Dascena Announces Publication of Prospective Study Evaluating Effect of its Machine Learning Algorithm on Severe Sepsis Prediction

Dascena Announces Publication of Prospective Study Evaluating Effect of its Machine Learning Algorithm on Severe Sepsis Prediction

April 30, 2020

Dascena, Inc., a machine learning diagnostic algorithm company that is targeting early disease intervention to improve patient care outcomes, announced today the publication of the company’s prospective study evaluating its algorithm for the prediction of severe sepsis. The publication, “Effect of a Sepsis Prediction Algorithm on Patient Mortality, Length of Stay, and Readmission: a Prospective Multicenter Clinical Outcomes Evaluation of Real-world Patient Data from 9 US Hospitals,” was published today in the peer-reviewed journal BMJ Health & Care Informatics.

“Sepsis is notoriously difficult to diagnose and treat, resulting in significant mortality and a high cost of treatment,” said Ritankar Das, chief executive officer of Dascena. “Our algorithm helps clinicians identify sepsis at an earlier stage, thereby allowing for earlier intervention to improve patient outcomes, and in turn, reduces the costs associated with treatment.”

Study Design

The study prospectively evaluated multiyear, multicenter real-world clinical data from 75,147 patient encounters that were monitored by the InSight® machine learning algorithm for sepsis prediction at facilities ranging from community hospitals to large academic centers. Hospitalized patients, including patients in intensive care units (ICUs) and emergency department visits were included. Data was evaluated to determine the algorithm’s effect on outcomes including in-hospital mortality, hospital length of stay, and 30-day readmission. This study, which was conducted in both ICU and non-ICU patients, confirms the significant mortality benefit observed in a previous intensive care unit study (LINK).

During the InSight® algorithm operation, patient data was captured from the hospitals’ electronic health records in real-time and hospital staff were informed when a patient was determined to be at high risk for sepsis.

Study Findings

Of the 75,147 patient encounters monitored by the InSight® algorithm, 17,758 patient hospital stays met two or more Systemic Inflammatory Response Syndrome (SIRS) criteria and were therefore included in the analysis. The InSight® algorithm implementation resulted in:

  • 39.50% reduction of in-hospital mortality (p<.001)
  • 32.27% reduction of length of stay (p<.001)
  • 22.74% reduction in 30-day readmission (p<.001)

“We partnered with Dascena, starting in 2017, to bring the latest technology in the fight against sepsis to our hospital. We have found that the machine learning algorithm can pick up subtle factors in the patient that may not be obvious until much later in the illness,” said Hoyt J. Burdick, M.D., senior vice president and chief medical officer of Cabell Huntington Hospital and lead author on the study. “We are excited to report data today from one of the largest studies of its kind, of improvements in both increased patient survival and reduced healthcare costs.”

Read the full paper here.

Interested in learning more?