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.

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.

Development of the PSYCHS: Positive SYmptoms and Diagnostic Criteria for the CAARMS Harmonized with the SIPS

AIM

To harmonize two ascertainment and severity rating instruments commonly used for the clinical high risk syndrome for psychosis (CHR-P): the Structured Interview for Psychosis-risk Syndromes (SIPS) and the Comprehensive Assessment of At-Risk Mental States (CAARMS).

METHODS

The initial workshop is described in the companion report from Addington et al. After the workshop, lead experts for each instrument continued harmonizing attenuated positive symptoms and criteria for psychosis and CHR-P through an intensive series of joint videoconferences.

RESULTS

Full harmonization was achieved for attenuated positive symptom ratings and psychosis criteria, and modest harmonization for CHR-P criteria. The semi-structured interview, named Positive SYmptoms and Diagnostic Criteria for the CAARMS Harmonized with the SIPS (PSYCHS), generates CHR-P criteria and severity scores for both CAARMS and SIPS.

CONCLUSIONS

Using the PSYCHS for CHR-P ascertainment, conversion determination, and attenuated positive symptom severity rating will help in comparing findings across studies and in meta-analyses.

Distinct multimodal biological and functional profiles of symptom-based subgroups in recent-onset psychosis

Symptom heterogeneity characterizes psychotic disorders and hinders the delineation of underlying biomarkers. Here, we identify symptom-based subtypes of recent-onset psychosis (ROP) patients from the multi-center PRONIA (Personalized Prognostic Tools for Early Psychosis Management) database and explore their multimodal biological and functional signatures. We clustered N = 328 ROP patients based on their maximum factor scores in an exploratory factor analysis on the Positive and Negative Syndrome Scale items. We assessed inter-subgroup differences and compared to N = 464 healthy control (HC) individuals regarding gray matter volume (GMV), neurocognition, polygenic risk scores, and longitudinal functioning trajectories. Finally, we evaluated factor stability at 9- and 18-month follow-ups. A 4-factor solution optimally explained symptom heterogeneity, showing moderate longitudinal stability. The ROP-MOTCOG (Motor/Cognition) subgroup was characterized by GMV reductions within salience, control and default mode networks, predominantly throughout cingulate regions, relative to HC individuals, had the most impaired neurocognition and the highest genetic liability for schizophrenia. ROP-SOCWD (Social Withdrawal) patients showed GMV reductions within medial fronto-temporal regions of the control, default mode, and salience networks, and had the lowest social functioning across time points. ROP-POS (Positive) evidenced GMV decreases in salience, limbic and frontal regions of the control and default mode networks. The ROP-AFF (Affective) subgroup showed GMV reductions in the salience, limbic, and posterior default-mode and control networks, thalamus and cerebellum. GMV reductions in fronto-temporal regions of the salience and control networks were shared across subgroups. Our results highlight the existence of behavioral subgroups with distinct neurobiological and functional profiles in early psychosis, emphasizing the need for refined symptom-based diagnosis and prognosis frameworks.

Alterations of Functional Connectivity Dynamics in Affective and Psychotic Disorders

BACKGROUND

Psychosis and depression patients exhibit widespread neurobiological abnormalities. The analysis of dynamic functional connectivity (dFC), allows for the detection of changes in complex brain activity patterns, providing insights into common and unique processes underlying these disorders.

METHODS

In the present study, we report the analysis of dFC in a large patient sample including 127 clinical high-risk patients (CHR), 142 recent-onset psychosis (ROP) patients, 134 recent-onset depression (ROD) patients, and 256 healthy controls (HC). A sliding window-based technique was used to calculate the time-dependent FC in resting-state MRI data, followed by clustering to reveal recurrent FC states in each diagnostic group.

RESULTS

We identified five unique FC states, which could be identified in all groups with high consistency (rmean = 0.889, sd = 0.116). Analysis of dynamic parameters of these states showed a characteristic increase in the lifetime and frequency of a weakly-connected FC state in ROD patients (p < 0.0005) compared to most other groups, and a common increase in the lifetime of a FC state characterised by high sensorimotor and cingulo-opercular connectivities in all patient groups compared to the HC group (p < 0.0002). Canonical correlation analysis revealed a mode which exhibited significant correlations between dFC parameters and clinical variables (r = 0.617, p < 0.0029), which was associated with positive psychosis symptom severity and several dFC parameters.

CONCLUSIONS

Our findings indicate diagnosis-specific alterations of dFC and underline the potential of dynamic analysis to characterize disorders such as depression, psychosis and clinical risk states.

Classifying autism in a clinical population based on motion synchrony: a proof-of-concept study using real-life diagnostic interviews

Predictive modeling strategies are increasingly studied as a means to overcome clinical bottlenecks in the diagnostic classification of autism spectrum disorder. However, while some findings are promising in the light of diagnostic marker research, many of these approaches lack the scalability for adequate and effective translation to everyday clinical practice. In this study, our aim was to explore the use of objective computer vision video analysis of real-world autism diagnostic interviews in a clinical sample of children and young individuals in the transition to adulthood to predict diagnosis. Specifically, we trained a support vector machine learning model on interpersonal synchrony data recorded in Autism Diagnostic Observation Schedule (ADOS-2) interviews of patient-clinician dyads. Our model was able to classify dyads involving an autistic patient (n = 56) with a balanced accuracy of 63.4% against dyads including a patient with other psychiatric diagnoses (n = 38). Further analyses revealed no significant associations between our classification metrics with clinical ratings. We argue that, given the above-chance performance of our classifier in a highly heterogeneous sample both in age and diagnosis, with few adjustments this highly scalable approach presents a viable route for future diagnostic marker research in autism.

Deep Learning-Based Retinal Layer Segmentation in Optical Coherence Tomography Scans of Patients with Inherited Retinal Diseases

BACKGROUND

In optical coherence tomography (OCT) scans of patients with inherited retinal diseases (IRDs), the measurement of the thickness of the outer nuclear layer (ONL) has been well established as a surrogate marker for photoreceptor preservation. Current automatic segmentation tools fail in OCT segmentation in IRDs, and manual segmentation is time-consuming.

METHODS AND MATERIAL

Patients with IRD and an available OCT scan were screened for the present study. Additionally, OCT scans of patients without retinal disease were included to provide training data for artificial intelligence (AI). We trained a U-net-based model on healthy patients and applied a domain adaption technique to the IRD patients' scans.

RESULTS

We established an AI-based image segmentation algorithm that reliably segments the ONL in OCT scans of IRD patients. In a test dataset, the dice score of the algorithm was 98.7%. Furthermore, we generated thickness maps of the full retinal thickness and the ONL layer for each patient.

CONCLUSION

Accurate segmentation of anatomical layers on OCT scans plays a crucial role for predictive models linking retinal structure to visual function. Our algorithm for segmentation of OCT images could provide the basis for further studies on IRDs.

Machine learning classification of autism spectrum disorder based on reciprocity in naturalistic social interactions

Autism spectrum disorder is characterized by impaired social communication and interaction. As a neurodevelopmental disorder typically diagnosed during childhood, diagnosis in adulthood is preceded by a resource-heavy clinical assessment period. The ongoing developments in digital phenotyping give rise to novel opportunities within the screening and diagnostic process. Our aim was to quantify multiple non-verbal social interaction characteristics in autism and build diagnostic classification models independent of clinical ratings. We analyzed videos of naturalistic social interactions in a sample including 28 autistic and 60 non-autistic adults paired in dyads and engaging in two conversational tasks. We used existing open-source computer vision algorithms for objective annotation to extract information based on the synchrony of movement and facial expression. These were subsequently used as features in a support vector machine learning model to predict whether an individual was part of an autistic or non-autistic interaction dyad. The two prediction models based on reciprocal adaptation in facial movements, as well as individual amounts of head and body motion and facial expressiveness showed the highest precision (balanced accuracies: 79.5% and 68.8%, respectively), followed by models based on reciprocal coordination of head (balanced accuracy: 62.1%) and body (balanced accuracy: 56.7%) motion, as well as intrapersonal coordination processes (balanced accuracy: 44.2%). Combinations of these models did not increase overall predictive performance. Our work highlights the distinctive nature of non-verbal behavior in autism and its utility for digital phenotyping-based classification. Future research needs to both explore the performance of different prediction algorithms to reveal underlying mechanisms and interactions, as well as investigate the prospective generalizability and robustness of these algorithms in routine clinical care.

Algorithmic fairness in precision psychiatry: analysis of prediction models in individuals at clinical high risk for psychosis

BACKGROUND

Computational models offer promising potential for personalised treatment of psychiatric diseases. For their clinical deployment, fairness must be evaluated alongside accuracy. Fairness requires predictive models to not unfairly disadvantage specific demographic groups. Failure to assess model fairness prior to use risks perpetuating healthcare inequalities. Despite its importance, empirical investigation of fairness in predictive models for psychiatry remains scarce.

