Thirona Develops Novel AI Software for Cystic Fibrosis

Thirona Develops Novel AI Software for Cystic Fibrosis

Healthcare Tech Outlook | Tuesday, April 06, 2021

Eva van Rikxoort, CEO, Thirona

Thirona’s lung quantification software package LungQ includes a new AI-based algorithm called PRAGMA-AI that automatically detects CF-related lung abnormalities, including abnormal airways and collapsed lung tissue.

FREMONT, CA : Thirona, an Artificial Intelligence (AI) software firm specializing in medical image analysis, developed an AI algorithm that redefines Cystic Fibrosis (CF) care. PRAGMA-AI is a new algorithm that allows for quick, automated analysis of CT scans of CF patients to detect and quantify lung abnormalities. These tests are vital in assessing a patient’s condition and determining the best treatment options, but they are difficult to achieve in humans’ clinical care. The release of PRAGMA-AI opens the door to widespread use in clinical trials and clinical care for improved diagnostics, patient monitoring, and treatment planning.

Evaluation in Seconds

CF is a rare genetic disorder with 70,000 confirmed cases worldwide that causes severe lung problems and shortens life expectancy. Clinical experts previously developed PRAGMA-CF, a quantitative tool for evaluating CF lung disease on CT scans, to assist in the decision-making process. However, PRAGMA-CF is time-intensive, requiring highly trained data analysts and taking up to several hours per patient–an impossible task in a clinical environment. Thirona, a medical AI software company that works on diseases such as COPD, Asthma, and Tuberculosis, has now automated this process, which has far-reaching implications for patient care. Without the need for human intervention, their approach can evaluate CF patients’ CT scans in a matter of seconds.

High Diagnostic Performance

Thirona’s lung quantification software package LungQ includes a new AI-based algorithm called PRAGMA-AI that automatically detects CF-related lung abnormalities, including abnormal airways and collapsed lung tissue. CF lung disease’s pattern and magnitude can be determined using these measurements, which are sensitive and objective. This is crucial information, as it allows physicians to monitor disease progression and make medical decisions based on it. A significant number of CF patient scans, LungQ PRAGMA-AI, have been validated, demonstrating high diagnostic efficiency comparable to qualified human analysts.

Search for New Treatments

These developments pave the way for using the PRAGMA method in both clinical trials and clinical care. Prof. Harm Tiddens from Erasmus Medical Center, who co-developed the original PRAGMA-CF method, is proud to see the method automated. “It allows for large scale investigation of CF lung disease in both research studies and clinical trials. This is a crucial component in the evaluation of new expensive treatment options for patients suffering from CF”, says Prof. Tiddens. He further explains: “CF patient registries, collecting information on the health status of CF patients, have already shown interest in the PRAGMA-AI method. They use patient information to create care guidelines, drive quality improvement, and to study CF treatments and outcomes.”

Weekly Brief