In Clinical Trial Clare Medical AI Platform Reduces Hospital Admissions and ER Visits by 77%

Clare Medical of New Jersey (“Clare”), a provider of in-home comprehensive medical care to seniors throughout New Jersey, announced overwhelming positive results, of its recently completed large-scale trial, evaluating its Artificial Intelligence (AI)-based diagnostic platform’s utility in preventing ER visits and hospitalizations.

Latest Aithority Insights: Xage Releases Novel Multi-Layer Multi-Factor Authentication Protection for Critical Infrastructure

In the trial involving approximately 300 elderly patients having significant disease burdens, it was found that utilization of the model dramatically reduced by 77%, the number of patients who experienced an ER visit or hospitalization, after being identified by the model as having a high probability of requiring one within a 30-day period. In October, 2020 Clare announced data confirming validation of its Artificial Intelligence (AI)-based diagnostic tool’s ability to accurately forecast which patients were at an increased risk of a hospital admission within an error range of only 3%.

The AI model, developed by Elie Donath, M.D, MPH, MBA, Clare’s Director of Data Analytics, identifies patients who are at high risk of requiring an ER visit or hospitalization by evaluating a variety of datapoints contained in their medical records associated with their most recent set of clinical encounters, which is automatically ingested into the model. Based on this data, the model forecasts which diseases or conditions need to be addressed to attempt to avoid the patient having an ER visit or hospitalization. In the recently completed trial, the most common conditions identified included COPD exacerbations (11.7%), fall/fractures (11.7%) and cardiovascular events like myocardial infarction or stroke/TIA (9.0%). If an alarm is triggered by the model identifying a patient at risk, the overseeing physician can provide a variety of directives to providers to address with the patient, over the phone or during their next visit (I.e., medication adjustment, diet/medication compliance, symptom awareness, etc.) to avoid the need for an ER visit or hospitalization. In the trial, alarms were triggered, and directives were provided for 41.4% (124/299) of patients. Of those 124 patients, only 28 (23%) ended up requiring an ER visit or hospitalization. Although some patients (approximately 10% of the trial population), were lost to follow-up and several of those patients may have required an ER visit or hospitalization – our results are sufficiently compelling that even including all those patients as having had an ER or hospital visit would not significantly impact our findings.

Data Privacy and Security: Chicago Public Schools Suffers Major Data Breach Affecting 100K Accounts

Clare’s novel proprietary AI-based diagnostic platform during the past year has been enhanced to provide continuous and instantaneous uploads and updates of data in real-time and to delineate the variables that drive the model’s prediction and thereby identify, for the provider, the primary reason(s) that a given probability score was generated.

Commenting on the AI -based platform enhanced capabilities, Dr. Donath stated, “These new enhancements significantly cut down the amount of time needed to delve into the chart and attempt to delineate the various predictors that the model is honing in on. In contrast to other AI-based diagnostic strategies, which do not really provide the tools to understand why a given recommendation is made, this approach both identifies a patient as being at high-risk and provides direction as to what can be done to prevent an unfortunate outcome. It is unlike most AI-based prediction algorithms currently in deployment in this regard.”

Commenting on the potential value of the platform, Ron Lipstein, CEO of Clare Medical, said, “A large part of our business revolves around our ability to keep patients out of the hospital and implementation of this model has helped us achieve high marks in this regard. As performance-based care becomes more prevalent, effective predictive models and diagnostic tools such as the one developed by Clare, will become more necessary and valuable to healthcare organizations. We look forward to exploring ways our very compelling diagnostic tool can generate value to Clare, our affiliates and other healthcare organizations.”

Read More About Aithority News : KNIME Accelerates Data Science Democratization Through Snowflake Collaboration

[To share your insights with us, please write to sghosh@martechseries.com]