AIMS

To evaluate fairness in prediction models for development of psychosis and functional outcome.

METHOD

Using data from the PRONIA study, we examined fairness in 13 published models for prediction of transition to psychosis (n = 11) and functional outcome (n = 2) in people at clinical high risk for psychosis or with recent-onset depression. Using accuracy equality, predictive parity, false-positive error rate balance and false-negative error rate balance, we evaluated relevant fairness aspects for the demographic attributes 'gender' and 'educational attainment' and compared them with the fairness of clinicians' judgements.

RESULTS

Our findings indicate systematic bias towards assigning less favourable outcomes to individuals with lower educational attainment in both prediction models and clinicians' judgements, resulting in higher false-positive rates in 7 of 11 models for transition to psychosis. Interestingly, the bias patterns observed in algorithmic predictions were not significantly more pronounced than those in clinicians' predictions.

CONCLUSIONS

Educational bias was present in algorithmic and clinicians' predictions, assuming more favourable outcomes for individuals with higher educational level (years of education). This bias might lead to increased stigma and psychosocial burden in patients with lower educational attainment and suboptimal psychosis prevention in those with higher educational attainment.

Transdiagnostic subgroups of cognitive impairment in early affective and psychotic illness

Cognitively impaired and spared patient subgroups were identified in psychosis and depression, and in clinical high-risk for psychosis (CHR). Studies suggest differences in underlying brain structural and functional characteristics. It is unclear whether cognitive subgroups are transdiagnostic phenomena in early stages of psychotic and affective disorder which can be validated on the neural level. Patients with recent-onset psychosis (ROP; N = 140; female = 54), recent-onset depression (ROD; N = 130; female = 73), CHR (N = 128; female = 61) and healthy controls (HC; N = 270; female = 165) were recruited through the multi-site study PRONIA. The transdiagnostic sample and individual study groups were clustered into subgroups based on their performance in eight cognitive domains and characterized by gray matter volume (sMRI) and resting-state functional connectivity (rsFC) using support vector machine (SVM) classification. We identified an impaired subgroup (NROP = 79, NROD = 30, NCHR = 37) showing cognitive impairment in executive functioning, working memory, processing speed and verbal learning (all p < 0.001). A spared subgroup (NROP = 61, NROD = 100, NCHR = 91) performed comparable to HC. Single-disease subgroups indicated that cognitive impairment is stronger pronounced in impaired ROP compared to impaired ROD and CHR. Subgroups in ROP and ROD showed specific symptom- and functioning-patterns. rsFC showed superior accuracy compared to sMRI in differentiating transdiagnostic subgroups from HC (BACimpaired = 58.5%; BACspared = 61.7%, both: p < 0.01). Cognitive findings were validated in the PRONIA replication sample (N = 409). Individual cognitive subgroups in ROP, ROD and CHR are more informative than transdiagnostic subgroups as they map onto individual cognitive impairment and specific functioning- and symptom-patterns which show limited overlap in sMRI and rsFC. CLINICAL TRIAL REGISTRY NAME: German Clinical Trials Register (DRKS). Clinical trial registry URL: https://www.drks.de/drks_web/ . Clinical trial registry number: DRKS00005042.

Illusory generalizability of clinical prediction models

It is widely hoped that statistical models can improve decision-making related to medical treatments. Because of the cost and scarcity of medical outcomes data, this hope is typically based on investigators observing a model's success in one or two datasets or clinical contexts. We scrutinized this optimism by examining how well a machine learning model performed across several independent clinical trials of antipsychotic medication for schizophrenia. Models predicted patient outcomes with high accuracy within the trial in which the model was developed but performed no better than chance when applied out-of-sample. Pooling data across trials to predict outcomes in the trial left out did not improve predictions. These results suggest that models predicting treatment outcomes in schizophrenia are highly context-dependent and may have limited generalizability.

A multivariate cognitive approach to predict social functioning in recent onset psychosis in response to computerized cognitive training

Clinical and neuroimaging data has been increasingly used in recent years to disentangle heterogeneity of treatment response to cognitive training (CT) and predict which individuals may achieve the highest benefits. CT has small to medium effects on improving cognitive and social functioning in recent onset psychosis (ROP) patients, who show the most profound cognitive and social functioning deficits among psychiatric patients. We employed multivariate pattern analysis (MVPA) to investigate the potential of cognitive data to predict social functioning improvement in response to 10 h of CT in patients with ROP. A support vector machine (SVM) classifier was trained on the naturalistic data of the Personalized Prognostic Tools for Early Psychosis Management (PRONIA) study sample to predict functioning in an independent sample of 70 ROP patients using baseline cognitive data. PRONIA is a part of a FP7 EU grant program that involved 7 sites across 5 European countries, designed and conducted with the main aim of identifying (bio)markers associated with an enhanced risk of developing psychosis in order to improve early detection and prognosis. Social functioning was predicted with a balanced accuracy (BAC) of 66.4% (Sensitivity 78.8%; Specificity 54.1%; PPV 60.5%; NPV 74.1%; AUC 0.64; P = 0.01). The most frequently selected cognitive features (mean feature weights > ± 0.2) included the (1) correct number of symbol matchings within the Digit Symbol Substitution Test, (2) the number of distracting stimuli leading to an error within 300 and 200 trials in the Continuous Performance Test and (3) the dynamics of verbal fluency between 15 and 30 s within the Verbal Fluency Test, phonetic part. Next, the SVM classifier generated on the PRONIA sample was applied to the intervention sample, that obtained 54 ROP patients who were randomly assigned to a social cognitive training (SCT) or treatment as usual (TAU) group and dichotomized into good (GF-S ≥ 7) and poor (GF-S < 7) functioning patients based on their level of Global Functioning-Social (GF-S) score at follow-up (FU). By applying the initial PRONIA classifier, using out-of-sample cross-validation (OOCV) to the sample of ROP patients who have undergone the CT intervention, a BAC of 59.3% (Sensitivity 70.4%; Specificity 48.1%; PPV 57.6%; NPV 61.9%; AUC 0.63) was achieved at T0 and a BAC of 64.8% (Sensitivity 66.7%; Specificity 63.0%; PPV 64.3%; NPV 65.4%; AUC 0.66) at FU. After SCT intervention, a significant improvement in predicted social functioning values was observed in the SCT compared to TAU group (P ≤0.05; ES[Cohens' d] = 0.18). Due to a small sample size and modest variance of social functioning of the intervention sample it was not feasible to predict individual response to SCT in the current study. Our findings suggest that the use of baseline cognitive data could provide a robust individual estimate of future social functioning, while prediction of individual response to SCT using cognitive data that can be generated in the routine patient care remains to be addressed in large-scale cognitive training trials.

Five dominant dimensions of brain aging are identified via deep learning: associations with clinical, lifestyle, and genetic measures

Brain aging is a complex process influenced by various lifestyle, environmental, and genetic factors, as well as by age-related and often co-existing pathologies. MRI and, more recently, AI methods have been instrumental in understanding the neuroanatomical changes that occur during aging in large and diverse populations. However, the multiplicity and mutual overlap of both pathologic processes and affected brain regions make it difficult to precisely characterize the underlying neurodegenerative profile of an individual from an MRI scan. Herein, we leverage a state-of-the art deep representation learning method, Surreal-GAN, and present both methodological advances and extensive experimental results that allow us to elucidate the heterogeneity of brain aging in a large and diverse cohort of 49,482 individuals from 11 studies. Five dominant patterns of neurodegeneration were identified and quantified for each individual by their respective (herein referred to as) R-indices. Significant associations between R-indices and distinct biomedical, lifestyle, and genetic factors provide insights into the etiology of observed variances. Furthermore, baseline R-indices showed predictive value for disease progression and mortality. These five R-indices contribute to MRI-based precision diagnostics, prognostication, and may inform stratification into clinical trials.

Genomic loci influence patterns of structural covariance in the human brain

Normal and pathologic neurobiological processes influence brain morphology in coordinated ways that give rise to patterns of structural covariance (PSC) across brain regions and individuals during brain aging and diseases. The genetic underpinnings of these patterns remain largely unknown. We apply a stochastic multivariate factorization method to a diverse population of 50,699 individuals (12 studies and 130 sites) and derive data-driven, multi-scale PSCs of regional brain size. PSCs were significantly correlated with 915 genomic loci in the discovery set, 617 of which are newly identified, and 72% were independently replicated. Key pathways influencing PSCs involve reelin signaling, apoptosis, neurogenesis, and appendage development, while pathways of breast cancer indicate potential interplays between brain metastasis and PSCs associated with neurodegeneration and dementia. Using support vector machines, multi-scale PSCs effectively derive imaging signatures of several brain diseases. Our results elucidate genetic and biological underpinnings that influence structural covariance patterns in the human brain.

