Implementing Precision Psychiatry: A Systematic Review of Individualized Prediction Models for Clinical Practice

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.

Optimising the use of electronic medical records for large scale research in psychiatry

The explosion and abundance of digital data could facilitate large-scale research for psychiatry and mental health. Research using so-called "real world data"-such as electronic medical/health records-can be resource-efficient, facilitate rapid hypothesis generation and testing, complement existing evidence (e.g. from trials and evidence-synthesis) and may enable a route to translate evidence into clinically effective, outcomes-driven care for patient populations that may be under-represented. However, the interpretation and processing of real-world data sources is complex because the clinically important 'signal' is often contained in both structured and unstructured (narrative or "free-text") data. Techniques for extracting meaningful information (signal) from unstructured text exist and have advanced the re-use of routinely collected clinical data, but these techniques require cautious evaluation. In this paper, we survey the opportunities, risks and progress made in the use of electronic medical record (real-world) data for psychiatric research.

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.

On the Road to Individualizing Pharmacotherapy for Adolescents and Adults with Schizophrenia - Results from an Expert Consensus Following the Delphi Method

Introduction

Schizophrenia is a severe mental illness that usually begins in late adolescence or early adulthood. Current pharmacological treatments, while acceptably effective for many patients, are rarely clinically tailored or individualized. The lack of sufficient etiopathological knowledge of the disease, together with overall comparable effect sizes for efficacy between available antipsychotics and the absence of clinically actionable biomarkers, has hindered the advance of individualized medicine in the treatment of schizophrenia. Nevertheless, some degree of stratification based on clinical markers could guide treatment choices and help clinicians move toward individualized psychiatry. To this end, a panel of experts met to formally discuss the current approach to individualized treatment in schizophrenia and to define how treatment individualization could help improve clinical outcomes.

Methods

A task force of seven experts iteratively developed, evaluated, and refined questionnaire items, which were then evaluated using the Delphi method. Descriptive statistics were used to summarize and rank expert responses. Expert discussion, informed by the results of a scoping review on personalizing the pharmacologic treatment of adults and adolescents with schizophrenia, ultimately generated recommendations to guide individualized pharmacologic treatment in this population.

Results

There was substantial agreement among the expert group members, resulting in the following recommendations: 1) individualization of treatment requires consideration of the patient's diagnosis, clinical presentation, comorbidities, previous treatment response, drug tolerability, adherence patterns, and social factors; 2) patient preferences should be considered in a shared decision-making approach; 3) identified barriers to personalized care that need to be overcome include the lack of actionable biomarkers and mechanistic similarities between available treatments, but digital tools should be increasingly used to enhance individualized treatment.

Conclusion

Individualized care can help provide effective, tailored treatments based on an individual's clinical characteristics, disease trajectory, family and social environment, and goals and preferences.

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

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

Five-year follow-up of the iBerry Study: screening in early adolescence to identify those at risk of psychopathology in emerging adulthood

The iBerry Study, a Dutch population-based high-risk cohort (n = 1022) examines the transition from subclinical symptoms to psychiatric disorders in adolescents. Here, we present the first follow-up measurement, approximately 3 years after baseline assessment and 5 years after the screening based on self-reported emotional and behavioral problems (SDQ-Y). We give an update on the data collection, details on the (non)response, and the results on psychopathology outcomes. The first follow-up (2019-2022) had a response rate of 79% (n = 807). Our results at baseline (mean age 15.0 years) have shown the effectiveness of using the SDQ-Y to select a cohort oversampled for the risk of psychopathology. At first follow-up (mean age 18.1 years), the previously administered SDQ-Y remains predictive for selecting adolescents at risk. At follow-up, 47% of the high-risk adolescents showed significant mental health problems based on self- and parent reports and 46% of the high-risk adolescents met the criteria for multiple DSM-5 diagnoses. Compared to low-risk adolescents, high-risk adolescents had a sevenfold higher odds of significant emotional and behavioral problems at follow-up. Comprehensive assessment on psychopathology, substance abuse, psychotic symptoms, suicidality, nonsuicidal self-injury, addiction to social media and/or video gaming, and delinquency, as well as social development, and the utilization of healthcare and social services were conducted. This wave, as well as the ones to follow, track these adolescents into their young adulthood to identify risk factors, elucidate causal mechanisms, and discern pathways leading to both common and severe mental disorders. Results from the iBerry Study will provide leads for preventive interventions.

On the interplay between state-dependent reconfigurations of global signal correlation and BOLD fluctuations: An fMRI study

BACKGROUND

The dynamics of global, state-dependent reconfigurations in brain connectivity are yet unclear. We aimed at assessing reconfigurations of the global signal correlation coefficient (GSCORR), a measure of the connectivity between each voxel timeseries and the global signal, from resting-state to a stop-signal task. The secondary aim was to assess the relationship between GSCORR and blood-oxygen-level-dependent (BOLD) activations or deactivation across three different trial-conditions (GO, STOP-correct, and STOP-incorrect).

METHODS

As primary analysis we computed whole-brain, voxel-wise GSCORR during resting-state (GSCORR-rest) and stop-signal task (GSCORR-task) in 107 healthy subjects aged 21-50, deriving GSCORR-shift as GSCORR-task minus GSCORR-rest. GSCORR-tr and trGSCORR-shift were also computed on the task residual time series to quantify the impact of the task-related activity during the trials. To test the secondary aim, brain regions were firstly divided in one cluster showing significant task-related activation and one showing significant deactivation across the three trial conditions. Then, correlations between GSCORR-rest/task/shift and activation/deactivation in the two clusters were computed. As sensitivity analysis, GSCORR-shift was computed on the same sample after performing a global signal regression and GSCORR-rest/task/shift were correlated with the task performance.

RESULTS

Sensory and temporo-parietal regions exhibited a negative GSCORR-shift. Conversely, associative regions (ie. left lingual gyrus, bilateral dorsal posterior cingulate gyrus, cerebellum areas, thalamus, posterolateral parietal cortex) displayed a positive GSCORR-shift (FDR-corrected p < 0.05). GSCORR-shift showed similar patterns to trGSCORR-shift (magnitude increased) and after global signal regression (magnitude decreased). Concerning BOLD changes, Brodmann area 6 and inferior parietal lobule showed activation, while posterior parietal lobule, cuneus, precuneus, middle frontal gyrus showed deactivation (FDR-corrected p < 0.05). No correlations were found between GSCORR-rest/task/shift and beta-coefficients in the activation cluster, although negative correlations were observed between GSCORR-task and GO/STOP-correct deactivation (Pearson rho=-0.299/-0.273; Bonferroni-p < 0.05). Weak associations between GSCORR and task performance were observed (uncorrected p < 0.05).

CONCLUSION

GSCORR state-dependent reconfiguration indicates a reallocation of functional resources to associative areas during stop-signal task. GSCORR, activation and deactivation may represent distinct proxies of brain states with specific neurofunctional relevance.

Accelerating Medicines Partnership® Schizophrenia (AMP® SCZ): Rationale and Study Design of the Largest Global Prospective Cohort Study of Clinical High Risk for Psychosis

This article describes the rationale, aims, and methodology of the Accelerating Medicines Partnership® Schizophrenia (AMP® SCZ). This is the largest international collaboration to date that will develop algorithms to predict trajectories and outcomes of individuals at clinical high risk (CHR) for psychosis and to advance the development and use of novel pharmacological interventions for CHR individuals. We present a description of the participating research networks and the data processing analysis and coordination center, their processes for data harmonization across 43 sites from 13 participating countries (recruitment across North America, Australia, Europe, Asia, and South America), data flow and quality assessment processes, data analyses, and the transfer of data to the National Institute of Mental Health (NIMH) Data Archive (NDA) for use by the research community. In an expected sample of approximately 2000 CHR individuals and 640 matched healthy controls, AMP SCZ will collect clinical, environmental, and cognitive data along with multimodal biomarkers, including neuroimaging, electrophysiology, fluid biospecimens, speech and facial expression samples, novel measures derived from digital health technologies including smartphone-based daily surveys, and passive sensing as well as actigraphy. The study will investigate a range of clinical outcomes over a 2-year period, including transition to psychosis, remission or persistence of CHR status, attenuated positive symptoms, persistent negative symptoms, mood and anxiety symptoms, and psychosocial functioning. The global reach of AMP SCZ and its harmonized innovative methods promise to catalyze the development of new treatments to address critical unmet clinical and public health needs in CHR individuals.

