Biodesix publishes data on new COVID-19 artificial intelligence-based algorithm for use in clinical decision support systems

Tuesday February 9, 2021 0 comments Tags: Boulder, Biodesix, Scott Hutton, COVID-19

BOULDER -- Biodesix, Inc. (Nasdaq: BDSX) today announced a publication describing the development of a new AI-based COVID-19 algorithm and important data from a related study.Biodesix_logoUSE 

The paper, entitled, “Predicting Prognosis in COVID-19 Patients using Machine Learning and Readily Available Clinical Data,” demonstrates the AI-based algorithm’s ability to rapidly and accurately help physicians predict risk of severe outcomes for patients with COVID-19 infection utilizing readily available patient data collected upon hospital admission.

The AI-based algorithm, designed to be easily incorporated into existing clinical decision support systems, helps identify those patients who are likely to require intervention, such as treatment with ventilators and admission to intensive care units, or those patients who may develop acute respiratory distress syndrome (ARDS), versus those who likely will not require intervention.

The machine learning, AI-based algorithm was developed using Biodesix’s Diagnostic Cortex AI platform in close collaboration with a leading academic center to stratify hospitalized COVID-19 patients by risk of severe outcomes.

The study used the AI-based algorithm to predict the outcomes of 559 patients; 229 patients who were hospitalized with COVID-19 were used in algorithm development, and 330 patients with COVID-19 in a blinded, independent validation.

Using 26 easily obtainable variables, such as patient characteristics, vital signs, and readily available laboratory test values, the study showed that the AI-based algorithm accurately segmented patients into those who will likely need intervention and those who will not.

“The ability to rapidly determine a patient’s risk of severe COVID disease, early, easily, and accurately, can help physicians to identify those who could benefit from specialized treatment and early interventions and get them the care they require in the optimal treatment window,” said Robert Georgantas, senior VP of research and translational science at Biodesix.

“At the same time, the AI-based algorithm may help to avoid unnecessary treatment for patients deemed to be at lower risk, for whom heroic interventions may cause harm.”

“We are extremely excited about this algorithm based on our proprietary AI platform and its ability to support treatment of patients with COVID-19,” said Scott Hutton, CEO of Biodesix.

“Implementing this during the initial patient assessment can offer physicians the necessary insight to quickly and confidently choose the appropriate treatment for each patient.

“This ability is especially valuable now, during the pandemic, when timely treatment decisions are crucial and critical resources such as ICU beds and ventilators can be scarce.”

Biodesix is working with a U.S.-based COVID-19 consortia and another international COVID-19 consortia consisting of major academic institutions to perform additional large, blinded, independent validation testing of the AI-based algorithm, and is currently exploring options for making this widely available for hospitals to incorporate into their clinical decision support systems.