Machine-Learning prediction of comorbid substance use disorders in ADHD youth using Swedish registry data

Use of Machine Learning Models to Differentiate Neurodevelopment Conditions Through Digitally Collected Data: Cross-Sectional Questionnaire Study

BACKGROUND

Diagnosis of child and adolescent psychopathologies involves a multifaceted approach, integrating clinical observations, behavioral assessments, medical history, cognitive testing, and familial context information. Digital technologies, especially internet-based platforms for administering caregiver-rated questionnaires, are increasingly used in this field, particularly during the screening phase. The ascent of digital platforms for data collection has propelled advanced psychopathology classification methods such as supervised machine learning (ML) into the forefront of both research and clinical environments. This shift, recently called psycho-informatics, has been facilitated by gradually incorporating computational devices into clinical workflows. However, an actual integration between telemedicine and the ML approach has yet to be fulfilled.

OBJECTIVE

Under these premises, exploring the potential of ML applications for analyzing digitally collected data may have significant implications for supporting the clinical practice of diagnosing early psychopathology. The purpose of this study was, therefore, to exploit ML models for the classification of attention-deficit/hyperactivity disorder (ADHD) and autism spectrum disorder (ASD) using internet-based parent-reported socio-anamnestic data, aiming at obtaining accurate predictive models for new help-seeking families.

METHODS

In this retrospective, single-center observational study, socio-anamnestic data were collected from 1688 children and adolescents referred for suspected neurodevelopmental conditions. The data included sociodemographic, clinical, environmental, and developmental factors, collected remotely through the first Italian internet-based screening tool for neurodevelopmental disorders, the Medea Information and Clinical Assessment On-Line (MedicalBIT). Random forest (RF), decision tree, and logistic regression models were developed and evaluated using classification accuracy, sensitivity, specificity, and importance of independent variables.

RESULTS

The RF model demonstrated robust accuracy, achieving 84% (95% CI 82-85; P<.001) for ADHD and 86% (95% CI 84-87; P<.001) for ASD classifications. Sensitivities were also high, with 93% for ADHD and 95% for ASD. In contrast, the DT and LR models exhibited lower accuracy (DT 74%, 95% CI 71-77; P<.001 for ADHD; DT 79%, 95% CI 77-82; P<.001 for ASD; LR 61%, 95% CI 57-64; P<.001 for ADHD; LR 63%, 95% CI 60-67; P<.001 for ASD) and sensitivities (DT: 82% for ADHD and 88% for ASD; LR: 62% for ADHD and 68% for ASD). The independent variables considered for classification differed in importance between the 2 models, reflecting the distinct characteristics of the 3 ML approaches.

CONCLUSIONS

This study highlights the potential of ML models, particularly RF, in enhancing the diagnostic process of child and adolescent psychopathology. Altogether, the current findings underscore the significance of leveraging digital platforms and computational techniques in the diagnostic process. While interpretability remains crucial, the developed approach might provide valuable screening tools for clinicians, highlighting the significance of embedding computational techniques in the diagnostic process.

The genetic epidemiology of schizotypal personality disorder

BACKGROUND

The concept of schizotypal personality disorder (SPD) emerged from observations of personality characteristics common in relatives of schizophrenic patients. While often studied in family designs, few studies and none with genetic measures, have examined SPD in epidemiological samples.

METHODS

We studied individuals born in Sweden 1940-2000 with an ICD-10 diagnosis of SPD with no prior schizophrenia (SZ) diagnosis (n = 2292). Demographic features, patterns of comorbidity, and Family Genetic Risk Scores (FGRS) were assessed from multiple Swedish registries. Prediction of progression to SZ was assessed by Cox models.

RESULTS

SPD was rare, with a prevalence of 0.044%, and had high levels of comorbidity with autism spectrum disorder (ASD), OCD, ADHD, and major depression (MD), and increased rates of being single, unemployed and in receipt of welfare. Affected individuals had elevated levels of FGRS for SZ (+0.42), ASD (+0.30), MD (+0.29), and ADHD (+0.20). Compared to cases of schizophrenia, they had significantly lower rates of FGRSSZ, but significantly elevated rates of genetic risk for ASD, MD, and ADHD. Over a mean follow-up of 8.7 years, 14.6% of SPD cases received a first diagnosis of SZ, the risk for which was significantly increased by levels of FGRSSZ, male sex, young age at SPD diagnosis and an in-patient SPD diagnosis and significantly decreased by comorbidity with MD, ASD, and ADHD.

