Predicting clinical trial success and protocol feasibility with machine learning - ON-1120

Project type: Research
Desired discipline(s): Medicine, Life Sciences, Computer science, Mathematical Sciences
Company: Banting AI
Project Length: Flexible
Preferred start date: As soon as possible.
Language requirement: Flexible
Location(s): ON, Canada
No. of positions: 1
Desired education level: Master'sPhDPostdoctoral fellow
Open to applicants registered at an institution outside of Canada: Yes

About the company: 

At Banting AI, we’re dedicated to making clinical trials faster, simpler, and more accessible. We use advanced artificial intelligence to streamline clinical research, helping sponsors and sites accelerate timelines, reduce costs, and deliver innovative treatments to patients more effectively. Founded in Canada, Banting AI is committed to improving healthcare outcomes at home and abroad.

Describe the project.: 

Clinical trial protocols frequently face operational hurdles, underestimated site and patient burdens, and high participant dropout rates, driving increased trial costs and delays. This project will develop and validate machine learning models to proactively evaluate clinical trial feasibility and predict trial success—specifically targeting recruitment targets, participant retention, minimal deviations, and achievement of primary endpoints.

Leveraging retrospective Canadian clinical trial data (historical protocol information, operational outcomes, and performance metrics), this research will explicitly identify critical protocol components predictive of operational challenges, participant burdens, and dropout risks. The goal is not only predictive accuracy but also to directly inform the development of practical, actionable, and improved protocol design methodologies that reduce operational burdens, lower trial-related costs, and enhance overall trial predictability and efficiency.

Required expertise/skills: 

• Predictive modeling and statistical analysis.
• Practical experience with machine learning frameworks (e.g., TensorFlow, PyTorch).
• Familiarity with clinical trial protocols, operations, and key performance metrics.
• Data management expertise (structured/unstructured clinical datasets).
• Strong collaborative and communication skills.
• Understanding of Canadian healthcare regulations, data governance, and privacy standards (PIPEDA).