Seedlabs
Source research

Diagnosing attention-deficit hyperactivity disorder (ADHD) using artificial intelligence: a clinical study in the UK

Tianhua Chen, Ilias Tachmazidis, Sotiris Batsakis, Marios Adamou, Emmanuel P. Papadakis, Grigoris Antoniou · 2023 · 45 citationsRead the paper

Attention-deficit hyperactivity disorder (ADHD) is a neurodevelopmental disorder affecting a large percentage of the adult population. A series of ongoing efforts has led to the development of a hybrid AI algorithm (a combination of a machine learning model and a knowledge-based model) for assisting adult ADHD diagnosis, and its clinical trial currently operating in the largest National Health Service (NHS) for adults with ADHD in the UK. Most recently, more data was made available that has lead to a total collection of 501 anonymized records as of 2022 July. This prompted the ongoing research to carefully examine the model by retraining and optimizing the machine learning algorithm in order to update the model with better generalization capability. Based on the large data collection so far, this paper also pilots a study to examine the effectiveness of variables other than the Diagnostic Interview for ADHD in adults (DIVA) assessment, which adds considerable cost in the screenining process as it relies on specially trained senior clinicians. Results reported in this paper demonstrate that the newly trained machine learning model reaches an accuracy of 75.03% when all features are used; the hybrid model obtains an accuracy of 93.61%. Exceeding what clinical experts expected in the absence of DIVA, achieving an accuracy of 65.27% using a rule-based machine learning model alone encourages the development of a cost effective model in the future.

What the full text shows

Deployed in practice
  • The hybrid AI model (ML + knowledge-based) achieved the highest diagnostic accuracy. — 93.61% accuracy (When referring complex cases to medical experts (Yes/No/Expert outcome))
  • The machine learning model using all available features reached a specific accuracy. — 75.03% accuracy (Using all features including DIVA assessments)
  • A rule-based machine learning model can diagnose ADHD without the costly DIVA assessment. — 65.27% accuracy (Excluding DIVA attributes; trained on full dataset)
  • Removing DIVA attributes significantly reduces the performance of the ML model. — Test accuracy dropped from 66.48% to 58.08% (10-fold cross-validation comparison)
  • The knowledge-based (KR) model accuracy increases when referring complex cases to experts. — 81.37% to 92.42% accuracy (Moving from Yes/No outcome to Yes/No/Expert outcome)
Setup
501 anonymized adult ADHD patient records (236 positive, 265 negative) from an NHS provider in the UK, containing 66 independent attributes.
How
The researchers developed a hybrid system combining a Classification and Regression Tree (CART) machine learning model with a rule-based knowledge model derived from expert interviews. They performed hyper-parameter optimization via grid search and validated the ML model using 10-fold cross-validation.
Limitations
The ML model without DIVA attributes did not reach a high enough accuracy for clinical testing. · The current knowledge model relies on DIVA values and cannot be used in the DIVA-less hybrid approach. · The dataset is skewed toward male subjects (322 males vs 179 females).

Summarized by Gemma 4 from the open-access full text · 8 Oct 2026. Read it