Adenoma Detection Rate Falls at the End of the Day in a Large Multi-site Sample

Improvement in adenoma detection rate by artificial intelligence-assisted colonoscopy: Multicenter quasi-randomized controlled trial

Background and study aims

Adenoma detection rate (ADR) is a key performance measure with variability among endoscopists. Artificial intelligence (AI) in colonoscopy could reduce this variability and has shown to improve ADR. This study assessed the impact of AI on ADR among Danish endoscopists of varying experience levels.

Patients and methods

We conducted a prospective, quasi-randomized, controlled, multicenter trial involving patients aged 18 and older undergoing screening, surveillance, and diagnostic colonoscopy at four centers. Participants were assigned to AI-assisted colonoscopy (GI Genius, Medtronic) or conventional colonoscopy. Endoscopists were classified as experts (> 1000 colonoscopies) or non-experts (≤ 1000 colonoscopies). The primary outcome was ADR. We performed a subgroup analysis stratified on endoscopist experience and a subset analysis of the screening population.

Results

A total of 795 patients were analyzed: 400 in the AI group and 395 in the control group. The AI group demonstrated a significantly higher ADR than the control group (59.1% vs. 46.6%, P < 0.001). The increase was significant among experts (59.9% vs. 47.3%, P < 0.002) but not among non-experts. AI assistance significantly improved ADR (74.4% vs. 58.1%, P = 0.003) in screening colonoscopies. Polyp detection rate (PDR) was also higher in the AI group (69.8% vs. 56.2%, P < 0.001). There was no significant difference in the non-neoplastic resection rate (NNRR) (15.1% vs. 17.1%, P = 0.542).

Conclusions

AI-assisted colonoscopy significantly increased ADR by 12.5% overall, with a notable 16.3% increase in the screening population. The unchanged NNRR indicates that the higher PDR was due to increased ADR, not unnecessary resections.

Fine-Grained Temporal Site Monitoring in EGD Streams via Visual Time-Aware Embedding and Vision-Text Asymmetric Coworking

Esophagogastroduodenoscopy (EGD) requires inspecting plentiful upper gastrointestinal (UGI) sites completely for a precise cancer screening. Automated temporal site monitoring for EGD assistance is thus of high demand, yet often fails if directly applying the existing methods of online action detection. The key challenges are two-fold: 1) the global camera motion dominates, invalidating the temporal patterns derived from the object optical flows, and 2) the UGI sites are fine-grained, yielding highly homogenized appearances. In this paper, we propose an EGD-customized model, powered by two novel designs, i.e., Visual Time-aware Embedding plus Vision-text Asymmetric Coworking (VTE+VAC), for real-time accurate fine-grained UGI site monitoring. Concretely, VTE learns visual embeddings by differentiating frames via classification losses, and meanwhile by reordering the sampled time-agnostic frames to be temporally coherent via a ranking loss. Such joint objective encourages VTE to capture the sequential relation without resorting to the inapplicable object optical flows, and thus to provide the time-aware frame-wise embeddings. In the subsequent analysis, VAC uses a temporal sliding window, and extracts vision-text multimodal knowledge from each frame and its corresponding textualized prediction via the learned VTE and a frozen BERT. The text embeddings help provide more representative cues, but also may cause misdirection due to prediction errors. Thus, VAC randomly drops or replaces historical predictions to increase the error tolerance to avoid collapsing onto the last few predictions. Qualitative and quantitative experiments demonstrate that the proposed method achieves superior performance compared to other state-of-the-art methods, with an average F1-score improvement of at least 7.66%.

Use of a Novel Artificial Intelligence System Leads to the Detection of Significantly Higher Number of Adenomas During Screening and Surveillance Colonoscopy: Results From a Large, Prospective, US Multicenter, Randomized Clinical Trial

INTRODUCTION

Adenoma per colonoscopy (APC) has recently been proposed as a quality measure for colonoscopy. We evaluated the impact of a novel artificial intelligence (AI) system, compared with standard high-definition colonoscopy, for APC measurement.

METHODS

This was a US-based, multicenter, prospective randomized trial examining a novel AI detection system (EW10-EC02) that enables a real-time colorectal polyp detection enabled with the colonoscope (CAD-EYE). Eligible average-risk subjects (45 years or older) undergoing screening or surveillance colonoscopy were randomized to undergo either CAD-EYE-assisted colonoscopy (CAC) or conventional colonoscopy (CC). Modified intention-to-treat analysis was performed for all patients who completed colonoscopy with the primary outcome of APC. Secondary outcomes included positive predictive value (total number of adenomas divided by total polyps removed) and adenoma detection rate.