A deep learning approach for acute liver failure prediction with combined fully connected and convolutional neural networks

BACKGROUND

Acute Liver Failure (ALF) is a critical medical condition with rapid development, often caused by viral infections, hepatotoxic drug abuse, or other severe liver diseases. Timely and accurate prediction of ALF occurrence is clinically crucial. However, predicting ALF poses challenges due to the diverse physiological differences among patients and the dynamic nature of the disease.

OBJECTIVE

This study introduces a deep learning approach that combines fully connected and convolutional neural networks for effective ALF prediction. The goal is to overcome limitations of traditional machine learning methods and enhance predictive model performance and generalization.

METHODS

The proposed model integrates a fully connected neural network for handling basic patient features and a convolutional neural network dedicated to capturing temporal patterns in patient data. The combination allows automatic learning of complex patterns and abstract features present in highly dynamic medical data associated with ALF.

RESULTS

The model's effectiveness is demonstrated through comprehensive experiments and performance evaluations. It outperforms traditional machine learning methods, achieving 94.8% accuracy and superior generalization capabilities.

CONCLUSIONS

The study highlights the potential of deep learning in ALF prediction, emphasizing the importance of considering individualized medical factors. Future research should focus on improving model robustness, addressing imbalanced data, and further exploring personalized features for enhanced predictive accuracy in real-world clinical scenarios.

Running in the FAMILY: understanding and predicting the intergenerational transmission of mental illness

Over 50% of children with a parent with severe mental illness will develop mental illness by early adulthood. However, intergenerational transmission of risk for mental illness in one's children is insufficiently considered in clinical practice, nor is it sufficiently utilised into diagnostics and care for children of ill parents. This leads to delays in diagnosing young offspring and missed opportunities for protective actions and resilience strengthening. Prior twin, family, and adoption studies suggest that the aetiology of mental illness is governed by a complex interplay of genetic and environmental factors, potentially mediated by changes in epigenetic programming and brain development. However, how these factors ultimately materialise into mental disorders remains unclear. Here, we present the FAMILY consortium, an interdisciplinary, multimodal (e.g., (epi)genetics, neuroimaging, environment, behaviour), multilevel (e.g., individual-level, family-level), and multisite study funded by a European Union Horizon-Staying-Healthy-2021 grant. FAMILY focuses on understanding and prediction of intergenerational transmission of mental illness, using genetically informed causal inference, multimodal normative prediction, and animal modelling. Moreover, FAMILY applies methods from social sciences to map social and ethical consequences of risk prediction to prepare clinical practice for future implementation. FAMILY aims to deliver: (i) new discoveries clarifying the aetiology of mental illness and the process of resilience, thereby providing new targets for prevention and intervention studies; (ii) a risk prediction model within a normative modelling framework to predict who is at risk for developing mental illness; and (iii) insight into social and ethical issues related to risk prediction to inform clinical guidelines.

Shaping tomorrow's support: baseline clinical characteristics predict later social functioning and quality of life in schizophrenia spectrum disorder

PURPOSE

We aimed to explore the multidimensional nature of social inclusion (mSI) among patients diagnosed with schizophrenia spectrum disorder (SSD), and to identify the predictors of 3-year mSI and the mSI prediction using traditional and data-driven approaches.

METHODS

We used the baseline and 3-year follow-up data of 1119 patients from the Genetic Risk and Outcome in Psychosis (GROUP) cohort in the Netherlands. The outcome mSI was defined as clusters derived from combined analyses of thirteen subscales from the Social Functioning Scale and the brief version of World Health Organization Quality of Life questionnaires through K-means clustering. Prediction models were built through multinomial logistic regression (ModelMLR) and random forest (ModelRF), internally validated via bootstrapping and compared by accuracy and the discriminability of mSI subgroups.

RESULTS

We identified five mSI subgroups: "very low (social functioning)/very low (quality of life)" (8.58%), "low/low" (12.87%), "high/low" (49.24%), "medium/high" (18.05%), and "high/high" (11.26%). The mSI was robustly predicted by a genetic predisposition for SSD, premorbid adjustment, positive, negative, and depressive symptoms, number of met needs, and baseline satisfaction with the environment and social life. The ModelRF (61.61% [54.90%, 68.01%]; P =0.013) was cautiously considered outperform the ModelMLR (59.16% [55.75%, 62.58%]; P =0.994).

CONCLUSION

We introduced and distinguished meaningful subgroups of mSI, which were modestly predictable from baseline clinical characteristics. A possibility for early prediction of mSI at the clinical stage may unlock the potential for faster and more impactful social support that is specifically tailored to the unique characteristics of the mSI subgroup to which a given patient belongs.

Using Electronic Health Records to Facilitate Precision Psychiatry

The use of clinical prediction models to produce individualized risk estimates can facilitate the implementation of precision psychiatry. As a source of data from large, clinically representative patient samples, electronic health records (EHRs) provide a platform to develop and validate clinical prediction models, as well as potentially implement them in routine clinical care. The current review describes promising use cases for the application of precision psychiatry to EHR data and considers their performance in terms of discrimination (ability to separate individuals with and without the outcome) and calibration (extent to which predicted risk estimates correspond to observed outcomes), as well as their potential clinical utility (weighing benefits and costs associated with the model compared to different approaches across different assumptions of the number needed to test). We review 4 externally validated clinical prediction models designed to predict psychosis onset, psychotic relapse, cardiometabolic morbidity, and suicide risk. We then discuss the prospects for clinically implementing these models and the potential added value of integrating data from evidence syntheses, standardized psychometric assessments, and biological data into EHRs. Clinical prediction models can utilize routinely collected EHR data in an innovative way, representing a unique opportunity to inform real-world clinical decision making. Combining data from other sources (e.g., meta-analyses) or enhancing EHR data with information from research studies (clinical and biomarker data) may enhance our abilities to improve the performance of clinical prediction models.

The self, neuroscience and psychosis study: Testing a neurophenomenological model of the onset of psychosis

AIM

Basic self disturbance is a putative core vulnerability marker of schizophrenia spectrum disorders. The primary aims of the Self, Neuroscience and Psychosis (SNAP) study are to: (1) empirically test a previously described neurophenomenological self-disturbance model of psychosis by examining the relationship between specific clinical, neurocognitive, and neurophysiological variables in UHR patients, and (2) develop a prediction model using these neurophenomenological disturbances for persistence or deterioration of UHR symptoms at 12-month follow-up.

METHODS

SNAP is a longitudinal observational study. Participants include 400 UHR individuals, 100 clinical controls with no attenuated psychotic symptoms, and 50 healthy controls. All participants complete baseline clinical and neurocognitive assessments and electroencephalography. The UHR sample are followed up for a total of 24 months, with clinical assessment completed every 6 months.

RESULTS

This paper presents the protocol of the SNAP study, including background rationale, aims and hypotheses, design, and assessment procedures.

CONCLUSIONS

The SNAP study will test whether neurophenomenological disturbances associated with basic self-disturbance predict persistence or intensification of UHR symptomatology over a 2-year follow up period, and how specific these disturbances are to a clinical population with attenuated psychotic symptoms. This may ultimately inform clinical care and pathoaetiological models of psychosis.

