Health

Artificial intelligence helps physicians better assess the effectiveness of bladder cancer treatment

With the help of machine learning tools, doctors are able to determine whether their patients have responded to bladder cancer treatment. Credit: Justine Ross / Michigan Medicine

In small but multidisciplinary centers, the human brain-based system improves the evaluation of whether or not patients with bladder cancer have found a complete response to chemotherapy prior to radical cystectomy (bladder removal surgery).

However researchers warn that AI does not replace human intelligence and is their own tool should not be used.

“If you use the tool carefully, it can help you,” said Lubomir Hadjiyski, Ph.D., professor of radiology at the University of Michigan School of Medicine and lead author of the study.

When the patients progressed bladder painDoctors remove all of them bladder in an effort to maintain cancer from return or propagation to other organs or locations. Additional evidence builds, though, that surgery may not be necessary if the patient has no evidence of disease after chemotherapy.

However, it is difficult to determine whether the lesion left after treatment is the only tissue that becomes necrotic or scar as a result of treatment or cancer remains. Researchers wonder if AI can help.

“The big question is when you have such a temporary device near you, how does that affect the doctor?” Hadjiyski said. “Will it help? Will it confuse them? Will it raise their profile or will they ignore it?”

Fourteen doctors from various disciplines – including radiology, urology and oncology – and two colleagues and medical student reviewed immunizations and post-treatment for bladder cancer 157. The providers provided ratings for three measures that assessed the level of response to chemotherapy and the next treatment recommendations for each patient (radiation or surgery). ).

Then the producers looked at the points that the computer counted. Low scores indicate a low probability of a complete response to chemo and vice versa for high scores. Manufacturers can review their value or leave them unchanged. Their final value was compared with the tumor samples taken during the bladder removal procedure to measure accuracy.

Throughout the various disciplines and experience levels, developers have seen improvements in their value with the AI ​​system. Inexperienced ones make more profit, by being able to do research at the same level as the experienced participants.

“This is a unique part of this study that highlights some interesting observations about the audience,” Hadjiyski said.

The tool helped producers from educational institutions than those who worked at health centers just focus on hospital care.

The study is part of an ongoing NIH program, led by Hadjiyski and Ajjai Alva, MD, a professor of obstetrics and gynecology at UM, to develop and evaluate biomarker-based tools to support decision making responses to bladder cancer treatment. .

In more than two decades of AI research to identify different types of cancer and their treatment, Hadjiyski said he noted that machine learning tools can be as useful as second opinion to help doctors make decisions, but they may also make mistakes.

“One interesting thing we found out was that the computer is making more errors on a different part of the case than the radiologist would have done,” he said. “Which means that if the equipment is used correctly, it provides an opportunity for improvement but does not replace medical judgment.”


Studies confirm the cure for bladder cancer


Learn more:
Di Sun E et Al, the help of specialists experienced professional skilled specialists experienced specialists professionals ………………………………….. Tomography (2022). DOI: 10.3390 / tomography8020054

hint: Artificial intelligence helps physicians assess the effectiveness of bladder cancer treatment (2022, April 22) retrieved April 22, 2022 from https://medicalxpress.com/news/2022-04-artificial-intelligence-physicians- effectiveness-bladder.html

This document is copyrighted. Apart from any genuine transaction for the purpose of personal analysis or investigation, no part may be reproduced without our written permission. Content is provided for informational purposes only.



Artificial intelligence helps physicians better assess the effectiveness of bladder cancer treatment Source link Artificial intelligence helps physicians better assess the effectiveness of bladder cancer treatment

Related Articles

Back to top button