorders, there is a clear need for continued research involving multiple stakeholders, and rigorous studies showing that these technologies can successfully drive measurable improvements in mental health outcomes.

Artificial Intelligence for Mental Health and Mental Illnesses: an Overview

PURPOSE OF REVIEW

Artificial intelligence (AI) technology holds both great promise to transform mental healthcare and potential pitfalls. This article provides an overview of AI and current applications in healthcare, a review of recent original research on AI specific to mental health, and a discussion of how AI can supplement clinical practice while considering its current limitations, areas needing additional research, and ethical implications regarding AI technology.

RECENT FINDINGS

We reviewed 28 studies of AI and mental health that used electronic health records (EHRs), mood rating scales, brain imaging data, novel monitoring systems (e.g., smartphone, video), and social media platforms to predict, classify, or subgroup mental health illnesses including depression, schizophrenia or other psychiatric illnesses, and suicide ideation and attempts. Collectively, these studies revealed high accuracies and provided excellent examples of AI's potential in mental healthcare, but most should be considered early proof-of-concept works demonstrating the potential of using machine learning (ML) algorithms to address mental health questions, and which types of algorithms yield the best performance. As AI techniques continue to be refined and improved, it will be possible to help mental health practitioners re-define mental illnesses more objectively than currently done in the DSM-5, identify these illnesses at an earlier or prodromal stage when interventions may be more effective, and personalize treatments based on an individual's unique characteristics. However, caution is necessary in order to avoid over-interpreting preliminary results, and more work is required to bridge the gap between AI in mental health research and clinical care.

Mapping the rise of digital mental health technologies: Emerging issues for law and society

The use of digital technologies in mental health initiatives is expanding, leading to calls for clearer legal and regulatory frameworks. However, gaps in knowledge about the scale and nature of change impede efforts to develop responsible public governance in the early stages of what may be the mass uptake of 'digital mental health technologies'. This article maps established and emerging technologies in the mental health context with an eye to locating major socio-legal issues. The paper discusses various types of technology, including those designed for information sharing, communication, clinical decision support, 'digital therapies', patient and/or population monitoring and control, bio-informatics and personalised medicine, and service user health informatics. The discussion is organised around domains of use based on the actors who use the technologies, and those on whom they are used. These actors go beyond mental health service users and practitioners/service providers, and include health and social system or resource managers, data management services, private companies that collect personal data (such as major technology corporations and data brokers), and multiple government agencies and private sector actors across diverse fields of criminal justice, education, and so on. The mapping exercise offers a starting point to better identify cross-cutting legal, ethical and social issues at the convergence of digital technology and contemporary mental health practice.

The risks of risk. Regulating the use of machine learning for psychosis prediction

Recent advances in Machine Learning (ML) have the potential to revolutionise psychosis prediction and psychiatric assessment. This article has two objectives. First, it clarifies which aspects of English Law are relevant in order to regulate the use of ML in clinical research on psychosis prediction. It is argued that its lawful implementation will depend upon the legal requirements regarding the balance between potential harms and benefits, particularly with reference to: (i) any additional risks introduced by the use of ML for data analysis and outcome prediction; and (ii) the inclusion of vulnerable research populations such as minors or incapacitated adults. Second, this article investigates how clinical prediction via ML might affect the practice of risk assessment under mental health legislation, with reference to English Law. It is argued that there is a potential for virtuous applications of clinical prediction in psychiatry. However, reaffirming the distinction between psychosis risk and risk of harm is paramount. Establishing psychosis risk and assessing a person's risk of harm are discrete practices, and so should remain when using artificial intelligence for psychiatric assessment. Evaluating whether clinical prediction via ML might benefit individuals with psychosis will depend on which risk we try to assess and on what we try to predict, whether this is psychosis transition, a psychotic relapse, self-harm and suicidality, or harm to others.

Subtypes in patients with opioid misuse: A prognostic enrichment strategy using electronic health record data in hospitalized patients

BACKGROUND

Approaches are needed to better delineate the continuum of opioid misuse that occurs in hospitalized patients. A prognostic enrichment strategy with latent class analysis (LCA) may facilitate treatment strategies in subtypes of opioid misuse. We aim to identify subtypes of patients with opioid misuse and examine the distinctions between the subtypes by examining patient characteristics, topic models from clinical notes, and clinical outcomes.

METHODS

This was an observational study of inpatient hospitalizations at a tertiary care center between 2007 and 2017. Patients with opioid misuse were identified using an operational definition applied to all inpatient encounters. LCA with eight class-defining variables from the electronic health record (EHR) was applied to identify subtypes in the cohort of patients with opioid misuse. Comparisons between subtypes were made using the following approaches: (1) descriptive statistics on patient characteristics and healthcare utilization using EHR data and census-level data; (2) topic models with natural language processing (NLP) from clinical notes; (3) association with hospital outcomes.

FINDINGS

The analysis cohort was 6,224 (2.7% of all hospitalizations) patient encounters with opioid misuse with a data corpus of 422,147 clinical notes. LCA identified four subtypes with differing patient characteristics, topics from the clinical notes, and hospital outcomes. Class 1 was categorized by high hospital utilization with known opioid-related conditions (36.5%); Class 2 included patients with illicit use, low socioeconomic status, and psychoses (12.8%); Class 3 contained patients with alcohol use disorders with complications (39.2%); and class 4 consisted of those with low hospital utilization and incidental opioid misuse (11.5%). The following hospital outcomes were the highest for each subtype when compared against the other subtypes: readmission for class 1 (13.9% vs. 10.5%, p<0.01); discharge against medical advice for class 2 (12.3% vs. 5.3%, p<0.01); and in-hospital death for classes 3 and 4 (3.2% vs. 1.9%, p<0.01).

CONCLUSIONS

A 4-class latent model was the most parsimonious model that defined clinically interpretable and relevant subtypes for opioid misuse. Distinct subtypes were delineated after examining multiple domains of EHR data and applying methods in artificial intelligence. The approach with LCA and readily available class-defining substance use variables from the EHR may be applied as a prognostic enrichment strategy for targeted interventions.