The promise of machine learning in predicting treatment outcomes in psychiatry

Diagnostic accuracy of large language models in psychiatry

INTRODUCTION

Medical decision-making is crucial for effective treatment, especially in psychiatry where diagnosis often relies on subjective patient reports and a lack of high-specificity symptoms. Artificial intelligence (AI), particularly Large Language Models (LLMs) like GPT, has emerged as a promising tool to enhance diagnostic accuracy in psychiatry. This comparative study explores the diagnostic capabilities of several AI models, including Aya, GPT-3.5, GPT-4, GPT-3.5 clinical assistant (CA), Nemotron, and Nemotron CA, using clinical cases from the DSM-5.

METHODS

We curated 20 clinical cases from the DSM-5 Clinical Cases book, covering a wide range of psychiatric diagnoses. Four advanced AI models (GPT-3.5 Turbo, GPT-4, Aya, Nemotron) were tested using prompts to elicit detailed diagnoses and reasoning. The models' performances were evaluated based on accuracy and quality of reasoning, with additional analysis using the Retrieval Augmented Generation (RAG) methodology for models accessing the DSM-5 text.

RESULTS

The AI models showed varied diagnostic accuracy, with GPT-3.5 and GPT-4 performing notably better than Aya and Nemotron in terms of both accuracy and reasoning quality. While models struggled with specific disorders such as cyclothymic and disruptive mood dysregulation disorders, others excelled, particularly in diagnosing psychotic and bipolar disorders. Statistical analysis highlighted significant differences in accuracy and reasoning, emphasizing the superiority of the GPT models.

DISCUSSION

The application of AI in psychiatry offers potential improvements in diagnostic accuracy. The superior performance of the GPT models can be attributed to their advanced natural language processing capabilities and extensive training on diverse text data, enabling more effective interpretation of psychiatric language. However, models like Aya and Nemotron showed limitations in reasoning, indicating a need for further refinement in their training and application.

CONCLUSION

AI holds significant promise for enhancing psychiatric diagnostics, with certain models demonstrating high potential in interpreting complex clinical descriptions accurately. Future research should focus on expanding the dataset and integrating multimodal data to further enhance the diagnostic capabilities of AI in psychiatry.

Psychosis Prognosis Predictor: A continuous and uncertainty-aware prediction of treatment outcome in first-episode psychosis

INTRODUCTION

Machine learning models have shown promising potential in individual-level outcome prediction for patients with psychosis, but also have several limitations. To address some of these limitations, we present a model that predicts multiple outcomes, based on longitudinal patient data, while integrating prediction uncertainty to facilitate more reliable clinical decision-making.

MATERIAL AND METHODS

We devised a recurrent neural network architecture incorporating long short-term memory (LSTM) units to facilitate outcome prediction by leveraging multimodal baseline variables and clinical data collected at multiple time points. To account for model uncertainty, we employed a novel fuzzy logic approach to integrate the level of uncertainty into individual predictions. We predicted antipsychotic treatment outcomes in 446 first-episode psychosis patients in the OPTiMiSE study, for six different clinical scenarios. The treatment outcome measures assessed at both week 4 and week 10 encompassed symptomatic remission, clinical global remission, and functional remission.

RESULTS

Using only baseline predictors to predict different outcomes at week 4, leave-one-site-out validation AUC ranged from 0.62 to 0.66; performance improved when clinical data from week 1 was added (AUC = 0.66-0.71). For outcome at week 10, using only baseline variables, the models achieved AUC = 0.56-0.64; using data from more time points (weeks 1, 4, and 6) improved the performance to AUC = 0.72-0.74. After incorporating prediction uncertainties and stratifying the model decisions based on model confidence, we could achieve accuracies above 0.8 for ~50% of patients in five out of the six clinical scenarios.

CONCLUSION

We constructed prediction models utilizing a recurrent neural network architecture tailored to clinical scenarios derived from a time series dataset. One crucial aspect we incorporated was the consideration of uncertainty in individual predictions, which enhances the reliability of decision-making based on the model's output. We provided evidence showcasing the significance of leveraging time series data for achieving more accurate treatment outcome prediction in the field of psychiatry.

AI-driven innovations in Alzheimer's disease: Integrating early diagnosis, personalized treatment, and prognostic modelling

Alzheimer's disease (AD) presents a significant challenge in neurodegenerative research and clinical practice due to its complex etiology and progressive nature. The integration of artificial intelligence (AI) into the diagnosis, treatment, and prognostic modelling of AD holds promising potential to transform the landscape of dementia care. This review explores recent advancements in AI applications across various stages of AD management. In early diagnosis, AI-enhanced neuroimaging techniques, including MRI, PET, and CT scans, enable precise detection of AD biomarkers. Machine learning models analyze these images to identify patterns indicative of early cognitive decline. Additionally, AI algorithms are employed to detect genetic and proteomic biomarkers, facilitating early intervention. Cognitive and behavioral assessments have also benefited from AI, with tools that enhance the accuracy of neuropsychological tests and analyze speech and language patterns for early signs of dementia. Personalized treatment strategies have been revolutionized by AI-driven approaches. In drug discovery, virtual screening and drug repurposing, guided by predictive modelling, accelerate the identification of effective treatments. AI also aids in tailoring therapeutic interventions by predicting individual responses to treatments and monitoring patient progress, allowing for dynamic adjustment of care plans. Prognostic modelling, another critical area, utilizes AI to predict disease progression through longitudinal data analysis and risk prediction models. The integration of multi-modal data, combining clinical, genetic, and imaging information, enhances the accuracy of these predictions. Deep learning techniques are particularly effective in fusing diverse data types to uncover new insights into disease mechanisms and progression. Despite these advancements, challenges remain, including ethical considerations, data privacy, and the need for seamless integration of AI tools into clinical workflows. This review underscores the transformative potential of AI in AD management while highlighting areas for future research and development. By leveraging AI, the healthcare community can improve early diagnosis, personalize treatments, and predict disease outcomes more accurately, ultimately enhancing the quality of life for individuals with AD.

Cross-EHR validation of antidepressant response algorithm and links with genetics of psychiatric traits

Objective

Antidepressants are commonly prescribed medications in the United States, however, factors underlying response are poorly understood. Electronic health records (EHRs) provide a cost-effective way to create and test response algorithms on large, longitudinal cohorts. We describe a new antidepressant response algorithm, validation in two independent EHR databases, and genetic associations with antidepressant response.

Method

We deployed the algorithm in EHRs at Vanderbilt University Medical Center (VUMC), the All of Us Research Program, and the Mass General Brigham Healthcare System (MGB) and validated response outcomes with patient health questionnaire (PHQ) scores. In a meta-analysis across all sites, worse antidepressant response associated with higher PHQ-8 scores (beta = 0.20, p-value = 1.09 × 10-18).

Results

We used polygenic scores to investigate the relationship between genetic liability of psychiatric disorders and response to first antidepressant trial across VUMC and MGB. After controlling for depression diagnosis, higher polygenic scores for depression, schizophrenia, bipolar, and cross-disorders associated with poorer response to the first antidepressant trial (depression: p-value = 2.84 × 10-8, OR = 1.07; schizophrenia: p-value = 5.93 × 10-4, OR = 1.05; bipolar: p-value = 1.99 × 10-3, OR = 1.04; cross-disorders: p-value = 1.03 × 10-3, OR = 1.05).

Conclusions

Overall, we demonstrate our antidepressant response algorithm can be deployed across multiple EHR systems to increase sample size of genetic and epidemiologic studies of antidepressant response.

EEG-based Signatures of Schizophrenia, Depression, and Aberrant Aging: A Supervised Machine Learning Investigation

BACKGROUND

Electroencephalography (EEG) is a noninvasive, cost-effective, and robust tool, which directly measures in vivo neuronal mass activity with high temporal resolution. Combined with state-of-the-art machine learning (ML) techniques, EEG recordings could potentially yield in silico biomarkers of severe mental disorders.

HYPOTHESIS

Pathological and physiological aging processes influence the electrophysiological signatures of schizophrenia (SCZ) and major depressive disorder (MDD).

STUDY DESIGN

From a single-center cohort (N = 735, 51.6% male) comprising healthy control individuals (HC, N = 245) and inpatients suffering from SCZ (N = 250) or MDD (N = 240), we acquired resting-state 19 channel-EEG recordings. Using repeated nested cross-validation, support vector machine models were trained to (1) classify patients with SCZ or MDD and HC individuals and (2) predict age in HC individuals. The age model was applied to patient groups to calculate Electrophysiological Age Gap Estimation (EphysAGE) as the difference between predicted and chronological age. The links between EphysAGE, diagnosis, and medication were then further explored.

