A precision health approach to medication management in neurodivergence: a model development and validation study using four international cohorts
Listed in
This article is not in any list yet, why not save it to one of your lists.Abstract
Background
Psychotropic medications are commonly used for neurodivergent children, but their effectiveness varies, making prescribing challenging and potentially exposing individuals to multiple medication trials. We developed artificial intelligence (AI) models to predict medication success for stimulants, anti-depressants, and anti-psychotics. We first demonstrate feasibility using cross-sectional data from three research cohorts, then use a cohort of patients from a pharmacology clinic to predict medication choice by class, longitudinally, from electronic medical records (EMRs).
Methods
Models were built to predict cross-sectional medication usage from the Child Behaviour Checklist. Data from the Province of Ontario Neurodevelopmental (POND) network ( N =598) trained and tested the models, while data from the Healthy Brain Network (HBN; N =1,764) and Adolescent Brain Cognitive Development (ABCD; N =2,396) studies were used for external validation. For the EMR cohort, data from the Psychopharmacology Program (PPP; N =312) at Holland Bloorview Kids Rehabilitation Hospital were used to predict longitudinal success. Stacked ensemble models were built separately for each medication class, and area under the receiving operating characteristic curve (AU-ROC) evaluated performance.
Findings
The research cohorts demonstrated feasibility, with internal testing (POND) achieving an AU-ROC (mean [95% CI]) of 0.72 [0.71,0.74] for stimulants, 0.83 [0.80,0.85] for anti-depressants, and 0.79 [0.76,0.82] for anti-psychotics. Performance in external testing sets (HBN and ABCD) confirmed generalizability. In the EMR cohort (PPP), AU-ROC were high: 0.90 [0.88,0.91] for anti-psychotics, 0.82 [0.92,0.83] for stimulants and 0.82 [0.80,0.84] for anti-depressants.
Interpretation
This study demonstrates the feasibility of using AI to enhance medication management for neurodivergent children, with expert clinician decisions learned with high accuracy. These findings support the potential for AI decision aids in community settings, promoting faster access to personalized care while highlighting the complexity of clinical and sociodemographic factors influencing medication decisions.
Funding
Funding was provided by the Canadian Institutes of Health Research (Operating Grant #527447) and Ontario Brain Institute.
Research in context
Evidence before this study
Current medication management practices for neurodevelopmental conditions, particularly for children who have not responded to first-line options, are based clinical best guess approaches that can have negative effects on children, their caregivers, and the health system. Precision health tools using artificial intelligence, which are suitable for community use, have the potential to improve the health system’s capacity for providing timely and impactful care. We searched PubMed on October 17, 2024, for studies published in English evaluating artificial intelligence approaches for medication management in neurodivergence using the terms (“autism” OR “neurodevelopmental condition” OR “neurodevelopmental disorder” OR “neurodivergence”) AND (“artificial intelligence” OR “machine learning” OR “deep learning” OR “prediction”) AND (“medication management” OR “medication response” OR “medication appropriateness” OR “medication decision support”) also including terms where “drug” is substituted for “medication”. We did not find any relevant studies.
Added value of this study
This study demonstrates the feasibility of using AI to assist in medication management for neurodivergent children, with a strong ability to learn expert clinical decisions. These findings show AI may be able to support access to faster, more personalized treatment decisions regarding psychotropic medications. We also identified the relevant clinical and demographic features to the model’s medication recommendations, as well as several biases with respect to sociodemographic factors, highlighting the complexity of factors that contribute to clinical decision-making.
Implications of all the available evidence
This work highlights AI’s potential to improve medication management for neurodivergent children, by offering personalized treatment recommendations. However, identified biases underscore the need for addressing existing inequities. Future research should focus on prospective validation, integration into clinical practice, and bias mitigation to ensure equitable access to effective treatments for all children.
