For the study, the research team used CT scans and medical records of 944 lung cancer patients treated with high-dose radiation. The study participants’ pre-treatment scans were loaded into a deep-learning model, which screened the scans and used an algorithm to develop an image signature that can predict the patient’s treatment outcomes. To generate a personalized radiation dosage, the image signature is then merged with data from the individual’s health records to incorporate clinical risk factors.
After testing the AI neural network on an independent cohort, researchers found that the technology was able to reduce radiation treatment failure probability to less than 5 percent.
“While highly effective in many clinical settings, radiotherapy can greatly benefit from dose optimization capabilities,” said Mohamed Abazeed, MD, PhD, lead study author and a radiation oncologist at Cleveland Clinic, according to a news release. “This framework will help physicians develop data-driven, personalized dosage schedules that can maximize the likelihood of treatment success and mitigate radiation side effects for patients.”
The AI framework can be customized to fit the specific patient population of any medical center that implements the tool, according to the report.
More articles on artificial intelligence:
HP Enterprise is using AI, blockchain to advance automation while enhancing data privacy
Most people feel unprepared for the AI-powered future, poll finds: 4 notes
AI detects ‘covert consciousness’ in unresponsive patients with severe brain injury
