VivoSim Labs Inc. (NASDAQ: VIVS) announced the availability of an AI prediction tool that uses human intestinal tissue models to predict whether drug compounds may cause diarrhea in patients. The tool combines the company's NAMkind intestinal models with machine learning analytics to identify drug-induced disruptions to intestinal function.

The AI model was trained using data from dozens of compounds tested in VivoSim's 3D tissue-based assays. The company reported the model achieved 96% predictive accuracy for potential diarrhea occurrence. The system, called VitroSense, measures multiple data endpoints from NAMkind intestine assays and feeds this information into the AI model to assess diarrhea risk for novel compounds.

"The high biological fidelity of NAMkind models allows us to generate data in line with what is seen in humans," said Keith Murphy, VivoSim Executive Chairman. "By using that high-quality data to train AI models, we get much more accurate predictions."

The NAMkind intestinal models can simulate both oral and intravenous drug administration routes by exposing different portions of the multilayered tissue structure. The models have been tested with antibody-drug conjugates and can detect differential effects on intestinal epithelium.

VivoSim is working with clients to provide screening for intestinal effects of oncology antibody-drug conjugate candidates. The company's liver and small intestine toxicology services are available in the United States, Europe, and through distributors in Korea and China.

The San Diego-based company provides drug testing services using 3D human tissue models as alternatives to animal testing methods. VivoSim focuses on liver and intestinal toxicology insights for pharmaceutical and biotechnology partners.