STUDY RESULTS

The classification models robustly discriminated SCZ from HC (balanced accuracy, BAC = 72.7%, P < .001), MDD from HC (BAC = 67.0%, P < .001), and SCZ from MDD individuals (BAC = 63.2%, P < .001). Notably, central alpha (8-11 Hz) power decrease was the most consistently predictive feature for SCZ and MDD. Higher EphysAGE was associated with an increased likelihood of being misclassified as SCZ in HC and MDD (ρHC = 0.23, P < .001; ρMDD = 0.17, P = .01).

CONCLUSIONS

ML models can extract electrophysiological signatures of MDD and SCZ for potential clinical use. However, the impact of aging processes on diagnostic separability calls for timely application of such models, possibly in early recognition settings.

Predicting anxiety treatment outcome in community mental health services using linked health administrative data

Anxiety disorders is ranked as the most common class of mental illness disorders globally, affecting hundreds of millions of people and significantly impacting daily life. Developing reliable predictive models for anxiety treatment outcomes holds immense potential to help guide the development of personalised care, optimise resource allocation and improve patient outcomes. This research investigates whether community mental health treatment for anxiety disorder is associated with reliable changes in Kessler psychological distress scale (K10) scores and whether pre-treatment K10 scores and past health service interactions can accurately predict reliable change (improvement). The K10 assessment was administered to 46,938 public patients in a community setting within the Western Australia dataset in 2005-2022; of whom 3794 in 4067 episodes of care were reassessed at least twice for anxiety disorders, obsessive-compulsive disorder, or reaction to severe stress and adjustment disorders (ICD-10 codes F40-F43). Reliable change on the K10 was calculated and used with the post-treatment score as the outcome variables. Machine learning models were developed using features from a large health service administrative linked dataset that includes the pre-treatment K10 assessment as well as community mental health episodes of care, emergency department presentations, and inpatient admissions for prediction. The classification model achieved an area under the receiver operating characteristic curve of 0.76 as well as an F1 score, precision and recall of 0.69, and the regression model achieved an R2 of 0.37 with mean absolute error of 5.58 on the test dataset. While the prediction models achieved moderate performance, they also underscore the necessity for regular patient monitoring and the collection of more clinically relevant and contextual patient data to further improve prediction of treatment outcomes.

The challenges of using machine learning models in psychiatric research and clinical practice

To understand the complex nature of heterogeneous psychiatric disorders, scientists and clinicians are required to employ a wide range of clinical, endophenotypic, neuroimaging, genomic, and environmental data to understand the biological mechanisms of psychiatric illness before this knowledge is applied into clinical setting. Machine learning (ML) is an automated process that can detect patterns from large multidimensional datasets and can supersede conventional statistical methods as it can detect both linear and non-linear relationships. Due to this advantage, ML has potential to enhance our understanding, improve diagnosis, prognosis and treatment of psychiatric disorders. The current review provides an in-depth examination of, and offers practical guidance for, the challenges encountered in the application of ML models in psychiatric research and clinical practice. These challenges include the curse of dimensionality, data quality, the 'black box' problem, hyperparameter tuning, external validation, class imbalance, and data representativeness. These challenges are particularly critical in the context of psychiatry as it is expected that researchers will encounter them during the stages of ML model development and deployment. We detail practical solutions and best practices to effectively mitigate the outlined challenges. These recommendations have the potential to improve reliability and interpretability of ML models in psychiatry.

Precision Mental Health and Data-Informed Decision Support in Psychological Therapy: An Example

Outcome measurement including data-informed decision support for therapists in psychological therapy has developed impressively over the past two decades. New technological developments such as computerized data assessment, and feedback tools have facilitated advanced implementation in several seetings. Recent developments try to improve the clinical decision-making process by connecting clinical practice better with empirical data. For example, psychometric data can be used by clinicians to personalize the selection of therapeutic programs, strategies or modules and to monitor a patient's response to therapy in real time. Furthermore, clinical support tools can be used to improve the treatment for patients at risk for a negative outcome. Therefore, measurement-based care can be seen as an important and integral part of clinical competence, practice, and training. This is comparable to many other areas in the healthcare system, where continuous monitoring of health indicators is common in day-to-day clinical practice (e.g., fever, blood pressure). In this paper, we present the basic concepts of a data-informed decision support system for tailoring individual psychological interventions to specific patient needs, and discuss the implications for implementing this form of precision mental health in clinical practice.

Leveraging Single-Case Experimental Designs to Promote Personalized Psychological Treatment: Step-by-Step Implementation Protocol with Stakeholder Involvement of an Outpatient Clinic for Personalized Psychotherapy

Our objective is to implement a single-case experimental design (SCED) infrastructure in combination with experience-sampling methods (ESM) into the standard diagnostic procedure of a German outpatient research and training clinic. Building on the idea of routine outcome monitoring, the SCED infrastructure introduces intensive longitudinal data collection, individual effectiveness measures, and the opportunity for systematic manipulation to push personalization efforts further. It aims to empower psychotherapists and patients to evaluate their own treatment (idiographic perspective) and to enable researchers to analyze open questions of personalized psychotherapy (nomothetic perspective). Organized around the principles of agile research, we plan to develop, implement, and evaluate the SCED infrastructure in six successive studies with continuous stakeholder involvement: In the project development phase, the business model for the SCED infrastructure is developed that describes its vision in consideration of the context (Study 1). Also, the infrastructure's prototype is specified, encompassing the SCED procedure, ESM protocol, and ESM survey (Study 2 and 3). During the optimization phase, feasibility and acceptability are tested and the infrastructure is adapted accordingly (Study 4). The evaluation phase includes a pilot implementation study to assess implementation outcomes (Study 5), followed by actual implementation using a within-institution A-B design (Study 6). The sustainability phase involves continuous monitoring and improvement. We discuss to what extent the generated data could be used to address current questions of personalized psychotherapy research. Anticipated barriers and limitations during the implementation processes are outlined.

Examining the Most Important Risk Factors for Predicting Youth Persistent and Distressing Psychotic-Like Experiences

BACKGROUND

Persistence and distress distinguish more clinically significant psychotic-like experiences (PLEs) from those that are less likely to be associated with impairment and/or need for care. Identifying risk factors that identify clinically relevant PLEs early in development is important for improving our understanding of the etiopathogenesis of these experiences. Machine learning analyses were used to examine the most important baseline factors distinguishing persistent distressing PLEs.

METHODS

Using Adolescent Brain Cognitive Development (ABCD) Study data on PLEs from 3 time points (ages 9-13 years), we created the following groups: individuals with persistent distressing PLEs (n = 305), individuals with transient distressing PLEs (n = 374), and individuals with low-level PLEs demographically matched to either the persistent distressing PLEs group (n = 305) or the transient distressing PLEs group (n = 374). Random forest classification models were trained to distinguish persistent distressing PLEs from low-level PLEs, transient distressing PLEs from low-level PLEs, and persistent distressing PLEs from transient distressing PLEs. Models were trained using identified baseline predictors as input features (i.e., cognitive, neural [cortical thickness, resting-state functional connectivity], developmental milestone delays, internalizing symptoms, adverse childhood experiences).

RESULTS

The model distinguishing persistent distressing PLEs from low-level PLEs showed the highest accuracy (test sample accuracy = 69.33%; 95% CI, 61.29%-76.59%). The most important predictors included internalizing symptoms, adverse childhood experiences, and cognitive functioning. Models for distinguishing persistent PLEs from transient distressing PLEs generally performed poorly.

CONCLUSIONS

Model performance metrics indicated that while most important factors overlapped across models (e.g., internalizing symptoms), adverse childhood experiences were especially important for predicting persistent distressing PLEs. Machine learning analyses proved useful for distinguishing the most clinically relevant group from the least clinically relevant group but showed limited ability to distinguish among clinically relevant groups that differed in PLE persistence.

New horizons in prediction modelling using machine learning in older people's healthcare research

Machine learning (ML) and prediction modelling have become increasingly influential in healthcare, providing critical insights and supporting clinical decisions, particularly in the age of big data. This paper serves as an introductory guide for health researchers and readers interested in prediction modelling and explores how these technologies support clinical decisions, particularly with big data, and covers all aspects of the development, assessment and reporting of a model using ML. The paper starts with the importance of prediction modelling for precision medicine. It outlines different types of prediction and machine learning approaches, including supervised, unsupervised and semi-supervised learning, and provides an overview of popular algorithms for various outcomes and settings. It also introduces key theoretical ML concepts. The importance of data quality, preprocessing and unbiased model performance evaluation is highlighted. Concepts of apparent, internal and external validation will be introduced along with metrics for discrimination and calibration for different types of outcomes. Additionally, the paper addresses model interpretation, fairness and implementation in clinical practice. Finally, the paper provides recommendations for reporting and identifies common pitfalls in prediction modelling and machine learning. The aim of the paper is to help readers understand and critically evaluate research papers that present ML models and to serve as a first guide for developing, assessing and implementing their own.