CONCLUSIONS

Our results not only support the designation of SPD as a schizophrenia spectrum disorder but also suggest potentially important etiologic links between SPD and ASD and, to a lesser extent, ADHD, OCD, and MD.

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

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

A primer on the use of machine learning to distil knowledge from data in biological psychiatry

Applications of machine learning in the biomedical sciences are growing rapidly. This growth has been spurred by diverse cross-institutional and interdisciplinary collaborations, public availability of large datasets, an increase in the accessibility of analytic routines, and the availability of powerful computing resources. With this increased access and exposure to machine learning comes a responsibility for education and a deeper understanding of its bases and bounds, borne equally by data scientists seeking to ply their analytic wares in medical research and by biomedical scientists seeking to harness such methods to glean knowledge from data. This article provides an accessible and critical review of machine learning for a biomedically informed audience, as well as its applications in psychiatry. The review covers definitions and expositions of commonly used machine learning methods, and historical trends of their use in psychiatry. We also provide a set of standards, namely Guidelines for REporting Machine Learning Investigations in Neuropsychiatry (GREMLIN), for designing and reporting studies that use machine learning as a primary data-analysis approach. Lastly, we propose the establishment of the Machine Learning in Psychiatry (MLPsych) Consortium, enumerate its objectives, and identify areas of opportunity for future applications of machine learning in biological psychiatry. This review serves as a cautiously optimistic primer on machine learning for those on the precipice as they prepare to dive into the field, either as methodological practitioners or well-informed consumers.

Attention deficit hyperactivity and oppositional defiant disorder symptoms in adolescence and risk of substance use disorders-A general population-based birth cohort study

BACKGROUND

Externalizing symptoms are associated with risk of future substance use disorder (SUD). Few longitudinal studies exist using general population-based samples which assess the spectrum of attention deficit hyperactivity disorder (ADHD) and oppositional defiant disorder (ODD) symptoms.

AIMS/OBJECTIVES

We aimed to study the associations between adolescent ADHD symptoms and subsequent SUD and additionally examine whether the risk of SUD is influenced by comorbid oppositional defiant disorder (ODD) symptoms.

METHODS

The Northern Finland Birth Cohort 1986 was linked to nationwide health care register data for incident SUD diagnoses until age 33 years (n = 6278, 49.5% male). ADHD/ODD-case status at age 16 years was defined using parent-rated ADHD indicated by Strengths and Weaknesses of ADHD symptoms and Normal Behaviors (SWAN) questionnaire with 95% percentile cut-off. To assess the impact of ODD comorbidity on SUD risk, participants were categorized into four groups based on their ADHD/ODD case status. Cox-regression analysis with hazard ratios (HRs) and 95% confidence intervals (CIs) were used to study associations between adolescent ADHD/ODD case statuses and subsequent SUD.

RESULTS

In all, 552 participants (8.8%) presented with ADHD case status at the age of 16 years, and 154/6278 (2.5%) were diagnosed with SUD during the follow-up. ADHD case status was associated with SUD during the follow-up (HR = 3.84, 95% CI 2.69-5.50). After adjustments for sex, family structure, and parental psychiatric disorder and early substance use the association with ADHD case status and SUD remained statistically significant (HR = 2.60, 95% CI 1.70-3.98). The risk of SUD remained elevated in individuals with ADHD case status irrespective of ODD symptoms.

CONCLUSIONS

ADHD in adolescence was associated with incident SUD in those with and without symptoms of ODD. The association of ADHD and SUD persisted even after adjustment for a wide range of potential confounds. This emphasizes the need to identify preventative strategies for adolescents with ADHD so as to improve health outcomes.

