A cutting-edge AI model has been developed to predict adverse drug reactions, possibly revolutionizing early-stage drug safety assessment before clinical trials.
The significance of Adverse Drug Reactions
Adverse drug reactions (ADRs) are a major cause of hospital admissions and treatment discontinuation worldwide. However, conventional approaches often fail to detect rare or delayed effects of medicinal products. In order to improve early detection, a research team from the Medical University of Sofia has developed a deep learning model that can predict the likelihood of ADRs based solely on a drug’s chemical structure.
The Development Process
The AI model was built using a neural network trained with reference pharmacovigilance data. Input features were derived from SMILES codes – a standard format representing molecular structure. predictions were generated for six major ADRs: hepatotoxicity, nephrotoxicity, cardiotoxicity, neurotoxicity, hypertension, and photosensitivity.
The model successfully identified many expected reactions while producing relatively few false positives, demonstrating acceptable accuracy in predicting ADRs.
Real-World Applications
Testing of the model with well-characterized drugs resulted in predictions consistent with known side-effect profiles. For example,it estimated a 94.06% probability of hepatotoxicity for erythromycin, an 88.44% probability for nephrotoxicity and a 75.8% probability for hypertension in cisplatin. Additionally, the model predicted a 22% likelihood of photosensitivity for cisplatin and a higher likelihood of photosensitivity (64.8%) for the experimental compound ezeprogind. For enadoline, a novel molecule, the model returned low probability scores across all ADRs, suggesting minimal risk.
These results demonstrate the potential of this AI model as a decision-support tool in early-phase drug discovery and regulatory safety monitoring. The authors note that incorporating factors such as dose levels and patient-specific parameters could further enhance its performance.
The Research Article:
Ruseva V., Dobrev S., Getova-Kolarova V., Peneva A., getov I., Dimitrova M., Petkova V.. In situ development of an artificial intelligence (AI) model for early detection of adverse drug reactions (ADRs) to ensure drug safety.Pharmacia :1-8.https://doi.org/10.3897/pharmacia.72.e160997
Related Articles:
Volunteer “Community Scientists” Do a Pretty Darn Good Job Generating Usable Data
AI models have revolutionized drug safety in ways we never thought possible.