1. Baker, Kathy A. PhD, APRN, ACNS-BC, FCNS, FAAN
  2. Editor-in-Chief

Article Content

One of the things I have always loved about my years as an endoscopy nurse is the specialty's use of technology to diagnose and treat gastrointestinal (GI) disorders. Technology continues to explode in our field with new initiatives around artificial intelligence (AI) and robotics. For example, a recent randomized controlled cross-over trial (Wallace et al., 2022) based in eight centers (n = 230) reported that the use of AI compared to standard colonoscopy significantly reduces the adenoma miss rate (18.1% vs. 33.3%, respectively), particularly with small, difficult-to-see lesions. Notably, AI was able to minimize the miss rate of flat neoplasia (<10 mm) lesions in the proximal and distal colon. The results are impressive in that a twofold reduction in the miss rate of colorectal neoplasia was reported with obvious implications for improved colorectal cancer prevention in patients seeking screening. Additionally, AI colonoscopy significantly reduced the false-negative rate (6.8% vs. 29.6%) of polyp detection (i.e., incorrectly finding no neoplasia when neoplasia was in fact present).

Kathy A. Baker, PhD,... - Click to enlarge in new windowKathy A. Baker, PhD, APRN, ACNS-BC, FCNS, FAAN

A more immediate, practical use of technology is the development of a smartphone application that uses AI to assess stool characteristics (Pimentel et al., 2022). Generally, many individuals struggle to describe their stool characteristics to a healthcare provider, yet accuracy is very important for screening and assessment, particularly when a provider is determining whether or not an emergent versus routine clinical evaluation is warranted, or whether over-the-counter medications and dietary alterations will address a reported digestive problem. In individuals with diarrhea-predominant irritable bowel syndrome, use of the smartphone application was found to increase the accuracy of stool description, with AI stool characterization being more accurate than self-report for analyzing the severity of diarrhea. The AI is based on the Bristol Stool Scale (Lewis & Heaton, 1997), used frequently in clinical practice and clinical trials to classify stool form. This application can be extremely useful for both clinical practice and clinical trials by increasing the accuracy of stool characterization.


In another recent study, Martin et al. (2020) reported on early developments in robotic endoscopy including their development of intelligent and autonomous control strategies for magnetic endoscopy. They note, magnetically actuated endoscopes have demonstrated the potential to reduce pain and cost, enhance diagnostic capabilities, and improve therapeutic interventions. The authors make the case that intelligent autonomous control of magnetic endoscopes with machine vision is actually practical, safe, and more accurate than endoscopist-driven or teleoperated (predefined trajectories) colonoscopy. Since the colonic environment changes constantly (due to gravity, changes in patient position, peristalsis, insufflation, tissue folds, water, and fecal debris), using predeveloped, predefined trajectories (such as teleoperated robotics) would soon become inaccurate in this ever-changing environment and require constant user updates, which is impracticable. As a result, the researchers have developed the capability for semi-autonomous navigation of the colon using magnetic endoscopy, which proved safe and efficacious in their early animal (porcine) trial.


The results of Martin et al.'s (2020) study show that "endoscope teleoperation and semi-autonomous navigation outperform conventional colonoscopy for novice and newly trained operators, reducing the time to reach the cecum to a value comparable to that of experienced clinicians." They believe magnetic endoscopy can "reduce the complexity of endoscopic procedures by automating the manual aspects of endoscope manipulation, thus reducing the burden on the operator and enabling more focus on the clinical aspects of the procedure" (p. 596). Because autonomous controlled endoscopes require a reduced skillset for the navigation of magnetic endoscope devices, the researchers argue that colonoscopy has the potential to be safer and require fewer resources in terms of trained endoscopists, allowing for the potential to screen more individuals and potentially increase early diagnosis of colorectal cancer.


Artificial intelligence certainly has the potential to accelerate innovation, improve decision-making, automate and accelerate processes, and promote cost savings for both patients and healthcare organizations (McGrow, 2019). The Nursing and Artificial Intelligence Leadership Collaborative has identified current and potential uses of AI in nursing including enhanced nursing documentation with the use of speech recognition technologies, text mining of nursing documentation to identify opportunities for quality improvement based on risk detection for falls or pressure injuries, or deviations from processes in pain, catheter, and ventilator management. In addition to identification of trends in documentation that may point to opportunities for quick and accurate improvement in care, AI will be useful for nurses to easily access and integrate data related to environment, genomics, health data, and patient/community sociodemographics (Ronquillo et al., 2021).


Gastroenterology nurses and associates may already be familiar with AI for clinical decision-making, managing disease, promoting health, engaging with patients, and facilitating improved operations within the GI unit. Regardless of your current familiarity, the use of AI in technology is destined to transform gastroenterology practice and care delivery. Involvement of GI nurses and associates in the development and implementation of AI in the GI setting is imperative to assure clinical applications for nursing are prioritized; clinical predictive algorithms are meaningful, complete, and accurate; clinical workflows are clearly presented; and technical teams understand the critical nuances of the patient experience. Artificial intelligence can help us be better at what we do, but we must be knowledgeable and involved from development through implementation to assure AI benefits our discipline, specialty, and priorities of nursing care (Ronquillo et al., 2021).


If you are involved in using AI in your practice setting, consider sharing your experience by writing a column or manuscript for Gastroenterology Nursing, submitting an abstract to present at the celebratory 50th Society of Gastroenterology Nurses and Associates (SGNA) annual course, or volunteering to develop an SGNA podcast to further the use of AI technology in GI practice. Technology has always been an important part of modern GI care delivery. Let's assure nurses and associates are involved in establishing priority AI applications with meaningful outcomes relative to our patients' and nursing needs.




Lewis S. J., Heaton K. W. (1997). Stool form scale as a useful guide to intestinal transit time. Scandinavian Journal of Gastroenterology, 32(9), 920-924. doi:10.3109/00365529709011203 [Context Link]


Martin J. W., Scaglioni B., Norton J. C., Subramanian V., Arezzo A., Obstein K. L., Valdastri P. (2020). Enabling the future of colonoscopy with intelligent and autonomous magnetic manipulation. Nature Machine Intelligence, 2(10), 595-606. Retrieved August 7, 2022, from[Context Link]


McGrow K. (2019). Artificial intelligence: Essentials for nursing. Nursing, 49(9), 46-49. doi:10.1097/01.NURSE.0000577716.57052.8d [Context Link]


Pimentel M., Mathur R., Wang J., Chang C., Hosseini A., Fiorentino A., Rezaie A. (2022). A smartphone application using artificial intelligence is superior to subject self-reporting when assessing stool form. American Journal of Gastroenterology, 117(7), 1118-1124. doi:10.14309/ajg.0000000000001723 [Context Link]


Ronquillo C. E., Peltonen L. M., Pruinelli L., Chu C. H., Bakken S., Beduschi A., Topaz M. (2021). Artificial intelligence in nursing: Priorities and opportunities from an international invitational think-tank of the Nursing and Artificial Intelligence Leadership Collaborative. Journal of Advanced Nursing, 77(9), 3707-3717. doi:10.1111/jan.14855 [Context Link]


Wallace M. B., Sharma P., Bhandari P., East J., Antonelli G., Lorenzetti R., Hassan C. (2022). Impact of artificial intelligence on miss rate of colorectal neoplasia. Gastroenterology, 163(1), 295-304.e5. doi:10.1053/j.gastro.2022.03.007 [Context Link]