Structural and Functional Brain Patterns Predict Formal Thought Disorder's Severity and Its Persistence in Recent-Onset Psychosis: Results From the PRONIA Study

BACKGROUND

Formal thought disorder (FThD) is a core feature of psychosis, and its severity and long-term persistence relates to poor clinical outcomes. However, advances in developing early recognition and management tools for FThD are hindered by a lack of insight into the brain-level predictors of FThD states and progression at the individual level.

METHODS

Two hundred thirty-three individuals with recent-onset psychosis were drawn from the multisite European Prognostic Tools for Early Psychosis Management study. Support vector machine classifiers were trained within a cross-validation framework to separate two FThD symptom-based subgroups (high vs. low FThD severity), using cross-sectional whole-brain multiband fractional amplitude of low frequency fluctuations, gray matter volume and white matter volume data. Moreover, we trained machine learning models on these neuroimaging readouts to predict the persistence of high FThD subgroup membership from baseline to 1-year follow-up.

RESULTS

Cross-sectionally, multivariate patterns of gray matter volume within the salience, dorsal attention, visual, and ventral attention networks separated the FThD severity subgroups (balanced accuracy [BAC] = 60.8%). Longitudinally, distributed activations/deactivations within all fractional amplitude of low frequency fluctuation sub-bands (BACslow-5 = 73.2%, BACslow-4 = 72.9%, BACslow-3 = 68.0%), gray matter volume patterns overlapping with the cross-sectional ones (BAC = 62.7%), and smaller frontal white matter volume (BAC = 73.1%) predicted the persistence of high FThD severity from baseline to follow-up, with a combined multimodal balanced accuracy of BAC = 77%.

CONCLUSIONS

We report the first evidence of brain structural and functional patterns predictive of FThD severity and persistence in early psychosis. These findings open up avenues for the development of neuroimaging-based diagnostic, prognostic, and treatment options for the early recognition and management of FThD and associated poor outcomes.

Automated extraction of speech and turn-taking parameters in autism allows for diagnostic classification using a multivariable prediction model

Autism spectrum disorder (ASD) is diagnosed on the basis of speech and communication differences, amongst other symptoms. Since conversations are essential for building connections with others, it is important to understand the exact nature of differences between autistic and non-autistic verbal behaviour and evaluate the potential of these differences for diagnostics. In this study, we recorded dyadic conversations and used automated extraction of speech and interactional turn-taking features of 54 non-autistic and 26 autistic participants. The extracted speech and turn-taking parameters showed high potential as a diagnostic marker. A linear support vector machine was able to predict the dyad type with 76.2% balanced accuracy (sensitivity: 73.8%, specificity: 78.6%), suggesting that digitally assisted diagnostics could significantly enhance the current clinical diagnostic process due to their objectivity and scalability. In group comparisons on the individual and dyadic level, we found that autistic interaction partners talked slower and in a more monotonous manner than non-autistic interaction partners and that mixed dyads consisting of an autistic and a non-autistic participant had increased periods of silence, and the intensity, i.e. loudness, of their speech was more synchronous.

Prevalence of cognitive impairments and strengths in the early course of psychosis and depression

BACKGROUND

Studies investigating cognitive impairments in psychosis and depression have typically compared the average performance of the clinical group against healthy controls (HC), and do not report on the actual prevalence of cognitive impairments or strengths within these clinical groups. This information is essential so that clinical services can provide adequate resources to supporting cognitive functioning. Thus, we investigated this prevalence in individuals in the early course of psychosis or depression.

METHODS

A comprehensive cognitive test battery comprising 12 tests was completed by 1286 individuals aged 15-41 (mean age 25.07, s.d. 5.88) from the PRONIA study at baseline: HC (N = 454), clinical high risk for psychosis (CHR; N = 270), recent-onset depression (ROD; N = 267), and recent-onset psychosis (ROP; N = 295). Z-scores were calculated to estimate the prevalence of moderate or severe deficits or strengths (>2 s.d. or 1-2 s.d. below or above HC, respectively) for each cognitive test.

RESULTS

Impairment in at least two cognitive tests was as follows: ROP (88.3% moderately, 45.1% severely impaired), CHR (71.2% moderately, 22.4% severely impaired), ROD (61.6% moderately, 16.2% severely impaired). Across clinical groups, impairments were most prevalent in tests of working memory, processing speed, and verbal learning. Above average performance (>1 s.d.) in at least two tests was present for 40.5% ROD, 36.1% CHR, 16.1% ROP, and was >2 SDs in 1.8% ROD, 1.4% CHR, and 0% ROP.

CONCLUSIONS

These findings suggest that interventions should be tailored to the individual, with working memory, processing speed, and verbal learning likely to be important transdiagnostic targets.

Neurocognitive skills and vulnerability for psychosis in depression and across the psychotic spectrum: findings from the PRONIA Consortium

BACKGROUND

Neurocognitive deficits are a core feature of psychosis and depression. Despite commonalities in cognitive alterations, it remains unclear if and how the cognitive deficits in patients at clinical high risk for psychosis (CHR) and those with recent-onset psychosis (ROP) are distinct from those seen in recent-onset depression (ROD).

AIMS

This study was carried out within the European project 'Personalized Prognostic Tools for Early Psychosis Management', and aimed to characterise the cognitive profiles of patients with psychosis or depression.

METHOD

We examined cognitive profiles for patients with ROP (n = 105), patients with ROD (n = 123), patients at CHR (n = 116) and healthy controls (n = 372) across seven sites in five European countries. Confirmatory factor analysis identified four cognitive factors independent of gender, education and site: speed of processing, attention and working memory, verbal learning and spatial learning.

RESULTS

Patients with ROP performed worse than healthy controls in all four domains (P < 0.001), whereas performance of patients with ROD was not affected (P > 0.05). Patients at CHR performed worse than healthy controls in speed of processing (P = 0.001) and spatial learning (P = 0.003), but better than patients with ROP across all cognitive domains (all P ≤ 0.01). CHR and ROD groups did not significantly differ in any cognitive domain. These findings were independent of comorbid depressive symptoms, substance consumption and illness duration.

CONCLUSIONS

These results show that neurocognitive abilities are affected in CHR and ROP, whereas ROD seems spared. Although our findings may support the notion that those at CHR have a specific vulnerability to psychosis, future studies investigating broader transdiagnostic risk cohorts in longitudinal designs are needed.

Prevalence of Neuroradiological Abnormalities in First-Episode Psychosis: A Systematic Review and Meta-analysis

Importance

Individuals presenting with first-episode psychosis (FEP) may have a secondary ("organic") etiology to their symptoms that can be identified using neuroimaging. Because failure to detect such cases at an early stage can have serious clinical consequences, it has been suggested that brain magnetic resonance imaging (MRI) should be mandatory for all patients presenting with FEP. However, this remains a controversial issue, partly because the prevalence of clinically relevant MRI abnormalities in this group is unclear.

Objective

To derive a meta-analytic estimate of the prevalence of clinically relevant neuroradiological abnormalities in FEP.

Data Sources

Electronic databases Ovid, MEDLINE, PubMed, Embase, PsychINFO, and Global Health were searched up to July 2021. References and citations of included articles and review articles were also searched.

Study Selection

Magnetic resonance imaging studies of patients with FEP were included if they reported the frequency of intracranial radiological abnormalities.

Data Extraction and Synthesis

Independent extraction was undertaken by 3 researchers and a random-effects meta-analysis of pooled proportions was calculated. Moderators were tested using subgroup and meta-regression analyses. Heterogeneity was evaluated using the I2 index. The robustness of results was evaluated using sensitivity analyses. Publication bias was assessed using funnel plots and Egger tests.

Main Outcomes and Measures

Proportion of patients with a clinically relevant radiological abnormality (defined as a change in clinical management or diagnosis); number of patients needed to scan to detect 1 such abnormality (number needed to assess [NNA]).

Results

Twelve independent studies (13 samples) comprising 1613 patients with FEP were included. Of these patients, 26.4% (95% CI, 16.3%-37.9%; NNA of 4) had an intracranial radiological abnormality, and 5.9% (95% CI, 3.2%-9.0%) had a clinically relevant abnormality, yielding an NNA of 18. There were high degrees of heterogeneity among the studies for these outcomes, 95% to 73%, respectively. The most common type of clinically relevant finding was white matter abnormalities, with a prevalence of 0.9% (95% CI, 0%-2.8%), followed by cysts, with a prevalence of 0.5% (95% CI, 0%-1.4%).

Conclusions and Relevance

This systematic review and meta-analysis found that 5.9% of patients presenting with a first episode of psychosis had a clinically relevant finding on MRI. Because the consequences of not detecting these abnormalities can be serious, these findings support the use of MRI as part of the initial clinical assessment of all patients with FEP.

