QuantHealth’s AI simulates 100+ clinical trials with 85% accuracy

QuantHealth, an AI-focused clinical trial design company based out of Tel Aviv, has announced the completion of more than 100 simulated clinical trials, reporting an 85% accuracy rate. The company, which received $17 million in a Series A funding round with backing from Accenture, aims to chip away at the steep costs and stubborn timelines of drug development.

The company says its technology is able to predict clinical trial outcomes with significantly higher accuracy than current success rates in the pharmaceutical industry. Specifically, QuantHealth claims its AI can predict phase 2 trial outcomes with 88% accuracy (compared to the actual success rate of 28.9%), and phase 3 trial outcomes with 83.2% accuracy (versus the industry average of 57.8%). For decades, the pharma sector has faced waning efficiency rates — a phenomenon informally known as “Eroom’s Law, a sort of inverse of Moore’s Law for transistors in semiconductors — which incidentally, is also stalling.

“Let’s face the facts — 90% of drugs that make it to clinical trials don’t make it to market,” said Orr Inbar, co-founder and CEO of QuantHealth, in a 2023 interview. “They fail somewhere between phase 1 and phase 3.”

The company’s proprietary AI-based Clinical-Simulator system combines a reported 1 trillion data points spanning clinical and pharmacological domains. In the mix are data from 350 million patients and more than 700,000 drug entities to predict individual patient responses within trials. QuantHealth’s simulator can predict clinical trial results with high accuracy, allowing users to answer mission-critical questions such as trial go/no-go, cohort optimization, drug repurposing, and more.

In its press release, the company also shared a case study noting significant improvements over the status quo of drug trials:

Reported accuracy rates

QuantHealth claims the following accuracy rates compared to national averages:

Therapeutic Area	QuantHealth	National Average
Oncology	88%	29.7%
Immune & Inflammation	80%	42.2%
Gastroenterology	83%	41.6%
Respiratory	84%	31.4%
Phase 2 trials	88%	28.9%
Phase 3 trials	83.2%	57.8%

The AI in clinical trial landscape

Several companies are using AI to optimize clinical trials. Among them are:

• Unlearn.AI specializes in “digital twins” of patients to reduce control group sizes, accelerating the trial process and allowing more patients to receive experimental treatments. This approach is especially beneficial for complex diseases like Alzheimer’s.
• Trials.ai offers an AI-driven platform focused on optimizing clinical trial protocols by analyzing existing data and suggesting designs that can improve efficiency and patient outcomes.
• Atomwise uses deep learning technology for drug discovery and predicting trial performance by analyzing molecular structures.
• Medidata (formerly known as Acorn AI) offers advanced analytics and AI solutions for clinical trial design using real-world data. This integration enhances the relevance and applicability of trial results, leading to better outcomes and faster time-to-market for new treatments.
• Saama Technologies provides an AI-driven platform that supports various aspects of clinical trial operations, including patient recruitment and trial management.
• Deep 6 AI specializes in using AI to match patients with clinical trials by mining EMR data, improving recruitment rates and ensuring trials are conducted with relevant participants.
• Antidote employs machine learning to connect patients with suitable clinical trials, helping patients find trials that match their medical conditions and treatment goals.
• Insilico Medicine (inClinico) has used AI (inClinico) to predict the outcomes of phase 2 and 3 clinical trials. The company also has used AI to help with the planning and execution of clinical trials by forecasting patient response to new treatments, optimizing trial design, and reducing the risk of trial failure.