Daijiworld Media Network - Mangaluru

Mangaluru, Apr 13: As Artificial Intelligence (AI) begins to assist treatments such as dialysis in government hospitals, medical experts say the technology is transforming kidney care while also raising serious ethical and clinical questions about its role in patient treatment.

Doctors broadly agree that AI is a useful tool in diagnosis and treatment. It is particularly showing promise in detecting chronic kidney disease (CKD) at an early stage, often much before traditional clinical diagnosis.

Speaking to DH, Dr Topoti Mukherjee, Lead Consultant, Nephrology and Kidney Transplant at a private hospital, said recent studies indicate that deep learning algorithms can identify CKD risk factors 6 to 12 months earlier than conventional methods.

She added that AI-based imaging using convolutional neural networks in renal scan analysis has been able to detect structural kidney abnormalities that may not be visible through traditional imaging techniques.

Experts note that this shift from reactive diagnosis to predictive risk assessment is especially important in CKD, which often remains asymptomatic in early stages.

Highlighting the balance between AI and clinical judgement, Dr Arun Kumar J, Consultant Nephrologist, said there are instances where AI findings may not align with real-world clinical conditions.

“Sometimes AI picks up trends that are not obvious at first glance. At the end of the day, the responsibility sits with the clinician. The final decision has to come from us. AI can inform the decision, but it does not make it,” he said.

In dialysis care, AI is also playing an increasing role by enabling more personalised and safer treatment. It continuously monitors parameters such as blood pressure, fluid levels and toxin removal, while also predicting possible complications and assisting doctors in adjusting treatment.

Dr Kishan A, Consultant Nephrologist, said this has improved outcomes, reduced emergencies, and enhanced efficiency in dialysis centres. However, he cautioned that AI still has limitations.

“Its effectiveness depends on data quality, and it may miss sudden or rare complications. High costs, data privacy concerns and the need for staff training remain challenges. AI cannot replace clinical judgement and requires constant human oversight,” he said.

Experts also point to ethical concerns surrounding AI in healthcare.

Dr Anoop M Gowda, Senior Consultant Nephrologist and Transplant Physician, said patient care fundamentally depends on human interaction, which technology cannot replace.

He also raised concerns about accountability, questioning whether responsibility lies with doctors, developers, or systems when outcomes go wrong.

“AI depends on expensive infrastructure and data often drawn from Western populations, which limits its relevance in India. While promising, it must be used cautiously with clinical judgement, with doctors ultimately guiding decisions,” he said.