Automated identification and assignment of colonoscopy surveillance recommendations for individuals with colorectal polyps

A foundation systematic review of natural language processing applied to gastroenterology & hepatology

OBJECTIVE

This review assesses the progress of NLP in gastroenterology to date, grades the robustness of the methodology, exposes the field to a new generation of authors, and highlights opportunities for future research.

DESIGN

Seven scholarly databases (ACM Digital Library, Arxiv, Embase, IEEE Explore, Pubmed, Scopus and Google Scholar) were searched for studies published between 2015 and 2023 that met the inclusion criteria. Studies lacking a description of appropriate validation or NLP methods were excluded, as were studies ufinavailable in English, those focused on non-gastrointestinal diseases and those that were duplicates. Two independent reviewers extracted study information, clinical/algorithm details, and relevant outcome data. Methodological quality and bias risks were appraised using a checklist of quality indicators for NLP studies.

RESULTS

Fifty-three studies were identified utilising NLP in endoscopy, inflammatory bowel disease, gastrointestinal bleeding, liver and pancreatic disease. Colonoscopy was the focus of 21 (38.9%) studies; 13 (24.1%) focused on liver disease, 7 (13.0%) on inflammatory bowel disease, 4 (7.4%) on gastroscopy, 4 (7.4%) on pancreatic disease and 2 (3.7%) on endoscopic sedation/ERCP and gastrointestinal bleeding. Only 30 (56.6%) of the studies reported patient demographics, and only 13 (24.5%) had a low risk of validation bias. Thirty-five (66%) studies mentioned generalisability, but only 5 (9.4%) mentioned explainability or shared code/models.

CONCLUSION

NLP can unlock substantial clinical information from free-text notes stored in EPRs and is already being used, particularly to interpret colonoscopy and radiology reports. However, the models we have thus far lack transparency, leading to duplication, bias, and doubts about generalisability. Therefore, greater clinical engagement, collaboration, and open sharing of appropriate datasets and code are needed.

Consensus statements on the current landscape of artificial intelligence applications in endoscopy, addressing roadblocks, and advancing artificial intelligence in gastroenterology

BACKGROUND AND AIMS

The American Society for Gastrointestinal Endoscopy (ASGE) AI Task Force along with experts in endoscopy, technology space, regulatory authorities, and other medical subspecialties initiated a consensus process that analyzed the current literature, highlighted potential areas, and outlined the necessary research in artificial intelligence (AI) to allow a clearer understanding of AI as it pertains to endoscopy currently.

METHODS

A modified Delphi process was used to develop these consensus statements.

RESULTS

Statement 1: Current advances in AI allow for the development of AI-based algorithms that can be applied to endoscopy to augment endoscopist performance in detection and characterization of endoscopic lesions. Statement 2: Computer vision-based algorithms provide opportunities to redefine quality metrics in endoscopy using AI, which can be standardized and can reduce subjectivity in reporting quality metrics. Natural language processing-based algorithms can help with the data abstraction needed for reporting current quality metrics in GI endoscopy effortlessly. Statement 3: AI technologies can support smart endoscopy suites, which may help optimize workflows in the endoscopy suite, including automated documentation. Statement 4: Using AI and machine learning helps in predictive modeling, diagnosis, and prognostication. High-quality data with multidimensionality are needed for risk prediction, prognostication of specific clinical conditions, and their outcomes when using machine learning methods. Statement 5: Big data and cloud-based tools can help advance clinical research in gastroenterology. Multimodal data are key to understanding the maximal extent of the disease state and unlocking treatment options. Statement 6: Understanding how to evaluate AI algorithms in the gastroenterology literature and clinical trials is important for gastroenterologists, trainees, and researchers, and hence education efforts by GI societies are needed. Statement 7: Several challenges regarding integrating AI solutions into the clinical practice of endoscopy exist, including understanding the role of human-AI interaction. Transparency, interpretability, and explainability of AI algorithms play a key role in their clinical adoption in GI endoscopy. Developing appropriate AI governance, data procurement, and tools needed for the AI lifecycle are critical for the successful implementation of AI into clinical practice. Statement 8: For payment of AI in endoscopy, a thorough evaluation of the potential value proposition for AI systems may help guide purchasing decisions in endoscopy. Reliable cost-effectiveness studies to guide reimbursement are needed. Statement 9: Relevant clinical outcomes and performance metrics for AI in gastroenterology are currently not well defined. To improve the quality and interpretability of research in the field, steps need to be taken to define these evidence standards. Statement 10: A balanced view of AI technologies and active collaboration between the medical technology industry, computer scientists, gastroenterologists, and researchers are critical for the meaningful advancement of AI in gastroenterology.

