10/26/2026  |   Marissa Russo  |  Fierce Biotech

https://www.fiercebiotech.com/cro/microsoft-bi-team-launch-digital-patient-twins-trial-design-improvements 

Boehringer Ingelheim and Microsoft have launched a collaboration to explore the use of AI-powered digital patient twins to improve clinical trial design.

Digital patient twins are computational representations of individual patients that use clinical and other relevant data to predict how a disease might progress and how outcomes could evolve under different scenarios, according to an Oct. 22 release. 

“The aim is not to mimic or replace an entire clinical trial. The research will explore disease-progression modelling, predictive outcome modelling, patient stratification and advanced trial simulation,” a Boehringer Ingelheim spokesperson told Fierce.

The research aims to support the design of more patient-centric and efficient clinical trials. One approach the companies plan to explore is the use of digital patient twins to create synthetic or hybrid control arms, potentially reducing the number of patients needed in conventional control groups.

The approach could accelerate the generation of clinical evidence, allowing patients to access new treatments sooner while improving the efficiency of drug development.

“This remains exploratory research, and any application would require rigorous validation and regulatory acceptance,” the spokesperson added.

Boehringer said the precise datasets have not yet been determined, but the research could draw on clinical trial, real-world or biological data, subject to appropriate authorization and oversight.

The program will initially focus on lung health, with plans to explore its potential across additional diseases and therapeutic areas. No other specific areas have been identified.

The collaboration follows AstraZeneca's recent partnership with Oracle to improve patient recruitment for clinical trials. AstraZeneca has also integrated AI across its operations, including developing an open-source generative AI framework called Reinvent, which has halved the time needed to identify molecular structures that could become potential new medicines.