An Israeli artificial intelligence (AI)/healthcare startup called Medial EarlySign, has developed a machine learning model that’s able to predict which diabetes patients are more at risk from suffering with kidney damage in the near future. Using the AI diagnosis’ have increased by as much as a quarter.
“Immense efforts are invested in developing treatment protocols to reduce the number of patients who will develop renal dysfunction due to diabetes,” said Medial EarlySign’s chief medical officer,” Ran Goshen, MD. “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.”
When put into testing, the AI managed to detect those patients affected before any symptoms were present by analysing various diagnostic codes, lab tests, electronic health records (EHRs), medications, and demographic information.
“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,” explained Itamar Raz, MD and leader of the Israel National Council of Diabetes. “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 than can lead to improved prediabetic patient risk stratification.”
Kidney problems often accompany diabetes. It’s estimated that around 20-40% of all diabetes patients suffer in this way as a side effect. If doctors can diagnose cases of renal dysfunction earlier on for example, could lead to delayed or even prevented damage. Diabetes has been a target for AI applications for quite some time now with various breakthroughs emerging all across the globe. Earlier this week, an Iowa-based startup called IDx had been commended by the FDA for its “breakthrough device”, a deep learning diabetic retinopathy diagnostic system.
Other areas of healthcare that AI has helped recently includes helping diabetics lose weight and determining the efficacy of insulin needed for daily care. Medial EarlySign is tackling diabetes in various ways through the help of AI. Not only does it concentrate on prediabetes but it also tracks its progression as well through its algorithmic calculators and predictive models. This new revelation confirms just how important it is to have high quality data to hand as well as advanced analytics to give people the best chance of living a healthy life.