The heterogeneity of attenuated and brief limited psychotic symptoms: association of contents with age, sex, country, religion, comorbidities, and functioning

Introduction

The Attenuated Psychosis Symptoms (APS) syndrome mostly represents the ultra-high-risk state of psychosis but, as does the Brief Intermittent Psychotic Symptoms (BIPS) syndrome, shows a large variance in conversion rates. This may be due to the heterogeneity of APS/BIPS that may be related to the effects of culture, sex, age, and other psychiatric morbidities. Thus, we investigated the different thematic contents of APS and their association with sex, age, country, religion, comorbidity, and functioning to gain a better understanding of the psychosis-risk syndrome.

Method

A sample of 232 clinical high-risk subjects according to the ultra-high risk and basic symptom criteria was recruited as part of a European study conducted in Germany, Italy, Switzerland, and Finland. Case vignettes, originally used for supervision of inclusion criteria, were investigated for APS/BIPS contents, which were compared for sex, age, country, religion, functioning, and comorbidities using chi-squared tests and regression analyses.

Result

We extracted 109 different contents, mainly of APS (96.8%): 63 delusional, 29 hallucinatory, and 17 speech-disorganized contents. Only 20 contents (18.3%) were present in at least 5% of the sample, with paranoid and referential ideas being the most frequent. Thirty-one (28.5%) contents, in particular, bizarre ideas and perceptual abnormalities, demonstrated an association with age, country, comorbidity, or functioning, with regression models of country and obsessive-compulsive disorders explaining most of the variance: 55.8 and 38.3%, respectively. Contents did not differ between religious groups.

Conclusion

Psychosis-risk patients report a wide range of different contents of APS/BIPS, underlining the psychopathological heterogeneity of this group but also revealing a potential core set of contents. Compared to earlier reports on North-American samples, our maximum prevalence rates of contents were considerably lower; this likely being related to a stricter rating of APS/BIPS and cultural influences, in particular, higher schizotypy reported in North-America. The various associations of some APS/BIPS contents with country, age, comorbidities, and functioning might moderate their clinical severity and, consequently, the related risk for psychosis and/or persistent functional disability.

Serum immune markers and transition to psychosis in individuals at clinical high risk

Individuals at clinical high risk (CHR) for psychosis have been found to have altered cytokine levels, but whether these changes are related to clinical outcomes remains unclear. We addressed this issue by measuring serum levels of 20 immune markers in 325 participants (n = 269 CHR, n = 56 healthy controls) using multiplex immunoassays, and then followed up the CHR sample to determine their clinical outcomes. Among 269 CHR individuals, 50 (18.6 %) developed psychosis by two years. Univariate and machine learning techniques were used to compare levels of inflammatory markers in CHR subjects and healthy controls, and in CHR subjects who had (CHR-t), or had not (CHR-nt) transitioned to psychosis. An ANCOVA identified significant group differences (CHR-t, CHR-nt and controls) and post-hoc tests indicated that VEGF levels and the IL-10/IL-6 ratio were significantly higher in CHR-t than CHR-nt, after adjusting for multiple comparisons. Using a penalised logistic regression classifier, CHR participants were distinguished from controls with an area-under the curve (AUC) of 0.82, with IL-6 and IL-4 levels the most important discriminating features. Transition to psychosis was predicted with an AUC of 0.57, with higher VEGF level and IL-10/IL-6 ratio the most important discriminating features. These data suggest that alterations in the levels of peripheral immune markers are associated with the subsequent onset of psychosis. The association with increased VEGF levels could reflect altered blood-brain-barrier (BBB) permeability, while the link with an elevated IL-10/IL-6 ratio points to an imbalance between anti- and pro-inflammatory cytokines.

Psychosis brain subtypes validated in first-episode cohorts and related to illness remission: results from the PHENOM consortium

Using machine learning, we recently decomposed the neuroanatomical heterogeneity of established schizophrenia to discover two volumetric subgroups-a 'lower brain volume' subgroup (SG1) and an 'higher striatal volume' subgroup (SG2) with otherwise normal brain structure. In this study, we investigated whether the MRI signatures of these subgroups were also already present at the time of the first-episode of psychosis (FEP) and whether they were related to clinical presentation and clinical remission over 1-, 3-, and 5-years. We included 572 FEP and 424 healthy controls (HC) from 4 sites (Sao Paulo, Santander, London, Melbourne) of the PHENOM consortium. Our prior MRI subgrouping models (671 participants; USA, Germany, and China) were applied to both FEP and HC. Participants were assigned into 1 of 4 categories: subgroup 1 (SG1), subgroup 2 (SG2), no subgroup membership ('None'), and mixed SG1 + SG2 subgroups ('Mixed'). Voxel-wise analyses characterized SG1 and SG2 subgroups. Supervised machine learning analyses characterized baseline and remission signatures related to SG1 and SG2 membership. The two dominant patterns of 'lower brain volume' in SG1 and 'higher striatal volume' (with otherwise normal neuromorphology) in SG2 were identified already at the first episode of psychosis. SG1 had a significantly higher proportion of FEP (32%) vs. HC (19%) than SG2 (FEP, 21%; HC, 23%). Clinical multivariate signatures separated the SG1 and SG2 subgroups (balanced accuracy = 64%; p < 0.0001), with SG2 showing higher education but also greater positive psychosis symptoms at first presentation, and an association with symptom remission at 1-year, 5-year, and when timepoints were combined. Neuromorphological subtypes of schizophrenia are already evident at illness onset, separated by distinct clinical presentations, and differentially associated with subsequent remission. These results suggest that the subgroups may be underlying risk phenotypes that could be targeted in future treatment trials and are critical to consider when interpreting neuroimaging literature.

Assessment of Neuroanatomical Endophenotypes of Autism Spectrum Disorder and Association With Characteristics of Individuals With Schizophrenia and the General Population

Importance

Autism spectrum disorder (ASD) is associated with significant clinical, neuroanatomical, and genetic heterogeneity that limits precision diagnostics and treatment.

Objective

To assess distinct neuroanatomical dimensions of ASD using novel semisupervised machine learning methods and to test whether the dimensions can serve as endophenotypes also in non-ASD populations.

Design, Setting, and Participants

This cross-sectional study used imaging data from the publicly available Autism Brain Imaging Data Exchange (ABIDE) repositories as the discovery cohort. The ABIDE sample included individuals diagnosed with ASD aged between 16 and 64 years and age- and sex-match typically developing individuals. Validation cohorts included individuals with schizophrenia from the Psychosis Heterogeneity Evaluated via Dimensional Neuroimaging (PHENOM) consortium and individuals from the UK Biobank to represent the general population. The multisite discovery cohort included 16 internationally distributed imaging sites. Analyses were performed between March 2021 and March 2022.

Main Outcomes and Measures

The trained semisupervised heterogeneity through discriminative analysis models were tested for reproducibility using extensive cross-validations. It was then applied to individuals from the PHENOM and the UK Biobank. It was hypothesized that neuroanatomical dimensions of ASD would display distinct clinical and genetic profiles and would be prominent also in non-ASD populations.

Results

Heterogeneity through discriminative analysis models trained on T1-weighted brain magnetic resonance images of 307 individuals with ASD (mean [SD] age, 25.4 [9.8] years; 273 [88.9%] male) and 362 typically developing control individuals (mean [SD] age, 25.8 [8.9] years; 309 [85.4%] male) revealed that a 3-dimensional scheme was optimal to capture the ASD neuroanatomy. The first dimension (A1: aginglike) was associated with smaller brain volume, lower cognitive function, and aging-related genetic variants (FOXO3; Z = 4.65; P = 1.62 × 10-6). The second dimension (A2: schizophrenialike) was characterized by enlarged subcortical volumes, antipsychotic medication use (Cohen d = 0.65; false discovery rate-adjusted P = .048), partially overlapping genetic, neuroanatomical characteristics to schizophrenia (n = 307), and significant genetic heritability estimates in the general population (n = 14 786; mean [SD] h2, 0.71 [0.04]; P < 1 × 10-4). The third dimension (A3: typical ASD) was distinguished by enlarged cortical volumes, high nonverbal cognitive performance, and biological pathways implicating brain development and abnormal apoptosis (mean [SD] β, 0.83 [0.02]; P = 4.22 × 10-6).

Conclusions and Relevance

This cross-sectional study discovered 3-dimensional endophenotypic representation that may elucidate the heterogeneous neurobiological underpinnings of ASD to support precision diagnostics. The significant correspondence between A2 and schizophrenia indicates a possibility of identifying common biological mechanisms across the 2 mental health diagnoses.

