Improved accuracy, reduced workload, priority to urgent treatment: AIIMS turns to AI to read X-rays

“This AI tool dramatically speeds up initial assessment and allows clinicians to identify potential abnormalities much sooner,” said Dr Raju Sharma, professor and head of the radiology department at AIIMS.

Doctors say the software uses deep learning algorithms – a form of artificial intelligence that identifies patterns in large datasets – to detect nodules in chest X-rays and spot early signs of abnormalities in images.

AIIMS, however, plans to develop its own AI system in the near future.

“The system was customized during a pilot phase, and AIIMS aims to eventually develop its own AI tool. While still experimental, it is already helping improve workflow by easing workload pressure, speeding care, and enhancing diagnostic accuracy,” said Dr Devasenathipathy K, professor of radio diagnosis at AIIMS.

How It Will Be Used
According to Dr Sharma, the AI tool will play an important role in triaging cases, helping radiologists and clinicians prioritise patients based on urgency when the AI detects an abnormality. He emphasised that AI is a support tool, not a replacement for human expertise. “All images undergo a detailed review by a group of radiologists and clinicians before treatment begins,” Dr Sharma said. “The bottom line is that it might work 24/7, but the decision is that of a radiologist,” he added.

He emphasised that AI is a support tool, not a replacement for human expertise. “All images undergo a detailed review by a group of radiologists and clinicians before treatment begins,” Dr Sharma said.

“It’s a fully evolved technology but cannot replace the radiologist. The bottom line is that it might work 24/7, but the decision is that of a radiologist,” he added.

Dr Devasenathipathy highlights that AI-generated reports are carefully reviewed. “We carry out weekly joint conferences to ensure thorough review and discussion of all AI-assisted reports. There is strong oversight, and these findings are never used in isolation,” he said.

Why It Matters
The radiology outpatient department at AIIMS sees roughly 1,000 patients a day, Dr Devasenathipathy said. “From 9 a.m. to 5 p.m., we have four to five radiologists handling routine chest X-ray cases. At night, radiologists also examine CT scans and ultrasound reports,” he explained.

The AI tool is expected to reduce some of that burden. “The system generates provisional reports, which are always reviewed by radiologists and clinicians before treatment. This helps reduce turnaround time,” Dr Devasenathipathy said.

For patients, the difference could be noticeable. “If a patient gets an X-ray and goes to the doctor, they can now receive a preliminary report to share during consultation,” he said.

During emergencies, especially late at night or early morning, junior doctors often manage patients without senior supervision. “Without quick initial results, it can be difficult to identify which patients need urgent attention first,” Dr Sharma said.

The AI tool helps in these situations, he explained. “It triages chest radiographs by analyzing findings related to the lungs, heart, bones, and diaphragm, indicating which cases require priority. It has a sensitivity of 99.7%, detecting nearly all abnormalities.”

“In emergency situations, junior doctors can use the software for support and learning, which helps reduce missed findings and speeds treatment,” Dr Devasenathipathy said.