THEBUSINESSBYTES
BUREAU
BHUBANESWAR,
JULY 2, 2026
Researchers from KIIT
Deemed to be University (KIIT-DU) have published a significant paper in the
prestigious medical journal The Lancet,
underscoring the need to incorporate age-related tumour biology into the
evaluation of artificial intelligence (AI)-based breast cancer screening.
The publication argues
that integrating biological differences across age groups into AI-assisted
mammography assessments could provide a more accurate measure of the
technology’s effectiveness in detecting breast cancer.
The article, authored
by Dr. Pratap Kumar Jena, Associate Professor, Sabyasachi Shukla, PhD Scholar,
and Dr. Ramya Pinnamaneni, Director of the School of Public Health at KIIT,
contends that AI-powered mammography tools should be assessed not only for
their technological performance but also for the biological variations in
tumour growth across different age groups. Such an approach, the researchers
say, would generate stronger evidence on the clinical effectiveness of breast
cancer screening.
The KIIT team
presented these observations in response to findings from the Swedish MASAI
(Mammography Screening with Artificial Intelligence) trial, one of the world’s
largest studies evaluating AI in breast cancer screening. While the trial
concluded that AI-assisted screening detected more cancers and outperformed the
conventional double-reading method by radiologists, the KIIT researchers
believe the study did not sufficiently account for age-related differences in
tumour biology.
According to the
researchers, breast cancer does not progress uniformly across all age groups.
Tumours in younger women often grow more rapidly, whereas those in older women
tend to develop more slowly and remain detectable for longer durations.
This variation in the
“window of detectability” can significantly influence the perceived performance
of AI systems, potentially making them appear either more or less effective
than they actually are.
“If AI-based screening assessments do not
account for age-related differences in tumour growth and the window of
detectability, estimates of screening effectiveness may be incomplete,” said
Dr. Pratap Kumar Jena. “Integrating biological factors into AI evaluation
frameworks could improve predictive accuracy and reduce errors in assessing AI
performance.”
The publication marks
another notable scholarly contribution by KIIT researchers to the growing
global discourse on AI-assisted healthcare. Earlier this year, the same
research team published a correspondence in The Lancet Digital Health,
highlighting key methodological considerations in evaluating AI-assisted
mammography, including the importance of accounting for the preclinical “window
of detectability” (or sojourn time) and clarifying critical screening metrics.
Building on their
earlier work, the researchers have recommended that future AI-supported
mammography studies incorporate mathematical models that account for
age-related variations in cancer growth. They believe such an approach would
enable a more accurate assessment of AI’s true clinical value and support
healthcare systems in making better-informed breast cancer screening decisions
for women across different age groups.
