Prediction of estimated risk for bipolar disorder using machine learning and structural MRI features.

BACKGROUND: Individuals with bipolar disorder are commonly correctly diagnosed a decade after symptom onset. Machine learning techniques may aid in early recognition and reduce the disease burden. As both individuals at risk and those with a manifest disease display structural brain markers, structural magnetic resonance imaging may provide relevant classification features. METHODS: Following a pre-registered protocol, we trained linear support vector machine (SVM) to classify individuals according to their estimated risk for bipolar disorder using regional cortical thickness of help-seeking individuals from seven study sites (N = 276). We estimated the risk using three state-of-the-art assessment instruments (BPSS-P, BARS, EPIbipolar). RESULTS: For BPSS-P, SVM achieved a fair performance of Cohen's κ of 0.235 (95% CI 0.11-0.361) and a balanced accuracy of 63.1% (95% CI 55.9-70.3) in the 10-fold cross-validation. In the leave-one-site-out cross-validation, the model performed with a Cohen's κ of 0.128 (95% CI -0.069 to 0.325) and a balanced accuracy of 56.2% (95% CI 44.6-67.8). BARS and EPIbipolar could not be predicted. In post hoc analyses, regional surface area, subcortical volumes as well as hyperparameter optimization did not improve the performance. CONCLUSIONS: Individuals at risk for bipolar disorder, as assessed by BPSS-P, display brain structural alterations that can be detected using machine learning. The achieved performance is comparable to previous studies which attempted to classify patients with manifest disease and healthy controls. Unlike previous studies of bipolar risk, our multicenter design permitted a leave-one-site-out cross-validation. Whole-brain cortical thickness seems to be superior to other structural brain features.

Larger putamen in individuals at risk and with manifest bipolar disorder.

BACKGROUND: Individuals at risk for bipolar disorder (BD) have a wide range of genetic and non-genetic risk factors, like a positive family history of BD or (sub)threshold affective symptoms. Yet, it is unclear whether these individuals at risk and those diagnosed with BD share similar gray matter brain alterations. METHODS: In 410 male and female participants aged 17-35 years, we compared gray matter volume (3T MRI) between individuals at risk for BD (as assessed using the EPIbipolar scale; n = 208), patients with a DSM-IV-TR diagnosis of BD (n = 87), and healthy controls (n = 115) using voxel-based morphometry in SPM12/CAT12. We applied conjunction analyses to identify similarities in gray matter volume alterations in individuals at risk and BD patients, relative to healthy controls. We also performed exploratory whole-brain analyses to identify differences in gray matter volume among groups. ComBat was used to harmonize imaging data from seven sites. RESULTS: Both individuals at risk and BD patients showed larger volumes in the right putamen than healthy controls. Furthermore, individuals at risk had smaller volumes in the right inferior occipital gyrus, and BD patients had larger volumes in the left precuneus, compared to healthy controls. These findings were independent of course of illness (number of lifetime manic and depressive episodes, number of hospitalizations), comorbid diagnoses (major depressive disorder, attention-deficit hyperactivity disorder, anxiety disorder, eating disorder), familial risk, current disease severity (global functioning, remission status), and current medication intake. CONCLUSIONS: Our findings indicate that alterations in the right putamen might constitute a vulnerability marker for BD.

[Individual placement and support in mental health services: evaluation of routine clinical data using a retrospective chart review]. / Individual Placement and Support in der psychiatrischen Versorgung: Evaluation klinischer Routinedaten mittels eines retrospektiven Chart-Reviews.

BACKGROUND: People with severe mental illnesses are often excluded from working life and would like support to (re)enter the general labor market as part of the psychiatric treatment. Individual placement and support (IPS) is an effective method of finding and retaining work in the general labor market. The aim of the study was to determine the integration rates of IPS into the general labor market in acute and postacute psychiatric settings, identifying patient, setting and program characteristics associated with (re)entering work. METHOD: A retrospective chart review (RCR) of routine clinical data between 2016 and 2021 was carried out. The IPS program adherence was rated using the IPS fidelity scale. RESULTS: A total of 375 patients participated in the IPS with at least 4 appointments. The (re)integration rate into the general labor market was 51.7%. A shorter time period to the last working day, diagnosis of F1, F2, F3 (vs. F4), change of treatment setting and IPS in the psychiatric institute outpatient department (PIA), IPS fidelity and the number of IPS coaching sessions were positively correlated with (re)integration into work. CONCLUSION: The implementation of IPS in clinical mental healthcare is possible and leads to high integration rates in the open labor market. An early start of IPS during the clinical treatment can promote social inclusion.