Umbrella Review: Atlas of the Meta-Analytical Evidence of Early-Onset Psychosis

OBJECTIVE

Early-onset psychosis (EOP) refers to the development of psychosis before the age of 18 years. We aimed to summarize, for the first time, the meta-analytical evidence in the field of this vulnerable population and to provide evidence-based recommendations.

METHOD

We performed a Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA)-compliant, pre-registered (PROSPERO: CRD42022350868) systematic review of several databases and registers to identify meta-analyses of studies conducted in EOP individuals to conduct an umbrella review. Literature search, screening, data extraction, and quality assessment were carried out independently. Results were narratively reported, clustered across core domains. Quality assessment was performed with the Assessment of Multiple Systematic Reviews-2 (AMSTAR-2) tool.

RESULTS

A total of 30 meta-analyses were included (373 individual studies, 25,983 participants, mean age 15.1 years, 38.3% female). Individuals with EOP showed more cognitive impairments compared with controls and individuals with adult/late-onset psychosis. Abnormalities were observed meta-analytically in neuroimaging markers but not in oxidative stress and inflammatory response markers. In all, 60.1% of EOP individuals had a poor prognosis. Clozapine was the antipsychotic with the highest efficacy for overall, positive, and negative symptoms. Tolerance to medication varied among the evaluated antipsychotics. The risk of discontinuation of antipsychotics for any reason or side effects was low or equal compared to placebo.

CONCLUSION

EOP is associated with cognitive impairment, involuntary admissions, and poor prognosis. Antipsychotics can be efficacious in EOP, but tolerability and safety need to be taken into consideration. Clozapine should be considered in EOP individuals who are resistant to 2 non-clozapine antipsychotics. Further meta-analytical research is needed on response to psychological interventions and other prognostic factors.

STUDY PREREGISTRATION INFORMATION

Early Onset Psychosis: Umbrella Review on Diagnosis, Prognosis and Treatment factors; https://www.crd.york.ac.uk/PROSPERO/; CRD42022350868.

The Translational Future of Stress Neurobiology and Psychosis Vulnerability: A Review of the Evidence

Psychosocial stress is a well-established risk factor for psychosis, yet the neurobiological mechanisms underlying this relationship have yet to be fully elucidated. Much of the research in this field has investigated hypothalamic-pituitary-adrenal (HPA) axis function and immuno-inflammatory processes among individuals with established psychotic disorders. However, as such studies are limited in their ability to provide knowledge that can be used to develop preventative interventions, it is important to shift the focus to individuals with increased vulnerability for psychosis (i.e., high-risk groups). In the present article, we provide an overview of the current methods for identifying individuals at high-risk for psychosis and review the psychosocial stressors that have been most consistently associated with psychosis risk. We then describe a network of interacting physiological systems that are hypothesised to mediate the relationship between psychosocial stress and the manifestation of psychotic illness and critically review evidence that abnormalities within these systems characterise highrisk populations. We found that studies of high-risk groups have yielded highly variable findings, likely due to (i) the heterogeneity both within and across high-risk samples, (ii) the diversity of psychosocial stressors implicated in psychosis, and (iii) that most studies examine single markers of isolated neurobiological systems. We propose that to move the field forward, we require well-designed, largescale translational studies that integrate multi-domain, putative stress-related biomarkers to determine their prognostic value in high-risk samples. We advocate that such investigations are highly warranted, given that psychosocial stress is undoubtedly a relevant risk factor for psychotic disorders.

Electronic health records and stratified psychiatry: bridge to precision treatment?

The use of a stratified psychiatry approach that combines electronic health records (EHR) data with machine learning (ML) is one potentially fruitful path toward rapidly improving precision treatment in clinical practice. This strategy, however, requires confronting pervasive methodological flaws as well as deficiencies in transparency and reporting in the current conduct of ML-based studies for treatment prediction. EHR data shares many of the same data quality issues as other types of data used in ML prediction, plus some unique challenges. To fully leverage EHR data's power for patient stratification, increased attention to data quality and collection of patient-reported outcome data is needed.

Psychiatric Comorbidities and Schizophrenia in Youths With Attention-Deficit/Hyperactivity Disorder

Importance

The association between attention-deficit/hyperactivity disorder (ADHD) and schizophrenia has received increased attention; however, evidence on the association between psychiatric comorbidities and subsequent schizophrenia in patients with ADHD is limited.

Objective

To investigate the risk of being diagnosed with schizophrenia in children and adolescents with ADHD considering the presence of psychiatric comorbidity.

Design, Setting, and Participants

This was a population-based, retrospective cohort study using the Health Insurance Review and Assessment claims database from January 1, 2007, to December 31, 2019. Participants were children and adolescents aged 5 to 19 years who received an ADHD diagnosis between January 1, 2010, and December 31, 2018, in the nationwide claims data of Korea. Data were analyzed from January 2010 to December 2019.

Interventions or Exposures

The presence of psychiatric comorbidity was assessed from diagnosis records within 1 year before ADHD diagnosis. Comorbidities were further categorized according to the number of comorbidities and specific comorbid disorders.

Main Outcomes and Measures

Cox proportional hazard models were used to estimate hazard ratios (HRs) and 95% CIs, examining the association between psychiatric comorbidities and the risk of being diagnosed with schizophrenia. Furthermore, the occurrence of psychiatric comorbidity during the follow-up period was explored among patients without psychiatric comorbidity at baseline.

Results

A total of 211 705 patients with newly diagnosed ADHD were included. A total of 157 272 patients (74.3%) were male, and the age of 5 to 9 years showed the highest distribution (115 081 patients [54.4%]). Patients with psychiatric comorbidity had a significantly higher risk of being diagnosed with schizophrenia than those without (adjusted HR, 2.14; 95% CI, 2.05-2.23). The association between schizophrenia and psychiatric comorbidity became progressively greater with the increasing number of comorbidities. Several individual psychiatric disorders showed an association with development of schizophrenia, with ASD, intellectual disability, tic disorder, depression, and bipolar disorder being the top 5 disorders most associated. Furthermore, 3244 patients (73.8%) without psychiatric comorbidities experienced the emergence of other psychiatric disorders before schizophrenia occurrence.

Conclusions and Relevance

In this retrospective cohort study involving children and adolescents with ADHD, the presence of psychiatric comorbidity in patients with ADHD was associated with an increased risk of being diagnosed with schizophrenia, with an increased risk observed in multiple comorbidities and a wide variety of comorbidities. These findings highlight the significance of assessing and managing psychiatric comorbidities in patients with ADHD to decrease subsequent schizophrenia risk and allow for early intervention.

Testing anxiety and reward processing in anorexia nervosa as predictors of longitudinal clinical outcomes

Anorexia nervosa (AN) is a psychiatric disorder with a tenuous longitudinal course marked by a high risk of relapse. Previous studies suggest that aberrant threat perception and reward processing operate in many with AN, and may produce obstacles to treatment engagement; therefore, these could potentially represent predictors for longitudinal clinical outcomes. In this study, anxiety and reward symptoms, behaviors, and neural circuit connectivity were measured in intensively treated AN-restrictive subtype patients (n = 33) and healthy controls (n = 31). Participants underwent an fMRI experiment using a monetary reward task in combination with either overlapping individually tailored anxiety-provoking words or neutral words. Behavioral/psychometric measures consisted of reaction times on the monetary reward task and self-ratings on anxiety symptoms at study entry. We tested multimodal, multivariate models based on neural, behavioral, and psychometric measures of reward and anxiety to predict physiological (Body Mass Index; BMI) and psychological (eating disorder symptom severity) longitudinal outcomes in AN over six months. Our results indicated that higher anxiety symptom psychometric scores significantly predicted BMI reductions at follow-up. Untreated anxiety after intensive treatment could put individuals with AN at heightened risk for weight loss. This represents a potentially modifiable risk factor that could be targeted more aggressively to help reduce the chance of future clinical worsening.

