• Skip to main content
  • Skip to secondary menu
  • Skip to primary sidebar
  • Skip to secondary sidebar
  • Skip to footer

  • Opinion
  • Health IT
    • Behavioral Health
    • Care Coordination
    • EMR/EHR
    • Interoperability
    • Patient Engagement
    • Population Health Management
    • Revenue Cycle Management
    • Social Determinants of Health
  • Digital Health
    • AI
    • Blockchain
    • Precision Medicine
    • Telehealth
    • Wearables
  • Startups
  • M&A
  • Value-based Care
    • Accountable Care (ACOs)
    • Medicare Advantage
  • Life Sciences
  • Research

Can Artifical Intelligence Solve The Chronic Kidney Disease Epidemic?

by Girish Nadkarni, MD, Assistant Professor in the Department of Medicine, Division of Nephrology, at Mount Sinai, and Co-Founder of RenalytixAI 06/25/2019 Leave a Comment

  • LinkedIn
  • Twitter
  • Facebook
  • Email
  • Print
Can Artifical Intelligence Solve The Chronic Kidney Disease Epidemic?
Girish Nadkarni, MD, Assistant Professor, Dept. of Medicine, Division of Nephrology, at Mount Sinai, and Co-Founder of RenalytixAI

Chronic kidney disease (CKD) is a growing epidemic worldwide. Currently, there are 850 million individuals suffering from CKD globally, with 40 million in the United States alone. Of these individuals, 96 percent are not aware of having CKD, as kidney disease often exhibits no symptoms until it has progressed to a late stage.

As this epidemic continues to grow, healthcare providers and organizations are working to determine how artificial intelligence (AI) can be used to analyze electronic health records and other biomedical data to help clinicians diagnose CKD at its earliest stage and identify the right course of treatment for patients before it is too late.

Current Challenges in Diagnosing and Treating Kidney Disease

Kidney disease is one of the most expensive medical conditions in the United States, estimated to cost the U.S. healthcare system $114 billion a year. Much of this cost stems from the inability of providers to easily diagnose patients and determine the right course of treatment for patients with early-stage disease, using currently available tools. This is one of several key challenges facing the industry today, and one where AI is poised to make a big impact.

The critical challenges are:

– The Lack of Effective Tools for Patient Risk Stratification: Currently, kidney disease is a diagnosis that is used as a “catch-all” for any variation of the disease. A patient may be in the early stages, unlikely to progress to late-stage disease, or nearing renal failure. However, there is currently no effective way for clinicians to determine the current risk level of each patient, whether or not they are going to progress, and at what rate they will progress. Without a means of patient stratification, clinicians are not able to allocate resources effectively, leading to additional costs and negative impacts on patient outcomes. 

– A Shortage of Nephrologists: Today, in the U.S., there is a very limited number of specialists – nephrologists – to handle the ever-increasing number of patients with kidney disease. According to the Centers for Disease Control’s (CDC) estimates, there are still only slightly more than 9,000 nephrologists in the U.S. – or a staggering ratio of one specialist to 1,666 patients. Without tools to effectively stratify patients, the few nephrologists in practice today are having to divide their time between both patients with rapid disease progression – who are in need of immediate and intensive intervention – as well as patients with a low risk of progression, who can likely be managed at the primary care level.

– Patients Aren’t Aware of Their Kidney Function or Level of Disease: According to the CDC, 91-96 percent of individuals with CKD are unaware that they have it. This is mainly because the signs and symptoms of kidney disease often do not present until the disease has progressed to its advanced stages. In fact, nearly 50 percent of individuals with Stage IV kidney disease are unaware of the severity of their reduced kidney function. This challenge, combined with the lack of patient stratification tools, and the shortage of specialized care, creates a critical need for new diagnostic tools to help with early detection and intervention.

To overcome these challenges, healthcare systems, providers, and organizations are turning to emerging technologies like AI and machine learning to create new approaches to kidney disease diagnosis.

The Promise of AI in Healthcare

Over the last several years, the world has seen the positive impact that technologies such as AI and machine learning have had on a number of industries such as logistics, retail, financial services and more. Now, there is true promise being shown in how these technologies can help to improve healthcare, especially when it comes to using electronic health record (EHR) data and other medical data to analyze patterns and relationships that can help develop meaningful risk stratification, predictive analytics, and clinical decision support tools.

EHRs include massive amounts of data, but that information is coming from disparate sources, in various formats and structures, from different locations and times. This makes it difficult to analyze the data in a timely and reliable manner in order to extract meaningful insights.  

By leveraging AI, we now have the ability to take this disjointed information and derive meaningful patterns that can be used by healthcare providers to help make decisions for each patient.

Changing the Course of Chronic Kidney Disease Using AI and Predictive Analytics  

Some of the key areas where AI has been most impactful is in powering predictive analytics and clinical decision support tools across a number of disease areas, including cancer, neurology, and cardiology. One of the most promising new areas where AI is being used is in nephrology, helping to diagnose and treat chronic kidney disease.

