Leveraging large language models and traditional machine learning ensembles for ADHD detection from narrative transcripts

TL;DR

This study develops an ensemble method combining large language models and traditional ML to improve ADHD detection from narrative transcripts, demonstrating enhanced accuracy and robustness over individual models.

Contribution

The paper introduces a novel ensemble framework integrating LLaMA3, RoBERTa, and SVM for psychiatric text classification, specifically ADHD detection, showing improved performance over single models.

Findings

Ensemble achieved an F1 score of 0.71.

Ensemble outperformed individual models in recall.

Hybrid architecture enhances robustness and sensitivity.

Abstract

Despite rapid advances in large language models (LLMs), their integration with traditional supervised machine learning (ML) techniques that have proven applicability to medical data remains underexplored. This is particularly true for psychiatric applications, where narrative data often exhibit nuanced linguistic and contextual complexity, and can benefit from the combination of multiple models with differing characteristics. In this study, we introduce an ensemble framework for automatically classifying Attention-Deficit/Hyperactivity Disorder (ADHD) diagnosis (binary) using narrative transcripts. Our approach integrates three complementary models: LLaMA3, an open-source LLM that captures long-range semantic structure; RoBERTa, a pre-trained transformer model fine-tuned on labeled clinical narratives; and a Support Vector Machine (SVM) classifier trained using TF-IDF-based lexical features. These models are aggregated through a majority voting mechanism to enhance predictive robustness. The dataset includes 441 instances, including 352 for training and 89 for validation. Empirical results show that the ensemble outperforms individual models, achieving an F$_1$ score of 0.71 (95\% CI: [0.60-0.80]). Compared to the best-performing individual model (SVM), the ensemble improved recall while maintaining competitive precision. This indicates the strong sensitivity of the ensemble in identifying ADHD-related linguistic cues. These findings demonstrate the promise of hybrid architectures that leverage the semantic richness of LLMs alongside the interpretability and pattern recognition capabilities of traditional supervised ML, offering a new direction for robust and generalizable psychiatric text classification.