CaresAI at CT-DEB26: Detecting Dosing Errors In Clinical Trials Using Domain-Specific Transformer Embeddings and Classification Models
2026-06-29 • Computation and Language
Computation and Language
AI summaryⓘ
The authors studied how to find dosing mistakes in clinical trial plans using special language models trained on medical texts. They tested different models to turn trial text into computer-readable form and then used these with traditional machine learning methods to spot errors. Their results showed that models tailored to biology worked better than general clinical ones, and combining models didn't help much. The best methods could fairly accurately predict when a trial might have dosing problems, which could help keep patients safer and improve trial quality.
Medication errorsDosing errorsClinical trialsTransformer modelsBioBERTMachine learningROC-AUCClinicalBERTGradient boostingPatient safety
Authors
Leon Hamnett, Favour Igwezeke, Joseph Itopa Abubakar, Mary Adetutu Adewunmi
Abstract
Medication errors, particularly dosing errors in clinical trials (CT), can lead to patient harm, adverse drug events and worse patient outcomes. Dosing errors are preventable, and early identification can improve trial integrity and mitigate subsequent clinical and financial burden. This study aims to detect dosing errors within CT protocols by evaluating text representations of trial information using transformer-based language models trained on biomedical corpora. CT textual data was encoded using several models, including ClinicalBERT, PubMedBERT, BioBERT, and MedCPT, and integrated with categorical features. These text embeddings were used as input to classical machine learning models and neural network architectures within an experimental framework. Performance was primarily assessed using ROC-AUC with respect to predicting dosage error. Under a logistic regression baseline, BioBERT consistently outperformed alternative encoders, achieving an ROC-AUC of 0.794, a 3.95% improvement over the ClinicalBERT baseline. Combining multiple embeddings did not yield improvements, indicating that domain alignment outweighs representational stacking. Gradient boosting models, support vector classifiers, logistic regression, and residual neural networks achieved the strongest performance for predicting dosage error, achieving ROC-AUCs: 0.821 to 0.853. Overall, the integration of domain-specific transformer embeddings with structured metadata enables discrimination of trials meeting a predefined elevated dosing error risk criterion, advancing safety monitoring and supporting informed regulatory decision-making.