1 hr ago
IIT Madras, CMC Vellore Develop AI Tools for Kidney Disease
Researchers in India have created three computer tools to help doctors find kidney problems earlier.
One tool estimates whether a person may be at risk of chronic kidney disease.
Another examines CT scan pictures and identifies healthy kidneys, cysts, stones, or tumours.
A third tool creates a three-dimensional picture of a kidney from a CT scan.
This picture helps doctors measure the size of a tumour and how much of the kidney it affects.
The CT scan system was trained using more than 12,000 images.
The researchers hope earlier detection will help doctors plan treatment sooner.
They are still testing the tools with more patient information.
Their long-term goal is to support personalised kidney care and digital models of patients’ kidneys.
Researchers from IIT Madras and CMC Vellore developed three AI-based kidney disease tools.
A machine learning model predicts chronic kidney disease risk using clinical and laboratory information.
A deep learning system analyzes CT scans and classifies kidneys as normal or affected by cysts, stones, or tumours.
A 3D imaging platform measures kidney tumour volume and the percentage of kidney involvement.
Researchers plan further validation with additional patient data and partnerships with healthcare institutions.
- Who
- Researchers from the Indian Institute of Technology Madras and Christian Medical College, Vellore, including GL Samuel and Jennifer Delighta.
- What
- They developed three AI tools for predicting kidney disease risk, analyzing CT scans, and measuring kidney tumours in 3D.
- Where
- The research involved the Indian Institute of Technology Madras and Christian Medical College, Vellore; the report was issued from New Delhi.
- When
- The development was reported on September 3.
- Why
- The tools are intended to support earlier diagnosis, faster clinical decisions, and more patient-specific treatment planning.
Key facts
- Institutions
- Indian Institute of Technology Madras and Christian Medical College, Vellore
- Number of tools
- Three AI-based technologies
- Risk prediction
- Uses clinical and laboratory information to estimate chronic kidney disease risk
- CT classifier
- Distinguishes normal kidneys, cysts, stones, and tumours
- Training data
- The CT image classifier was trained with more than 12,000 images
- 3D imaging
- Measures tumour volume and the percentage of kidney involvement
- Next steps
- Researchers plan to test the models with more patient data and pursue healthcare partnerships
Quotes
GL Samuel
Professor in the Department of Mechanical Engineering at IIT Madras
“These tools can enable earlier diagnosis, which could help slow down the disease process and reduce the need for expensive interventions like dialysis. The team aimed to develop intelligent systems that would help clinicians make quicker and more informed decisions.”
theprint.in
“We used machine learning along with clinical knowledge to develop tools that would assist in the earlier detection of kidney diseases and give more detailed information specific to the patient.”
theprint.in
Jennifer Delighta
Research scholar at IIT Madras
“These AI tools can help detect at-risk patients early and plan their treatment more effectively. The patient-specific imaging framework is of significant promise as it goes beyond the standard measurements to give a more comprehensive picture of the extent of the disease.”
theprint.in
Sources
Related news
Kidney Disease Can Stay Hidden, But Simple Tests Help
Parliamentary panel recommends mandatory kidney tests every six months
London Surgeons Use AI in World-First Brain Tumour Operation
AI Helps Reveal Hidden Heart Risks Between Heartbeats
Gates Foundation Sees India Leading AI Health, Agriculture Innovation
New heart guidelines recommend kidney screening with two simple tests
Heart Valve Disease: The Quiet Health Threat That Steals Stamina
Lakshadweep's TB Elimination Success Offers Lessons for India
Doctor Sparks Debate on Merit vs Privilege in NEET Exam Row
Telangana Issues Advisory on Seasonal Covid Rise