CONCLUSIONS

The consensus process led by the ASGE AI Task Force and experts from various disciplines has shed light on the potential of AI in endoscopy and gastroenterology. AI-based algorithms have shown promise in augmenting endoscopist performance, redefining quality metrics, optimizing workflows, and aiding in predictive modeling and diagnosis. However, challenges remain in evaluating AI algorithms, ensuring transparency and interpretability, addressing governance and data procurement, determining payment models, defining relevant clinical outcomes, and fostering collaboration between stakeholders. Addressing these challenges while maintaining a balanced perspective is crucial for the meaningful advancement of AI in gastroenterology.

ChatGPT4 Outperforms Endoscopists for Determination of Postcolonoscopy Rescreening and Surveillance Recommendations

BACKGROUND & AIMS

Large language models including Chat Generative Pretrained Transformers version 4 (ChatGPT4) improve access to artificial intelligence, but their impact on the clinical practice of gastroenterology is undefined. This study compared the accuracy, concordance, and reliability of ChatGPT4 colonoscopy recommendations for colorectal cancer rescreening and surveillance with contemporary guidelines and real-world gastroenterology practice.

METHODS

History of present illness, colonoscopy data, and pathology reports from patients undergoing procedures at 2 large academic centers were entered into ChatGPT4 and it was queried for the next recommended colonoscopy follow-up interval. Using the McNemar test and inter-rater reliability, we compared the recommendations made by ChatGPT4 with the actual surveillance interval provided in the endoscopist's procedure report (gastroenterology practice) and the appropriate US Multisociety Task Force (USMSTF) guidance. The latter was generated for each case by an expert panel using the clinical information and guideline documents as reference.

RESULTS

Text input of de-identified data into ChatGPT4 from 505 consecutive patients undergoing colonoscopy between January 1 and April 30, 2023, elicited a successful follow-up recommendation in 99.2% of the queries. ChatGPT4 recommendations were in closer agreement with the USMSTF Panel (85.7%) than gastroenterology practice recommendations with the USMSTF Panel (75.4%) (P < .001). Of the 14.3% discordant recommendations between ChatGPT4 and the USMSTF Panel, recommendations were for later screening in 26 (5.1%) and for earlier screening in 44 (8.7%) cases. The inter-rater reliability was good for ChatGPT4 vs USMSTF Panel (Fleiss κ, 0.786; 95% CI, 0.734-0.838; P < .001).

CONCLUSIONS

Initial real-world results suggest that ChatGPT4 can define routine colonoscopy screening intervals accurately based on verbatim input of clinical data. Large language models have potential for clinical applications, but further training is needed for broad use.

Improving Concordance Between Clinicians With Australian Guidelines for Bowel Cancer Prevention Using a Digital Application: Randomized Controlled Crossover Study

BACKGROUND

Australia's bowel cancer prevention guidelines, following a recent revision, are among the most complex in the world. Detailed decision tables outline screening or surveillance recommendations for 230 case scenarios alongside cessation recommendations for older patients. While these guidelines can help better allocate limited colonoscopy resources, their increasing complexity may limit their adoption and potential benefits. Therefore, tools to support clinicians in navigating these guidelines could be essential for national bowel cancer prevention efforts. Digital applications (DAs) represent a potentially inexpensive and scalable solution but are yet to be tested for this purpose.

OBJECTIVE

This study aims to assess whether a DA could increase clinician adherence to Australia's new colorectal cancer screening and surveillance guidelines and determine whether improved usability correlates with greater conformance to guidelines.

METHODS

As part of a randomized controlled crossover study, we created a clinical vignette quiz to evaluate the efficacy of a DA in comparison with the standard resource (SR) for making screening and surveillance decisions. Briefings were provided to study participants, which were tailored to their level of familiarity with the guidelines. We measured the adherence of clinicians according to their number of guideline-concordant responses to the scenarios in the quiz using either the DA or the SR. The maximum score was 18, with higher scores indicating improved adherence. We also tested the DA's usability using the System Usability Scale.

