However, the use of AI in drug development is still in its early stages and faces challenges such as a lack of trust and explainability, as well as issues related to the handling of unstructured and heterogeneous data. The author argues that overcoming these challenges will require a significant amount of AI talent, individuals who have mastered AI and have a strong scientific background to understand the existing data and build AI systems that work transparently with it.
Key takeaways:
- The FDA has declared a shortage of Adderall and other ADHD treatments, as well as drugs for the treatment of cancer and serious diseases, causing difficulty for millions of people in accessing their prescriptions.
- Most drug shortages are caused by a combination of factors including regulatory restrictions, formulation considerations, supply chain breakdowns, and a lack of manufacturers to meet demand.
- Artificial Intelligence (AI) and machine learning could potentially solve the drug shortage problem by accelerating drug development and discovery, de-risking the experimentation process, reducing errors, and supporting the reformulation of already existing treatments.
- Despite its potential, the use of AI in drug development faces challenges such as a lack of trust and explainability, the sheer amount of unstructured and heterogeneous data in life sciences, and the need for AI talent with a strong scientific background.