Challenges and prospects in bridging precision medicine and artificial intelligence in genomic psychiatric treatment

Precision medicine is transforming psychiatric treatment by tailoring personalized healthcare interventions based on clinical, genetic, environmental, and lifestyle factors to optimize medication management. This study investigates how artificial intelligence (AI) and machine learning (ML) can address key challenges in integrating pharmacogenomics (PGx) into psychiatric care. In this integration, AI analyzes vast genomic datasets to identify genetic markers linked to psychiatric conditions. AI-driven models integrating genomic, clinical, and demographic data demonstrated high accuracy in predicting treatment outcomes for major depressive disorder and bipolar disorder. This study also examines the pressing challenges and provides strategic directions for integrating AI and ML in genomic psychiatry, highlighting the importance of ethical considerations and the need for personalized treatment. Effective implementation of AI-driven clinical decision support systems within electronic health records is crucial for translating PGx into routine psychiatric care. Future research should focus on developing enhanced AI-driven predictive models, privacy-preserving data exchange, and robust informatics systems to optimize patient outcomes and advance precision medicine in psychiatry.

Do patients prefer a human doctor, artificial intelligence, or a blend, and is this preference dependent on medical discipline? Empirical evidence and implications for medical practice

Today the doctor-patient relationship typically takes place in a face-to-face setting. However, with the advent of artificial intelligence (AI) systems, two further interaction scenarios are possible: an AI system supports the doctor's decision regarding diagnosis and/or treatment while interacting with the patient, or an AI system could even substitute the doctor and hence a patient interacts with a chatbot (i.e., a machine) alone. Against this background, we report on an online experiment in which we analyzed data from N = 1,183 people. The data was collected in German-speaking countries (Germany, Austria, Switzerland). The participants were asked to imagine they had been suffering from medical conditions of unknown origin for some time and that they were therefore visiting a health center to seek advice from a doctor. We developed descriptions of patient-doctor interactions (referred to as vignettes), thereby manipulating the patient's interaction partner: (i) human doctor, (ii) human doctor with an AI system, and (iii) an AI system only (i.e., chatbot). Furthermore, we manipulated medical discipline: (i) cardiology, (ii) orthopedics, (iii) dermatology, and (iv) psychiatry. Based on this 3 × 4 experimental within-subjects design, our results indicate that people prefer a human doctor, followed by a human doctor with an AI system, and an AI system alone came in last place. Specifically, based on these 12 hypothetical interaction situations, we found a significant main effect of a patient's interaction partner on trust, distrust, perceived privacy invasion, information disclosure, treatment adherence, and satisfaction. Moreover, perceptions of trust, distrust, and privacy invasion predicted information disclosure, treatment adherence, and satisfaction as a function of interaction partner and medical discipline. We found that the situation in psychiatry is different from the other three disciplines. Specifically, the six outcome variables differed strongly between psychiatry and the three other disciplines in the "human doctor with an AI system" condition, while this effect was not that strong in the other conditions (human doctor, chatbot). These findings have important implications for the use of AI in medical care and in the interaction between patients and their doctors.

Towards full recovery with lurasidone: effective doses in the treatment of agitation, affective, positive, and cognitive symptoms in schizophrenia and of dual psychosis

The management of schizophrenia necessitates a comprehensive treatment paradigm that considers individual patient nuances and the efficacy of lurasidone in addressing schizophrenia symptoms, particularly at elevated dosages. Numerous randomized trials have affirmed the efficacy of lurasidone across various dimensions of schizophrenia, demonstrating marked enhancements in positive, negative and cognitive symptoms compared to a placebo. In addition, lurasidone exhibits potential in ameliorating agitation amongst acutely ill patients, showcasing greater efficacy at higher doses. However, despite the favourable outcomes observed with higher lurasidone doses, routine clinical practice often opts for lower doses, potentially limiting its maximal therapeutic impact. Furthermore, lurasidone also shows efficacy in reducing post-psychotic depression in dual psychosis. Moreover, practical insights into lurasidone usage encompass swift dose escalation within a 1-5-day span and recommended combination strategies with other medications such as benzodiazepines for insomnia or agitation, beta-blockers for akathisia, and antihistamines or antimuscarinic drugs for patients transitioning rapidly from antipsychotics with substantial antihistamine and/or anticholinergic effects. Finally, a series of clinical cases is presented, highlighting benefits of lurasidone in terms of cognitive function, functional recovery and other therapeutic aspects for the management of schizophrenia.

Machine Learning Assists in the Design and Application of Microneedles

Microneedles (MNs), characterized by their micron-sized sharp tips, can painlessly penetrate the skin and have shown significant potential in disease treatment and biosensing. With the development of artificial intelligence (AI), the design and application of MNs have experienced substantial innovation aided by machine learning (ML). This review begins with a brief introduction to the concept of ML and its current stage of development. Subsequently, the design principles and fabrication methods of MNs are explored, demonstrating the critical role of ML in optimizing their design and preparation. Integration between ML and the applications of MNs in therapy and sensing were further discussed. Finally, we outline the challenges and prospects of machine learning-assisted MN technology, aiming to advance its practical application and development in the field of smart diagnosis and treatment.

Predicting treatment resistance in schizophrenia patients: Machine learning highlights the role of early pathophysiologic features

Detecting patients with a high-risk profile for treatment-resistant schizophrenia (TRS) can be beneficial for implementing individually adapted therapeutic strategies and better understanding the TRS etiology. The aim of this study was to explore, with machine learning methods, the impact of demographic and clinical patient characteristics on TRS prediction, for already established risk factors and unexplored ones. This was a retrospective study of 500 patients admitted during 2020 to the University Hospital Group for Paris Psychiatry. We hypothesized potential TRS risk factors. The selected features were coded into structured variables in a new dataset, by processing patients discharge summaries and medical narratives with natural-language processing methods. We compared three machine learning models (XGBoost, logistic elastic net regression, logistic regression without regularization) for predicting TRS outcome. We analysed feature impact on the models, suggesting the following factors as markers of a high-risk TRS profile: early age at first contact with psychiatry, antipsychotic treatment interruptions due to non-adherence, absence of positive symptoms at baseline, educational problems and adolescence mental disorders in the personal psychiatric history. Specifically, we found a significant association with TRS outcome for age at first contact with psychiatry and medication non-adherence. Our findings on TRS risk factors are consistent with the review of the literature and suggest potential in using early pathophysiologic features for TRS prediction. Results were encouraging with the use of natural-langage processing techniques to leverage raw data provided by discharge summaries, combined with machine leaning models. These findings are a promising step for helping clinicians adapt their guidelines to early detection of TRS.

Development of a harmonized sociodemographic and clinical questionnaire for mental health research: A Delphi-method-based consensus recommendation

OBJECTIVE

Harmonized tools are essential for reliable data sharing and accurate identification of relevant factors in mental health research. The primary objective of this study was to create a harmonized questionnaire to collect demographic, clinical and behavioral data in diverse clinical trials in adult psychiatry.

METHODS

We conducted a literature review and examined 24 questionnaires used in previously published randomized controlled trials in psychiatry, identifying a total of 27 domains previously explored. Using a Delphi-method process, a task force team comprising experts in psychiatry, epidemiology and statistics selected 15 essential domains for inclusion in the final questionnaire.

RESULTS

The final selection resulted in a concise set of 22 questions. These questions cover factors such as age, sex, gender, ancestry, education, living arrangement, employment status, home location, relationship status, and history of medical and mental illness. Behavioral factors like physical activity, diet, smoking, alcohol and illicit drug use were also included, along with one question addressing family history of mental illness. Income was excluded due to high confounding and redundancy, while language was included as a measure of migration status.

CONCLUSION

The recommendation and adoption of this harmonized tool for the assessment of demographic, clinical and behavioral data in mental health research can enhance data consistency and enable comparability across clinical trials.