Association of Complement and Coagulation Pathway Proteins With Treatment Response in First-Episode Psychosis: A Longitudinal Analysis of the OPTiMiSE Clinical Trial

BACKGROUND AND HYPOTHESIS

Treatment response to specific antipsychotic medications is difficult to predict on clinical grounds alone. The current study hypothesizes that the baseline complement pathway activity predicts the treatment response and investigates the relationship between baseline plasma biomarkers with treatment response to antipsychotic medications.

STUDY DESIGN

Baseline plasma samples were collected from first episode of psychosis patients (n = 243) from a multi-center clinical trial. The participants were treated with amisulpride for 4 weeks. Levels of complement and coagulation proteins at baseline were measured using both data-dependent and data-independent mass spectrometry approaches. The primary outcome was remission status at 4 weeks and the secondary outcomes included change in psychotic and functional symptoms over the period of treatment. In addition, immunoassays were performed at baseline for complement C1R, as well as for activation markers C4a and sC5b-9.

STUDY RESULTS

The plasma level of complement variant C4A was significantly associated with remission at 4 weeks. Moreover, higher levels of several complement and coagulation pathway proteins were associated with a reduction in psychotic symptoms and an improvement in functioning. Immunoassays showed an association of baseline levels of C1R and C4a as well as complement activation marker sC5b-9 levels with treatment response.

CONCLUSION

The results demonstrated that the response to antipsychotic treatment might be related to pre-treatment levels of plasma complement and coagulation pathway proteins. This is consistent with independent evidence associating immune dysfunction with the pathophysiology of psychosis. Moreover, these results inform the development of novel therapeutic approaches that target the complement system for psychosis.

Digital mental health: challenges and next steps

Digital innovations in mental health offer great potential, but present unique challenges. Using a consensus development panel approach, an expert, international, cross-disciplinary panel met to provide a framework to conceptualise digital mental health innovations, research into mechanisms and effectiveness and approaches for clinical implementation. Key questions and outputs from the group were agreed by consensus, and are presented and discussed in the text and supported by case examples in an accompanying appendix. A number of key themes emerged. (1) Digital approaches may work best across traditional diagnostic systems: we do not have effective ontologies of mental illness and transdiagnostic/symptom-based approaches may be more fruitful. (2) Approaches in clinical implementation of digital tools/interventions need to be creative and require organisational change: not only do clinicians and patients need training and education to be more confident and skilled in using digital technologies to support shared care decision-making, but traditional roles need to be extended, with clinicians working alongside digital navigators and non-clinicians who are delivering protocolised treatments. (3) Designing appropriate studies to measure the effectiveness of implementation is also key: including digital data raises unique ethical issues, and measurement of potential harms is only just beginning. (4) Accessibility and codesign are needed to ensure innovations are long lasting. (5) Standardised guidelines for reporting would ensure effective synthesis of the evidence to inform clinical implementation. COVID-19 and the transition to virtual consultations have shown us the potential for digital innovations to improve access and quality of care in mental health: now is the ideal time to act.

The non-specific nature of mental health and structural brain outcomes following childhood trauma

BACKGROUND

Childhood trauma (CT) is associated with an increased risk of mental health disorders; however, it is unknown whether this represents a diagnosis-specific risk factor for specific psychopathology mediated by structural brain changes. Our aim was to explore whether (i) a predictive CT pattern for transdiagnostic psychopathology exists, and whether (ii) CT can differentiate between distinct diagnosis-dependent psychopathology. Furthermore, we aimed to identify the association between CT, psychopathology and brain structure.

METHODS

We used multivariate pattern analysis in data from 643 participants of the Personalised Prognostic Tools for Early Psychosis Management study (PRONIA), including healthy controls (HC), recent onset psychosis (ROP), recent onset depression (ROD), and patients clinically at high-risk for psychosis (CHR). Participants completed structured interviews and self-report measures including the Childhood Trauma Questionnaire, SCID diagnostic interview, BDI-II, PANSS, Schizophrenia Proneness Instrument, Structured Interview for Prodromal Symptoms and structural MRI, analyzed by voxel-based morphometry.

RESULTS

(i) Patients and HC could be distinguished by their CT pattern with a reasonable precision [balanced accuracy of 71.2% (sensitivity = 72.1%, specificity = 70.4%, p ≤ 0.001]. (ii) Subdomains 'emotional neglect' and 'emotional abuse' were most predictive for CHR and ROP, while in ROD 'physical abuse' and 'sexual abuse' were most important. The CT pattern was significantly associated with the severity of depressive symptoms in ROD, ROP, and CHR, as well as with the PANSS total and negative domain scores in the CHR patients. No associations between group-separating CT patterns and brain structure were found.

CONCLUSIONS

These results indicate that CT poses a transdiagnostic risk factor for mental health disorders, possibly related to depressive symptoms. While differences in the quality of CT exposure exist, diagnostic differentiation was not possible suggesting a multi-factorial pathogenesis.

Patterns of risk-Using machine learning and structural neuroimaging to identify pedophilic offenders

Background

Child sexual abuse (CSA) has become a focal point for lawmakers, law enforcement, and mental health professionals. With high prevalence rates around the world and far-reaching, often chronic, individual, and societal implications, CSA and its leading risk factor, pedophilia, have been well investigated. This has led to a wide range of clinical tools and actuarial instruments for diagnosis and risk assessment regarding CSA. However, the neurobiological underpinnings of pedosexual behavior, specifically regarding hands-on pedophilic offenders (PO), remain elusive. Such biomarkers for PO individuals could potentially improve the early detection of high-risk PO individuals and enhance efforts to prevent future CSA.

Aim

To use machine learning and MRI data to identify PO individuals.

Methods

From a single-center male cohort of 14 PO individuals and 15 matched healthy control (HC) individuals, we acquired diffusion tensor imaging data (anisotropy, diffusivity, and fiber tracking) in literature-based regions of interest (prefrontal cortex, anterior cingulate cortex, amygdala, and corpus callosum). We trained a linear support vector machine to discriminate between PO and HC individuals using these WM microstructure data. Post hoc, we investigated the PO model decision scores with respect to sociodemographic (age, education, and IQ) and forensic characteristics (psychopathy, sexual deviance, and future risk of sexual violence) in the PO subpopulation. We assessed model specificity in an external cohort of 53 HC individuals.

Results

The classifier discriminated PO from HC individuals with a balanced accuracy of 75.5% (sensitivity = 64.3%, specificity = 86.7%, P ₅₀₀₀ = 0.018) and an out-of-sample specificity to correctly identify HC individuals of 94.3%. The predictive brain pattern contained bilateral fractional anisotropy in the anterior cingulate cortex, diffusivity in the left amygdala, and structural prefrontal cortex-amygdala connectivity in both hemispheres. This brain pattern was associated with the number of previous child victims, the current stance on sexuality, and the professionally assessed risk of future sexual violent reoffending.

Conclusion

Aberrant white matter microstructure in the prefronto-temporo-limbic circuit could be a potential neurobiological correlate for PO individuals at high-risk of reoffending with CSA. Although preliminary and exploratory at this point, our findings highlight the general potential of MRI-based biomarkers and particularly WM microstructure patterns for future CSA risk assessment and preventive efforts.

Neurobiologically Based Stratification of Recent-Onset Depression and Psychosis: Identification of Two Distinct Transdiagnostic Phenotypes

BACKGROUND

Identifying neurobiologically based transdiagnostic categories of depression and psychosis may elucidate heterogeneity and provide better candidates for predictive modeling. We aimed to identify clusters across patients with recent-onset depression (ROD) and recent-onset psychosis (ROP) based on structural neuroimaging data. We hypothesized that these transdiagnostic clusters would identify patients with poor outcome and allow more accurate prediction of symptomatic remission than traditional diagnostic structures.

METHODS

HYDRA (Heterogeneity through Discriminant Analysis) was trained on whole-brain volumetric measures from 577 participants from the discovery sample of the multisite PRONIA study to identify neurobiologically driven clusters, which were then externally validated in the PRONIA replication sample (n = 404) and three datasets of chronic samples (Centre for Biomedical Research Excellence, n = 146; Mind Clinical Imaging Consortium, n = 202; Munich, n = 470).

RESULTS

The optimal clustering solution was two transdiagnostic clusters (cluster 1: n = 153, 67 ROP, 86 ROD; cluster 2: n = 149, 88 ROP, 61 ROD; adjusted Rand index = 0.618). The two clusters contained both patients with ROP and patients with ROD. One cluster had widespread gray matter volume deficits and more positive, negative, and functional deficits (impaired cluster), and one cluster revealed a more preserved neuroanatomical signature and more core depressive symptomatology (preserved cluster). The clustering solution was internally and externally validated and assessed for clinical utility in predicting 9-month symptomatic remission, outperforming traditional diagnostic structures.

