Artificial intelligence (AI) is increasingly being used to enhance the efficiency and accuracy of clinical trials, addressing long-standing challenges in drug development. Sophisticated modeling and simulation techniques are showing promise in improving the success rates of novel drugs entering human studies. The pharmaceutical industry has historically struggled with low efficiency rates, with only about 14% of drugs entering clinical trials ultimately being approved by the FDA, according to the Congressional Budget Office (CBO). The cost of developing a single drug can exceed $2 billion, making the need for more efficient processes critical.
AI-Driven Clinical Trial Simulations
The primary goal of modeling software in clinical research is to simulate clinical trials, reducing the need for expensive and time-consuming traditional trials. Companies like QuantHealth are at the forefront of this innovation. QuantHealth, an AI-focused clinical trial design company, has reported completing over 100 simulated clinical trials with an 85% accuracy rate. Their proprietary AI-based Clinical-Simulator system combines over 1 trillion data points across clinical and pharmacological domains to optimize clinical development. According to CEO Orr Inbar, this system allows for rapid evaluation of various parameters, including endpoint success, commercial viability, and protocol feasibility.
The In-Silico platform generates evidence on how a therapy will perform across all clinical phases, starting as soon as its mechanism is known and preclinical evidence has been established. This synthetic evidence generation engine supports trial planning, indication selection, drug repurposing, and in-licensing asset evaluation.
Data Acquisition and Model Training
One of the significant challenges in developing AI models for clinical trials is acquiring large datasets for training. QuantHealth has partnered with OMNY, which represents data from 50 provider organizations nationally, including hospital systems, nonprofits, community practices, pediatric hospitals, and national cancer institutes, representing 78 million patients, or a third of Americans. They have also licensed over 350 million patients' data from databases to gain a comprehensive view of each patient, incorporating additional databases in genetics, cell biology, pharmacology, and biological cascades. The company builds its foundation using clinical trial results and FDA data, incorporating real-world data (RWD) and clinical knowledge graphs, along with the sponsor's own data.
QuantHealth's 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%), according to company data. This level of accuracy enables users to make informed decisions on trial go/no-go, cohort optimization, and drug repurposing.
AI for Dose Prediction and Drug Development
Another critical area where AI is making a significant impact is in accurately predicting appropriate dosing. Certara is using AI to accelerate the drug development process by seamlessly incorporating simulations with other approaches to model dosing based on prior non-human studies. The US Food and Drug Administration (FDA) has a long-standing collaboration with Certara, utilizing its software for reviewing new drug and biologics applications. The FDA has also awarded grants to expand its predictive models for assessing drug virtual bioequivalence (VBE) and to create a formulation toolbox for topically applied drugs. These capabilities facilitate safer, faster, and more cost-effective product development of both complex generics and novel drugs.
Certara's AI platform mines millions of documents and unstructured data sources in a systematic manner, coupling publicly available data with a pharmaceutical company's proprietary data to build a unique database. This platform analyzes approximately six million public sources, including regulatory databases, filings, memos, and scientific meeting data.
Applications in Discovery and Biomarker Identification
AI-driven simulations are also used to predict clinical endpoints in discovery for novel mechanisms and to identify new biomarkers. The models capture fundamental biology and simulate the effects on biomarkers, cell types, and cytokines when a compound is introduced into the system. This allows researchers to predict clinical endpoints for novel mechanisms earlier in the development process.
Overall, AI is providing growing support for the drug development process, with applications ranging from reviewing vast amounts of data to building biological maps and models of new mechanisms of action and predicting clinical endpoints. AI-based clinical simulation systems have the potential to save the pharmaceutical industry billions of dollars and significantly reduce development timelines.