One example is a new technology that uses machine learning algorithms to assess predictive blood-based biomarkers, in combination with electronic health record information, to detect CKD at its earliest stages and predict who could progress to dialysis and transplant, and who would progress more slowly.

This predictive model can enable healthcare providers to stratify risk, ultimately determining what level of care each patient needs – whether they need to seek attention from a nephrologist, or if they could be managed at the primary care level, and how often they need to be seen. It can also assist in the recommendation of personalized drug/therapy response for individual patients as well as other lifestyle changes patients should make to stop or slow down disease progression before it is too late and drastic intervention is needed.

In addition, AI, data and biomarkers can aid in the area of kidney transplantation, a space where there has been little progress in the past 10 years. The number of kidney transplants continues to rise in the U.S. and globally, with a failure rate of nearly 20 percent within the first three years. AI is expected to help physicians make significant improvements in the identification of and monitoring for kidney transplant rejection and in the accurate dosing of immune-suppression therapy.

There is also hope that this combination of AI, EHR data and biomarkers will be able to help define specific types of kidney disease, and determine which pharmaceuticals that are currently utilized for other indications can be repurposed for CKD.  

We’re just beginning to see the potential AI holds for healthcare and particularly CKD, one of the world’s fast-growing epidemics, and the excitement continues to grow in the nephrology community.

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.

  • LinkedIn
  • Twitter
  • Facebook
  • Email
  • Print

Tagged With: AI, AI in healthcare, algorithms, Artificial Intelligence, Biomarkers, Biomedical Data, cancer, Clinical Decision Support, decision support, Electronic Health Record, Kidney Disease, Machine Learning, MD, Mount Sinai, patient stratification, Personalized Medicine, physicians, Predictive Analytics, Primary Care, RenalytixAI, risk, risk stratification

Tap Native

Get in-depth healthcare technology analysis and commentary delivered straight to your email weekly

Reader Interactions

Primary Sidebar

Subscribe to HIT Consultant

Latest insightful articles delivered straight to your inbox weekly.

Submit a Tip or Pitch

Featured Insights

2025 EMR Software Pricing Guide

2025 EMR Software Pricing Guide

Featured Interview

Kinetik CEO Sufian Chowdhury on Fighting NEMT Fraud & Waste

Most-Read

2019 MedTech Breakthrough Award Category Winners Announced

MedTech Breakthrough Announces 2025 MedTech Breakthrough Award Winners

WeightWatchers Files for Bankruptcy to Eliminate $1.15B in Debt

WeightWatchers Files for Bankruptcy to Eliminate $1.15B in Debt

KLAS: Epic Dominates 2024 EHR Market Share Amid Focus on Vendor Partnership; Oracle Health Sees Losses Despite Tech Advances

KLAS: Epic Dominates 2024 EHR Market Share Amid Focus on Vendor Partnership; Oracle Health Sees Losses Despite Tech Advances

'Cranky Index' Reveals EHR Alert Frustration Peaks Midweek, Highest Among Admin Staff

‘Cranky Index’ Reveals EHR Alert Frustration Peaks Midweek, Highest Among Admin Staff

Madison Dearborn Partners to Acquire Significant Stake in NextGen Healthcare

Madison Dearborn Partners to Acquire Significant Stake in NextGen Healthcare

Wandercraft Begins Clinical Trials for Physical AI-Powered Personal Exoskeleton

Wandercraft Begins Clinical Trials for Physical AI-Powered Personal Exoskeleton

Chipiron Secures $17M to Transform MRI Access with Portable Scanner

Chipiron Secures $17M to Transform MRI Access with Portable Scanner

Abbott to Integrate FreeStyle Libre Glucose Data with Epic EHR

Abbott to Integrate FreeStyle Libre Glucose Data with Epic EHR

5 Ways New Trump Administration Tariffs Are Impacting U.S. Healthcare Now

5 Ways Trump Administration Tariffs Are Impacting U.S. Healthcare Now

iCAD, GE HealthCare Integrate to Advance Breast Cancer Detection with AI

RadNet to Acquire iCAD for $103M in All-Stock Transaction

Secondary Sidebar

Footer

Company

  • About Us
  • Advertise with Us
  • Reprints and Permissions
  • Submit An Op-Ed
  • Contact
  • Subscribe

Editorial Coverage

  • Opinion
  • Health IT
    • Care Coordination
    • EMR/EHR
    • Interoperability
    • Population Health Management
    • Revenue Cycle Management
  • Digital Health
    • Artificial Intelligence
    • Blockchain Tech
    • Precision Medicine
    • Telehealth
    • Wearables
  • Startups
  • Value-Based Care
    • Accountable Care
    • Medicare Advantage

Connect

Subscribe to HIT Consultant Media

Latest insightful articles delivered straight to your inbox weekly

Copyright © 2025. HIT Consultant Media. All Rights Reserved. Privacy Policy |