Specialized inpatient treatment for young people with early psychosis: acute-treatment and 12-month results.

The objective of the study was to investigate the development of clinical outcomes of young people with early psychosis in a specialized inpatient treatment and assess the feasibility of such an intervention in an inpatient setting. The study was a prospective cohort study of patients with early psychosis treated at the specialized inpatient treatment "Fühinterventions-und Therapiezentrum, FRITZ" (early intervention and therapy center) in Berlin, Germany. The primary outcomes were attitudes towards psychiatric medication and patient satisfaction with treatment after 6 weeks. Secondary outcomes were clinical symptoms, functioning, remission, recovery, all-cause treatment discontinuation, and rehospitalisation at 6 and 12 months after inpatient treatment. We recruited 95 inpatients with early psychosis. Attitudes towards psychiatric medication (Δ6weeks = 3.00, d6weeks = 0.55; Δ6mo = 2.15, d6mo = 0.35; Δ12mo = 3.03, d12mo = 0.52) and patient satisfaction (Δ6weeks = 0.21, d6weeks = 0.40; Δ6mo = 0.32, d6mo = 0.43; Δ12mo = 0.13, d12mo = 0.17) changed with medium effect sizes at six weeks up to a 6- and 12-month follow-up. Clinical outcomes changed significantly with medium-to-large-effect sizes over 12 months CGIΔ12mo = 1.64, d12mo = -1.12; PANSS totalΔ12mo = 20.10, d12mo = -0.76; GAFΔ12mo = 19.58, d12mo = 1.25). The all-cause treatment discontinuation rate was 13.69% (n = 13) at a 6-month and 35.79% (n = 34) at a 12-month follow-up. The rehospitalization rate was 30.53% (n = 29) at a 6-month and 43.16% (n = 41) at a 12-month follow-up. Patients with specialized inpatient treatment for early psychosis showed improvements in attitude towards psychiatric medication, patient satisfaction, symptoms, and functioning for up to 12 months.Trial registration: DRKS00024351, 2021/02/11 retrospectively registered.

The Patient, Investigator, Nurse, Carer Questionnaire (PINC-Q): a cross-sectional, retrospective, non-interventional study exploring the impact of less frequent medication administration with paliperidone palmitate 3-monthly as maintenance treatment for schizophrenia.

BACKGROUND: To understand the implications of switching from paliperidone palmitate 1-monthly (PP1M) to paliperidone palmitate 3-monthly (PP3M) treatment of schizophrenia from the perspective of four key stakeholders: patients, physicians, nurses and carers. METHODS: This was a cross-sectional, retrospective, non-interventional study comprising a one-time questionnaire (PINC-Q) for adult patients (aged ≥18 years) with schizophrenia (International Classification of Diseases; ICD-10) and their physician, nurse and carer. Questionnaires were developed in association with patient and carer advocacy groups (GAMIAN and EUFAMI) and following an advisory board formed of psychiatrists and nurses. The degree of alignment between stakeholders was also examined. RESULTS: Responses were received from a total of 224 evaluable patients. For most patients (88.4%), responses were received from at least two other stakeholders. Patients were moderately ill with mild-to-moderate lack of insight and had received PP1M for a mean (standard deviation [SD]) of 23.9 (21.28) months before switching to PP3M (duration mean [SD] 12.8 [3.72] months). The most frequently reported reasons to switch from PP1M to PP3M were 'to live life as normally as possible' and 'patient convenience'. Over 79% of responses within each stakeholder group stated that PP3M helped the patients, with increased patient activity and social involvement, improved frequency and quality of physician-patient and nurse-patient communication and decreased perceived stigma. CONCLUSIONS: The results of this study add to the increasing body of evidence supporting the benefits of PP3M in a population of patients with schizophrenia representative of real-world clinical practice.

Treatment Goals for Patients with Schizophrenia - A Narrative Review of Physician and Patient Perspectives.

