HomeTechnologyArtificial intelligenceMammography vigilance is important despite AI takeover

Mammography vigilance is important despite AI takeover

Health screening should change depending on technological advances, such as the use of artificial intelligence (AI) in the mammography process, but new methods should not affect vigilance, according to an article published in April 2022 in the journal Climacteric.

In addition to talking about the use of AI in mammography, the article titled “Changes to health screening — we need to stay vigilant” comments on the limitations of studies to date and the features of future studies that could provide the information needed. is to properly assess the impact of the introduction of AI in screening mammography.

The article states that there are established criteria for using a new health screening program described more than 50 years ago and that these criteria still apply. However, it shouldn’t be assumed that once some form of health screening is in place, it should be continued forever, as there is always room for improvement, it adds.

dr. Mahira Yunus, interventional chest radiologist, at Fakeeh University Hospital in Dubai, citing the article, says the progress in the techniques of mammographic screening have already happened. “There is the shift from screen film to digital mammography and the use of breast tomosynthesis as an alternative to two-view digital mammography for breast cancer screening. Another change in mammography screening is on the horizon with the integration of AI into the interpretation of mammography images,” she explains.

According to the article, “Why is the introduction of AI in screening mammography being considered? Even the best performing mammography screening program (with a low interval cancer count combined with a low recall rate) will miss some cancers which then present themselves as interval cancers ahead of the next scheduled one. screening round.

Must Read
RBC Capital Markets launches second algorithm on AI-based electronic trading platform

The article also adds: “Previous publications on the value of AI in the analysis of radiology images have been optimistic, and there were even predictions that AI would threaten the future of the radiology specialty. It may sound like a simple exercise to determine whether incorporating AI into mammographic screening improves the performance of a screening program. However, the reality is that, despite hundreds of publications on the subject in recent years, a systematic review by Freeman et al. has shown that the picture is still not clear.”

Explain, Dr. Yunus adds that in integrating AI with mammography, it is possible that AI will improve sensitivity and reduce the number of interval cancers. “As we already know even the best-performing mammography screening program will miss some cancers, which then present as interval cancers,” she says.

In addition, screening programs usually use two independent readers and are therefore relatively expensive to run and using AI can help reduce these costs, she adds.

According to Dr. Yunusthe paper argues that while it may seem like a simple exercise to determine whether integrating AI into mammographic screening improves the performance of a screening program, especially when the AI system previously detected microcalcifications associated with ductal carcinoma on the spot, it has been claimed that AI program detected very slow growing tumors (leading to overtreatment).

The ideal approach for evaluating AI in a mammographic screening program would be a randomized controlled trial in which the performance of a trained AI program is prospectively evaluated in a screening environment, where the comparator was standard practice, according to the article.

The article also adds that more prospective studies should be done, while establishing the accuracy of the results should be reported as real numbers (true positives, false positives, true negatives, and false negatives), which would affect the calculation of sensitivity. and allows specificity in both the AI ​​system and the comparator (and the difference between them).

However, the introduction of technology in the use of health screening should not affect vigilance. “All of the above reasoning does not rule out the need to be vigilant when using health screening technology,” says Dr. Yunus.

“Healthcare providers should be careful when introducing new technology into a screening program. It should not be assumed that what appears to be a simple change leaves the balance between advantages and disadvantages unchanged,” she adds.

Must Read
The Linux Foundation's AgStack Project to Build World's First Global Dataset of Agricultural Field Boundaries


Asma Ali Zain is an independent journalist and a regular contributor to Omnia Health.

RELATED ARTICLES

LEAVE A REPLY

Please enter your comment!
Please enter your name here

Most Popular

Recent Comments