A scoping review of artificial intelligence-based methods for diabetes risk prediction

The increasing prevalence of type 2 diabetes mellitus (T2DM) and its associated health complications highlight the need to develop predictive models for early diagnosis and intervention. While many artificial intelligence (AI) models for T2DM risk prediction have emerged, a comprehensive review of their advancements and challenges is currently lacking. This scoping review maps out the existing literature on AI-based models for T2DM prediction, adhering to the PRISMA extension for Scoping Reviews guidelines. A systematic search of longitudinal studies was conducted across four databases, including PubMed, Scopus, IEEE-Xplore, and Google Scholar. Forty studies that met our inclusion criteria were reviewed. Classical machine learning (ML) models dominated these studies, with electronic health records (EHR) being the predominant data modality, followed by multi-omics, while medical imaging was the least utilized. Most studies employed unimodal AI models, with only ten adopting multimodal approaches. Both unimodal and multimodal models showed promising results, with the latter being superior. Almost all studies performed internal validation, but only five conducted external validation. Most studies utilized the area under the curve (AUC) for discrimination measures. Notably, only five studies provided insights into the calibration of their models. Half of the studies used interpretability methods to identify key risk predictors revealed by their models. Although a minority highlighted novel risk predictors, the majority reported commonly known ones. Our review provides valuable insights into the current state and limitations of AI-based models for T2DM prediction and highlights the challenges associated with their development and clinical integration.

Precision medicine in complex diseases-Molecular subgrouping for improved prediction and treatment stratification

Complex diseases are caused by a combination of genetic, lifestyle, and environmental factors and comprise common noncommunicable diseases, including allergies, cardiovascular disease, and psychiatric and metabolic disorders. More than 25% of Europeans suffer from a complex disease, and together these diseases account for 70% of all deaths. The use of genomic, molecular, or imaging data to develop accurate diagnostic tools for treatment recommendations and preventive strategies, and for disease prognosis and prediction, is an important step toward precision medicine. However, for complex diseases, precision medicine is associated with several challenges. There is a significant heterogeneity between patients of a specific disease-both with regards to symptoms and underlying causal mechanisms-and the number of underlying genetic and nongenetic risk factors is often high. Here, we summarize precision medicine approaches for complex diseases and highlight the current breakthroughs as well as the challenges. We conclude that genomic-based precision medicine has been used mainly for patients with highly penetrant monogenic disease forms, such as cardiomyopathies. However, for most complex diseases-including psychiatric disorders and allergies-available polygenic risk scores are more probabilistic than deterministic and have not yet been validated for clinical utility. However, subclassifying patients of a specific disease into discrete homogenous subtypes based on molecular or phenotypic data is a promising strategy for improving diagnosis, prediction, treatment, prevention, and prognosis. The availability of high-throughput molecular technologies, together with large collections of health data and novel data-driven approaches, offers promise toward improved individual health through precision medicine.

An umbrella review of candidate predictors of response, remission, recovery, and relapse across mental disorders

We aimed to identify diagnosis-specific/transdiagnostic/transoutcome multivariable candidate predictors (MCPs) of key outcomes in mental disorders. We conducted an umbrella review (protocol  link ), searching MEDLINE/Embase (19/07/2022), including systematic reviews of studies reporting on MCPs of response, remission, recovery, or relapse, in DSM/ICD-defined mental disorders. From published predictors, we filtered MCPs, validating MCP criteria. AMSTAR2/PROBAST measured quality/risk of bias of systematic reviews/individual studies. We included 117 systematic reviews, 403 studies, 299,888 individuals with mental disorders, testing 796 prediction models. Only 4.3%/1.2% of the systematic reviews/individual studies were at low risk of bias. The most frequently targeted outcome was remission (36.9%), the least frequent was recovery (2.5%). Studies mainly focused on depressive (39.4%), substance-use (17.9%), and schizophrenia-spectrum (11.9%) disorders. We identified numerous MCPs within disorders for response, remission and relapse, but none for recovery. Transdiagnostic MCPs of remission included lower disease-specific symptoms (disorders = 5), female sex/higher education (disorders = 3), and quality of life/functioning (disorders = 2). Transdiagnostic MCPs of relapse included higher disease-specific symptoms (disorders = 5), higher depressive symptoms (disorders = 3), and younger age/higher anxiety symptoms/global illness severity/ number of previous episodes/negative life events (disorders = 2). Finally, positive trans-outcome MCPs for depression included less negative life events/depressive symptoms (response, remission, less relapse), female sex (response, remission) and better functioning (response, less relapse); for schizophrenia, less positive symptoms/higher depressive symptoms (remission, less relapse); for substance use disorder, marital status/higher education (remission, less relapse). Male sex, younger age, more clinical symptoms and comorbid mental/physical symptoms/disorders were poor prognostic factors, while positive factors included social contacts and employment, absent negative life events, higher education, early access/intervention, lower disease-specific and comorbid mental and physical symptoms/conditions, across mental disorders. Current data limitations include high risk of bias of studies and extraction of single predictors from multivariable models. Identified MCPs can inform future development, validation or refinement of prediction models of key outcomes in mental disorders.

Development and validation of a prediction model for rehospitalization among people with schizophrenia discharged from acute inpatient care

Objective

Relapses and rehospitalization prevent the recovery of individuals with schizophrenia or related psychoses. We aimed to build a model to predict the risk of rehospitalization among people with schizophrenia or related psychoses, including those with multiple episodes.

Methods

This retrospective cohort study included individuals aged 18 years or older, with schizophrenia or related psychoses, and discharged between January 2014 and December 2018 from one of three Japanese psychiatric hospital acute inpatient care ward. We collected nine predictors at the time of recruitment, followed up with the participants for 12 months, and observed whether psychotic relapse had occurred. Next, we applied the Cox regression model and used an elastic net to avoid overfitting. Then, we examined discrimination using bootstrapping, Steyerberg's method, and "leave-one-hospital-out" cross-validation. We also constructed a bias-corrected calibration plot.

Results

Data from a total of 805 individuals were analyzed. The significant predictors were the number of previous hospitalizations (HR 1.42, 95% CI 1.22-1.64) and the current length of stay in days (HR 1.31, 95% CI 1.04-1.64). In model development for relapse, Harrell's c-index was 0.59 (95% CI 0.55-0.63). The internal and internal-external validation for rehospitalization showed Harrell's c-index to be 0.64 (95% CI 0.59-0.69) and 0.66 (95% CI 0.57-0.74), respectively. The calibration plot was found to be adequate.

Conclusion

The model showed moderate discrimination of readmission after discharge. Carefully defining a research question by seeking needs among the population with chronic schizophrenia with multiple episodes may be key to building a useful model.

Improving mental health care in depression: A call for action

Depressive disorders have one of the highest disability-adjusted life years (DALYs) of all medical conditions, which led the European Psychiatric Association to propose a policy paper, pinpointing their unmet health care and research needs. The first part focuses on what can be currently done to improve the care of patients with depression, and then discuss future trends for research and healthcare. Through the narration of clinical cases, the different points are illustrated. The necessary political framework is formulated, to implement such changes to fundamentally improve psychiatric care. The group of European Psychiatrist Association (EPA) experts insist on the need for (1) increased awareness of mental illness in primary care settings, (2) the development of novel (biological) markers, (3) the rapid implementation of machine learning (supporting diagnostics, prognostics, and therapeutics), (4) the generalized use of electronic devices and apps into everyday treatment, (5) the development of the new generation of treatment options, such as plasticity-promoting agents, and (6) the importance of comprehensive recovery approach. At a political level, the group also proposed four priorities, the need to (1) increase the use of open science, (2) implement reasonable data protection laws, (3) establish ethical electronic health records, and (4) enable better healthcare research and saving resources.