Machine learning in attention-deficit/hyperactivity disorder: new approaches toward understanding the neural mechanisms

Attention-deficit/hyperactivity disorder (ADHD) is a highly prevalent and heterogeneous neurodevelopmental disorder in children and has a high chance of persisting in adulthood. The development of individualized, efficient, and reliable treatment strategies is limited by the lack of understanding of the underlying neural mechanisms. Diverging and inconsistent findings from existing studies suggest that ADHD may be simultaneously associated with multivariate factors across cognitive, genetic, and biological domains. Machine learning algorithms are more capable of detecting complex interactions between multiple variables than conventional statistical methods. Here we present a narrative review of the existing machine learning studies that have contributed to understanding mechanisms underlying ADHD with a focus on behavioral and neurocognitive problems, neurobiological measures including genetic data, structural magnetic resonance imaging (MRI), task-based and resting-state functional MRI (fMRI), electroencephalogram, and functional near-infrared spectroscopy, and prevention and treatment strategies. Implications of machine learning models in ADHD research are discussed. Although increasing evidence suggests that machine learning has potential in studying ADHD, extra precautions are still required when designing machine learning strategies considering the limitations of interpretability and generalization.

Prediction of disease comorbidity using explainable artificial intelligence and machine learning techniques: A systematic review

OBJECTIVE

Disease comorbidity is a major challenge in healthcare affecting the patient's quality of life and costs. AI-based prediction of comorbidities can overcome this issue by improving precision medicine and providing holistic care. The objective of this systematic literature review was to identify and summarise existing machine learning (ML) methods for comorbidity prediction and evaluate the interpretability and explainability of the models.

MATERIALS AND METHODS

The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework was used to identify articles in three databases: Ovid Medline, Web of Science and PubMed. The literature search covered a broad range of terms for the prediction of disease comorbidity and ML, including traditional predictive modelling.

RESULTS

Of 829 unique articles, 58 full-text papers were assessed for eligibility. A final set of 22 articles with 61 ML models was included in this review. Of the identified ML models, 33 models achieved relatively high accuracy (80-95%) and AUC (0.80-0.89). Overall, 72% of studies had high or unclear concerns regarding the risk of bias.

DISCUSSION

This systematic review is the first to examine the use of ML and explainable artificial intelligence (XAI) methods for comorbidity prediction. The chosen studies focused on a limited scope of comorbidities ranging from 1 to 34 (mean = 6), and no novel comorbidities were found due to limited phenotypic and genetic data. The lack of standard evaluation for XAI hinders fair comparisons.

CONCLUSION

A broad range of ML methods has been used to predict the comorbidities of various disorders. With further development of explainable ML capacity in the field of comorbidity prediction, there is a significant possibility of identifying unmet health needs by highlighting comorbidities in patient groups that were not previously recognised to be at risk for particular comorbidities.

Predicting childhood and adolescent attention-deficit/hyperactivity disorder onset: a nationwide deep learning approach

Attention-deficit/hyperactivity disorder (ADHD) is a heterogeneous disorder with a high degree of psychiatric and physical comorbidity, which complicates its diagnosis in childhood and adolescence. We analyzed registry data from 238,696 persons born and living in Sweden between 1995 and 1999. Several machine learning techniques were used to assess the ability of registry data to inform the diagnosis of ADHD in childhood and adolescence: logistic regression, random Forest, gradient boosting, XGBoost, penalized logistic regression, deep neural network (DNN), and ensemble models. The best fitting model was the DNN, achieving an area under the receiver operating characteristic curve of 0.75, 95% CI (0.74-0.76) and balanced accuracy of 0.69. At the 0.45 probability threshold, sensitivity was 71.66% and specificity was 65.0%. There was an overall agreement in the feature importance among all models (τ > .5). The top 5 features contributing to classification were having a parent with criminal convictions, male sex, having a relative with ADHD, number of academic subjects failed, and speech/learning disabilities. A DNN model predicting childhood and adolescent ADHD trained exclusively on Swedish register data achieved good discrimination. If replicated and validated in an external sample, and proven to be cost-effective, this model could be used to alert clinicians to individuals who ought to be screened for ADHD and to aid clinicians' decision-making with the goal of decreasing misdiagnoses. Further research is needed to validate results in different populations and to incorporate new predictors.