RESULTS

Of 117 participants, 80 were included in the final analysis. Using the SR, the adherence of participants was rated a median (IQR) score of 10 (7.75-13) out of 18. The participants' adherence improved by 40% (relative risk 1.4, P<.001) when using the DA, reaching a median (IQR) score of 14 (12-17) out of 18. The DA was rated highly for usability with a median (IQR) score of 90 (72.5-95) and ranked in the 96th percentile of systems. There was a moderate correlation between the usability of the DA and better adherence (rs=0.4; P<.001). No differences between the adherence of specialists and nonspecialists were found, either with the SR (10 vs 9; P=.47) or with the DA (13 vs 15; P=.24). There was no significant association between participants who were less adherent with the DA (n=17) and their age (P=.06), experience with decision support tools (P=.51), or academic involvement with a university (P=.39).

CONCLUSIONS

DAs can significantly improve the adoption of complex Australian bowel cancer prevention guidelines. As screening and surveillance guidelines become increasingly complex and personalized, these tools will be crucial to help clinicians accurately determine the most appropriate recommendations for their patients. Additional research to understand why some practitioners perform worse with DAs is required. Further improvements in application usability may optimize guideline concordance further.

Use of artificial intelligence in the management of T1 colorectal cancer: a new tool in the arsenal or is deep learning out of its depth?

The field of artificial intelligence is rapidly evolving, and there has been an interest in its use to predict the risk of lymph node metastasis in T1 colorectal cancer. Accurately predicting lymph node invasion may result in fewer patients undergoing unnecessary surgeries; conversely, inadequate assessments will result in suboptimal oncological outcomes. This narrative review aims to summarize the current literature on deep learning for predicting the probability of lymph node metastasis in T1 colorectal cancer, highlighting areas of potential application and barriers that may limit its generalizability and clinical utility.

Development and Evaluation of a Surveillance System for Follow-Up After Colorectal Polypectomy

Importance

The adherence of physicians and patients to published colorectal postpolypectomy surveillance guidelines varies greatly, and patient follow-up is critical but time consuming.

Objectives

To evaluate the accuracy of an automatic surveillance (AS) system in identifying patients after polypectomy, assigning surveillance intervals for different risks of patients, and proactively following up with patients on time.

Design, Setting, and Participants

In this diagnostic/prognostic study, endoscopic and pathological reports of 47 544 patients undergoing colonoscopy at 3 hospitals between January 1, 2017, and June 30, 2022, were collected to develop an AS system based on natural language processing. The performance of the AS system was fully evaluated in internal and external tests according to 5 guidelines worldwide and compared with that of physicians. A multireader, multicase (MRMC) trial was conducted to evaluate use of the AS system and physician guideline adherence, and prospective data were collected to evaluate the success rate in contacting patients and the association with reduced human workload. Data analysis was conducted from July to September 2022.

Exposures

Assistance of the AS system.

Main Outcomes and Measures

The accuracy of the system in identifying patients after polypectomy, stratifying patient risk levels, and assigning surveillance intervals in internal (Renmin Hospital of Wuhan University), external 1 (Wenzhou Central Hospital), and external 2 (The First People's Hospital of Yichang) test sets; the accuracy of physicians and their time burden with and without system assistance; and the rate of successfully informed patients of the system were evaluated.

Results

Test sets for 16 106 patients undergoing colonoscopy (mean [SD] age, 51.90 [13.40] years; 7690 females [47.75%]) were evaluated. In internal, external 1, and external 2 test sets, the system had an overall accuracy of 99.91% (95% CI, 99.83%-99.95%), 99.54% (95% CI, 99.30%-99.70%), and 99.77% (95% CI, 99.41%-99.91%), respectively, for identifying types of patients and achieved an overall accuracy of at least 99.30% (95% CI, 98.67%-99.63%) in the internal test set, 98.89% (95% CI, 98.33%-99.27%) in external test set 1, and 98.56% (95% CI, 95.86%-99.51%) in external test set 2 for stratifying patient risk levels and assigning surveillance intervals according to 5 guidelines. The system was associated with increased mean (SD) accuracy among physicians vs no AS system in 105 patients (98.67% [1.28%] vs 78.10% [18.01%]; P = .04) in the MRMC trial. In a prospective trial, the AS system successfully informed 82 of 88 patients (93.18%) and was associated with reduced burden of follow-up time vs no AS system (0 vs 2.86 h).

Conclusions and Relevance

This study found that an AS system was associated with improved adherence to guidelines among physicians and reduced workload among physicians and nurses.

