Is AI the Key to Solving the Growing CKD Epidemic?

Updated on June 11, 2019

By Girish Nadkarni, MD

In the past five years, artificial intelligence (AI) has become a strategic tool for businesses across various industries, including financial services, retail, and logistics. More recently, the healthcare industry has started to see the positive impact that AI and subsets such as machine learning can have in helping the industry solve critical medical issues. 

There are countless AI applications being developed across healthcare, many with transformational potential. From clinical research to hospital care, diagnostics and drug development, AI applications have the potential to fundamentally reshape the healthcare landscape over the next decade. 

One of the most promising applications of AI in healthcare today is in diagnostics and clinical decision support for chronic diseases. A great example of this is the use of AI to help combat the growing, worldwide epidemic of chronic kidney disease (CKD). The diagnosis of CKD and its progression has been challenging for decades. 

Currently, 850 million individuals suffer from the disease around the world and 40 million in the U.S. alone, costing the U.S. healthcare systems $114 billion a year. As fewer than 1-in-10 patients are aware that they have CKD, it is difficult to diagnose and treat the millions of people with this disease each year. 

As this epidemic grows in importance and cost, the industry is beginning to enlist the help of AI and machine learning to solve three of the primary challenges associated with the diagnoses and treatment of CKD, which include: (1) the lack of awareness among patients that they have the disease; (2) the availability of effective tools for patient risk stratification; (3) and the limited number of nephrologists – a speciality that only has approximately one specialist for 1,666 patients

Today, the few nephrologists in practice must divide their time between patients with a fast-progressing variation of CKD and those with a low risk of progression, with no reliable way to stratify these patients. This, in turn, wastes valuable resources and time. Thanks to advances in AI and data analysis, this may soon be a thing of the past. 

Using machine learning algorithms to analyze electronic health record (EHR) information and proven predictive blood-based biomarkers associated with kidney disease, researchers have created a predictive model to help more quickly diagnose patients with CKD, identify CKD patients with a high risk of progressing to dialysis and transplant and those who would advance at a slower pace. This application of AI for CKD holds great promise, as it will enable healthcare providers to better stratify patients and determine which patients must be seen by a specialist. 

The predictive model derived from the combination of machine learning, EHR data, and biomarkers can help lessen the burden on the specialists and make more time for patients with aggressive forms of kidney disease by determining which patients can be managed at the primary care level.

AI and machine learning – in combination with EHR and other health data – also shows promise in:

  • Personalized medicine: Healthcare providers will be able to provide personalized recommendations on drug/therapy response for each CKD patient, as well as lifestyle changes they should make to halt or slow down disease progression before drastic intervention is needed.
  • Identifying new and specific types of kidney disease: “Kidney disease” is used as a “catch-all” diagnosis for any variation of the disease. AI applications could soon help the medical community define specific types of kidney disease and their likely path of progression. 
  • Repurposing pharmaceuticals for new indications: AI may soon help determine which pharmaceuticals currently utilized for other indications can be repurposed for CKD. 
  • Kidney transplantation: AI could soon help physicians make significant improvements in the identification of and monitoring for kidney transplant rejection, and in the accurate dosing of immune-suppression therapy following transplants. This can ultimately help curtail the rate of transplant failure in this area, which currently stands at nearly 20 percent within the first three years.

AI is showing true promise and success in healthcare, especially in the field of nephrology. The utilization of this technology will enable the community to slow or potentially stop the growing CKD epidemic as well as improve the overall treatment of patients. 

Girish Nadkarni, MD, is an Assistant Professor in the Department of Medicine, Division of Nephrology, at the Icahn School of Medicine at Mount Sinai, Clinical Director of the Charles Bronfman Institute of Personalized Medicine, and co-founder of RenalytixAI, a developer of artificial intelligence-enabled diagnostics for kidney disease. 

14556571 1295515490473217 259386398988773604 o

The Editorial Team at Healthcare Business Today is made up of skilled healthcare writers and experts, led by our managing editor, Daniel Casciato, who has over 25 years of experience in healthcare writing. Since 1998, we have produced compelling and informative content for numerous publications, establishing ourselves as a trusted resource for health and wellness information. We offer readers access to fresh health, medicine, science, and technology developments and the latest in patient news, emphasizing how these developments affect our lives.