What happened
Anil Kane, executive director and global head of technical & scientific affairs at Thermo Fisher Scientific, told BioProcess International that AI and advanced analytics can help teams identify hard-to-see patterns in areas such as enrollment forecasting and clinical supply planning.
Why it matters
Kane said his firm has applied AI in sterile fill-finish manufacturing to reduce rejection rates, and used AI, machine learning and predictive modeling in oral solid dose form development — a shift away from the trial-and-error approach he said is gone.
What to watch
Kane expects these capabilities to get better at connecting signals, with the next step being to understand how changes in one part of a development program affect another; he said validation, data provenance, transparency and human oversight grow more important as AI nears regulated decisions.
WHO IT HITSBiopharma development and manufacturing teams — particularly those running clinical supply planning, enrollment forecasting and fill-finish operations — face pressure to keep human experts in the loop for validation as AI tools move closer to regulated decisions.
Ask the AI about this article →
Summaries like this, in your inbox every morning.
Kane's comments come as AI tools keep spreading through biopharmaceutical development and manufacturing. He described a landscape where the technology already has broad influence on how biotech companies do business, and where conferences now devote numerous talks to AI's efficiency gains.
At the same time, he drew a clear line between what AI can do and what it needs. The stronger the dataset, the better the machine learning and the more robust the model, he said. He also described a shift in expectations, saying the days of trial and error are gone and that stakeholders no longer have the time or appetite to go back to the drawing board on predictive modeling.
Whether that balance holds will likely hinge on how companies handle validation and human oversight as these tools move toward regulated decisions. For now, Kane frames AI as an amplifier of speed and efficiency rather than a replacement — one that still depends on subject matter experts to make the call.
For example, today's edition would include:
AI-summarized, only the topics you pick — one digest a day via Email, Slack, or Discord.
Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. Q&As are published on this page for other readers too.
PCAST co-chair David Sacks posted on X on September 12 in response to Anthropic CEO Dario Amodei's essay "We M…
ServiceNow AI crossed $1 billion in annual contract value in the second quarter, and the author predicts it tr…
The Motley Fool laid out a $5,000 AI portfolio split across three layers: $2,500 in Amazon, $1,750 in Taiwan S…
Fortinet acquired Virtue AI, a move aimed at extending its AI security and strengthening real-time protection…
A Korean office worker wrote on the community "リメンバー" that he asked ChatGPT about chest tightness and breathin…
SCREEN and Lasertec both fell to lower revenue and profit in their latest fiscal years, but now forecast reven…