Lack of evidence for predictive utility from resting state fMRI data for individual exposure-based cognitive behavioral therapy outcomes: A machine learning study in two large multi-site samples in anxiety disorders

Data-based predictions of individual Cognitive Behavioral Therapy (CBT) treatment response are a fundamental step towards precision medicine. Past studies demonstrated only moderate prediction accuracy (i.e. ability to discriminate between responders and non-responders of a given treatment) when using clinical routine data such as demographic and questionnaire data, while neuroimaging data achieved superior prediction accuracy. However, these studies may be considerably biased due to very limited sample sizes and bias-prone methodology. Adequately powered and cross-validated samples are a prerequisite to evaluate predictive performance and to identify the most promising predictors. We therefore analyzed resting state functional magnet resonance imaging (rs-fMRI) data from two large clinical trials to test whether functional neuroimaging data continues to provide good prediction accuracy in much larger samples. Data came from two distinct German multicenter studies on exposure-based CBT for anxiety disorders, the Protect-AD and SpiderVR studies. We separately and independently preprocessed baseline rs-fMRI data from n = 220 patients (Protect-AD) and n = 190 patients (SpiderVR) and extracted a variety of features, including ROI-to-ROI and edge-functional connectivity, sliding-windows, and graph measures. Including these features in sophisticated machine learning pipelines, we found that predictions of individual outcomes never significantly differed from chance level, even when conducting a range of exploratory post-hoc analyses. Moreover, resting state data never provided prediction accuracy beyond the sociodemographic and clinical data. The analyses were independent of each other in terms of selecting methods to process resting state data for prediction input as well as in the used parameters of the machine learning pipelines, corroborating the external validity of the results. These similar findings in two independent studies, analyzed separately, urge caution regarding the interpretation of promising prediction results based on neuroimaging data from small samples and emphasizes that some of the prediction accuracies from previous studies may result from overestimation due to homogeneous data and weak cross-validation schemes. The promise of resting-state neuroimaging data to play an important role in the prediction of CBT treatment outcomes in patients with anxiety disorders remains yet to be delivered.

Improving Mental Health Outcomes in Patients with Major Depressive Disorder in the Gulf States: A Review of the Role of Electronic Enablers in Monitoring Residual Symptoms

Up to 75% of individuals with major depressive disorder (MDD) may have residual symptoms such as amotivation or anhedonia, which prevent full functional recovery and are associated with relapse. Globally and in the Gulf region, primary care physicians (PCPs) have an important role in alleviating stigma and in identifying and monitoring the residual symptoms of depression, as PCPs are the preliminary interface between patients and specialists in the collaborative care model. Therefore, mental healthcare upskilling programmes for PCPs are needed, as are basic instruments to evaluate residual symptoms swiftly and accurately in primary care. Currently, few if any electronic enablers have been designed to specifically monitor residual symptoms in patients with MDD. The objectives of this review are to highlight how accurate evaluation of residual symptoms with an easy-to-use electronic enabler in primary care may improve functional recovery and overall mental health outcomes, and how such an enabler may guide pharmacotherapy selection and positively impact the patient journey. Here, we show the potential advantages of electronic enablers in primary care, which include the possibility for a deeper "dive" into the patient journey and facilitation of treatment optimisation. At the policy and practice levels, electronic enablers endorsed by government agencies and local psychiatric associations may receive greater PCP attention and backing, improve patient involvement in shared clinical decision-making, and help to reduce the general stigma around mental health disorders. In the Gulf region, an easy-to-use electronic enabler in primary care, incorporating aspects of the Hamilton Depression Rating Scale to monitor amotivation, and aspects of the Montgomery-Åsberg Depression Rating Scale to monitor anhedonia, could markedly improve the patient journey from residual symptoms through to full functional recovery in individuals with MDD.

Factors of acute respiratory infection among under-five children across sub-Saharan African countries using machine learning approaches

Symptoms of Acute Respiratory infections (ARIs) among under-five children are a global health challenge. We aimed to train and evaluate ten machine learning (ML) classification approaches in predicting symptoms of ARIs reported by mothers among children younger than 5 years in sub-Saharan African (sSA) countries. We used the most recent (2012-2022) nationally representative Demographic and Health Surveys data of 33 sSA countries. The air pollution covariates such as global annual surface particulate matter (PM 2.5) and the nitrogen dioxide available in the form of raster images were obtained from the National Aeronautics and Space Administration (NASA). The MLA was used for predicting the symptoms of ARIs among under-five children. We randomly split the dataset into two, 80% was used to train the model, and the remaining 20% was used to test the trained model. Model performance was evaluated using sensitivity, specificity, accuracy, and the area under the receiver operating characteristic curve. A total of 327,507 under-five children were included in the study. About 7.10, 4.19, 20.61, and 21.02% of children reported symptoms of ARI, Severe ARI, cough, and fever in the 2 weeks preceding the survey years respectively. The prevalence of ARI was highest in Mozambique (15.3%), Uganda (15.05%), Togo (14.27%), and Namibia (13.65%,), whereas Uganda (40.10%), Burundi (38.18%), Zimbabwe (36.95%), and Namibia (31.2%) had the highest prevalence of cough. The results of the random forest plot revealed that spatial locations (longitude, latitude), particulate matter, land surface temperature, nitrogen dioxide, and the number of cattle in the houses are the most important features in predicting the diagnosis of symptoms of ARIs among under-five children in sSA. The RF algorithm was selected as the best ML model (AUC = 0.77, Accuracy = 0.72) to predict the symptoms of ARIs among children under five. The MLA performed well in predicting the symptoms of ARIs and associated predictors among under-five children across the sSA countries. Random forest MLA was identified as the best classifier to be employed for the prediction of the symptoms of ARI among under-five children.

Electrophysiological Correlates of Reward Anticipation in Subjects with Schizophrenia: An ERP Microstate Study

The current study aimed to investigate alterations of event-related potentials (ERPs) microstate during reward anticipation in subjects with schizophrenia (SCZ), and their association with hedonic experience and negative symptoms. EEG data were recorded in thirty SCZ and twenty-three healthy controls (HC) during the monetary incentive delay task in which reward, loss and neutral cues were presented. Microstate analysis and standardized low-resolution electromagnetic tomography (sLORETA) were applied to EEG data. Furthermore, analyses correlating a topographic index (the ERPs score), calculated to quantify brain activation in relationship to the microstate maps, and scales assessing hedonic experience and negative symptoms were performed. Alterations in the first (125.0-187.5 ms) and second (261.7-414.1 ms) anticipatory cue-related microstate classes were observed. In SCZ, reward cues were associated to shorter duration and earlier offset of the first microstate class as compared to the neutral condition. In the second microstate class, the area under the curve was smaller for both reward and loss anticipation cues in SCZ as compared to HC. Furthermore, significant correlations between ERPs scores and the anticipation of pleasure scores were detected, while no significant association was found with negative symptoms. sLORETA analysis showed that hypo-activation of the cingulate cortex, insula, orbitofrontal and parietal cortex was detected in SCZ as compared to HC. Abnormalities in ERPs could be traced already during the early stages of reward processing and were associated with the anticipation of pleasure, suggesting that these dysfunctions might impair effective evaluation of incoming pleasant experiences. Negative symptoms and anhedonia are partially independent results.

Predicting Outcome in Clear Aligner Treatment: A Machine Learning Analysis

Background/Objectives: Machine learning (ML) models predicting the risk of refinement (i.e., a subsequent course of treatment being necessary) in clear aligner therapy (CAT) were developed and evaluated. Methods: An anonymized sample of 9942 CAT patients (70.6% females, 29.4% males, age range 18-64 years, median 30.5 years), as provided by DrSmile, a large European CAT provider based in Berlin, Germany, was used. Three different ML methods were employed: (1) logistic regression with L1 regularization, (2) extreme gradient boosting (XGBoost), and (3) support vector classification with a radial basis function kernel. In total, 74 factors were selected as predictors for these methods and are consistent with clinical reasoning. Results: On a held-out test set with a true-positive rate of 0.58, the logistic regression model has an area under the ROC curve (AUC) of 0.67, an average precision (AP) of 0.73, and Brier loss of 0.22; the XGBoost model has an AUC of 0.67, an AP of 0.74, and Brier loss of 0.22; and the support vector model has a recall of 0.61 and a precision of 0.64. The logistic regression and XGBoost models identify predictors influencing refinement risk, including patient compliance, interproximal enamel reduction (IPR) and certain planned tooth movements, for example, lingual translation of maxillary incisors being associated with the lowest risk of refinement and rotation of mandibular incisors with the highest risk. Conclusions: These findings suggest moderate, well-calibrated predictive accuracy with both regularized logistic regression and XGBoost and underscore the influence the identified factors have on the risk of refinement in CAT, emphasizing their importance in the careful planning of orthodontic treatment and the potential for shorter treatment times, less patient discomfort, and fewer clinic visits. Identification of at-risk individuals could support tailored clinical decision-making and enable targeted interventions.