INTRODUCTION: There are many possible treatment goals for patients with schizophrenia. Two major perspectives on treatment goals are the patient's and the physician's perspective. Patient-centered treatment mandates that an individual patient's treatment goals are taken into account when treatment is planned. In this narrative review, we address the commonalities and differences of the patient's and physician's perspectives. METHODS: We searched for literature on treatment goals for patients with schizophrenia from the last 10 years. RESULTS: Fifty-two relevant records were identified, 4 of which directly compare patient's and physician's perspectives. Two further articles used the same set of goals to ask patients or physicians for their assessment. DISCUSSION: Agreement between patients and physicians regarding valuation of treatment goals was high. However, physicians tended to put more emphasis on the classical "textbook" goals of symptom resolution and functioning, while patients stressed well-being and quality of life more. Results on treatment goals from patients are difficult to generalize, since recruiting representative patient samples is challenging and patient subgroups may have differing priorities.

Clinical Risk Constellations for the Development of Bipolar Disorders.

The early recognition of psychiatric disorders has been a focus of research in the last decades and has led to improvements in clinical care, especially in the area of early psychosis. Like non-affective psychosis, bipolar disorders are often diagnosed with a delay that can lead to long periods of untreated illness and impact long-term outcomes. This article presents the rationale for early recognition in bipolar disorder and presents the current evidence for the identification of risk factors, their assessment and validity in predicting the onset of bipolar disorder.

Efficacy of cognitive-behavioral group therapy in patients at risk for serious mental illness presenting with subthreshold bipolar symptoms: Results from a prespecified interim analysis of a multicenter, randomized, controlled study.

OBJECTIVE: Most patients with bipolar disorders (BD) exhibit prodromal symptoms before a first (hypo)manic episode. Patients with clinically significant symptoms fulfilling at-risk criteria for serious mental illness (SMI) require effective and safe treatment. Cognitive-behavioral psychotherapy (CBT) has shown promising results in early stages of BD and in patients at high risk for psychosis. We aimed to investigate whether group CBT can improve symptoms and functional deficits in young patients at risk for SMI presenting with subthreshold bipolar symptoms. METHOD: In a multicenter, randomized, controlled trial, patients at clinical risk for SMI presenting with subthreshold bipolar symptoms aged 15-30 years were randomized to 14 weeks of at-risk for BD-specific group CBT or unstructured group meetings. Primary efficacy endpoints were differences in affective symptomatology and psychosocial functioning at 14 weeks. At-risk status was defined as a combination of subthreshold bipolar symptomatology, reduction of psychosocial functioning and a family history for (schizo)affective disorders. A prespecified interim analysis was conducted at 75% of the targeted sample. RESULTS: Of 128 screened participants, 75 were randomized to group CBT (n = 38, completers = 65.8%) vs unstructured group meetings (n = 37, completers = 78.4%). Affective symptomatology and psychosocial functioning improved significantly at week 14 (P < .001) and during 6 months (P < .001) in both groups, without significant between-group differences. Findings are limited by the interim character of the analysis, the use of not fully validated early detection interviews, a newly adapted intervention manual, and the substantial drop-outs. CONCLUSIONS: Results suggest that young patients at-risk for SMI presenting with subthreshold bipolar symptoms benefit from early group sessions. The degree of specificity and psychotherapeutic interaction needed requires clarification.

Acute and Long-term Memantine Add-on Treatment to Risperidone Improves Cognitive Dysfunction in Patients with Acute and Chronic Schizophrenia.

INTRODUCTION: Patients with schizophrenia are mainly characterized by negative symptoms and cognitive dysfunction. In this proof-of-concept study we tested effects on cognition and negative symptoms of a 6- or 24-week memantine add-on treatment to risperidone in patients with acute or chronic schizophrenia. MATERIALS AND METHODS: Patients with an acute episode of schizophrenia (n=11) and predominating positive symptoms were randomized to a 6-week add-on treatment with memantine (10 mg twice a day) versus placebo and patients with chronic schizophrenia (n=13) and negative symptoms were randomized to a 24-week add-on treatment with memantine (10 mg twice a day) versus placebo. All patients received antipsychotic medication with risperidone (2-8 mg/day). Psychopathological changes were assessed with the Positive and Negative Syndrome Scale (PANSS) at baseline and after 2, 4, 6, 12, and 24 weeks. Cognitive function was measured at baseline, after 6 weeks, and 24 weeks. RESULTS: Patients with acute schizophrenia who received add-on treatment with memantine showed a significantly higher performance in attention intensity (p=0.043), problem-solving (p=0.043), verbal learning (p=0.050), and flexibility (p=0.049). Patients with chronic schizophrenia showed a significantly higher immediate memory in the memantine group compared to the placebo group (p=0.033) and a significantly greater reduction of the PANSS sum score if compared to the placebo group. DISCUSSIONS: Our study gives further evidence that memantine add-on treatment to risperidone may have neuroprotective effects and improve cognitive function in patients with schizophrenia. ClinicalTrials.gov Number: NCT00148590 and NCT00148616.

