Artificial Intelligence tool recommends optimal chemotherapy dosage

August 2022 Health Innovation Nalinee Pandey

Researchers from Singapore have developed an artificial intelligence (AI) tool, CURATE.AI that assists clinicians in formulating optimal and personalized dosages of chemotherapy for cancer patients. This tool has been developed by Professor Dean Ho and his team from the National University of Singapore (NUS).

Chemotherapy is given at a fixed dosage in general and thus may not result in optimal dosage for the patient and hence will influence the clinical outcomes for the patient. The main goal of CURATE.AI is to increase the efficacy as well as increase the duration of response for patients. Also, this tool can assist in reducing the recommended dosage and hence preventing any possible side effects for the patient.

PRECISE CURATE trial

The group performed a pilot clinical trial, PRECISE CURATE for testing the efficiency of the tool. The clinical study enrolled ten patients diagnosed with solid tumours and predominantly metastatic colorectal cancers. The majority of the clinicians accepted recommended doses for the patients (97%). Moreover, around 20% of these patients received lower than average dosage.

Dr Raghav Sundar, Principal Investigator of the PRECISE CURATE clinical trial said, “An important aspect of applying AI in medicine is the direct involvement of clinicians in building individualized datasets. The pilot trial represents a promising step towards incorporating CURATE.AI into the clinical workflow of dynamic dose selection in the treatment of solid tumours. A key aim of CURATE.AI is to enable truly personalized dosing for patients while also empowering clinicians to identify the optimal dose for each patient, without adding to their workload. In this way, clinicians can focus more on the patient and the caregiver.”

Reference

Agata Blasiak, Anh Truong, Wen Jeit, et al. PRECISE CURATE.AI: A prospective feasibility trial to dynamically modulate personalized chemotherapy dose with artificial intelligence. Journal of Clinical Oncology 2022 40:16_suppl, 1574-1574