Machine Learning Algorithm Identifies 25% More Patients at Risk, Compared with Commonly Used Clinical Tools
KFAR MALAL, Israel – February 5, 2018 – Medial EarlySign (www.earlysign.com), a leader of machine-learning based solutions to improve non-communicable disease management, today announced the results of an additional clinical data study in the domain of diabetes – identifying diabetic patients who are at highest risk for having renal dysfunction within one year.
Medial EarlySign’s machine-learning based model analyzed dozens of factors residing in Electronic Health Records (EHRs), including laboratory tests results, demographics, medication, diagnostic codes and others, to predict who might be at high risk for having renal dysfunction within one year. By isolating less than 5% of the 400,000 diabetic population selected among the company’s database of 15 million patients, the algorithm was able to identify 45% of patients who would progress to significant kidney damage within a year, prior to becoming symptomatic. This represents 25% more patients than would have been identified by commonly used clinical tools and judgment.
“Immense efforts are invested in developing treatment protocols to reduce the number of patients who will develop renal dysfunction due to diabetes,” said Dr. Ran Goshen, Medial EarlySign’s Chief Medical Officer. “Medial EarlySign’s algorithm can aid decision-makers, drug developers, insurers and providers to better allocate their capped resources and secure preferential clinical outcome as well. This can help reduce the likelihood for diabetes related end stage renal disease (ESRD).”
“The significant size and rapid growth of digital health databases now allow the application of advanced mathematical tools that can identify patterns in diverse patient populations in order to identify high risk patients,” said Dr. Itamar Raz, Head of the Israel National Council of Diabetes and Director Emeritus of the Diabetes Unit at Hadassah University Hospital. “Rather than relying only on small patient samples based on known risk factors, machine learning tools can reveal the slightest correlations among these parameters and discover additional risk indicators that can lead to improved prediabetic patient risk stratification.”
Kidney problems are one of the most common diabetes-related complications, affecting approximately 20%-40% of diabetics worldwide. In the U.S., over 36% of adult diabetics were estimated to have diabetic nephropathy or other form of renal dysfunction between 2011-2012, affecting roughly 11 million people. These numbers will continue to rise as diabetes becomes more prevalent. Early identification and treatment may help prevent or slow the progression of damage to the kidney, reducing the likelihood of future complications, such as ESRD.
This model joins a suite of predictive models and algorithmic calculators developed and researched by Medial EarlySign, with the goal of providing healthcare organizations a comprehensive set of predictive tools to address the challenge of engaging with the right patients and offering effective interventions to reduce morbidity and mortality from diabetes. In addition to renal dysfunction, the company’s research and development work also includes models for prediabetes to diabetes progression, diabetes-related cardiovascular disease, and additional collaborations focused on identifying successful interventions and optimizing engagement with diabetic and pre-diabetic individuals.
The prediabetes research follows successful clinical implementation of Medial EarlySign’s solution to identify patients at high risk of harboring lower GI Disorders, consolidated by research conducted in the U.S., EU and Israel by Kaiser Permanente, Oxford University and Maccabi Healthcare Services, respectively.
# # #
Learn more ● Diabetic CKD algorithm work