AI tool creates digital twins for health predictions

A new artificial intelligence tool that can create virtual representations of patients and predict individual health outcomes is seen as a potential game-changer for the clinical trials space.

Researchers at the University of Melbourne used three datasets containing thousands of electronic health records to train an existing large language model (LLM).

The AI ​​model, called DT-GPT, analyzed medical data from patients with Alzheimer’s disease or non-small cell lung cancer, as well as patients admitted to intensive care units.

The model created digital twins of these patients and predicted how their health was likely to change over time with treatment, which helped predict disease progression.

The model was able to make accurate predictions by leveraging its pre-existing knowledge of medical literature and evaluating the patient’s medical history including laboratory results, diagnoses, and…