A deep learning and natural language processing-based system for automatic identification and surveillance of high-risk patients undergoing upper endoscopy: A multicenter study

BACKGROUND

Timely identification and regular surveillance of patients at high risk are crucial for early diagnosis of upper gastrointestinal cancer. However, traditional manual surveillance method is time-consuming, and current surveillance rate is below 50%. Here, we aimed to develop a surveillance system named ENDOANGEL-AS (automatic surveillance) for automatic identification and surveillance of high-risk patients.

METHODS

7874 patients from Renmin Hospital of Wuhan University between May 1 and July 31, 2021 were used as the training set, 6762 patients between August 1 and October 31, 2021 as the internal test set, and 7570 patients from two other hospitals between August 1 and October 31, 2021 as the external test sets. We first extracted descriptions of abnormalities from endoscopic and pathological reports based on natural language processing techniques to identify individuals. Then patients were classified at nine risk levels according to endoscopic and pathological findings, and a deep learning model was trained to identify demarcation line (DL) in gastric low-grade intraepithelial neoplasia (LGIN) using 1561 white-light still images for risk stratification of gastric LGIN. Finally, patients undergoing upper endoscopy were classified and assigned one of ten surveillance intervals according to guidelines. The performance of ENDOANGEL-AS was evaluated and compared with physicians.

FINDINGS

Patient identification module achieved an accuracy of 100% and 99.91% in internal and external test sets, respectively. Risk level classification module achieved an accuracy of 100% and 99.85% in the internal and external test sets, respectively. DL identification module achieved an accuracy of 87.88%. ENDOANGEL-AS on surveillance interval assignment achieved an accuracy of 99.23% and 99.67% in internal and external test sets, respectively. ENDOANGEL-AS had significantly higher accuracy compared with physicians (99.00% vs 38.87%, p < 0.001). The accuracy (63.67%, p < 0.001) of endoscopists with the assistance of ENDOANGEL-AS was significantly improved.

INTERPRETATION

We established a surveillance system that can automatically identify patients and assign surveillance intervals with high accuracy and good transferability.

FUNDING

This work was partly supported by a grant from the Hubei Province Major Science and Technology Innovation Project (2018-916-000-008) and the Fundamental Research Funds for the Central Universities (2042021kf0084).

Artificial intelligence-assisted colonoscopy: a narrative review of current data and clinical applications

Colonoscopy is the reference standard procedure for the prevention and diagnosis of colorectal cancer, which is a leading cause of cancer-related deaths in Singapore. Artificial intelligence systems are automated, objective and reproducible. Artificial intelligence-assisted colonoscopy has recently been introduced into clinical practice as a clinical decision support tool. This review article provides a summary of the current published data and discusses ongoing research and current clinical applications of artificial intelligence-assisted colonoscopy.

Patient and clinician perceptions of the immediate release of electronic health information

OBJECTIVES

The 21st Century Cures Act requires that institutions release all electronic health information (EHI) to patients immediately. We aimed to understand patient and clinician attitudes toward the immediate release of EHI to patients.

METHODS

Patients and clinicians representing distinct specialties at a single academic medical center completed a survey to assess attitudes toward the immediate release of results. Differences between patient and clinician responses were compared using chi-square and student's t-test for categorical and continuous variables, respectively. A two-sided significance level of 0.05 was used for all statistical tests.

RESULTS

69 clinicians and 57 patients completed the survey. Both patients (89.7%) and clinicians (80.6%) agreed or strongly agreed-here after referred to as agreed, that providing patients with access to their health information is necessary in delivering high-quality care. However, 62.7% of clinicians agreed that results released immediately would be more confusing than helpful, whereas the minority of patients agreed with this statement (15.8%) (p < 0.05). Providers were also more likely to disagree that patients are comfortable independently interpreting blood work results (p < 0.05), radiology results (p < 0.05) and pathology reports (p < 0.05). With regard to timing, the majority of patients (75.1%) felt their provider should contact them within 24 h of the release of an abnormal result, whereas only 9.0% of clinicians agreed with this timeframe (p < 0.05).

DISCUSSIONS

Patients and clinicians value information transparency. However, the immediate release of results is controversial, especially among clinicians. The discrepancy between patient and clinician perceptions underlines the importance of setting expectations about the communication of results. Additionally, our results emphasize the need to implement strategies to help improve patient comprehension, decrease patient distress and improve clinician workflows.