Experts are weighing the benefits and limitations of using artificial intelligence (AI) in colonoscopies. While AI can help detect polyps and lesions, the evidence supporting its effectiveness is still fuzzy.
Recent studies have shown that AI-powered computer-aided detection (CADe) systems can improve adenoma detection rates (ADR) during colonoscopies. For instance, a meta-analysis found that CADe systems increased ADR from 25.2% to 36.6%. However, other studies have raised concerns about the high false positive rates associated with these systems.
Another area of interest is computer-aided characterization (CADx), which uses AI to predict the histology of detected lesions. While CADx systems have shown promising results in standalone performance evaluations, more research is needed to confirm their effectiveness in real-world clinical settings.
Experts emphasize that AI should be viewed as a tool to augment human capabilities, rather than replace them. As the technology continues to evolve, it's essential to address concerns around accuracy, reliability, and clinical relevance.
