{
  "id": 5564073,
  "title": "IIT Madras and CMC build AI to catch kidney disease early",
  "url": "https://urgent.news/2026/09/04/iit-madras-and-cmc-build-ai-to-catch-kidney-disease-early",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-04T12:54:01.000Z",
  "source": {
    "name": "YourStory",
    "slug": "yourstory",
    "url": "https://yourstory.com/2026/09/ai-kidney-disease-detection-iit-madras-cmc-tools"
  },
  "original_language": "en",
  "account": "In a pioneering collaboration between IIT Madras and Christian Medical College (CMC), Vellore, researchers have developed three artificial intelligence (AI) tools aimed at early detection and assessment of kidney conditions. Announced on September 3, 2026, this groundbreaking work merges machine learning, medical imaging, and 3D reconstruction to provide clinicians with faster and standardized information for diagnosing kidney diseases.\n\nThe first tool utilizes routine clinical and laboratory data to predict an individual's risk of chronic kidney disease. The second tool employs deep learning to classify computed tomography (CT) scans, categorizing them as normal kidneys, cysts, stones, or tumours. The third tool is an open-source 3D imaging platform that reconstructs kidneys from CT scans, measuring tumour and kidney volumes to assist in surgical planning and disease monitoring over time.\n\nThe kidney disease risk model underwent rigorous testing across multiple machine learning algorithms before the researchers settled on a random forest approach. Initially developed using a public dataset of approximately 400 records containing 26 clinical and laboratory variables linked to chronic kidney disease, this tool has been refined to enhance its predictive accuracy.\n\nThe imaging system, trained on around 12,400 publicly available CT images, streamlines initial classification into four categories: normal kidney, cyst, stone, and tumour. The third tool offers a unique dimension by providing a 3D view of the reconstructed kidneys and calculating kidney and tumour volumes. This feature aids surgeons in planning procedures and enables doctors to monitor disease progression more effectively.\n\nLed by Prof G L Samuel and researcher Jennifer Delighta at IIT Madras, and in collaboration with Prof Santosh Varughese, a nephrologist at CMC Vellore, this project represents a significant step towards the development of a comprehensive \"digital twin\" of a patient's kidney. This virtual representation would integrate clinical and imaging data to model disease progression and support personalized medical decisions.\n\nThe researchers envision these AI tools as the foundation for future advancements in kidney disease management, aiming to identify problems at earlier stages to prevent disease progression and reduce the need for costly treatments such as dialysis.",
  "summary": "AI could help spot kidney disease earlier. IIT Madras and CMC Vellore have unveiled three tools for risk prediction, CT scan triage and 3D tumour assessment.",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}