Early detection of adults ADHD using electronic health records: A machine learning study

BackgroundAttention Deficit Hyperactivity Disorder (ADHD) affects 5-7.2% of children and 2.5% of adults.Despite its prevalence, ADHD remains underdiagnosed and undertreated, leading to significant challenges for affected individuals.Early diagnosis and intervention can prevent adverse outcomes and improve quality of life. MethodsWe developed a predictive model to identify adults with ADHD using Electronic Health Records (EHR).The dataset comprised 2,973 adult patients (aged 18 and above) diagnosed with ADHD and a control group of 4,447 adults referred to psychologists with no ADHD diagnosis.A transformer-based architecture was implemented, utilizing only clinical codes and gender as input features.Five folds cross-validation were adopted, and model performance was evaluated on held-out test data consisting of 800 patients, 400 of whom had an ADHD diagnosis. ResultsOur study demonstrated the ability to predict adult ADHD using clinical data, with a 6-month prediction period achieving an AUC of 0.79 (95% CI: 0.76-0.81),F1-score of 0.79 (95% CI: 0.76-0.81),sensitivity of 0.80 (95% CI: 0.77-0.84),and specificity of 0.77 (95% CI: 0.73-0.81).SHAP analysis revealed key clinical codes influencing ADHD predictions, including 'F158: Other specified mental and behavioral disorders due to use of other stimulants' and 'Y903: Blood alcohol level 0.60 -0.79 mg per 100 ml', reflecting established links between ADHD, substance use, and alcohol disorders. ConclusionsOur findings show that machine learning can effectively use clinical codes and demographic data from routine electronic health records to support early, cost-efficient diagnosis of adult ADHD, paving the way for earlier intervention and improved outcomes.