Polygenic and machine learning analysis of medication response in a prospective pediatric cohort initiating ADHD medication
- 1Center of Neurodevelopmental Disorders (KIND), Centre for Psychiatry Research, Department of Women and Children Health, Karolinska Institutet, Region Stockholm,
Abstract
While medication for attention deficit hyperactivity disorder (ADHD) is effective, predictors of treatment response remain poorly understood. Given the use of polygenic scores (PGS) in psychiatric conditions, we investigate their potential to predict ADHD medication response. In this work, we recruited 309 participants aged 6-17 years from the Swedish ADHD medication and predictors of treatment outcome (ADAPT) study (ClinicalTrials.gov: NCT02136147; June 2015), and calculated their PGS. Compared with a reference cohort (N=780), ADAPT showed higher PGS for ADHD (p<2.22e-16), and lower PGS for autism (p=0.0051), educational attainment (EA) (p=8e-10), and intelligence (p=7e-08). To assess the association between genetic effects and changes in Swanson, Nolan, and Pelham ADHD Rating Scale-version IV (SNAP-IV) scores, linear mixed-effects models tested the interaction between each PGS and time (baseline, 3-months). PGS for ADHD was associated with higher SNAP-IV scores overall ({beta}=0.1419, p=0.0078, FDR=0.0293) but not with a change at follow-up; whereas, PGS for EA was associated with lower overall scores ({beta}=-0.1161, p=0.0256, FDR=0.0679) and smaller reductions at follow-up ({beta}=0.0946, p=0.0453, FDR=0.1130). Subgroup analyses indicated that these effects were more prominent in adolescents ([≥]13 years) and individuals classified as responders to treatment. We further explored machine learning models combining clinical and genetic information across 14 models with 49 features. Although models could not empirically generalize, estimated information-theoretic upper bounds for classification accuracy were 72% with PGS, 84% with clinical and demographic variables, and 92% when combined. This study highlights the potential of using PGS and combining genetic and clinical data to improve treatment stratification in ADHD.
Related
- Gastrointestinal medication use patterns and incident depressive symptoms among adults aged 50 years or older: a prospective multicohort study
- Antiseizure medication-induced changes in serum ephrin-B2 and their association with treatment response in adults with generalised seizure disorders in Northern India: protocol for a prospective observational cohort study
- A Prospective Interventional Study Comparing a Multimodal Intervention Incorporating Behavior, Exercise, Nutrition, Medication, and Posture With Exercise and Medication in Patients With Chronic Nonspecific Low Back Pain
- The Effect of Medication Self-Management During Hospitalisation (SelfMED) on Medication Adherence Post-Discharge in Oncology Patients with Polypharmacy: A Prospective, Exploratory, Single-Centre, Non-Randomised Pre-Post Intervention Study with Sequential Control and Intervention Cohorts.
- Assessing medication safety culture in Norwegian pediatric wards: a first nationwide survey
BibTeX
@misc{escalerabalsera2026polygenic,
title = {{Polygenic and machine learning analysis of medication response in a prospective pediatric cohort initiating ADHD medication}},
author = {A. Escalera-Balsera and M. M. Lilja and M. Nordstrand and T. Falck-Ytter and E. Serlachius and J. Bhagia and K. Tammimies and L. Halldner},
howpublished = {medRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.09.26362635},
url = {https://www.medrxiv.org/content/10.64898/2026.09.09.26362635v1},
note = {CC BY-ND},
}
RIS
TY - UNPB
TI - Polygenic and machine learning analysis of medication response in a prospective pediatric cohort initiating ADHD medication
AU - A. Escalera-Balsera
AU - M. M. Lilja
AU - M. Nordstrand
AU - T. Falck-Ytter
AU - E. Serlachius
AU - J. Bhagia
AU - K. Tammimies
AU - L. Halldner
PY - 2026
DA - 2026/09/09
PB - medRxiv
DO - 10.64898/2026.09.09.26362635
UR - https://www.medrxiv.org/content/10.64898/2026.09.09.26362635v1
AB - While medication for attention deficit hyperactivity disorder (ADHD) is effective, predictors of treatment response remain poorly understood. Given the use of polygenic scores (PGS) in psychiatric conditions, we investigate their potential to predict ADHD medication response. In this work, we recruited 309 participants aged 6-17 years from the Swedish ADHD medication and predictors of treatment outcome (ADAPT) study (ClinicalTrials.gov: NCT02136147; June 2015), and calculated their PGS. Compared with a reference cohort (N=780), ADAPT showed higher PGS for ADHD (p<2.22e-16), and lower PGS for autism (p=0.0051), educational attainment (EA) (p=8e-10), and intelligence (p=7e-08). To assess the association between genetic effects and changes in Swanson, Nolan, and Pelham ADHD Rating Scale-version IV (SNAP-IV) scores, linear mixed-effects models tested the interaction between each PGS and time (baseline, 3-months). PGS for ADHD was associated with higher SNAP-IV scores overall ({beta}=0.1419, p=0.0078, FDR=0.0293) but not with a change at follow-up; whereas, PGS for EA was associated with lower overall scores ({beta}=-0.1161, p=0.0256, FDR=0.0679) and smaller reductions at follow-up ({beta}=0.0946, p=0.0453, FDR=0.1130). Subgroup analyses indicated that these effects were more prominent in adolescents ([≥]13 years) and individuals classified as responders to treatment. We further explored machine learning models combining clinical and genetic information across 14 models with 49 features. Although models could not empirically generalize, estimated information-theoretic upper bounds for classification accuracy were 72% with PGS, 84% with clinical and demographic variables, and 92% when combined. This study highlights the potential of using PGS and combining genetic and clinical data to improve treatment stratification in ADHD.
ER -