[Early Intervention in Schizophrenia - an Update]. / Frühintervention bei Schizophrenie ­ ein Update.

In Germany, psychoses are still diagnosed too late. The average duration of untreated psychosis is (DUP) one year. Early intervention should, therefore, be given higher priority. The shorter the duration of the DUP, the higher the probability of permanent recovery and a better long-term prognosis. Public education work and specialised early detection centres with low-threshold access can improve care and thus the prospects of patients, mostly young, and already in the early phase of the disease. In addition to anti-psychotic therapy, evidence-based psychotherapeutic procedures, family and peer work, as well as accompanying offers are necessary to support patients individually in being or remaining reintegrated into the labour market ("Individual Placement and Support", IPS). While in some countries, such as Denmark and Australia, the possibility of early intervention is already part of standard care, Germany has not yet gone beyond model projects. Changing this must be one of the main objectives for the coming years. With this review, the authors would therefore like to encourage further thinking and action.

[Motivational interviewing : A possibility for doctor-patient communication in schizophrenia?] / "Motivational interviewing" : Eine Möglichkeit der Arzt-Patienten-Kommunikation bei Schizophrenie?

Motivational interviewing (MI) has become established nowadays as an approach for a cooperative style of conversation to promote intrinsic motivation for change by exploring and resolving ambivalences. The change of addictive behavior is no longer sought by exerting pressure or lecturing/converting attempts of convincing or persuasion but by activating existing but "buried" or newly acquired self-motivation to change. The MI is now also used to change the treatment of other health-related behavior and chronic diseases, including schizophrenic disorders. Compared to the efficacy of MI in the addiction area, the data situation in schizophrenic patients is still insufficient. According to the available studies, MI can positively influence important aspects of disease-related impairments, such as medication adherence, the frequency and severity of psychotic relapses, the duration of hospitalization, the level of function, insight into the disease and cognitive rehabilitation. The practical implementation of MI requires a good knowledge of the method as well as changes in treatment principles and work processes.

[Quality of life as a target criterion in schizophrenia therapy]. / Lebensqualität als Zielkriterium in der Schizophrenietherapie.

Consideration of quality of life has developed into an important concept of a patient-oriented medicine in the last 50 years. With it, it should be possible to capture the subjective experience of the patients and describe its different dimensions. Today, the quality of life as a patient-reported endpoint is also an integral part of the early benefit assessment under the German Drug Market Reorganization Act. In the treatment of schizophrenic patients, however, improvement in quality of life as an accepted target criterion has only been established with delay.

Longitudinal changes in the antecedent and early manifest course of bipolar disorder-A narrative review of prospective studies.

OBJECTIVE: Prospective study designs ideally allow patients to be followed from the first manifestations of the illness or even from an at-risk stage. It can thus provide data on the predictive value of changes in clinical symptomatology, cognition or further biological markers to broaden our understanding of the etiopathology and symptomatic trajectory of bipolar disorders. The scope of this narrative review is to summarize evidence from prospectively collected data on psychopathological and other clinical and biological changes in the early developmental course of bipolar disorders. METHODS: The narrative review was based on a literature search conducted in February 2016 within the PubMed library for prospective study data of persons in antecedent and early manifest stages of manifest bipolar disorder published within the last 15 years. RESULTS: A total of 19 prospective studies were included. Regarding psychopathological features; personality, temperament and character traits as well as changes in sleep and circadian rhythm, the evidence suggests that risk factors for the development of bipolar disorder can already be described and should be studied further to understand their interaction, mediation with other factors and timing in the developmental process of bipolar disorder. Apart from the positive family history, childhood anxiety, sleep problems, subthreshold (hypo)manic symptoms and certain character traits/emotionality should be identified and monitored already in clinical practice as their presence likely increases risk of bipolar disorder. Up to date no substantiated evidence was found from prospective studies addressing cognitive features, life events, immunological parameters and morphological central nervous system changes as potential risk factors for bipolar disorder. CONCLUSION: For an improved understanding of episodic disorders, longitudinal data collection is essential. Since the etiology of bipolar disorders is complex, a number of potential risk factors have been proposed. Prospective studies addressing this spectrum and resilience factors are critical and will be best conducted within multi-site research networks or initiatives.