A review of diffusion MRI in mood disorders: mechanisms and predictors of treatment response

By measuring the molecular diffusion of water molecules in brain tissue, diffusion MRI (dMRI) provides unique insight into the microstructure and structural connections of the brain in living subjects. Since its inception, the application of dMRI in clinical research has expanded our understanding of the possible biological bases of psychiatric disorders and successful responses to different therapeutic interventions. Here, we review the past decade of diffusion imaging-based investigations with a specific focus on studies examining the mechanisms and predictors of therapeutic response in people with mood disorders. We present a brief overview of the general application of dMRI and key methodological developments in the field that afford increasingly detailed information concerning the macro- and micro-structural properties and connectivity patterns of white matter (WM) pathways and their perturbation over time in patients followed prospectively while undergoing treatment. This is followed by a more in-depth summary of particular studies using dMRI approaches to examine mechanisms and predictors of clinical outcomes in patients with unipolar or bipolar depression receiving pharmacological, neurostimulation, or behavioral treatments. Limitations associated with dMRI research in general and with treatment studies in mood disorders specifically are discussed, as are directions for future research. Despite limitations and the associated discrepancies in findings across individual studies, evolving research strongly indicates that the field is on the precipice of identifying and validating dMRI biomarkers that could lead to more successful personalized treatment approaches and could serve as targets for evaluating the neural effects of novel treatments.

A machine learning case study to predict rare clinical event of interest: imbalanced data, interpretability, and practical considerations

Accurate prediction of a rare and clinically important event following study treatment has been crucial in drug development. For instance, the rarity of an adverse event is often commensurate with the seriousness of medical consequences, and delayed detection of the rare adverse event can pose significant or even life-threatening health risks to patients. In this machine learning case study, we demonstrate with an example originated from a real clinical trial setting how to define and solve the rare clinical event prediction problem using machine learning in pharmaceutical industry. The unique contributions of this work include the proposal of a six-step investigation framework that facilitates the communication with non-technical stakeholders and the interpretation of the model performance in terms of practical consequences in the context of patient screenings for conducting a future clinical trial. In terms of machine learning methodology, for data splitting into the training and test sets, we adapt the rare-event stratified split approach (from scikit-learn) to further account for group splitting for multiple records of a patient simultaneously. To handle imbalanced data due to rare events in model training, the cost-sensitive learning approach is employed to give more weights to the minor class and the metrics precision together with recall are used to capture prediction performance instead of the raw accuracy rate. Finally, we demonstrate how to apply the state-of-the-art SHAP values to identify important risk factors to improve model interpretability.

Dynamic learning of individual-level suicidal ideation trajectories to enhance mental health care

There has recently been an increase in ongoing patient-report routine outcome monitoring for individuals within clinical care, which has corresponded to increased longitudinal information about an individual. However, many models that are aimed at clinical practice have difficulty fully incorporating this information. This is in part due to the difficulty in dealing with the irregularly time-spaced observations that are common in clinical data. Consequently, we built individual-level continuous-time trajectory models of suicidal ideation for a clinical population (N = 585) with data collected via a digital platform. We demonstrate how such models predict an individual's level and variability of future suicide ideation, with implications for the frequency that individuals may need to be observed. These individual-level predictions provide a more personalised understanding than other predictive methods and have implications for enhanced measurement-based care.

Predicting treatment response using machine learning: A registered report

OBJECTIVE

Previous research on psychotherapy treatment response has mainly focused on outpatients or clinical trial data which may have low ecological validity regarding naturalistic inpatient samples. To reduce treatment failures by proactively screening for patients at risk of low treatment response, gain more knowledge about risk factors and to evaluate treatments, accurate insights about predictors of treatment response in naturalistic inpatient samples are needed.

METHODS

We compared the performance of different machine learning algorithms in predicting treatment response, operationalized as a substantial reduction in symptom severity as expressed in the Patient Health Questionnaire Anxiety and Depression Scale. To achieve this goal, we used different sets of variables-(a) demographics, (b) physical indicators, (c) psychological indicators and (d) treatment-related variables-in a naturalistic inpatient sample (N = 723) to specify their joint and unique contribution to treatment success.

RESULTS

There was a strong link between symptom severity at baseline and post-treatment (R2 = .32). When using all available variables, both machine learning algorithms outperformed the linear regressions and led to an increment in predictive performance of R2 = .12. Treatment-related variables were the most predictive, followed psychological indicators. Physical indicators and demographics were negligible.

CONCLUSIONS

Treatment response in naturalistic inpatient settings can be predicted to a considerable degree by using baseline indicators. Regularization via machine learning algorithms leads to higher predictive performances as opposed to including nonlinear and interaction effects. Heterogenous aspects of mental health have incremental predictive value and should be considered as prognostic markers when modelling treatment processes.

Applications of artificial intelligence-machine learning for detection of stress: a critical overview

Psychological distress is a major contributor to human physiology and pathophysiology, and it has been linked to several conditions, such as auto-immune diseases, metabolic syndrome, sleep disorders, and suicidal thoughts and inclination. Therefore, early detection and management of chronic stress is crucial for the prevention of several diseases. Artificial intelligence (AI) and Machine Learning (ML) have promoted a paradigm shift in several areas of biomedicine including diagnosis, monitoring, and prognosis of disease. Here, our review aims to present some of the AI and ML applications for solving biomedical issues related to psychological stress. We provide several lines of evidence from previous studies highlighting that AI and ML have been able to predict stress and detect the brain normal states vs. abnormal states (notably, in post-traumatic stress disorder (PTSD)) with accuracy around 90%. Of note, AI/ML-driven technology applied to identify ubiquitously present stress exposure may not reach its full potential, unless future analytics focus on detecting prolonged distress through such technology instead of merely assessing stress exposure. Moving forward, we propose that a new subcategory of AI methods called Swarm Intelligence (SI) can be used towards detecting stress and PTSD. SI involves ensemble learning techniques to efficiently solve a complex problem, such as stress detection, and it offers particular strength in clinical settings, such as privacy preservation. We posit that AI and ML approaches will be beneficial for the medical and patient community when applied to predict and assess stress levels. Last, we encourage additional research to bring AI and ML into the standard clinical practice for diagnostics in the not-too-distant future.

Precision psychiatry: predicting predictability

Precision psychiatry is an emerging field that aims to provide individualized approaches to mental health care. An important strategy to achieve this precision is to reduce uncertainty about prognosis and treatment response. Multivariate analysis and machine learning are used to create outcome prediction models based on clinical data such as demographics, symptom assessments, genetic information, and brain imaging. While much emphasis has been placed on technical innovation, the complex and varied nature of mental health presents significant challenges to the successful implementation of these models. From this perspective, I review ten challenges in the field of precision psychiatry, including the need for studies on real-world populations and realistic clinical outcome definitions, and consideration of treatment-related factors such as placebo effects and non-adherence to prescriptions. Fairness, prospective validation in comparison to current practice and implementation studies of prediction models are other key issues that are currently understudied. A shift is proposed from retrospective studies based on linear and static concepts of disease towards prospective research that considers the importance of contextual factors and the dynamic and complex nature of mental health.

Enhancing psychiatric rehabilitation outcomes through a multimodal multitask learning model based on BERT and TabNet: An approach for personalized treatment and improved decision-making

Evaluating the rehabilitation status of individuals with serious mental illnesses (SMI) necessitates a comprehensive analysis of multimodal data, including unstructured text records and structured diagnostic data. However, progress in the effective assessment of rehabilitation status remains limited. Our study develops a deep learning model integrating Bidirectional Encoder Representations from Transformers (BERT) and TabNet through a late fusion strategy to enhance rehabilitation prediction, including referral risk, dangerous behaviors, self-awareness, and medication adherence, in patients with SMI. BERT processes unstructured textual data, such as doctor's notes, whereas TabNet manages structured diagnostic information. The model's interpretability function serves to assist healthcare professionals in understanding the model's predictive decisions, improving patient care. Our model exhibited excellent predictive performance for all four tasks, with an accuracy exceeding 0.78 and an area under the curve of 0.70. In addition, a series of tests proved the model's robustness, fairness, and interpretability. This study combines multimodal and multitask learning strategies into a model and applies it to rehabilitation assessment tasks, offering a promising new tool that can be seamlessly integrated with the clinical workflow to support the provision of optimized patient care.

Select or adjust? How information from early treatment stages boosts the prediction of non-response in internet-based depression treatment

BACKGROUND

Internet-based interventions produce comparable effectiveness rates as face-to-face therapy in treating depression. Still, more than half of patients do not respond to treatment. Machine learning (ML) methods could help to overcome these low response rates by predicting therapy outcomes on an individual level and tailoring treatment accordingly. Few studies implemented ML algorithms in internet-based depression treatment using baseline self-report data, but differing results hinder inferences on clinical practicability. This work compares algorithms using features gathered at baseline or early in treatment in their capability to predict non-response to a 6-week online program targeting depression.