Risk behaviors in substance use disorder in a sample of Egyptian female patients with or without symptoms of attention-deficit hyperactivity disorder

Background

Risk-taking behaviors are associated with attention-deficit hyperactivity disorder (ADHD) and substance use disorder (SUD). Individuals with both diagnoses have been reported to have an earlier onset, a longer course, and greater severity, with more relapses and greater difficulty remaining abstinent.

The current study was assessing females seeking treatment for SUDs for the presence of comorbid ADHD, to investigate the association between severity of SUD and co-occurring ADHD symptoms and to examine related risk behaviors. Therefore, thirty female patients were enrolled, and demographic data was collected. Participants were interviewed by SCID I, addiction severity index, Arabic-translated and validated version of the adult ADHD Self-Report Scale Barratt Impulsiveness Scale Version 11, and Arabic version of the Adult Scale of Hostility and Aggression.

Results

Thirty female patients were included in the study, and 33.3% had extreme severity, on the addiction severity index scale. Fifteen patients had ADHD symptoms; 33.3% had high likely scores, according to Adult ADHD Self-Reported Scale (ASRS). There is a significant difference regarding the age of onset of substance use and smoking (P = 0.029), first sexual activity (P = 0.002), number of sexual partners (P = 0.009), impairment in employment, and family and social relationships items (P = 0.024, P = 0.028, respectively) in SUD patients with ADHD symptoms than in SUD patients without ADHD symptoms.

Conclusion

Female patients diagnosed with adult ADHD have an earlier age of smoking and substance use, having first sexual activity at younger age, and having more sexual partners with more employment, family, and social relationship problems.

Machine Learning and MRI-based Diagnostic Models for ADHD: Are We There Yet?

OBJECTIVE

Machine learning (ML) has been applied to develop magnetic resonance imaging (MRI)-based diagnostic classifiers for attention-deficit/hyperactivity disorder (ADHD). This systematic review examines this literature to clarify its clinical significance and to assess the implications of the various analytic methods applied.

METHODS

A comprehensive literature search on MRI-based diagnostic classifiers for ADHD was performed and data regarding the utilized models and samples were gathered.

RESULTS

We found that, although most studies reported the classification accuracies, they varied in choice of MRI modalities, ML models, cross-validation and testing methods, and sample sizes. We found that the accuracies of cross-validation methods inflated the performance estimation compared with those of a held-out test, compromising the model generalizability. Test accuracies have increased with publication year but were not associated with training sample sizes. Improved test accuracy over time was likely due to the use of better ML methods along with strategies to deal with data imbalances.

CONCLUSION

Ultimately, large multi-modal imaging datasets, and potentially the combination with other types of data, like cognitive data and/or genetics, will be essential to achieve the goal of developing clinically useful imaging classification tools for ADHD in the future.

Optimizing Substance Use Treatment Selection Using Reinforcement Learning

Substance use disorder (SUD) exacts a substantial economic and social cost in the United States, and it is crucial for SUD treatment providers to match patients with feasible, effective, and affordable treatment plans. The availability of large SUD patient datasets allows for machine learning techniques to predict patient-level SUD outcomes, yet there has been almost no research on whether machine learning can be used to optimize or personalize which treatment plans SUD patients receive. We use contextual bandits (a reinforcement learning technique) to optimally map patients to SUD treatment plans, based on dozens of patient-level and geographic covariates. We also use near-optimal policies to incorporate treatments’ time-intensiveness and cost into our recommendations, to aid treatment providers and policymakers in allocating treatment resources. Our personalized treatment recommendation policies are estimated to yield higher remission rates than observed in our original dataset, and they suggest clinical insights to inform future research on data-driven SUD treatment matching.