Effectiveness of interdisciplinary vs. dermatological care of moderate-to-severe psoriasis: a pragmatic randomised controlled trial.

Psychiatric morbidity is frequent in patients with psoriasis. We compared the effectiveness of dermatological vs. interdisciplinary dermatological and psychiatric care for psoriasis. Adults with moderate-to-severe psoriasis were randomly allocated to dermatological (n = 24) or interdisciplinary care (n = 23) and treated accordingly. Primary endpoint was the mean change in Dermatology Life Quality Index (DLQI) at 6 months. Data was analysed by intention-to-treat. Mean ± SD change in DLQI was 7.5 ± 7.3 and 10.5 ± 9.9 after 6 months of dermatological and interdisciplinary care, respectively (p = 0.27). At baseline, 10 patients in the interdisciplinary treatment group (43%) had at least one psychiatric disorder. These patients showed significantly better DLQI response (DLQI change 14.8 ± 9.7) than patients receiving dermatological care only (p = 0.03). Ninety percent of psoriasis patients with DLQI scores exceeding psoriasis area and severity index (PASI) scores had comorbid psychiatric disease. Although psychiatric co-treatment is not generally required for patients with moderate-to-severe psoriasis, those patients with higher DLQI scores than PASI scores might benefit from interdisciplinary care.

Subjective experiences of an acceptance and mindfulness-based group intervention (Feel-Good-Group) in young people with early psychosis.

Background: Mindfulness-based interventions are promising psychological treatment approaches that may have more substantial long-lasting intervention effects than cognitive behavioral therapy when treating individuals with early psychosis. A pilot study analyzed mindfulness-based inpatient group therapy's feasibility and potential efficacy (Feel-Good). Objective: This paper explores the subjective experiences of participants in the Feel-Good inpatient therapy group to gain insight into the possible changes brought about by the mindfulness-based intervention. Methods: A semi-structured change interview was used to examine the experience of ten participants who participated in the Feel-Good intervention and the additional qualitative assessment. The interviews were conducted 16 weeks after the Feel-Good group ended (16-week Follow-Up). Interviews were transcribed verbatim and analyzed using thematic analysis. Results: The analysis generated five themes-one about personal changes brought about by the Feel-Good group, three about the group therapy experience, and one about wishes/modification suggestions to change and improve the Feel-Good group. The findings suggested that the Feel-Good group was perceived as very helpful, leading to numerous changes in one's overall well-being and relation to emotions. However, patients recommended a more directive therapeutic style and reduced time required for study assessments. Conclusion: Gathering qualitative insight from participants on the Feel-Good intervention revealed meaningful insight into patients' experience of change processes. In addition, participant suggestions help to improve the intervention and study design to increase therapy attendance rates and treatment satisfaction, potentially increasing treatment effectiveness in the future. Clinical trial registration: ClinicalTrials.gov, identifier NCT04592042.

soulspace: Integrated youth mental health care in Berlin, Germany-An introduction to the program and a description of its users.

AIM: A substantial gap between young people's need for mental health care services and their actual access to such services led worldwide organizations (e.g., the WHO) to recommend the implementation of early intervention programs and youth mental health services. Some countries around the world have established structures to meet this recommendation. In this paper, we describe soulspace as the first integrated youth mental health service for young people aged between 15 and 35 years in Berlin, Germany. METHODS: We introduce soulspace as easily accessible mental health care for young people, and we characterize soulspace along the lines of the internationally established eight key principles of integrated youth mental health services (Killackey, et al., 2020, World Economic Forum). Soulspace is a cooperation between clinical outpatient units of psychiatric clinics for adolescents and young adults as well as a community-based counselling service. It provides initial contact, counselling, diagnostics, and treatment. RESULTS: Our analyses of the pathways to soulspace and the characteristics of the soulspace users suggest that the low threshold is a facilitator to help finding for young people in comparison to more conventional early intervention models. That is, having transferred the early intervention center in a youth-facing counselling service as was done in soulspace seems to have reduced the threshold to seek help for families and for young people in need for support. CONCLUSIONS: In summary, with soulspace, an easily accessible mental health care service was established that integrates counselling and specialized psychiatric treatment if needed.

