Roughly 90% of drugs that enter clinical trials never make it to market — a failure rate that costs the pharmaceutical industry billions of dollars every year.

On Tuesday, an Israeli startup seeking to shrink that rate picked up $45 million in Series B financing. QuantHealth, which sells a simulation platform that tests clinical trials virtually before running them, has now raised $70 million since its founding in 2020. The Series B round was led by Qumra Capital, with participation from other funds including Sanofi Ventures, Pitango HealthTech, Artofin Venture Capital Fund and Esplanade Ventures.

QuantHealth CEO Orr Inbar argued that the clinical stage of drug development has remained largely untouched by AI innovation. He noted that most AI investment in drug discovery has flowed to early stages of the process, leaving clinical trial design largely stuck with outdated methods.

By using AI to simulate clinical trials before they begin, the startup’s platform can pinpoint how different patients will respond to treatment, which should ultimately lead to fewer trial failures and quicker access to more effective therapies for patients, Inbar explained.

“The healthcare industry generates nearly 30% of the world’s data. In life sciences, this data is not only incredibly large, but also incredibly complex,” he stated.

QuantHealth’s platform combines AI with large biomedical knowledge graphs, allowing it to capture clinical patterns at high resolution and identify insights into how drugs actually work in the body, Inbar said. That approach also lets the platform extend its predictions beyond large patient populations to rare diseases and small subpopulations, using transfer learning to generalize insights that would otherwise require far more data than exists for those groups.

Inbar pointed out that QuantHealth’s AI models can predict potential patient outcomes to existing and novel therapies with up to 90% accuracy. Having those predictions in hand before a trial even begins allows pharma companies to reduce patient exposure to treatments that are unlikely to work, he remarked.

To date, QuantHealth has simulated more than 600 clinical trials across 30 indications, Inbar added.

QuantHealth isn’t the only company applying AI to patient matching, though. As for competitors, Inbar noted that Noetik — an oncology-focused AI company that uses biological data to help drugmakers match patients to treatments — is occasionally brought up in the same conversation as QuantHealth. 

“We’re different in scope and stage. Noetik works within a single disease area, oncology, and centers on biological stratification of patients, while we simulate across multiple clinical trial stages, endpoints and therapeutic areas — answering questions like: Will this trial succeed? Should we change the endpoints, optimize the patient population, or adjust the design in some other way?” Inbar explained.

Instead of identifying the right patients for a treatment, QuantHealth helps determine whether the treatment — and the trial designed to test it — is set up to succeed in the first place.

The startup plans to pour its fresh capital into three areas: sharpening its AI models and expanding disease coverage, growing its team, and pushing its platform further into the drug development journey — including how treatments get positioned and brought to market.

Photo: BlackJack3D, Getty Images