METHODS

Our training and test sample encompassed 1270 and 318 individuals, respectively. We trained random forest algorithms on self-report and process features gathered at baseline and after 2 weeks of treatment. Non-responders were defined as participants not fulfilling the criteria for reliable and clinically significant change on PHQ-9 post-treatment. Our benchmark models were logistic regressions trained on baseline PHQ-9 sum or PHQ-9 early change, using 100 iterations of randomly sampled 80/20 train-test-splits.

RESULTS

Best performances were reached by our models involving early treatment characteristics (recall: 0.75-0.76; AUC: 0.71-0.77). Therapeutic alliance and early symptom change constituted the most important predictors. Models trained on baseline data were not significantly better than our benchmark.

CONCLUSIONS

Fair accuracies were only attainable by involving information from early treatment stages. In-treatment adaptation, instead of a priori selection, might constitute a more feasible approach for improving response when relying on easily accessible self-report features. Implementation trials are needed to determine clinical usefulness.

Prediction of treatment response in major depressive disorder using a hybrid of convolutional recurrent deep neural networks and effective connectivity based on EEG signal

In this study, we have developed a novel method based on deep learning and brain effective connectivity to classify responders and non-responders to selective serotonin reuptake inhibitors (SSRIs) antidepressants in major depressive disorder (MDD) patients prior to the treatment using EEG signal. The effective connectivity of 30 MDD patients was determined by analyzing their pretreatment EEG signals, which were then concatenated into delta, theta, alpha, and beta bands and transformed into images. Using these images, we then fine tuned a hybrid Convolutional Neural Network that is enhanced with bidirectional Long Short-Term Memory cells based on transfer learning. The Inception-v3, ResNet18, DenseNet121, and EfficientNet-B0 models are implemented as base models. Finally, the models are followed by BiLSTM and dense layers in order to classify responders and non-responders to SSRI treatment. Results showed that the EfficiencyNet-B0 has the highest accuracy of 98.33, followed by DensNet121, ResNet18 and Inception-v3. Therefore, a new method was proposed in this study that uses deep learning models to extract both spatial and temporal features automatically, which will improve classification results. The proposed method provides accurate identification of MDD patients who are responding, thereby reducing the cost of medical facilities and patient care.

Assessment of symptom severity in psychotic disorder patients based on heart rate variability and accelerometer mobility data

BACKGROUND

Advancement in mental health care requires easily accessible, efficient diagnostic and treatment assessment tools. Viable biomarkers could enable objectification and automation of the diagnostic and treatment process, currently dependent on a psychiatric interview. Available wearable technology and computational methods make it possible to incorporate heart rate variability (HRV), an indicator of autonomic nervous system (ANS) activity, into potential diagnostic and treatment assessment frameworks as a biomarker of disease severity in mental disorders, including schizophrenia and bipolar disorder (BD).

METHOD

We used a commercially available electrocardiography (ECG) chest strap with a built-in accelerometer, i.e. Polar H10, to record R-R intervals and physical activity of 30 hospitalized schizophrenia or BD patients and 30 control participants through ca. 1.5-2 h time periods. We validated a novel approach to data acquisition based on a flexible, patient-friendly and cost-effective setting. We analyzed the relationship between HRV and the Positive and Negative Syndrome Scale (PANSS) test scores, as well as the HRV and mobility coefficient. We also proposed a method of rest period selection based on R-R intervals and mobility data. The source code for reproducing all experiments is available on GitHub, while the dataset is published on Zenodo.

RESULTS

Mean HRV values were lower in the patient compared to the control group and negatively correlated with the results of the PANSS general subcategory. For the control group, we also discovered the inversely proportional dependency between the mobility coefficient, based on accelerometer data, and HRV. This relationship was less pronounced for the treatment group.

CONCLUSIONS

HRV value itself, as well as the relationship between HRV and mobility, may be promising biomarkers in disease diagnostics. These findings can be used to develop a flexible monitoring system for symptom severity assessment.

Predicting post-treatment symptom severity for adults receiving psychological therapy in routine care for generalised anxiety disorder: a machine learning approach

Approximately half of generalised anxiety disorder (GAD) patients do not recover from first-line treatments, and no validated prediction models exist to inform individuals or clinicians of potential treatment benefits. This study aimed to develop and validate an accurate and explainable prediction model of post-treatment GAD symptom severity. Data from adults receiving treatment for GAD in eight Improving Access to Psychological Therapies (IAPT) services (n=15,859) were separated into training, validation and holdout datasets. Thirteen machine learning algorithms were compared using 10-fold cross-validation, against two simple clinically relevant comparison models. The best-performing model was tested on the holdout dataset and model-specific explainability measures identified the most important predictors. A Bayesian Additive Regression Trees model out-performed all comparison models (MSE=16.54 [95 % CI=15.58; 17.51]; MAE=3.19; R²=0.33, including a single predictor linear regression model: MSE=20.70 [95 % CI=19.58; 21.82]; MAE=3.94; R²=0.14). The five most important predictors were: PHQ-9 anhedonia, GAD-7 annoyance/irritability, restlessness and fear items, then the referral-assessment waiting time. The best-performing model accurately predicted post-treatment GAD symptom severity using only pre-treatment data, outperforming comparison models that approximated clinical judgement and remaining within the GAD-7 error of measurement and minimal clinically important differences. This model could inform treatment decision-making and provide desired information to clinicians and patients receiving treatment for GAD.

Predicting Outcomes of Antidepressant Treatment in Community Practice Settings

OBJECTIVE

The authors examined whether machine-learning models could be used to analyze data from electronic health records (EHRs) to predict patients' responses to antidepressant medications.

METHODS

EHR data from a Washington State health system identified patients ages ≥13 years who started an antidepressant medication in 2016 in a community practice setting and had a baseline Patient Health Questionnaire-9 (PHQ-9) score of ≥10 and at least one PHQ-9 score recorded 14-180 days later. Potential predictors of a response to antidepressants were extracted from the EHR and included demographic characteristics, psychiatric and substance use diagnoses, past psychiatric medication use, mental health service use, and past PHQ-9 scores. Random-forest and penalized regression analyses were used to build models predicting follow-up PHQ-9 score and a favorable treatment response (≥50% improvement in score).

RESULTS

Among 2,469 patients starting antidepressant medication treatment, the mean±SD baseline PHQ-9 score was 17.3±4.5, and the mean lowest follow-up score was 9.2±5.9. Outcome data were available for 72% of the patients. About 48% of the patients had a favorable treatment response. The best-fitting random-forest models yielded a correlation between predicted and observed follow-up scores of 0.38 (95% CI=0.32-0.45) and an area under the receiver operating characteristic curve for a favorable response of 0.57 (95% CI=0.52-0.61). Results were similar for penalized regression models and for models predicting last PHQ-9 score during follow-up.

CONCLUSIONS

Prediction models using EHR data were not accurate enough to inform recommendations for or against starting antidepressant medication. Personalization of depression treatment should instead rely on systematic assessment of early outcomes.

Leveraging Novel Technologies and Artificial Intelligence to Advance Practice-Oriented Research

Mental health services are experiencing notable transformations as innovative technologies and artificial intelligence (AI) are increasingly utilized in a growing number of studies and services.These cutting-edge technologies carry the promise of substantial improvements in the field of mental health. Nevertheless, questions emerge about the alignment of novel technologies and AI systems with human needs, especially in the context of vulnerable populations receiving mental healthcare. The practice-oriented research (POR) model is pivotal in seamlessly integrating these emerging technologies into clinical research and practice. It underscores the importance of tight collaboration between clinicians and researchers, all driven by the central goal of ensuring and elevating client well-being. This paper focuses on how novel technologies can enhance the POR model and highlights its pivotal role in integrating these technologies into clinical research and practice. We discuss two key phases: pre-treatment, and during treatment. For each phase, we describe the challenges, present the major technological innovations, describe recent studies exemplifying technology use, and suggest future directions. Ethical concerns and the importance of aligning humans and technology are also considered, in addition to implications for practice and training.

Patient Perspectives on AI-Driven Predictions of Schizophrenia Relapses: Understanding Concerns and Opportunities for Self-Care and Treatment

Early detection and intervention for relapse is important in the treatment of schizophrenia spectrum disorders. Researchers have developed AI models to predict relapse from patient-contributed data like social media. However, these models face challenges, including misalignment with practice and ethical issues related to transparency, accountability, and potential harm. Furthermore, how patients who have recovered from schizophrenia view these AI models has been underexplored. To address this gap, we first conducted semi-structured interviews with 28 patients and reflexive thematic analysis, which revealed a disconnect between AI predictions and patient experience, and the importance of the social aspect of relapse detection. In response, we developed a prototype that used patients' Facebook data to predict relapse. Feedback from seven patients highlighted the potential for AI to foster collaboration between patients and their support systems, and to encourage self-reflection. Our work provides insights into human-AI interaction and suggests ways to empower people with schizophrenia.