Young people at risk for developing bipolar disorder: Two-year findings from the multicenter prospective, naturalistic Early-BipoLife study.

Early identification and intervention of individuals with an increased risk for bipolar disorder (BD) may improve the course of illness and prevent long­term consequences. Early-BipoLife, a multicenter, prospective, naturalistic study, examined risk factors of BD beyond family history in participants aged 15-35 years. At baseline, positively screened help-seeking participants (screenBD at-risk) were recruited at Early Detection Centers and in- and outpatient depression and attention-deficit/hyperactivity disorder (ADHD) settings, references (Ref) drawn from a representative cohort. Participants reported sociodemographics and medical history and were repeatedly examined regarding psychopathology and the course of risk factors. N = 1,083 screenBD at-risk and n = 172 Ref were eligible for baseline assessment. Within the first two years, n = 31 screenBD at-risk (2.9 %) and none of Ref developed a manifest BD. The cumulative transition risk was 0.0028 at the end of multistep assessment, 0.0169 at 12 and 0.0317 at 24 months (p = 0.021). The transition rate with a BD family history was 6.0 %, 4.7 % in the Early Phase Inventory for bipolar disorders (EPIbipolar), 6.6 % in the Bipolar Prodrome Interview and Symptom Scale-Prospective (BPSS-FP) and 3.2 % with extended Bipolar At-Risk - BARS criteria). In comparison to help-seeking young patients from psychosis detection services, transition rates in screenBD at-risk participants were lower. The findings of Early-BipoLife underscore the importance of considering risk factors beyond family history in order to improved early detection and interventions to prevent/ameliorate related impairment in the course of BD. Large long-term cohort studies are crucial to understand the developmental pathways and long-term course of BD, especially in people at- risk.

Linguistic findings in persons with schizophrenia-a review of the current literature.

Introduction: Alterations of verbalized thought occur frequently in psychotic disorders. We characterize linguistic findings in individuals with schizophrenia based on the current literature, including findings relevant for differential and early diagnosis. Methods: Review of literature published via PubMed search between January 2010 and May 2022. Results: A total of 143 articles were included. In persons with schizophrenia, language-related alterations can occur at all linguistic levels. Differentiating from findings in persons with affective disorders, typical symptoms in those with schizophrenia mainly include so-called "poverty of speech," reduced word and sentence production, impaired processing of complex syntax, pragmatic language deficits as well as reduced semantic verbal fluency. At the at-risk state, "poverty of content," pragmatic difficulties and reduced verbal fluency could be of predictive value. Discussion: The current results support multilevel alterations of the language system in persons with schizophrenia. Creative expressions of psychotic experiences are frequently found but are not in the focus of this review. Clinical examinations of linguistic alterations can support differential diagnostics and early detection. Computational methods (Natural Language Processing) may improve the precision of corresponding diagnostics. The relations between language-related and other symptoms can improve diagnostics.

Machine Learning Prediction of Estimated Risk for Bipolar Disorders Using Hippocampal Subfield and Amygdala Nuclei Volumes.

The pathophysiology of bipolar disorder (BD) remains mostly unclear. Yet, a valid biomarker is necessary to improve upon the early detection of this serious disorder. Patients with manifest BD display reduced volumes of the hippocampal subfields and amygdala nuclei. In this pre-registered analysis, we used structural MRI (n = 271, 7 sites) to compare volumes of hippocampus, amygdala and their subfields/nuclei between help-seeking subjects divided into risk groups for BD as estimated by BPSS-P, BARS and EPIbipolar. We performed between-group comparisons using linear mixed effects models for all three risk assessment tools. Additionally, we aimed to differentiate the risk groups using a linear support vector machine. We found no significant volume differences between the risk groups for all limbic structures during the main analysis. However, the SVM could still classify subjects at risk according to BPSS-P criteria with a balanced accuracy of 66.90% (95% CI 59.2-74.6) for 10-fold cross-validation and 61.9% (95% CI 52.0-71.9) for leave-one-site-out. Structural alterations of the hippocampus and amygdala may not be as pronounced in young people at risk; nonetheless, machine learning can predict the estimated risk for BD above chance. This suggests that neural changes may not merely be a consequence of BD and may have prognostic clinical value.