AI mines EHR data to predict diabetic patients at risk for kidney damage, study finds
Artificial intelligence start-up Medial EarlySign in a new study has shown how the combination of AI and EHR data can facilitate early detection and treatment of kidney problems and can help slow down – or even prevent – progression to end-stage renal disease.
Medial EarlySign's machine learning-based model analyzed dozens of factors residing in electronic health records, including laboratory test results, demographics, medications, diagnostic codes and others, to predict who might be at high risk for having renal dysfunction within one year.
By isolating less than 5 percent of the 400,000 diabetic population selected among the company's database of 15 million patients, the algorithm was able to identify 45 percent of patients who would progress to significant kidney damage within a year, prior to becoming symptomatic, the start-up reported. This represents 25 percent more patients than would have been identified by commonly used clinical tools and judgment, the company contended.
"Immense efforts are invested in developing treatment protocols to reduce the number of patients who will develop renal dysfunction due to diabetes," said Ran Goshen, MD, Medial EarlySign’s chief medical officer.
Goshen added that the startup’s algorithm can be used by hospitals, insurers and pharmaceutical companies to manage resources to reduce the likelihood for end-stage renal disease.
AI in healthcare is beginning to emerge out of its infancy, said Ted Willke, a senior principal engineer at Intel Labs.
"We're seeing healthcare organizations and hospitals move beyond AI-based proof-of-concepts and program pilots into developing and adopting systems that work the best for their needs," Willke said. "AI in healthcare, like in other industries, began as a way to help these organizations manage their vast amounts of data and simplify daily tasks, but we're starting to see the emergence of truly innovative uses of AI in healthcare – from finding complex patterns in medical imaging to genomic sequencing to designing patient treatment plans."
Additionally, right now, there's a huge interest in predictive clinical analytics or the process of inputting historical patient data into models to identify and forecast future events, he added.