Exploration of the individual and combined effects of predictors of engagement, dropout, and change from digital interventions for recurrent binge eating

OBJECTIVE

Our ability to predict responsiveness to digital interventions for eating disorders has thus far been poor, potentially for three reasons: (1) there has been a narrow set of predictors explored; (2) prediction has mostly focused on symptom change, ignoring other aspects of the user journey (uptake, early engagement); and (3) there is an excessive focus on the unique effects of predictors rather than the combined contributions of a predictor set. We evaluated the univariate and multivariate effects of outcome predictors in the context of a randomized trial (n = 398) of digitally delivered interventions for recurrent binge eating.

METHOD

Thirty baseline variables were selected as predictors, ranging from specific symptoms, to key protective factors, to technological acceptance, and to online treatment attitudes. Outcomes included uptake, early engagement, and remission. Univariate (d) and multivariate (D) standardized mean differences were calculated to estimate the individual and combined effects of predictors, respectively.

RESULTS

At the univariate level, few predictors produced an effect size larger than what is considered small (d > .20) across outcomes. However, our multivariate approach enhanced prediction (Ds = .65 to 1.12), producing accuracy rates greater than chance (63%-71% accuracy). Less than half of the chosen variables proved to be useful in contributing to predictions in multivariate models.

CONCLUSION

Findings suggest that accuracy in outcome prediction from digitally delivered interventions may be better driven by the aggregation of many small effects rather than one or several largely influential predictors. Replication with different data streams (sensor, neuroimaging) would be useful.

PUBLIC SIGNIFICANCE

Our ability to predict who will and will not benefit from digital interventions for eating disorders has been poor. We highlight the viability of a multivariate approach to outcome prediction, whereby prediction may be better driven by the aggregation of many small effects rather than one or a few influential predictors.

Routine Outcome Monitoring and Clinical Feedback in Psychotherapy: Recent Advances and Future Directions

In the past decade, there has been an increase in research related to the routine collection and active use of standardized patient data in psychotherapy. Research has increasingly focused on personalization of care to patients, clinical skills and interventions that modulate treatment outcomes, and implementation strategies, all of which appear to enhance the beneficial effects of ROM and feedback. In this article, we summarize trends and recent advances in the research on this topic and identify several essential directions for the field in the short to medium term. We anticipate a broadening of research from the focus on average effects to greater specificity around what kinds of feedback, provided at what time, to which individuals, in what settings, are most beneficial. We also propose that the field needs to focus on issues of health equity, ensuring that ROM can be a vehicle for increased wellbeing for those who need it most. The complexity of mental healthcare systems means that there may be multiple viable measurement solutions with varying costs and benefits to diverse stakeholders in different treatment contexts, and research is needed to identify the most influential components in each of these contexts.

Multimodal workflows optimally predict response to repetitive transcranial magnetic stimulation in patients with schizophrenia: a multisite machine learning analysis

The response variability to repetitive transcranial magnetic stimulation (rTMS) challenges the effective use of this treatment option in patients with schizophrenia. This variability may be deciphered by leveraging predictive information in structural MRI, clinical, sociodemographic, and genetic data using artificial intelligence. We developed and cross-validated rTMS response prediction models in patients with schizophrenia drawn from the multisite RESIS trial. The models incorporated pre-treatment sMRI, clinical, sociodemographic, and polygenic risk score (PRS) data. Patients were randomly assigned to receive active (N = 45) or sham (N = 47) rTMS treatment. The prediction target was individual response, defined as ≥20% reduction in pre-treatment negative symptom sum scores of the Positive and Negative Syndrome Scale. Our multimodal sequential prediction workflow achieved a balanced accuracy (BAC) of 94% (non-responders: 92%, responders: 95%) in the active-treated group and 50% in the sham-treated group. The clinical, clinical + PRS, and sMRI-based classifiers yielded BACs of 65%, 76%, and 80%, respectively. Apparent sadness, inability to feel, educational attainment PRS, and unemployment were most predictive of non-response in the clinical + PRS model, while grey matter density reductions in the default mode, limbic networks, and the cerebellum were most predictive in the sMRI model. Our sequential modelling approach provided superior predictive performance while minimising the diagnostic burden in the clinical setting. Predictive patterns suggest that rTMS responders may have higher levels of brain grey matter in the default mode and salience networks which increases their likelihood of profiting from plasticity-inducing brain stimulation methods, such as rTMS. The future clinical implementation of our models requires findings to be replicated at the international scale using stratified clinical trial designs.

Potential Applications of Artificial Intelligence (AI) in Managing Polypharmacy in Saudi Arabia: A Narrative Review

Prescribing medications is a fundamental practice in the management of illnesses that necessitates in-depth knowledge of clinical pharmacology. Polypharmacy, or the concurrent use of multiple medications by individuals with complex health conditions, poses significant challenges, including an increased risk of drug interactions and adverse reactions. The Saudi Vision 2030 prioritises enhancing healthcare quality and safety, including addressing polypharmacy. Artificial intelligence (AI) offers promising tools to optimise medication plans, predict adverse drug reactions and ensure drug safety. This review explores AI's potential to revolutionise polypharmacy management in Saudi Arabia, highlighting practical applications, challenges and the path forward for the integration of AI solutions into healthcare practices.

Large language models could change the future of behavioral healthcare: a proposal for responsible development and evaluation

Large language models (LLMs) such as Open AI's GPT-4 (which power ChatGPT) and Google's Gemini, built on artificial intelligence, hold immense potential to support, augment, or even eventually automate psychotherapy. Enthusiasm about such applications is mounting in the field as well as industry. These developments promise to address insufficient mental healthcare system capacity and scale individual access to personalized treatments. However, clinical psychology is an uncommonly high stakes application domain for AI systems, as responsible and evidence-based therapy requires nuanced expertise. This paper provides a roadmap for the ambitious yet responsible application of clinical LLMs in psychotherapy. First, a technical overview of clinical LLMs is presented. Second, the stages of integration of LLMs into psychotherapy are discussed while highlighting parallels to the development of autonomous vehicle technology. Third, potential applications of LLMs in clinical care, training, and research are discussed, highlighting areas of risk given the complex nature of psychotherapy. Fourth, recommendations for the responsible development and evaluation of clinical LLMs are provided, which include centering clinical science, involving robust interdisciplinary collaboration, and attending to issues like assessment, risk detection, transparency, and bias. Lastly, a vision is outlined for how LLMs might enable a new generation of studies of evidence-based interventions at scale, and how these studies may challenge assumptions about psychotherapy.

A deep learning quantification of patient specificity as a predictor of session attendance and treatment response to internet-enabled cognitive behavioural therapy for common mental health disorders

BACKGROUND

Increasing an individual's ability to focus on concrete, specific detail, thus reducing the tendency toward overly broad, decontextualised generalisations about the self and world, is a target within cognitive behavioural therapy (CBT). However, empirical investigation of the impact of within-treatment specificity on treatment outcomes is scarce. We evaluated whether the specificity of patient dialogue predicted a) end-of-treatment symptoms and b) session completion for CBT for common mental health issues.

METHODS

This preregistered (https://osf.io/agr4t) study trained a deep learning model to score the specificity of patient dialogue in transcripts from 353,614 internet-enabled CBT sessions for common mental health disorders, delivered on behalf of UK NHS services. Data were from obtained from 65,030 participants (n = 47,308 female, n = 241 unstated) aged 18-94 years (M = 34.69, SD = 12.35). Depressive disorders were the most common (39.1 %) primary diagnosis. Primary outcome was end-of-treatment score on the Patient Health Questionnaire-9 (PHQ-9). Secondary outcome was number of sessions attended.

RESULTS

Linear mixed-effects models demonstrated that increased patient specificity significantly predicted lower post-treatment symptoms on the PHQ-9, although the size and direction of the effect varied depending on the type of therapeutic activity being completed. Effect sizes were consistently small. Higher patient specificity was associated with completing a greater number of sessions.

LIMITATIONS

We are unable to infer causation from our data.

CONCLUSIONS

Although effect sizes were small, an effect of specificity was observed across common mental health disorders. Further studies are needed to explore whether encouraging patient specificity during CBT may provide an enhancement of treatment attendance and treatment effects.

Trajectories of remitted psychotic depression: identification of predictors of worsening by machine learning

BACKGROUND

Remitted psychotic depression (MDDPsy) has heterogeneity of outcome. The study's aims were to identify subgroups of persons with remitted MDDPsy with distinct trajectories of depression severity during continuation treatment and to detect predictors of membership to the worsening trajectory.