CONCLUSIONS

We identified two transdiagnostic neuroanatomically informed clusters that are clinically and biologically distinct, challenging current diagnostic boundaries in recent-onset mental health disorders. These results may aid understanding of the etiology of poor outcome patients transdiagnostically and improve development of stratified treatments.

Relationships between global functioning and neuropsychological predictors in subjects at high risk of psychosis or with a recent onset of depression

OBJECTIVE

Psychotic disorders are frequently associated with decline in functioning and cognitive difficulties are observed in subjects at clinical high risk (CHR) for psychosis. In this work, we applied automatic approaches to neurocognitive and functioning measures, with the aim of investigating the link between global, social and occupational functioning, and cognition.

METHODS

102 CHR subjects and 110 patients with recent onset depression (ROD) were recruited. Global assessment of functioning (GAF) related to symptoms (GAF-S) and disability (GAF-D). and global functioning social (GF-S) and role (GF-R), at baseline and of the previous month and year, and a set of neurocognitive measures, were used for classification and regression.

RESULTS

Neurocognitive measures related to GF-R at baseline (r = 0.20, p = 0.004), GF-S at present (r = 0.14, p = 0.042) and of the past year (r = 0.19, p = 0.005), for GAF-F of the past month (r = 0.24, p < 0.001) and GAF-D of the past year (r = 0.28, p = 0.002). Classification reached values of balanced accuracy of 61% for GF-R and GAF-D.

CONCLUSION

We found that neurocognition was related to psychosocial functioning. More specifically, a deficit in executive functions was associated to poor social and occupational functioning.

Ethical considerations for precision psychiatry: A roadmap for research and clinical practice

Precision psychiatry is an emerging field with transformative opportunities for mental health. However, the use of clinical prediction models carries unprecedented ethical challenges, which must be addressed before accessing the potential benefits of precision psychiatry. This critical review covers multidisciplinary areas, including psychiatry, ethics, statistics and machine-learning, healthcare and academia, as well as input from people with lived experience of mental disorders, their family, and carers. We aimed to identify core ethical considerations for precision psychiatry and mitigate concerns by designing a roadmap for research and clinical practice. We identified priorities: learning from somatic medicine; identifying precision psychiatry use cases; enhancing transparency and generalizability; fostering implementation; promoting mental health literacy; communicating risk estimates; data protection and privacy; and fostering the equitable distribution of mental health care. We hope this blueprint will advance research and practice and enable people with mental health problems to benefit from precision psychiatry.

Development of a probability calculator for psychosis risk in children, adolescents, and young adults

BACKGROUND

Assessment of risks of illnesses has been an important part of medicine for decades. We now have hundreds of 'risk calculators' for illnesses, including brain disorders, and these calculators are continually improving as more diverse measures are collected on larger samples.

METHODS

We first replicated an existing psychosis risk calculator and then used our own sample to develop a similar calculator for use in recruiting 'psychosis risk' enriched community samples. We assessed 632 participants age 8-21 (52% female; 48% Black) from a community sample with longitudinal data on neurocognitive, clinical, medical, and environmental variables. We used this information to predict psychosis spectrum (PS) status in the future. We selected variables based on lasso, random forest, and statistical inference relief; and predicted future PS using ridge regression, random forest, and support vector machines.

RESULTS

Cross-validated prediction diagnostics were obtained by building and testing models in randomly selected sub-samples of the data, resulting in a distribution of the diagnostics; we report the mean. The strongest predictors of later PS status were the Children's Global Assessment Scale; delusions of predicting the future or having one's thoughts/actions controlled; and the percent married in one's neighborhood. Random forest followed by ridge regression was most accurate, with a cross-validated area under the curve (AUC) of 0.67. Adjustment of the model including only six variables reached an AUC of 0.70.

CONCLUSIONS

Results support the potential application of risk calculators for screening and identification of at-risk community youth in prospective investigations of developmental trajectories of the PS.

dsMTL - a computational framework for privacy-preserving, distributed multi-task machine learning

MOTIVATION

In multi-cohort machine learning studies, it is critical to differentiate between effects that are reproducible across cohorts and those that are cohort-specific. Multi-task learning (MTL) is a machine learning approach that facilitates this differentiation through the simultaneous learning of prediction tasks across cohorts. Since multi-cohort data can often not be combined into a single storage solution, there would be the substantial utility of an MTL application for geographically distributed data sources.

RESULTS

Here, we describe the development of "dsMTL", a computational framework for privacy-preserving, distributed multi-task machine learning that includes three supervised and one unsupervised algorithms. First, we derive the theoretical properties of these methods and the relevant machine learning workflows to ensure the validity of the software implementation. Second, we implement dsMTL as a library for the R programming language, building on the DataSHIELD platform that supports the federated analysis of sensitive individual-level data. Third, we demonstrate the applicability of dsMTL for comorbidity modeling in distributed data. We show that comorbidity modeling using dsMTL outperformed conventional, federated machine learning, as well as the aggregation of multiple models built on the distributed datasets individually. The application of dsMTL was computationally efficient and highly scalable when applied to moderate-size (n < 500), real expression data given the actual network latency.

AVAILABILITY

dsMTL is freely available at https://github.com/transbioZI/dsMTLBase (server-side package) and https://github.com/transbioZI/dsMTLClient (client-side package).

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Schizophrenia Imaging Signatures and Their Associations With Cognition, Psychopathology, and Genetics in the General Population

OBJECTIVE

The prevalence and significance of schizophrenia-related phenotypes at the population level is debated in the literature. Here, the authors assessed whether two recently reported neuroanatomical signatures of schizophrenia-signature 1, with widespread reduction of gray matter volume, and signature 2, with increased striatal volume-could be replicated in an independent schizophrenia sample, and investigated whether expression of these signatures can be detected at the population level and how they relate to cognition, psychosis spectrum symptoms, and schizophrenia genetic risk.

METHODS

This cross-sectional study used an independent schizophrenia-control sample (N=347; ages 16-57 years) for replication of imaging signatures, and then examined two independent population-level data sets: typically developing youths and youths with psychosis spectrum symptoms in the Philadelphia Neurodevelopmental Cohort (N=359; ages 16-23 years) and adults in the UK Biobank study (N=836; ages 44-50 years). The authors quantified signature expression using support-vector machine learning and compared cognition, psychopathology, and polygenic risk between signatures.

RESULTS

Two neuroanatomical signatures of schizophrenia were replicated. Signature 1 but not signature 2 was significantly more common in youths with psychosis spectrum symptoms than in typically developing youths, whereas signature 2 frequency was similar in the two groups. In both youths and adults, signature 1 was associated with worse cognitive performance than signature 2. Compared with adults with neither signature, adults expressing signature 1 had elevated schizophrenia polygenic risk scores, but this was not seen for signature 2.

CONCLUSIONS

The authors successfully replicated two neuroanatomical signatures of schizophrenia and describe their prevalence in population-based samples of youths and adults. They further demonstrated distinct relationships of these signatures with psychosis symptoms, cognition, and genetic risk, potentially reflecting underlying neurobiological vulnerability.

Exploring Links Between Psychosis and Frontotemporal Dementia Using Multimodal Machine Learning: Dementia Praecox Revisited

Importance

The behavioral and cognitive symptoms of severe psychotic disorders overlap with those seen in dementia. However, shared brain alterations remain disputed, and their relevance for patients in at-risk disease stages has not been explored so far.

Objective

To use machine learning to compare the expression of structural magnetic resonance imaging (MRI) patterns of behavioral-variant frontotemporal dementia (bvFTD), Alzheimer disease (AD), and schizophrenia; estimate predictability in patients with bvFTD and schizophrenia based on sociodemographic, clinical, and biological data; and examine prognostic value, genetic underpinnings, and progression in patients with clinical high-risk (CHR) states for psychosis or recent-onset depression (ROD).

Design, Setting, and Participants

This study included 1870 individuals from 5 cohorts, including (1) patients with bvFTD (n = 108), established AD (n = 44), mild cognitive impairment or early-stage AD (n = 96), schizophrenia (n = 157), or major depression (n = 102) to derive and compare diagnostic patterns and (2) patients with CHR (n = 160) or ROD (n = 161) to test patterns' prognostic relevance and progression. Healthy individuals (n = 1042) were used for age-related and cohort-related data calibration. Data were collected from January 1996 to July 2019 and analyzed between April 2020 and April 2022.

Main Outcomes and Measures

Case assignments based on diagnostic patterns; sociodemographic, clinical, and biological data; 2-year functional outcomes and genetic separability of patients with CHR and ROD with high vs low pattern expression; and pattern progression from baseline to follow-up MRI scans in patients with nonrecovery vs preserved recovery.