A roadmap for applying machine learning when working with privacy-sensitive data: predicting non-response to treatment for eating disorders

OBJECTIVES

Applying machine-learning methodology to clinical data could present a promising avenue for predicting outcomes in patients receiving treatment for psychiatric disorders. However, preserving privacy when working with patient data remains a critical concern.

METHODS

In showcasing how machine-learning can be used to build a clinically relevant prediction model on clinical data, we apply two commonly used machine-learning algorithms (Random Forest and least absolute shrinkage and selection operator) to routine outcome monitoring data collected from 593 patients with eating disorders to predict absence of reliable improvement 12 months after entering outpatient treatment.

RESULTS

An RF model trained on data collected at baseline and after three months made 31.3% fewer errors in predicting lack of reliable improvement at 12 months, in comparison with chance. Adding data from a six-month follow-up resulted in only marginal improvements to accuracy.

CONCLUSION

We were able to build and validate a model that could aid clinicians and researchers in more accurately predicting treatment response in patients with EDs. We also demonstrated how this could be done without compromising privacy. ML presents a promising approach to developing accurate prediction models for psychiatric disorders such as ED.

Assessing violence risk in first-episode psychosis: external validation, updating and net benefit of a prediction tool (OxMIV)

BACKGROUND

Violence perpetration is a key outcome to prevent for an important subgroup of individuals presenting to mental health services, including early intervention in psychosis (EIP) services. Needs and risks are typically assessed without structured methods, which could facilitate consistency and accuracy. Prediction tools, such as OxMIV (Oxford Mental Illness and Violence tool), could provide a structured risk stratification approach, but require external validation in clinical settings.

OBJECTIVES

We aimed to validate and update OxMIV in first-episode psychosis and consider its benefit as a complement to clinical assessment.

METHODS

A retrospective cohort of individuals assessed in two UK EIP services was included. Electronic health records were used to extract predictors and risk judgements made by assessing clinicians. Outcome data involved police and healthcare records for violence perpetration in the 12 months post-assessment.

FINDINGS

Of 1145 individuals presenting to EIP services, 131 (11%) perpetrated violence during the 12 month follow-up. OxMIV showed good discrimination (area under the curve 0.75, 95% CI 0.71 to 0.80). Calibration-in-the-large was also good after updating the model constant. Using a 10% cut-off, sensitivity was 71% (95% CI 63% to 80%), specificity 66% (63% to 69%), positive predictive value 22% (19% to 24%) and negative predictive value 95% (93% to 96%). In contrast, clinical judgement sensitivity was 40% and specificity 89%. Decision curve analysis showed net benefit of OxMIV over comparison approaches.

CONCLUSIONS

OxMIV performed well in this real-world validation, with improved sensitivity compared with unstructured assessments.

CLINICAL IMPLICATIONS

Structured tools to assess violence risk, such as OxMIV, have potential in first-episode psychosis to support a stratified approach to allocating non-harmful interventions to individuals who may benefit from the largest absolute risk reduction.

What proportion of clinical prediction models make it to clinical practice? Protocol for a two-track follow-up study of prediction model development publications

INTRODUCTION

It is known that only a limited proportion of developed clinical prediction models (CPMs) are implemented and/or used in clinical practice. This may result in a large amount of research waste, even when considering that some CPMs may demonstrate poor performance. Cross-sectional estimates of the numbers of CPMs that have been developed, validated, evaluated for impact or utilized in practice, have been made in specific medical fields, but studies across multiple fields and studies following up the fate of CPMs are lacking.

METHODS AND ANALYSIS

We have conducted a systematic search for prediction model studies published between January 1995 and December 2020 using the Pubmed and Embase databases, applying a validated search strategy. Taking random samples for every calendar year, abstracts and articles were screened until a target of 100 CPM development studies were identified. Next, we will perform a forward citation search of the resulting CPM development article cohort to identify articles on external validation, impact assessment or implementation of those CPMs. We will also invite the authors of the development studies to complete an online survey to track implementation and clinical utilization of the CPMs.We will conduct a descriptive synthesis of the included studies, using data from the forward citation search and online survey to quantify the proportion of developed models that are validated, assessed for their impact, implemented and/or used in patient care. We will conduct time-to-event analysis using Kaplan-Meier plots.

ETHICS AND DISSEMINATION

No patient data are involved in the research. Most information will be extracted from published articles. We request written informed consent from the survey respondents. Results will be disseminated through publication in a peer-reviewed journal and presented at international conferences. OSF REGISTRATION: (https://osf.io/nj8s9).

Identifying Depression Early in Adolescence: assessing the performance of a risk score for future onset of depression in an independent Brazilian sample

OBJECTIVE

The Identifying Depression Early in Adolescence Risk Score (IDEA-RS) was recently developed in Brazil using data from the Pelotas 1993 Birth Cohort to estimate the individualized probability of developing depression in adolescence. This model includes 11 sociodemographic variables and has been assessed in longitudinal studies from four other countries. We aimed to test the performance of IDEA-RS in an independent, community-based, school-attending sample within the same country: the Brazilian High-Risk Cohort.

METHODS

Standard external validation, refitted, and case mix-corrected models were used to predict depression among 1442 youth followed from a mean age of 13.5 years at baseline to 17.7 years at follow-up, using probabilities calculated with IDEA-RS coefficients.

RESULTS

The area under the curve was 0.65 for standard external validation, 0.70 for the case mix-corrected model, and 0.69 for the refitted model, with discrimination consistently above chance for predicting depression in the new dataset. There was some degree of miscalibration, corrected by model refitting (calibration-in-the-large reduced from 0.77 to 0).

CONCLUSION

IDEA-RS was able to parse individuals with higher or lower probability of developing depression beyond chance in an independent Brazilian sample. Further steps should include model improvements and additional studies in populations with high levels of subclinical symptoms to improve clinical decision making.

Predicting type 2 diabetes prevalence for people with severe mental illness in a multi-ethnic East London population

BACKGROUND AND AIMS

Prevalence of type two diabetes mellitus (T2DM) in people with severe mental illness (SMI) is 2-3 times higher than in general population. Predictive modelling has advanced greatly in the past decade, and it is important to apply cutting-edge methods to vulnerable groups. However, few T2DM prediction models account for the presence of mental illness, and none seemed to have been developed specifically for people with SMI. Therefore, we aimed to develop and internally validate a T2DM prevalence model for people with SMI.

METHODS

We utilised a large cross-sectional sample representative of a multi-ethnic population from London (674,000 adults); 10,159 people with SMI formed our analytical sample (1,513 T2DM cases). We fitted a linear logistic regression and XGBoost as stand-alone models and as a stacked ensemble. Age, sex, body mass index, ethnicity, area-based deprivation, past hypertension, cardiovascular diseases, prescribed antipsychotics, and SMI illness were the predictors.

RESULTS

Logistic regression performed well while detecting T2DM presence for people with SMI: area under the receiver operator curve (ROC-AUC) was 0.83 (95 % CI 0.79-0.87). XGBoost and LR-XGBoost ensemble performed equally well, ROC-AUC 0.83 (95 % CI 0.79-0.87), indicating a negligible contribution of non-linear terms to predictive power. Ethnicity was the most important predictor after age. We demonstrated how the derived models can be utilised and estimated a 2.14 % (95 %CI 2.03 %-2.24 %) increase in T2DM prevalence in East London SMI population in 20 years' time, driven by the projected demographic changes.

CONCLUSIONS

Primary care data, the setting where prediction models could be most fruitfully used, provide enough information for well-performing T2DM prevalence models for people with SMI. We demonstrated how thorough internal cross-validation of an ensemble of a linear and machine-learning model can quantify the predictive value of non-linearity in the data.