METHOD

One hundred and twenty-six persons aged 18-85 years participated in a 36-week randomized placebo-controlled trial (RCT) that examined the clinical effects of continuing olanzapine once an episode of MDDPsy had remitted with sertraline plus olanzapine. Latent class mixed modeling was used to identify subgroups of participants with distinct trajectories of depression severity during the RCT. Machine learning was used to predict membership to the trajectories based on participant pre-trajectory characteristics.

RESULTS

Seventy-one (56.3%) participants belonged to a subgroup with a stable trajectory of depression scores and 55 (43.7%) belonged to a subgroup with a worsening trajectory. A random forest model with high prediction accuracy (AUC of 0.812) found that the strongest predictors of membership to the worsening subgroup were residual depression symptoms at onset of remission, followed by anxiety score at RCT baseline and age of onset of the first lifetime depressive episode. In a logistic regression model that examined depression score at onset of remission as the only predictor variable, the AUC (0.778) was close to that of the machine learning model.

CONCLUSIONS

Residual depression at onset of remission has high accuracy in predicting membership to worsening outcome of remitted MDDPsy. Research is needed to determine how best to optimize the outcome of psychotic MDDPsy with residual symptoms.

Application of machine learning methods for predicting under-five mortality: analysis of Nigerian demographic health survey 2018 dataset

BACKGROUND

Under-five mortality remains a significant public health issue in developing countries. This study aimed to assess the effectiveness of various machine learning algorithms in predicting under-five mortality in Nigeria and identify the most relevant predictors.

METHODS

The study used nationally representative data from the 2018 Nigeria Demographic and Health Survey. The study evaluated the performance of the machine learning models such as the artificial neural network, k-nearest neighbourhood, Support Vector Machine, Naïve Bayes, Random Forest, and Logistic Regression using the true positive rate, false positive rate, accuracy, precision, F-measure, Matthew's correlation coefficient, and the Area Under the Receiver Operating Characteristics.

RESULTS

The study found that machine learning models can accurately predict under-five mortality, with the Random Forest and Artificial Neural Network algorithms emerging as the best models, both achieving an accuracy of 89.47% and an AUROC of 96%. The results show that under-five mortality rates vary significantly across different characteristics, with wealth index, maternal education, antenatal visits, place of delivery, employment status of the woman, number of children ever born, and region found to be the top determinants of under-five mortality in Nigeria.

CONCLUSIONS

The findings suggest that machine learning models can be useful in predicting U5M in Nigeria with high accuracy. The study emphasizes the importance of addressing social, economic, and demographic disparities among the population in Nigeria. The study's findings can inform policymakers and health workers about developing targeted interventions to reduce under-five mortality in Nigeria.

Prediction of suicidal ideation with associated risk factors among university students in the southern part of Bangladesh: Machine learning approach

BACKGROUND

The prevalence of suicidal ideation has become an urgent issue, particularly among adolescents. The primary objective of this research is to determine the prevalence of suicidal ideation among students in the southern region of Bangladesh and to predict this phenomenon using machine learning (ML) models.

METHODS

The data collection process involved using a simple random sampling technique to gather information from university students located in the southern region of Bangladesh during the period spreading from April 2022 to June 2022. Upon accounting for missing values and non-response rates, the ultimate sample size was determined to be 584, with 51.5 % of participants identifying as male and 48.5 % female.

RESULTS

A significant proportion of students, precisely 19.9 %, reported experiencing suicidal ideation. Most participants were female (77 %) and unmarried (78 %). Within the machine learning (ML) framework, KNN exhibited the highest accuracy score of 91.45 %. In addition, the Random Forest (RF), and Categorical Boosting (CatBoost) algorithms exhibited comparable levels of accuracy, achieving scores of 90.60 and 90.59 respectively.

LIMITATIONS

Using a cross-sectional design in research limits the ability to establish causal relationships.

CONCLUSION

Mental health practitioners can employ the KNN model alongside patients' medical histories to detect those who may be at a higher risk of attempting suicide. This approach enables healthcare professionals to take appropriate measures, such as counselling, encouraging regular sleep patterns, and addressing depression and anxiety, to prevent suicide attempts.

Beyond Discrimination: Generative AI Applications and Ethical Challenges in Forensic Psychiatry

The advent and growing popularity of generative artificial intelligence (GenAI) holds the potential to revolutionise AI applications in forensic psychiatry and criminal justice, which traditionally relied on discriminative AI algorithms. Generative AI models mark a significant shift from the previously prevailing paradigm through their ability to generate seemingly new realistic data and analyse and integrate a vast amount of unstructured content from different data formats. This potential extends beyond reshaping conventional practices, like risk assessment, diagnostic support, and treatment and rehabilitation plans, to creating new opportunities in previously underexplored areas, such as training and education. This paper examines the transformative impact of generative artificial intelligence on AI applications in forensic psychiatry and criminal justice. First, it introduces generative AI and its prevalent models. Following this, it reviews the current applications of discriminative AI in forensic psychiatry. Subsequently, it presents a thorough exploration of the potential of generative AI to transform established practices and introduce novel applications through multimodal generative models, data generation and data augmentation. Finally, it provides a comprehensive overview of ethical and legal issues associated with deploying generative AI models, focusing on their impact on individuals as well as their broader societal implications. In conclusion, this paper aims to contribute to the ongoing discourse concerning the dynamic challenges of generative AI applications in forensic contexts, highlighting potential opportunities, risks, and challenges. It advocates for interdisciplinary collaboration and emphasises the necessity for thorough, responsible evaluations of generative AI models before widespread adoption into domains where decisions with substantial life-altering consequences are routinely made.

Use of glucagon-like peptide-1 receptor agonists in eating disorder populations

Glucagon-like peptide-1 receptor agonists (GLP-1As) are being used as approved or off-label treatments for weight loss. As such, there has been increasing concern about the potential for GLP-1As to impact eating disorder (ED) symptomatology. This article seeks to (1) review the current state of knowledge regarding GLP-1As and ED symptomatology; (2) provide recommendations for future research; and (3) guide ED clinicians in how to discuss GLP-1As in clinical practice. Although evidence is limited, it is possible that GLP-1As could exacerbate, or contribute to the development of, ED pathology and negatively impact ED treatment. Preliminary research on the use of GLP-1As to treat binge eating has been conducted; however, studies have design limitations and additional research is needed. Therefore, at the current time there is not sufficient evidence to support the use of GLP-1s to treat ED symptoms. In summary, more research is required before negative or positive conclusions can be drawn about the impact of GLP-1As on EDs psychopathology. Herein, we provide specific recommendations for future research and a guide to help clinicians navigate discussions with their clients about GLP-1As. A client handout is also provided. PUBLIC SIGNIFICANCE: Despite glucagon-like peptide-1 receptor agonists (GLP-1As; e.g., semaglutide) increasingly being the topic of clinical and public discourse, little is known about their potential impact on ED symptoms. It is possible that GLP-1As could maintain, worsen, or improve ED symptoms. This article reviews the limited literature on GLP-1As and ED symptoms, recommends future research, and provides clinicians with a guide for discussing GLP-1As with ED clients.

Prescription patterns in unipolar depression: A nationwide Danish register-based study of 113,175 individuals followed for 10 years

BACKGROUND

Evidence-based use of antidepressant medications is of major clinical importance. We aimed to uncover precription patterns in a large cohort of patients with unipolar depression.

MATERIAL AND METHODS

Using Danish nationwide registers, we identified individuals with a first-time hospital diagnosis of unipolar depression between January 1st, 2001, and December 31st, 2016. Redemeed prescriptions of antidepressants from five years before to five years after diagnosis were retreived. Lithium and relevant antipsychotics were included. Data were analyzed with descriptive statistics including sunburst plots. Cox regressions were used to rank the risk of treatment failure according to antidepressant category and depression severity, as measured by hazard ratios of drug shift.

RESULTS

The full study population consisted of 113,175 individuals. Selective Serotonin Reuptake Inhibitors was the predominantly prescribed first-line group, both before (55.4%) and after (47.7%) diagnosis and across depression severities. Changes of treatment strategy were frequent; 60.8%, 33.7%, and 17.1% reached a second, third, and fourth treatment trial after the hospital diagnosis, respectively. More than half of patients continued their pre-diagnosis antidepressant after diagnosis. The risk of change of treatment strategy was generally lower in mild-moderate depression and higher in severe depression, with tricyclic antidepressants carrying the highest risk in the former and the lowest risks in the latter. Overall, prescribing were often not in accordance with guidelines.

CONCLUSION

These findings uncover a potential for improving the clinical care for patients with unipolar depression through optimization of the use of marketed antidepressants.