How conflicting study designs explain differences in AI and colonoscopy detection results

In August 2025, The Lancet Gastroenterology & Hepatology published a finding that travelled the world: at four Polish centres, endoscopists who had spent months working with AI-assisted detection found fewer adenomas when performing a colonoscopy without it. The rate fell from 28.4% to 22.4%. Four months later, a Norwegian prospective trial with 5,013 colonoscopies and three phases found exactly nothing: neither loss nor gain of skill when the tool was withdrawn. And a third study, over three years, found sustained improvement. This article sorts out a scientific controversy that is live right now, and explains what separates the three designs.

The 30-second summary: the seven figures that matter

Each row identifies the study and its publication year. Observe that the initial three contradict each other, although all three were executed with high quality.

What you will find here

• The Polish study that raised the alarm and how it is built.

• The three-phase prospective trial that did not find the effect.

• What has been measured outside endoscopy: radiology and pathology.

• The uncomfortable detail regarding which lesions are identified with greater and lesser frequency.

The study that raised the alarm

Krzysztof Budzyń, Marcin Romańczyk alongside a broad team released a retrospective observational study in The Lancet Gastroenterology & Hepatology during 2025, which took place across four Polish endoscopy centres involved in the ACCEPT trial. Polyp detection tools were adopted by those facilities at the close of 2021, prompting the researchers to evaluate colonoscopy standards delivered without AI throughout the preceding three months against the subsequent three months following that deployment.

The sample comprised 1,443 patients, encompassing 795 prior to and 648 following the intervention, alongside a median age of 61 years. The main endpoint evaluated was the adenoma detection rate achieved during conventional, unassisted colonoscopy examinations.

The result: detection fell from 28.4% (226 of 795) to 22.4% (145 of 648), an absolute difference of −6.0 percentage points (95% CI: −10.5 to −1.6; p = 0.0089). In multivariable analysis, prior AI exposure remained an independent factor associated with that fall, with an odds ratio of 0.69.

What that design cannot separate

It is a retrospective observational study comparing two three-month periods. Anything that changed at those centres between late 2021 and early 2022 — staffing, workload, the kind of patient referred — enters the comparison alongside the AI. The authors phrase it cautiously: continuous exposure “might” reduce detection, “suggesting” a negative effect.

The trial that did not find the effect

Tor Anders Pedersen, Yuichi Mori along with their colleagues released a pragmatic, prospective, multicentre study in Endoscopy during late 2025 that was specifically formulated to resolve this inquiry. A total of 5,013 colonoscopies were performed across three sequential stages—pre-AI, during AI deployment, and post-withdrawal—by thirteen endoscopists, comprising seven novices and six veterans who had each completed upwards of a thousand procedures. Consequently, every clinician served as their own control.

The authors’ conclusion is clear: detection by inexperienced endoscopists increased while they were using the tool, and in unassisted colonoscopy neither improvement nor loss of skill was observed after the exposure period.

This layout surpasses the Polish alternative for this particular inquiry, owing to its prospective nature and the fact that every practitioner serves as their own benchmark. Furthermore, it involves a smaller cohort—thirteen compared to the participants across four facilities—and relies on an indirect metric, namely the fraction of colonoscopies revealing at least one polyp measuring 5 mm or greater, which lacks the established standing as a quality benchmark that adenoma detection enjoys.

What has been measured outside endoscopy

Pierre Heudel and colleagues published a scoping review on deskilling in medicine in ESMO Real World Data and Digital Oncology in 2026. Their general conclusion: evidence of clinical deskilling is scarce, but consistent across specialties. Three specific figures they record:

• In radiology, a controlled study with 27 breast imaging radiologists found that erroneous AI prompts increased false-positive recalls by up to 12%, even among experienced readers.

• In computational pathology, in experimental tasks under time pressure, more than 30% of participants reversed a correct initial diagnosis when exposed to an incorrect system suggestion.

• In cytology, the United Kingdom’s shift to primary human papillomavirus screening cut case volumes by 80% to 85% and consolidated laboratories from 45 to 8 centres, with direct consequences for training capacity.

That final detail highlights a distinction worth remembering. When an expert misses their touch through overreliance on automation, it differs fundamentally from an ecosystem failing to produce the foundational scenarios trainees study. The latter issue runs deep structurally and defies resolution via personal coaching.

The uncomfortable detail: what is detected more and less

A three-year Japanese observational study, with more than 4,700 matched colonoscopies, found no deterioration at all after introducing assisted detection, and even found accelerated learning curves among endoscopists who were already good detectors. It seemed to settle the debate in favour.

Darrien Henry and James East published a letter in Endoscopy in 2026 interpreting those identical statistics through a different lens. Within that research, detection rates for adenomas measuring 6 to 9 mm, 10 mm and above, those featuring high grade dysplasia, along with invasive cancer cases, proved markedly superior among the unassisted cohort. Furthermore, the incidence of invasive cancer was more than twice as high when the tool was absent compared to when it was utilized (p = 0.001).