Validation of the Collaborative Outcomes study on Health and Functioning during Infection Times (COH-FIT) questionnaire for adults

BACKGROUND

The Collaborative Outcome study on Health and Functioning during Infection Times (COH-FIT; www.coh-fit.com) is an anonymous and global online survey measuring health and functioning during the COVID-19 pandemic. The aim of this study was to test concurrently the validity of COH-FIT items and the internal validity of the co-primary outcome, a composite psychopathology "P-score".

METHODS

The COH-FIT survey has been translated into 30 languages (two blind forward-translations, consensus, one independent English back-translation, final harmonization). To measure mental health, 1-4 items ("COH-FIT items") were extracted from validated questionnaires (e.g. Patient Health Questionnaire 9). COH-FIT items measured anxiety, depressive, post-traumatic, obsessive-compulsive, bipolar and psychotic symptoms, as well as stress, sleep and concentration. COH-FIT Items which correlated r ≥ 0.5 with validated companion questionnaires, were initially retained. A P-score factor structure was then identified from these items using exploratory factor analysis (EFA) and confirmatory factor analyses (CFA) on data split into training and validation sets. Consistency of results across languages, gender and age was assessed.

RESULTS

From >150,000 adult responses by May 6th, 2022, a subset of 22,456 completed both COH-FIT items and validated questionnaires. Concurrent validity was consistently demonstrated across different languages for COH-FIT items. CFA confirmed EFA results of five first-order factors (anxiety, depression, post-traumatic, psychotic, psychophysiologic symptoms) and revealed a single second-order factor P-score, with high internal reliability (ω = 0.95). Factor structure was consistent across age and sex.

CONCLUSIONS

COH-FIT is a valid instrument to globally measure mental health during infection times. The P-score is a valid measure of multidimensional mental health.

A Microbial-Based Approach to Mental Health: The Potential of Probiotics in the Treatment of Depression

Probiotics are currently the subject of intensive research pursuits and also represent a multi-billion-dollar global industry given their vast potential to improve human health. In addition, mental health represents a key domain of healthcare, which currently has limited, adverse-effect prone treatment options, and probiotics may hold the potential to be a novel, customizable treatment for depression. Clinical depression is a common, potentially debilitating condition that may be amenable to a precision psychiatry-based approach utilizing probiotics. Although our understanding has not yet reached a sufficient level, this could be a therapeutic approach that can be tailored for specific individuals with their own unique set of characteristics and health issues. Scientifically, the use of probiotics as a treatment for depression has a valid basis rooted in the microbiota-gut-brain axis (MGBA) mechanisms, which play a role in the pathophysiology of depression. In theory, probiotics appear to be ideal as adjunct therapeutics for major depressive disorder (MDD) and as stand-alone therapeutics for mild MDD and may potentially revolutionize the treatment of depressive disorders. Although there is a wide range of probiotics and an almost limitless range of therapeutic combinations, this review aims to narrow the focus to the most widely commercialized and studied strains, namely Lactobacillus and Bifidobacterium, and to bring together the arguments for their usage in patients with major depressive disorder (MDD). Clinicians, scientists, and industrialists are critical stakeholders in exploring this groundbreaking concept.

Systematic review and meta-analysis on predictors of prognosis in patients with schizophrenia spectrum disorders: An overview of current evidence and a call for prospective research and open access to datasets

BACKGROUND

Schizophrenia spectrum disorders (SSD) have heterogeneous outcomes. If we could predict individual outcome and identify predictors of outcome, we could personalize and optimize treatment and care. Recent research showed that recovery rates tend to stabilize early in the course of disease. Short- to medium- term treatment goals are most relevant for clinical practice.

METHODS

We performed a systematic review and meta-analysis to identify predictors of outcome ≤1 year in prospective studies of patients with SSD. For our meta-analysis risk of bias was assessed with the QUIPS tool.

RESULTS

178 studies were included for analysis. Our systematic review and meta-analysis showed that the chance of symptomatic remission was lower in males, and in patients with longer duration of untreated psychosis, more symptoms, worse global functioning, more previous hospital admissions and worse treatment adherence. The chance of readmission was higher for patients with more previous admissions. The chance of functional improvement was lower in patients with worse functioning at baseline. For other proposed predictors of outcome, like age at onset and depressive symptoms, limited to no evidence was found.

DISCUSSION

This study illuminates predictors of outcome of SSD. Level of functioning at baseline was the best predictor of all investigated outcomes. Furthermore, we found no evidence for many predictors proposed in original research. Possible reasons for this include the lack of prospective research, between-study heterogeneity and incomplete reporting. We therefore recommend open access to datasets and analysis scripts, enabling other researchers to reanalyze and pool the data.

Deep Learning for Cross-Diagnostic Prediction of Mental Disorder Diagnosis and Prognosis Using Danish Nationwide Register and Genetic Data

Importance

Diagnoses and treatment of mental disorders are hampered by the current lack of objective markers needed to provide a more precise diagnosis and treatment strategy.

Objective

To develop deep learning models to predict mental disorder diagnosis and severity spanning multiple diagnoses using nationwide register data, family and patient-specific diagnostic history, birth-related measurement, and genetics.

Design, Setting, and Participants

This study was conducted from May 1, 1981, to December 31, 2016. For the analysis, which used a Danish population-based case-cohort sample of individuals born between 1981 and 2005, genotype data and matched longitudinal health register data were taken from the longitudinal Danish population-based Integrative Psychiatric Research Consortium 2012 case-cohort study. Included were individuals with mental disorders (attention-deficit/hyperactivity disorder [ADHD]), autism spectrum disorder (ASD), major depressive disorder (MDD), bipolar disorder (BD), schizophrenia spectrum disorders (SCZ), and population controls. Data were analyzed from February 1, 2021, to January 24, 2022.

Exposure

At least 1 hospital contact with diagnosis of ADHD, ASD, MDD, BD, or SCZ.

Main Outcomes and Measures

The predictability of (1) mental disorder diagnosis and (2) severity trajectories (measured by future outpatient hospital contacts, admissions, and suicide attempts) were investigated using both a cross-diagnostic and single-disorder setup. Predictive power was measured by AUC, accuracy, and Matthews correlation coefficient (MCC), including an estimate of feature importance.

Results

A total of 63 535 individuals (mean [SD] age, 23 [7] years; 34 944 male [55%]; 28 591 female [45%]) were included in the model. Based on data prior to diagnosis, the specific diagnosis was predicted in a multidiagnostic prediction model including the background population with an overall area under the curve (AUC) of 0.81 and MCC of 0.28, whereas the single-disorder models gave AUCs/MCCs of 0.84/0.54 for SCZ, 0.79/0.41 for BD, 0.77/0.39 for ASD, 0.74/0.38, for ADHD, and 0.74/0.38 for MDD. The most important data sets for multidiagnostic prediction were previous mental disorders and age (11%-23% reduction in prediction accuracy when removed) followed by family diagnoses, birth-related measurements, and genetic data (3%-5% reduction in prediction accuracy when removed). Furthermore, when predicting subsequent disease trajectories of the disorder, the most severe cases were the most easily predictable, with an AUC of 0.72.

Conclusions and Relevance

Results of this diagnostic study suggest the possibility of combining genetics and registry data to predict both mental disorder diagnosis and disorder progression in a clinically relevant, cross-diagnostic setting prior to clinical assessment.