Training a machine learning classifier to identify ADHD based on real-world clinical data from medical records

The diagnostic process of attention deficit hyperactivity disorder (ADHD) is complex and relies on criteria sensitive to subjective biases. This may cause significant delays in appropriate treatment initiation. An automated analysis relying on subjective and objective measures might not only simplify the diagnostic process and reduce the time to diagnosis, but also improve reproducibility. While recent machine learning studies have succeeded at distinguishing ADHD from healthy controls, the clinical process requires differentiating among other or multiple psychiatric conditions. We trained a linear support vector machine (SVM) classifier to detect participants with ADHD in a population showing a broad spectrum of psychiatric conditions using anonymized data from clinical records (N = 299 participants). We differentiated children and adolescents with ADHD from those not having the condition with an accuracy of 66.1%. SVM using single features showed slight differences between features and overlapping standard deviations of the achieved accuracies. An automated feature selection achieved the best performance using a combination 19 features. Real-world clinical data from medical records can be used to automatically identify individuals with ADHD among help-seeking individuals using machine learning. The relevant diagnostic information can be reduced using an automated feature selection without loss of performance. A broad combination of symptoms across different domains, rather than specific domains, seems to indicate an ADHD diagnosis.

A Bayesian learning model to predict the risk for cannabis use disorder

BACKGROUND

The prevalence of cannabis use disorder (CUD) has been increasing recently and is expected to increase further due to the rising trend of cannabis legalization. To help stem this public health concern, a model is needed that predicts for an adolescent or young adult cannabis user their personalized risk of developing CUD in adulthood. However, there exists no such model that is built using nationally representative longitudinal data.

METHODS

We use a novel Bayesian learning approach and data from Add Health (n = 8712), a nationally representative longitudinal study, to build logistic regression models using four different regularization priors: lasso, ridge, horseshoe, and t. The models are compared by their prediction performance on unseen data via 5-fold-cross-validation (CV). We assess model discrimination using the area under the curve (AUC) and calibration by comparing the expected (E) and observed (O) number of CUD cases. We also externally validate the final model on independent test data from Add Health (n = 570).

RESULTS

Our final model is based on lasso prior and has seven predictors: biological sex; scores on personality traits of neuroticism, openness, and conscientiousness; and measures of adverse childhood experiences, delinquency, and peer cannabis use. It has good discrimination and calibration performance as reflected by its respective AUC and E/O of 0.69 and 0.95 based on 5-fold CV and 0.71 and 1.10 on validation data.

CONCLUSION

This externally validated model may help in identifying adolescent or young adult cannabis users at high risk of developing CUD in adulthood.

Sex Differences in Substance Use, Prevalence, Pharmacological Therapy, and Mental Health in Adolescents with Attention-Deficit/Hyperactivity Disorder (ADHD)

Sex differences are poorly studied within the field of mental health, even though there is evidence of disparities (with respect to brain anatomy, activation patterns, and neurochemistry, etc.) that can significantly influence the etiology and course of mental disorders. The objective of this work was to review sex differences in adolescents (aged 13–18 years) diagnosed with ADHD (according to the DSM-IV, DSM-IV-TR and DSM-5 criteria) in terms of substance use disorder (SUD), prevalence, pharmacological therapy and mental health. We searched three academic databases (PubMed, Web of Science, and Scopus) and performed a narrative review of a total of 21 articles. The main conclusions of this research were (1) girls with ADHD are more at risk of substance use than boys, although there was no consensus on the prevalence of dual disorders; (2) girls are less frequently treated because of underdiagnosis and because they are more often inattentive and thereby show less disruptive behavior; (3) together with increased impairment in cognitive and executive functioning in girls, the aforementioned could be related to greater substance use and poorer functioning, especially in terms of more self-injurious behavior; and (4) early diagnosis and treatment of ADHD, especially in adolescent girls, is essential to prevent early substance use, the development of SUD, and suicidal behavior.

Co-occurring Mental Disorders in Transitional Aged Youth With Substance Use Disorders - A Narrative Review

Adolescence and emerging adulthood are often referred to as youth. Transitional psychiatry addresses this target group, which considers patients between 15 and 25 years of age. Substance use usually begins and peaks at this stage of life. Psychiatric disorders, foremost attention-deficit/hyperactivity disorder, and affective disorders, conduct disorders, and first-episodes psychosis frequently appear in early life stages. This review aims to provide a broad overview of transitional-aged youth's most common psychiatric comorbidities with substance use disorders. A literature search was conducted in Embase and Pubmed, and the main findings are described narratively. We present main findings for the following comorbidities: attention-deficit/hyperactivity disorder, conduct disorder, personality disorders, affective disorders, psychotic disorders, and the phenomena of overdose and suicidality. In conclusion, co-occurring mental health disorders are common and appear to facilitate the development of substance use disorders and exacerbate their overall course. Substance use also affects the severity and course of comorbid psychiatric disorders. Overall, data on transition-age youth with substance use disorders are highly inconsistent. Universal screening and treatment guidelines do not yet exist but should be aimed for in the future.