Results

Of 1870 included patients, 902 (48.2%) were female, and the mean (SD) age was 38.0 (19.3) years. The bvFTD pattern comprising prefrontal, insular, and limbic volume reductions was more expressed in patients with schizophrenia (65 of 157 [41.2%]) and major depression (22 of 102 [21.6%]) than the temporo-limbic AD patterns (28 of 157 [17.8%] and 3 of 102 [2.9%], respectively). bvFTD expression was predicted by high body mass index, psychomotor slowing, affective disinhibition, and paranoid ideation (R2 = 0.11). The schizophrenia pattern was expressed in 92 of 108 patients (85.5%) with bvFTD and was linked to the C9orf72 variant, oligoclonal banding in the cerebrospinal fluid, cognitive impairment, and younger age (R2 = 0.29). bvFTD and schizophrenia pattern expressions forecasted 2-year psychosocial impairments in patients with CHR and were predicted by polygenic risk scores for frontotemporal dementia, AD, and schizophrenia. Findings were not associated with AD or accelerated brain aging. Finally, 1-year bvFTD/schizophrenia pattern progression distinguished patients with nonrecovery from those with preserved recovery.

Conclusions and Relevance

Neurobiological links may exist between bvFTD and psychosis focusing on prefrontal and salience system alterations. Further transdiagnostic investigations are needed to identify shared pathophysiological processes underlying the neuroanatomical interface between the 2 disease spectra.

Creating sparser prediction models of treatment outcome in depression: a proof-of-concept study using simultaneous feature selection and hyperparameter tuning

Background

Predicting treatment outcome in major depressive disorder (MDD) remains an essential challenge for precision psychiatry. Clinical prediction models (CPMs) based on supervised machine learning have been a promising approach for this endeavor. However, only few CPMs have focused on model sparsity even though sparser models might facilitate the translation into clinical practice and lower the expenses of their application.

Methods

In this study, we developed a predictive modeling pipeline that combines hyperparameter tuning and recursive feature elimination in a nested cross-validation framework. We applied this pipeline to a real-world clinical data set on MDD treatment response and to a second simulated data set using three different classification algorithms. Performance was evaluated by permutation testing and comparison to a reference pipeline without nested feature selection.

Results

Across all models, the proposed pipeline led to sparser CPMs compared to the reference pipeline. Except for one comparison, the proposed pipeline resulted in equally or more accurate predictions. For MDD treatment response, balanced accuracy scores ranged between 61 and 71% when models were applied to hold-out validation data.

Conclusions

The resulting models might be particularly interesting for clinical applications as they could reduce expenses for clinical institutions and stress for patients.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12911-022-01926-2.

Clinical, Brain, and Multilevel Clustering in Early Psychosis and Affective Stages

Importance

Approaches are needed to stratify individuals in early psychosis stages beyond positive symptom severity to investigate specificity related to affective and normative variation and to validate solutions with premorbid, longitudinal, and genetic risk measures.

Objective

To use machine learning techniques to cluster, compare, and combine subgroup solutions using clinical and brain structural imaging data from early psychosis and depression stages.

Design, Setting, and Participants

A multisite, naturalistic, longitudinal cohort study (10 sites in 5 European countries; including major follow-up intervals at 9 and 18 months) with a referred patient sample of those with clinical high risk for psychosis (CHR-P), recent-onset psychosis (ROP), recent-onset depression (ROD), and healthy controls were recruited between February 1, 2014, to July 1, 2019. Data were analyzed between January 2020 and January 2022.

Main Outcomes and Measures

A nonnegative matrix factorization technique separately decomposed clinical (287 variables) and parcellated brain structural volume (204 gray, white, and cerebrospinal fluid regions) data across CHR-P, ROP, ROD, and healthy controls study groups. Stability criteria determined cluster number using nested cross-validation. Validation targets were compared across subgroup solutions (premorbid, longitudinal, and schizophrenia polygenic risk scores). Multiclass supervised machine learning produced a transferable solution to the validation sample.

Results

There were a total of 749 individuals in the discovery group and 610 individuals in the validation group. Individuals included those with CHR-P (n = 287), ROP (n = 323), ROD (n = 285), and healthy controls (n = 464), The mean (SD) age was 25.1 (5.9) years, and 702 (51.7%) were female. A clinical 4-dimensional solution separated individuals based on positive symptoms, negative symptoms, depression, and functioning, demonstrating associations with all validation targets. Brain clustering revealed a subgroup with distributed brain volume reductions associated with negative symptoms, reduced performance IQ, and increased schizophrenia polygenic risk scores. Multilevel results distinguished between normative and illness-related brain differences. Subgroup results were largely validated in the external sample.

Conclusions and Relevance

The results of this longitudinal cohort study provide stratifications beyond the expression of positive symptoms that cut across illness stages and diagnoses. Clinical results suggest the importance of negative symptoms, depression, and functioning. Brain results suggest substantial overlap across illness stages and normative variation, which may highlight a vulnerability signature independent from specific presentations. Premorbid, longitudinal, and genetic risk validation suggested clinical importance of the subgroups to preventive treatments.

Evidence of discontinuity between psychosis-risk and non-clinical samples in the neuroanatomical correlates of social function

Objective

Social dysfunction is a major feature of clinical-high-risk states for psychosis (CHR-P). Prior research has identified a neuroanatomical pattern associated with impaired social function outcome in CHR-P. The aim of the current study was to test whether social dysfunction in CHR-P is neurobiologically distinct or in a continuum with the lower end of the normal distribution of individual differences in social functioning.

Methods

We used a machine learning classifier to test for the presence of a previously validated brain structural pattern associated with impaired social outcome in CHR-P (CHR-outcome-neurosignature) in the neuroimaging profiles of individuals from two non-clinical samples (total n = 1763) and examined its association with social function, psychopathology and cognition.

Results

Although the CHR-outcome-neurosignature could be detected in a subset of the non-clinical samples, it was not associated was adverse social outcomes or higher psychopathology levels. However, participants whose neuroanatomical profiles were highly aligned with the CHR-outcome-neurosignature manifested subtle disadvantage in fluid (P_FDR = 0.004) and crystallized intelligence (P_FDR = 0.01), cognitive flexibility (P_FDR = 0.02), inhibitory control (P_FDR = 0.01), working memory (P_FDR = 0.0005), and processing speed (P_FDR = 0.04).

Conclusions

We provide evidence of divergence in brain structural underpinnings of social dysfunction derived from a psychosis-risk enriched population when applied to non-clinical samples. This approach appears promising in identifying brain mechanisms bound to psychosis through comparisons of patient populations to non-clinical samples with the same neuroanatomical profiles.

The potential of precision psychiatry: what is in reach?

Progress in developing personalised care for mental disorders is supported by numerous proof-of-concept machine learning studies in the area of risk assessment, diagnostics and precision prescribing. Most of these studies primarily use clinical data, but models might benefit from additional neuroimaging, blood and genetic data to improve accuracy. Combined, multimodal models might offer potential for stratification of patients for treatment. Clinical implementation of machine learning is impeded by a lack of wider generalisability, with efforts primarily focused on psychosis and dementia. Studies across all diagnostic groups should work to test the robustness of machine learning models, which is an essential first step to clinical implementation, and then move to prospective clinical validation. Models need to exceed clinicians' heuristics to be useful, and safe, in routine decision-making. Engagement of clinicians, researchers and patients in digitalisation and 'big data' approaches are vital to allow the generation and accessibility of large, longitudinal, prospective data needed for precision psychiatry to be applied into real-world psychiatric care.

Annual Research Review: Translational machine learning for child and adolescent psychiatry

Children and adolescents could benefit from the use of predictive tools that facilitate personalized diagnoses, prognoses, and treatment selection. Such tools have not yet been deployed using traditional statistical methods, potentially due to the limitations of the paradigm and the need to leverage large amounts of digital data. This review will suggest that a machine learning approach could address these challenges and is designed to introduce new readers to the background, methods, and results in the field. A rationale is first introduced followed by an outline of fundamental elements of machine learning approaches. To provide an overview of the use of the techniques in child and adolescent literature, a scoping review of broad trends is then presented. Selected studies are also highlighted in order to draw attention to research areas that are closest to translation and studies that exhibit a high degree of experimental innovation. Limitations to the research, and machine learning approaches generally, are outlined in the penultimate section highlighting issues related to sample sizes, validation, clinical utility, and ethical challenges. Finally, future directions are discussed that could enhance the possibility of clinical implementation and address specific questions relevant to the child and adolescent psychiatry. The review gives a broad overview of the machine learning paradigm in order to highlight the benefits of a shift in perspective towards practically oriented statistical solutions that aim to improve clinical care of children and adolescents.