Multi-omics data integration methods and their applications in psychiatric disorders

To study mental illness and health, in the past researchers have often broken down their complexity into individual subsystems (e.g., genomics, transcriptomics, proteomics, clinical data) and explored the components independently. Technological advancements and decreasing costs of high throughput sequencing has led to an unprecedented increase in data generation. Furthermore, over the years it has become increasingly clear that these subsystems do not act in isolation but instead interact with each other to drive mental illness and health. Consequently, individual subsystems are now analysed jointly to promote a holistic understanding of the underlying biological complexity of health and disease. Complementing the increasing data availability, current research is geared towards developing novel methods that can efficiently combine the information rich multi-omics data to discover biologically meaningful biomarkers for diagnosis, treatment, and prognosis. However, clinical translation of the research is still challenging. In this review, we summarise conventional and state-of-the-art statistical and machine learning approaches for discovery of biomarker, diagnosis, as well as outcome and treatment response prediction through integrating multi-omics and clinical data. In addition, we describe the role of biological model systems and in silico multi-omics model designs in clinical translation of psychiatric research from bench to bedside. Finally, we discuss the current challenges and explore the application of multi-omics integration in future psychiatric research. The review provides a structured overview and latest updates in the field of multi-omics in psychiatry.

The development and internal evaluation of a predictive model to identify for whom Mindfulness-Based Cognitive Therapy (MBCT) offers superior relapse prevention for recurrent depression versus maintenance antidepressant medication

Depression is highly recurrent, even following successful pharmacological and/or psychological intervention. We aimed to develop clinical prediction models to inform adults with recurrent depression choosing between antidepressant medication (ADM) maintenance or switching to Mindfulness-Based Cognitive Therapy (MBCT). Using data from the PREVENT trial (N=424), we constructed prognostic models using elastic net regression that combined demographic, clinical and psychological factors to predict relapse at 24 months under ADM or MBCT. Only the ADM model (discrimination performance: AUC=.68) predicted relapse better than baseline depression severity (AUC=.54; one-tailed DeLong's test: z=2.8, p=.003). Individuals with the poorest ADM prognoses who switched to MBCT had better outcomes compared to those who maintained ADM (48% vs. 70% relapse, respectively; superior survival times [z=-2.7, p=.008]). For individuals with moderate-to-good ADM prognosis, both treatments resulted in similar likelihood of relapse. If replicated, the results suggest that predictive modeling can inform clinical decision-making around relapse prevention in recurrent depression.

Replication of a predictive model for youth ADHD in an independent sample from a developing country

BACKGROUND

Very few predictive models in Psychiatry had their performance validated in independent external samples. A previously developed multivariable demographic model for attention-deficit/hyperactivity disorder (ADHD) accurately predicted young adulthood ADHD using clinical and demographical information collected in childhood in three samples from developed countries, but failed to replicate its performance in a sample from a developing country. Furthermore, consolidated risk factors for ADHD were not included among its predictors.

METHODS

Participants were 1905 children and adolescents from a community-based sample and followed from ages 6 to 14 years at baseline to ages 14 to 23 years (mean age 18) at follow-up. We applied the intercept and weights of the original model to the data, calculating the predicted probability of each participant according to the set of predictors collected in childhood, and compared the estimates with the actual outcome (ADHD) collected during adolescence and young adulthood. We explored the performance of the original model, and of models including novel predictors (prematurity, family history of ADHD, and polygenic risk score for ADHD).

RESULTS

The observed area under the curve of the original model was .76 (95% Confidence Interval .70 to .82). The multivariable demographical model outperformed single variable models using only prematurity, family history, or the ADHD PRS. Adding either of these variables, or all at once, did not improve the performance of the original demographical model.

CONCLUSIONS

Our findings suggest that the originally developed ADHD predictive model is suitable for use in different settings for clinical and research purposes.

Delirium screening in an acute care setting with a machine learning classifier based on routinely collected nursing data: A model development study

Delirium screening in acute care settings is a resource intensive process with frequent deviations from screening protocols. A predictive model relying only on daily collected nursing data for delirium screening could expand the populations covered by such screening programs. Here, we present the results of the development and validation of a series of machine-learning based delirium prediction models. For this purpose, we used data of all patients 18 years or older which were hospitalized for more than a day between January 1, 2014, and December 31, 2018, at a single tertiary teaching hospital in Zurich, Switzerland. A total of 48,840 patients met inclusion criteria. 18,873 (38.6%) were excluded due to missing data. Mean age (SD) of the included 29,967 patients was 71.1 (12.2) years and 12,231 (40.8%) were women. Delirium was assessed with the Delirium Observation Scale (DOS) with a total score of 3 or greater indicating that a patient is at risk for delirium. Additional measures included structured data collected for nursing process planning and demographic characteristics. The performance of the machine learning models was assessed using the area under the receiver operating characteristic curve (AUC). The training set consisted of 21,147 patients (mean age 71.1 (12.1) years; 8,630 (40.8%) women|) including 233,024 observations with 16,167 (6.9%) positive DOS screens. The test set comprised 8,820 patients (median age 71.1 (12.4) years; 3,601 (40.8%) women) with 91,026 observations with 5,445 (6.0%) positive DOS screens. Overall, the gradient boosting machine model performed best with an AUC of 0.933 (95% CI, 0.929 - 0.936). In conclusion, machine learning models based only on structured nursing data can reliably predict patients at risk for delirium in an acute care setting. Prediction models, using existing data collection processes, could reduce the resources required for delirium screening procedures in clinical practice.

Development and validation of a prognostic model for the early identification of COVID-19 patients at risk of developing common long COVID symptoms

BACKGROUND

The coronavirus disease 2019 (COVID-19) pandemic demands reliable prognostic models for estimating the risk of long COVID. We developed and validated a prediction model to estimate the probability of known common long COVID symptoms at least 60 days after acute COVID-19.

METHODS

The prognostic model was built based on data from a multicentre prospective Swiss cohort study. Included were adult patients diagnosed with COVID-19 between February and December 2020 and treated as outpatients, at ward or intensive/intermediate care unit. Perceived long-term health impairments, including reduced exercise tolerance/reduced resilience, shortness of breath and/or tiredness (REST), were assessed after a follow-up time between 60 and 425 days. The data set was split into a derivation and a geographical validation cohort. Predictors were selected out of twelve candidate predictors based on three methods, namely the augmented backward elimination (ABE) method, the adaptive best-subset selection (ABESS) method and model-based recursive partitioning (MBRP) approach. Model performance was assessed with the scaled Brier score, concordance c statistic and calibration plot. The final prognostic model was determined based on best model performance.

RESULTS

In total, 2799 patients were included in the analysis, of which 1588 patients were in the derivation cohort and 1211 patients in the validation cohort. The REST prevalence was similar between the cohorts with 21.6% (n = 343) in the derivation cohort and 22.1% (n = 268) in the validation cohort. The same predictors were selected with the ABE and ABESS approach. The final prognostic model was based on the ABE and ABESS selected predictors. The corresponding scaled Brier score in the validation cohort was 18.74%, model discrimination was 0.78 (95% CI: 0.75 to 0.81), calibration slope was 0.92 (95% CI: 0.78 to 1.06) and calibration intercept was -0.06 (95% CI: -0.22 to 0.09).

CONCLUSION

The proposed model was validated to identify COVID-19-infected patients at high risk for REST symptoms. Before implementing the prognostic model in daily clinical practice, the conduct of an impact study is recommended.

Psychotic relapse in people with schizophrenia within 12 months of discharge from acute inpatient care: protocol for development and validation of a prediction model based on a retrospective cohort study in three psychiatric hospitals in Japan

BACKGROUND

Schizophrenia is a severe mental illness characterized by recurrent psychoses that typically waxes and wanes through its prodromal, acute, and chronic phases. A large amount of research on individual prognostic factors for relapse in people with schizophrenia has been published, and a few logistic models exist to predict psychotic prognosis for people in the prodromal phase or after the first episode of psychosis. However, research on prediction models for people with schizophrenia, including those in the chronic phase and after multiple recurrences, is scarce. We aim to develop and validate a prediction model for this population.

