Context: In the last decade, the number of submissions from drugmakers that include an AI or machine-learning component has seen an exponential rise. In January 2025, the U.S. Food and Drug Administration (FDA) proposed draft guidelines on the use of artificial intelligence (AI) to assess the safety and effectiveness of drugs.
Relevance of the Topic:Mains: Role of AI in Drug-testing- Applications & Limitations.
Limitations of Conventional Testing & Need for AI
- Dependence on animal models:
- Pharma industries have traditionally used animal models’ response to various compounds to assess whether a drug can proceed to human clinical trials.
- But different populations globally respond differently to drugs and diseases according to age, sex, pre-existing medical conditions, and genetic variabilities etc. This range can not be captured by the response of a homogenous, lab-bred animal population.
- E.g., Rats can eliminate some drugs from their bodies much faster than humans. For the same dose level, humans need to be exposed to the drug for a longer duration.
- High cost and low success rates:
- It takes nearly 10 years and over a billion dollars to develop a drug using conventional (animal-based) processes, which have a success rate of only 14%.
Role of AI in drug development:
Limitations of the AI models
Despite the potential to overcome barriers of conventional testing, AI has its own challenges.
- Reliability and bias: Use of biased and/or under-representative data of a target population will also compromise the output. An incorrect prediction could have life-threatening implications.
- Lack of Transparency: Algorithms of most AI models are not open to independent scrutiny, nor is the data used to train them easily accessible. Hence the models’ performance can not be assessed as required.
- Ethical concerns: There is no legal accountability and responsibility arising out of the decisions made by AI (as AI models can self-learn and adapt over time).
Recent developments in AI-driven drug testing:
- US: FDA’s draft guidelines focusses on:
- Improving the quality and quantity of data used to train the AI model.
- Need to continuously monitor AI models for reliability. Encourage the industry to discuss and design appropriate ways to assess their AI models.
- Use of AI in the preclinical stage in particular to assess/approve the safety and effectiveness of a drug (or a compound of interest) before starting human clinical trials.
- India: New Drugs and Clinical Trials (Amendment) Rules 2023:
- It allowed data generated by advanced computational models to be used to assess the safety and efficacy of new drugs, freeing researchers from relying on animal trials alone.
There is a need for convergence of guidelines issued by global regulators that can help harmonise (i) government policy, (ii) manufacturers’ expectations and compliance burden, (iii) researchers’ strategy, and (iv) consumer safety. This will be crucial for utilising AI to develop a more effective and affordable healthcare system.