AI readiness in pharma: Getting the foundation right
AI readiness in pharma depends on data, not just AI. Read how real‑world data and interoperability enable scalable evidence generation.
AI in drug development is not a data problem – it’s an evidence problem
A new opinion piece by Narasimha Kumar, published in MedCity News, explores why “AI in Drug Development Is Not a Data Problem, It’s an Evidence Problem.” The article examines how the challenge is no longer collecting data, but preserving the context, meaning, and relationships that transform data into usable evidence.
Kumar argues that AI cannot reliably generate trusted evidence from fragmented clinical data alone. Instead, he calls for the development of connected evidence networks that preserve semantic meaning, clinical context, temporal sequencing, and multimodal relationships across the patient journey to support more reliable scientific and regulatory decision-making.
Excerpt from the article
The pharmaceutical industry has never had more data, but AI-powered drug development will not advance on data volume alone. Clinical trials, electronic health records, imaging archives, pathology reports, genomic repositories, laboratory systems and patient registries generate petabytes of information every year. Add the growing volume of patient-generated and real-world data, and the industry has more than enough raw material to fuel the next generation of AI-driven discovery.
Yet AI continues to struggle to connect observations into meaningful evidence. The reason is simple: drug development is not suffering from a shortage of data. It is suffering from a shortage of usable knowledge.
More from the same author
In “How data from medical practice can inform care,” published in MedNous, Kumar explores how real‑world data challenges traditional views of standard of care and enables more accurate, data‑driven decisions across trial design and evidence generation.
In “AI Readiness in Pharma – Getting the Foundation Right,” published in Bio‑IT World, Kumar examines how data fragmentation, complex regulations, and limited interoperability are slowing AI adoption—and what it takes to build trusted, cross‑border evidence ecosystems.
Last updated