METHODS

This is a retrospective cohort study to be undertaken in Japan. We will include participants aged 18 years or above, diagnosed with schizophrenia or related disorders, and discharged between January 2014 and December 2018 from one of the acute inpatient care wards of three geographically distinct psychiatric hospitals. We will collect pre-specified nine predictors at the time of recruitment, follow up the participants for 12 months after discharge, and observe whether our primary outcome of a relapse occurs. Relapse will be considered to have occurred in one of the following circumstances: (1) hospitalization; (2) psychiatrist's judgment that the person needs hospitalization; (3) increasing doses of antipsychotics; or (4) suicidal or homicidal ideation or behavior resulting from such ideation. We will develop a Cox regression model and avoid overfitting by penalizing coefficients using the elastic net. The model will be validated both internally and externally by bootstrapping and "leave-one-hospital-out" cross-validation, respectively. We will evaluate the model's performance in terms of discrimination and calibration. Decision curve analysis will be presented to aid decision-making. We will present a web application to visualize the model for ease of use in daily practice.

DISCUSSION

This will be the first prediction modeling study of relapse after discharge among people with both first and multiple episodes of schizophrenia using routinely collected data.

TRIAL REGISTRATION

This study was registered in the UMIN-CTR (UMIN000043345) on February 20, 2021.

Affective symptom dimensions in early-onset psychosis over time: a principal component factor analysis of the Young Mania Rating Scale and the Hamilton Depression Rating Scale

Early-onset psychosis (EOP) is a complex disorder characterized by a wide range of symptoms, including affective symptoms. Our aim was to (1) examine the dimensional structure of affective symptoms in EOP, (2) evaluate the predominance of the clinical dimensions and (3) assess the progression of the clinical dimensions over a 2-year period. STROBE-compliant prospective principal component factor analysis of Young Mania Rating Scale (YMRS) and Hamilton Depression Rating Scale-21 (HDRS-21) at baseline, 6-months, 1-year and 2-year follow-up. We included 108 EOP individuals (mean age = 15.5 ± 1.8 years, 68.5% male). The factor analysis produced a four-factor model including the following dimensions: mania, depression/anxiety, sleep and psychosis. It explained 47.4% of the total variance at baseline, 60.6% of the total variance at 6-months follow-up, 54.5% of the total variance at 1-year follow-up and 49.5% of the total variance at 2-year follow-up. According to the variance explained, the mania factor was predominant at baseline (17.4%), 6-month follow-up (23.5%) and 2-year follow-up (26.1%), while the depression/anxiety factor was predominant at 1-year follow-up (23.1%). The mania factor was the most stable; 58.3% items that appeared in this factor (with a load > 0.4) at any time point appeared in the same factor at ≥ 3/4 time points. Affective symptoms are frequent and persistent in EOP. Mania seems to be the most predominant and stable affective dimension. However, depression and anxiety may gain predominance with time. A comprehensive evaluation of the dimensional structure and the progression of affective symptoms may offer clinical and therapeutic advantages.

The promise of a model-based psychiatry: building computational models of mental ill health

Computational models have great potential to revolutionise psychiatry research and clinical practice. These models are now used across multiple subfields, including computational psychiatry and precision psychiatry. Their goals vary from understanding mechanisms underlying disorders to deriving reliable classification and personalised predictions. Rapid growth of new tools and data sources (eg, digital data, gamification, and social media) requires an understanding of the constraints and advantages of different modelling approaches in psychiatry. In this Series paper, we take a critical look at the range of computational models that are used in psychiatry and evaluate their advantages and disadvantages for different purposes and data sources. We describe mechanism-driven and mechanism-agnostic computational models and discuss how interpretability of models is crucial for clinical translation. Based on these evaluations, we provide recommendations on how to build computational models that are clinically useful.

Identifying adolescents at risk for depression: Assessment of a global prediction model in the Great Smoky Mountains Study

The Identifying Depression Early in Adolescence Risk Score (IDEA-RS) has been externally assessed in samples from four continents, but North America is lacking. Our aim here was to evaluate the performance of the IDEA-RS in predicting future onset of Major Depressive Disorder (MDD) in an adolescent population-based sample in the United States of America - the Great Smoky Mountains Study (GSMS). We applied the intercept and weights of the original IDEA-RS model developed in Brazil to generate individual probabilities for each participant of the GSMS at age 15 (N = 1029). We then evaluated the performance of such predictions against the diagnosis of MDD at age 19 using simple, case-mix corrected and refitted models. Furthermore, we compared how prioritizing the information provided by parents or by adolescents affected performance. The IDEA-RS exhibited a C-statistic of 0.63 (95% CI 0.53-0.74) to predict MDD in the GSMS when applying uncorrected weights. Case-mix corrected and refitted models enhanced performance to 0.69 and 0.67, respectively. No significant difference was found in performance by prioritizing the reports of adolescents or their parents. The IDEA-RS was able to parse out adolescents at risk for a later onset of depression in the GSMS cohort with above chance discrimination. The IDEA-RS has now showed above-chance performance in five continents.

The performance of machine learning models in predicting suicidal ideation, attempts, and deaths: A meta-analysis and systematic review

Research has posited that machine learning could improve suicide risk prediction models, which have traditionally performed poorly. This systematic review and meta-analysis evaluated the performance of machine learning models in predicting longitudinal outcomes of suicide-related outcomes of ideation, attempt, and death and examines outcome, data, and model types as potential covariates of model performance. Studies were extracted from PubMed, Web of Science, Embase, and PsycINFO. A bivariate mixed effects meta-analysis and meta-regression analyses were performed for studies using machine learning to predict future events of suicidal ideation, attempts, and/or deaths. Risk of bias was assessed for each study using an adaptation of the Prediction model Risk Of Bias Assessment Tool. Narrative review included 56 studies, and analyses examined 54 models from 35 studies. The models achieved a very good pooled AUC of 0.86, sensitivity of 0.66 (95% CI [0.60, 0.72)], and specificity of 0.87 (95% CI [0.84, 0.90]). Pooled AUCs for ideation, attempt, and death were similar at 0.88, 0.87, and 0.84 respectively. Model performance was highly varied; however, meta-regressions did not provide evidence that performance varied by outcome, data, or model types. Findings suggest that machine learning has the potential to improve suicide risk detection, with pooled estimates of machine learning performance comparing favourably to performance of traditional suicide prediction models. However, more studies with lower risk of bias are necessary to improve the application of machine learning in suicidology.

State-dependent reductions of local brain connectivity in schizophrenia and their relation to performance and symptoms: A functional magnetic resonance imaging study

State-dependent reallocation of cognitive resources is impaired in schizophrenia and may be underlined by alterations in brain local-connectivity. Increasing evidence suggests local connectivity reductions from rest to task in healthy individuals, while insufficient information is available for schizophrenia spectrum. Resting-state and stop-signal task fMRI scans of 107 healthy controls and 32 patients with DSM-IV-TR schizophrenia or schizoaffective disorder were analyzed. As primary aim we measured within-group shifts in local-connectivity from rest to task as voxel-wise Regional Homogeneity (ReHo-shift). Secondary aims were to test: i) Between-groups differences in ReHo-rest, ReHo-task and ReHo-shift; ii) ReHo covariations with task performance (=shorter reaction times) and severity of symptoms (SAPS/SANS scores). Age, sex, and education were accounted for as covariates. Motion, global-signal-regression, antipsychotic dosage and smoothing associations with ReHo were evaluated. Rest-to-task ReHo reductions occurred in both groups on a whole-brain level (False-Discovery-Rate p=0.05). Trends of greater ReHo reductions in patients versus controls were observed. Controls performed better than patients (p<0.001). ReHo negatively correlated with performance in both groups. ReHo-shift predicted worse performance in controls, but better performance in patients (uncorrected p=0.05). ReHo reductions correlated with severity of symptoms. State-dependent reconfigurations in local-connectivity provide new links between neurobiology and behavioral/clinical features of the schizophrenia spectrum.