A new meta-analysis confirms that the use of computer-aided detection (CADe) systems during colonoscopy detects more polyps and adenomas than conventional colonoscopy, but the effect on the detection of advanced colorectal neoplasia (ACN) remains unclear.

The research team, which focused on advanced neoplasia due to their clinical importance, found a small increase in the detection rate of ACN with CADe, but no difference in ACN detected by colonoscopy.

For ACN, “the ones we really care about, the findings have been discordant,” Dennis Shung, MD, MHS, PhD, of Yale School of Medicine, New Haven, Conn., said in an interview.

There was a “small positive signal” indicating the potential of AI to detect advanced neoplasia. “However, we can’t say for sure that it will help you find advanced colonic neoplasia,” Shung said.

Jeremy Glissen Brown, MD, MSc, a gastroenterologist at Duke Health, Durham, North Carolina, who was not involved in the study, said in an interview that it is “one of the most comprehensive systematic reviews and meta-analyses to date , examining both parallel and tandem randomized clinical trials (RCTs) of CADe in colonoscopy.”

“The results are generally consistent with previous RCTs and meta-analyses and show an improvement in important quality metrics, mainly an increase in adenomas per colonoscopy (APC), an increase in the adenoma detection rate (ADR) and a decrease of the adenoma miss rate. (AMR),” noted Glissen Brown.

The analysis was published online on October 21 in Annals of Internal Medicine.

Bigger, more accurate analysis

Previous meta-analyses of AI-assisted colonoscopy included up to 33 RCTs. In their updated meta-analysis, Shung and colleagues included 44 RCTs with 36,201 cases.

“The large sample size included in this study allowed us to examine the effectiveness of CADe in diagnosing clinically relevant colonic lesions with greater accuracy, which was not feasible in previous randomized clinical trials and reviews given the smaller size of sample,” they wrote.

For polyp detection, CADe-enhanced colonoscopy outperformed conventional colonoscopy in the mean number of polyps detected per colonoscopy (1.59 vs 1.27; incidence rate difference (IRD), 0.35) and polyp detection rate (54% vs of 46.5%; rate of return (RR), 1.21).

The same is true for adenoma detection. CADe-enhanced colonoscopy had a higher mean APC (0.98 vs 0.78; IRD, 0.22) and ADR (44.7% vs 36.7%; RR, 1.21), coupled with an AMR lower (16.1% vs 35.3%; RR, 0.47).

Mean ACN per colonoscopy was similar with and without CADe enhancement (0.16 vs 0.15; IRD, 0.01), but there was a small increase in the detection rate of ACN (12.7% vs 11.5% ; RR, 1.16).

Results of a subgroup analysis suggest a reduced benefit of CADe in patients with positive faecal immunoassay results, “which may indicate an attenuated benefit for using CADe systems for routine screening practice,” the study team wrote.

In a sensitivity analysis of overall adenoma detection according to baseline ADR, there was an increase in the benefit of CADe systems among providers with a lower ADR.

Use of the CADe systems resulted in the resection of nearly two additional neoplastic polyps per 10 colonoscopies and a “marginal” increase in withdrawal time (0.53 minutes), which may have “limited clinical significance,” the authors noted.

There were no clear differences in performance between the different CADe systems used in the included studies.

All studies were rated as ‘high concern’ for overall bias. Other limitations include study heterogeneity, lack of blinding between conventional and CADe-enhanced colonoscopies, and unexplained confounding factors.

Ready for Prime Time?

Is routine adoption of AI-assisted colonoscopy ready for prime time? Glissen Brown thinks so, with a few caveats.

“We are at a pivotal point in examining CADe for routine use in colonoscopy. CADe has been ready for prime time in the United States since at least 2021, and the CADe trial has made the field of gastroenterology a clinical leader in the number of high-quality randomized trials examining AI interventions,” said Glissen Brown. .

However, outside of the clinical trial setting, questions remain about implementation and successful implementation, he said.

“These include, but are not limited to, ways to optimize AI-human interaction to produce a successful AI-supplier partnership, reimbursement and cost issues, and issues of ethical AI development and implementation,” Glissen Brown said.

“We also need to continue to evaluate methods of estimating the use of CADe on downstream outcomes that matter, such as the effects of CADe on reducing colon cancer rates, rates of post-colonoscopy colorectal cancer (CRC), and the effect that CADe may have on CRC mortality. In addition, more studies on patient voice and patient preferences regarding the use of AI are greatly needed,” said Glissen Brown.

The American Gastroenterological Association has developed guidelines for the use of CADe systems during colonoscopy.

Clinicians are invited to review the draft guideline and share feedback during the public comment period, which ends on October 28.

The study had no specific funding. Disclosures for study authors are available with the original article. Glissen Brown is a consultant for Medtronic, Olympus and Odin Vision. He was also the lead author one of the studies included in the meta-analysis.