Social and Behavioral Determinants of Health in the Era of Artificial Intelligence with Electronic Health Records: A Scoping Review

Background. There is growing evidence that social and behavioral determinants of health (SBDH) play a substantial effect in a wide range of health outcomes. Electronic health records (EHRs) have been widely employed to conduct observational studies in the age of artificial intelligence (AI). However, there has been limited review into how to make the most of SBDH information from EHRs using AI approaches.Methods. A systematic search was conducted in six databases to find relevant peer-reviewed publications that had recently been published. Relevance was determined by screening and evaluating the articles. Based on selected relevant studies, a methodological analysis of AI algorithms leveraging SBDH information in EHR data was provided.Results. Our synthesis was driven by an analysis of SBDH categories, the relationship between SBDH and healthcare-related statuses, natural language processing (NLP) approaches for extracting SBDH from clinical notes, and predictive models using SBDH for health outcomes.Discussion. The associations between SBDH and health outcomes are complicated and diverse; several pathways may be involved. Using NLP technology to support the extraction of SBDH and other clinical ideas simplifies the identification and extraction of essential concepts from clinical data, efficiently unlocks unstructured data, and aids in the resolution of unstructured data-related issues.Conclusion. Despite known associations between SBDH and diseases, SBDH factors are rarely investigated as interventions to improve patient outcomes. Gaining knowledge about SBDH and how SBDH data can be collected from EHRs using NLP approaches and predictive models improves the chances of influencing health policy change for patient wellness, ultimately promoting health and health equity.

Alcohol use disorders and ADHD

Despite a growing literature on the complex bidirectional relationship of ADHD and substance use, reviews specifically focusing on alcohol are scarce. ADHD and AUD show a significant genetic overlap, including genes involved in gluatamatergic and catecholaminergic neurotransmission. ADHD drives risky behavior and negative experiences throughout the lifespan that subsequently enhance a genetically increased risk for Alcohol Use Disorders (AUD). Impulsive decisions and a maladaptive reward system make individuals with ADHD vulnerable for alcohol use and up to 43 % develop an AUD; in adults with AUD, ADHD occurs in about 20 %, but is vastly under-recognized and under-treated. Thus, routine screening and treatment procedures need to be implemented in AUD treatment. Long-acting stimulants or non-stimulants can be used to treat ADHD in individuals with AUD. However, it is crucial to combine medical treatment for ADHD with pharmacotherapy and psychotherapy for AUD, and other comorbid disorders. Identification of individuals at risk for AUD, especially those with ADHD and conduct disorder or oppositional defiant disorder, is a key factor to prevent negative outcomes.

A machine learning approach for predicting suicidal thoughts and behaviours among college students

Suicidal thoughts and behaviours are prevalent among college students. Yet little is known about screening tools to identify students at higher risk. We aimed to develop a risk algorithm to identify the main predictors of suicidal thoughts and behaviours among college students within one-year of baseline assessment. We used data collected in 2013–2019 from the French i-Share cohort, a longitudinal population-based study including 5066 volunteer students. To predict suicidal thoughts and behaviours at follow-up, we used random forests models with 70 potential predictors measured at baseline, including sociodemographic and familial characteristics, mental health and substance use. Model performance was measured using the area under the receiver operating curve (AUC), sensitivity, and positive predictive value. At follow-up, 17.4% of girls and 16.8% of boys reported suicidal thoughts and behaviours. The models achieved good predictive performance: AUC, 0.8; sensitivity, 79% for girls, 81% for boys; and positive predictive value, 40% for girls and 36% for boys. Among the 70 potential predictors, four showed the highest predictive power: 12-month suicidal thoughts, trait anxiety, depression symptoms, and self-esteem. We identified a parsimonious set of mental health indicators that accurately predicted one-year suicidal thoughts and behaviours in a community sample of college students.