Pattern of predictive features of continued cannabis use in patients with recent-onset psychosis and clinical high-risk for psychosis

Continued cannabis use (CCu) is an important predictor for poor long-term outcomes in psychosis and clinically high-risk patients, but no generalizable model has hitherto been tested for its ability to predict CCu in these vulnerable patient groups. In the current study, we investigated how structured clinical and cognitive assessments and structural magnetic resonance imaging (sMRI) contributed to the prediction of CCu in a group of 109 patients with recent-onset psychosis (ROP). We tested the generalizability of our predictors in 73 patients at clinical high-risk for psychosis (CHR). Here, CCu was defined as any cannabis consumption between baseline and 9-month follow-up, as assessed in structured interviews. All patients reported lifetime cannabis use at baseline. Data from clinical assessment alone correctly classified 73% (p < 0.001) of ROP and 59 % of CHR patients. The classifications of CCu based on sMRI and cognition were non-significant (ps > 0.093), and their addition to the interview-based predictor via stacking did not improve prediction significantly, either in the ROP or CHR groups (ps > 0.065). Lower functioning, specific substance use patterns, urbanicity and a lack of other coping strategies contributed reliably to the prediction of CCu and might thus represent important factors for guiding preventative efforts. Our results suggest that it may be possible to identify by clinical measures those psychosis-spectrum patients at high risk for CCu, potentially allowing to improve clinical care through targeted interventions. However, our model needs further testing in larger samples including more diverse clinical populations before being transferred into clinical practice.

Deep Generative Medical Image Harmonization for Improving Cross-Site Generalization in Deep Learning Predictors

BACKGROUND

In the medical imaging domain, deep learning-based methods have yet to see widespread clinical adoption, in part due to limited generalization performance across different imaging devices and acquisition protocols. The deviation between estimated brain age and biological age is an established biomarker of brain health and such models may benefit from increased cross-site generalizability.

PURPOSE

To develop and evaluate a deep learning-based image harmonization method to improve cross-site generalizability of deep learning age prediction.

STUDY TYPE

Retrospective.

POPULATION

Eight thousand eight hundred and seventy-six subjects from six sites. Harmonization models were trained using all subjects. Age prediction models were trained using 2739 subjects from a single site and tested using the remaining 6137 subjects from various other sites.

FIELD STRENGTH/SEQUENCE

Brain imaging with magnetization prepared rapid acquisition with gradient echo or spoiled gradient echo sequences at 1.5 T and 3 T.

ASSESSMENT

StarGAN v2, was used to perform a canonical mapping from diverse datasets to a reference domain to reduce site-based variation while preserving semantic information. Generalization performance of deep learning age prediction was evaluated using harmonized, histogram matched, and unharmonized data.

STATISTICAL TESTS

Mean absolute error (MAE) and Pearson correlation between estimated age and biological age quantified the performance of the age prediction model.

RESULTS

Our results indicated a substantial improvement in age prediction in out-of-sample data, with the overall MAE improving from 15.81 (±0.21) years to 11.86 (±0.11) with histogram matching to 7.21 (±0.22) years with generative adversarial network (GAN)-based harmonization. In the multisite case, across the 5 out-of-sample sites, MAE improved from 9.78 (±6.69) years to 7.74 (±3.03) years with histogram normalization to 5.32 (±4.07) years with GAN-based harmonization.

DATA CONCLUSION

While further research is needed, GAN-based medical image harmonization appears to be a promising tool for improving cross-site deep learning generalization.

LEVEL OF EVIDENCE

4 TECHNICAL EFFICACY: Stage 1.

Physical and mental health impact of COVID-19 on children, adolescents, and their families: The Collaborative Outcomes study on Health and Functioning during Infection Times - Children and Adolescents (COH-FIT-C&A)

BACKGROUND

The COVID-19 pandemic has altered daily routines and family functioning, led to closing schools, and dramatically limited social interactions worldwide. Measuring its impact on mental health of vulnerable children and adolescents is crucial.

METHODS

The Collaborative Outcomes study on Health and Functioning during Infection Times (COH-FIT - www.coh-fit.com) is an on-line anonymous survey, available in 30 languages, involving >230 investigators from 49 countries supported by national/international professional associations. COH-FIT has thee waves (until the pandemic is declared over by the WHO, and 6-18 months plus 24-36 months after its end). In addition to adults, COH-FIT also includes adolescents (age 14-17 years), and children (age 6-13 years), recruited via non-probability/snowball and representative sampling and assessed via self-rating and parental rating. Non-modifiable/modifiable risk factors/treatment targets to inform prevention/intervention programs to promote health and prevent mental and physical illness in children and adolescents will be generated by COH-FIT. Co-primary outcomes are changes in well-being (WHO-5) and a composite psychopathology P-Score. Multiple behavioral, family, coping strategy and service utilization factors are also assessed, including functioning and quality of life.

RESULTS

Up to June 2021, over 13,000 children and adolescents from 59 countries have participated in the COH-FIT project, with representative samples from eleven countries.

LIMITATIONS

Cross-sectional and anonymous design.

CONCLUSIONS

Evidence generated by COH-FIT will provide an international estimate of the COVID-19 effect on children's, adolescents' and families', mental and physical health, well-being, functioning and quality of life, informing the formulation of present and future evidence-based interventions and policies to minimize adverse effects of the present and future pandemics on youth.

The collaborative outcomes study on health and functioning during infection times in adults (COH-FIT-Adults): Design and methods of an international online survey targeting physical and mental health effects of the COVID-19 pandemic

BACKGROUND

. High-quality comprehensive data on short-/long-term physical/mental health effects of the COVID-19 pandemic are needed.

METHODS

. The Collaborative Outcomes study on Health and Functioning during Infection Times (COH-FIT) is an international, multi-language (n=30) project involving >230 investigators from 49 countries/territories/regions, endorsed by national/international professional associations. COH-FIT is a multi-wave, on-line anonymous, cross-sectional survey [wave 1: 04/2020 until the end of the pandemic, 12 months waves 2/3 starting 6/24 months threreafter] for adults, adolescents (14-17), and children (6-13), utilizing non-probability/snowball and representative sampling. COH-FIT aims to identify non-modifiable/modifiable risk factors/treatment targets to inform prevention/intervention programs to improve social/health outcomes in the general population/vulnerable subgrous during/after COVID-19. In adults, co-primary outcomes are change from pre-COVID-19 to intra-COVID-19 in well-being (WHO-5) and a composite psychopathology P-Score. Key secondary outcomes are a P-extended score, global mental and physical health. Secondary outcomes include health-service utilization/functioning, treatment adherence, functioning, symptoms/behaviors/emotions, substance use, violence, among others.

RESULTS

. Starting 04/26/2020, up to 14/07/2021 >151,000 people from 155 countries/territories/regions and six continents have participated. Representative samples of ≥1,000 adults have been collected in 15 countries. Overall, 43.0% had prior physical disorders, 16.3% had prior mental disorders, 26.5% were health care workers, 8.2% were aged ≥65 years, 19.3% were exposed to someone infected with COVID-19, 76.1% had been in quarantine, and 2.1% had been COVID 19-positive.

LIMITATIONS

. Cross-sectional survey, preponderance of non-representative participants.

CONCLUSIONS

. Results from COH-FIT will comprehensively quantify the impact of COVID-19, seeking to identify high-risk groups in need for acute and long-term intervention, and inform evidence-based health policies/strategies during this/future pandemics.

Using combined environmental-clinical classification models to predict role functioning outcome in clinical high-risk states for psychosis and recent-onset depression

BACKGROUND

Clinical high-risk states for psychosis (CHR) are associated with functional impairments and depressive disorders. A previous PRONIA study predicted social functioning in CHR and recent-onset depression (ROD) based on structural magnetic resonance imaging (sMRI) and clinical data. However, the combination of these domains did not lead to accurate role functioning prediction, calling for the investigation of additional risk dimensions. Role functioning may be more strongly associated with environmental adverse events than social functioning.

AIMS

We aimed to predict role functioning in CHR, ROD and transdiagnostically, by adding environmental adverse events-related variables to clinical and sMRI data domains within the PRONIA sample.

METHOD

Baseline clinical, environmental and sMRI data collected in 92 CHR and 95 ROD samples were trained to predict lower versus higher follow-up role functioning, using support vector classification and mixed k-fold/leave-site-out cross-validation. We built separate predictions for each domain, created multimodal predictions and validated them in independent cohorts (74 CHR, 66 ROD).

RESULTS

Models combining clinical and environmental data predicted role outcome in discovery and replication samples of CHR (balanced accuracies: 65.4% and 67.7%, respectively), ROD (balanced accuracies: 58.9% and 62.5%, respectively), and transdiagnostically (balanced accuracies: 62.4% and 68.2%, respectively). The most reliable environmental features for role outcome prediction were adult environmental adjustment, childhood trauma in CHR and childhood environmental adjustment in ROD.

CONCLUSIONS

Findings support the hypothesis that environmental variables inform role outcome prediction, highlight the existence of both transdiagnostic and syndrome-specific predictive environmental adverse events, and emphasise the importance of implementing real-world models by measuring multiple risk dimensions.