Their alternative interpretation is harsh and well argued: assisted detection may distract the endoscopist towards trivial lesions — adenomas of 1 to 5 mm and hyperplastic polyps — at the expense of advanced lesions, which are the ones that matter. The consistency of the effect direction across three different categories of advanced lesion, with very low p values, makes chance an unlikely explanation.

Omer Ahmad proposed in 2026, also in Endoscopy, the reading that best reconciles the three studies: they may not contradict one another, but rather be capturing different stages of human-machine adaptation, and what the Polish study measured may be transient, reversible cognitive offloading rather than permanent erosion of skill.

Practical application of these steps

Ordered by the strength of the evidence behind it:

• Do not view the discussion as completely resolved on either side. Three rigorous analyses point to three distinct outcomes, and their divergent methodologies account for the variance.

• Keep periods of unassisted practice. It is the recommendation that recurs in the endoscopy literature, precisely because of what is not known.

• Measure what kind of lesion you detect, rather than simply counting them. The specialty’s most rigorous review revealed that a higher volume of invasive cancer was uncovered without the software than with its assistance.

• Watch for erroneous prompts. In breast radiology they increased false-positive recalls by up to 12%, including among experienced readers.

• Think about training, not only about the already-trained professional. The British cytology case shows the problem may be that the cases people learn on disappear.

Frequently asked questions

Do doctors who use artificial intelligence lose skill?

It is not settled. The Polish observational study published in The Lancet Gastroenterology & Hepatology in 2025 found unassisted adenoma detection falling from 28.4% to 22.4% after AI was introduced, a difference of −6.0 points (p = 0.0089), but a later prospective trial with 5,013 colonoscopies observed neither loss nor gain after the tool was withdrawn.

Why do two sound studies arrive at conflicting conclusions?

Because of the design. The Polish trial is retrospective and evaluates a pair of three-month intervals, meaning that any shift at the core impacts the analysis; conversely, the Norwegian investigation is prospective, structured in three phases, and positions each endoscopist as their own baseline. A theory featured in Endoscopy suggests that both approaches could be documenting distinct phases of adaptation to the device.

Who does it affect most?

The evidence points to different effects by level. In the prospective trial, inexperienced endoscopists improved detection while using the AI, from 31.9% to 39.5% (OR 1.43), and returned to their baseline when it was withdrawn; among the experienced there was no significant effect in any of the three phases.

Does it occur outside the endoscopy setting as well?

There are signals in other specialties. Based on the 2026 review, a controlled trial involving 27 breast imaging radiologists revealed that flawed AI prompts elevated false-positive recalls by as much as 12% even among seasoned specialists, whereas in computational pathology over 30% of participants flipped a correct diagnosis when confronted with a faulty suggestion amid time constraints.

Does detecting more polyps mean preventing more cancer?

Not necessarily, and that is the most uncomfortable point. Revisiting the data from a three-year study, a letter published in Endoscopy in 2026 revealed that the detection of adenomas measuring 10 mm or greater, cases showing high-grade dysplasia, and instances of invasive cancer proved notably greater in the absence of the device, yielding an invasive cancer rate that exceeded double the amount (p = 0.001).

What we do not know

• Whether the effect is reversible. The transient cognitive offloading hypothesis is plausible, but nobody has measured what happens after withdrawing the tool for a long period.

• What happens to people trained with the tool from the start. The available studies do not include absolute beginners, the group where skill retention matters most.

• Whether it affects mortality. None of this work measures post-colonoscopy colorectal cancer or survival.

• How long the exposure needs to be. One study, which observes an impact, spans three months; another, showing no effect, evaluates varying durations; finally, the research noting enhancement lasts three years.

References

1. Budzyń, K., Romańczyk, M. et al. Endoscopist deskilling risk after exposure to artificial intelligence in colonoscopy: a multicentre, observational study. The Lancet Gastroenterology & Hepatology, 2025. DOI: 10.1016/s2468-1253(25)00133-5

2. Pedersen, T. A., Mori, Y. et al. Learning and deskilling effects of artificial intelligence in colonoscopy among endoscopists with different levels of experience: a pragmatic, prospective trial. Endoscopy, 2025. DOI: 10.1055/a-2858-7084

3. Heudel, P., Crochet, H. et al. Artificial intelligence in medicine: a scoping review of the risk of deskilling and loss of expertise among physicians. ESMO Real World Data and Digital Oncology, 2026. DOI: 10.1016/j.esmorw.2026.100693

4. Henry, D. and East, J. Artificial intelligence-supported polyp detection (CADe) at colonoscopy reduces the detection of high grade dysplasia and invasive cancer. Endoscopy, 2026. DOI: 10.1055/a-2749-8345

5. Ahmad, O. Human-artificial intelligence adaptation in colonoscopy: beyond deskilling and upskilling. Endoscopy, 2026. DOI: 10.1055/a-2896-9791

This material is purely informational and should not be considered medical guidance. The statistics mentioned stem from research featuring methodologies, fields, and timeframes that cannot be directly contrasted, and they outline an ongoing scientific discussion at the moment of publication.