RESULTS

In modified intention-to-treat analysis, of 1,031 subjects (age: 59.1 ± 9.8 years; 49.9% male), 510 underwent CAC vs 523 underwent CC with no significant differences in age, gender, ethnicity, or colonoscopy indication between the 2 groups. CAC led to a significantly higher APC compared with CC: 0.99 ± 1.6 vs 0.85 ± 1.5, P = 0.02, incidence rate ratio 1.17 (1.03-1.33, P = 0.02) with no significant difference in the withdrawal time: 11.28 ± 4.59 minutes vs 10.8 ± 4.81 minutes; P = 0.11 between the 2 groups. Difference in positive predictive value of a polyp being an adenoma among CAC and CC was less than 10% threshold established: 48.6% vs 54%, 95% CI -9.56% to -1.48%. There were no significant differences in adenoma detection rate (46.9% vs 42.8%), advanced adenoma (6.5% vs 6.3%), sessile serrated lesion detection rate (12.9% vs 10.1%), and polyp detection rate (63.9% vs 59.3%) between the 2 groups. There was a higher polyp per colonoscopy with CAC compared with CC: 1.68 ± 2.1 vs 1.33 ± 1.8 (incidence rate ratio 1.27; 1.15-1.4; P < 0.01).

DISCUSSION

Use of a novel AI detection system showed to a significantly higher number of adenomas per colonoscopy compared with conventional high-definition colonoscopy without any increase in colonoscopy withdrawal time, thus supporting the use of AI-assisted colonoscopy to improve colonoscopy quality ( ClinicalTrials.gov NCT04979962).

Initiatives to increase colonoscopy capacity - is there an impact on polyp detection? A UK National Endoscopy Database analysis

BACKGROUND

 To address mismatch between routine endoscopy capacity and demand, centers often implement initiatives to increase capacity, such as weekend working or using locums/agency staff (insourcing). However, there are concerns that such initiatives may negatively impact quality. We investigated polyp detection for weekend vs. weekday and insourced vs. standard procedures using data from the UK National Endoscopy Database.

METHODS

 We conducted a national, retrospective, cross-sectional study of diagnostic colonoscopies performed during 01/01-04/04/2019. The primary outcome was mean number of polyps (MNP) and the secondary outcome was polyp detection rate (PDR). Multi-level mixed-effect regression, fitting endoscopist as a random effect, was used to examine associations between procedure day (weekend/weekday) and type (insourced/standard) and these outcomes, adjusting for patient age, sex, and indication.

RESULTS

 92 879 colonoscopies (weekends: 19 977 [21.5 %]; insourced: 9909 [10.7 %]) were performed by 2496 endoscopists. For weekend colonoscopies, patients were less often male or undergoing screening-related procedures; for insourced colonoscopies, patients were younger and less often undergoing screening-related procedures (all P < 0.05). Fully adjusted MNP was significantly lower for weekend vs. weekday (incidence rate ratio [IRR] 0.86 [95 %CI 0.83-0.89]) and for insourced vs. standard procedures (IRR 0.91 [95 %CI 0.87-0.95]). MNP was highest for weekday standard procedures and lowest for weekend insourced procedures; there was no interaction between procedure day and type. Similar associations were found for PDR.

CONCLUSIONS

 Strategies to increase colonoscopy capacity may negatively impact polyp detection and should be monitored for quality. Reasons for this unwarranted variation require investigation.

The Effect of Oral Simethicone in a Bowel Preparation in a Colorectal Cancer Screening Colonoscopy Setting: A Randomized Controlled Trial

Introduction

Current guidelines suggest adding oral simethicone to bowel preparation for colonoscopy. However, its effect on key quality indicators for screening colonoscopy remains unclear. The primary aim was to assess the rate of adequate bowel preparation in split-dose high-volume polyethylene glycol (PEG), with or without simethicone.

Methods

This is an endoscopist-blinded, randomized controlled trial, including patients scheduled for colonoscopy after a positive faecal immunochemical test. Patients were randomly assigned to 4 L of PEG split dose (PEG) or 4 L of PEG split dose plus 500 mg oral simethicone (PEG + simethicone). The Boston Bowel Preparation Scale (BBPS) score, the preparation quality regarding bubbles using the Colon Endoscopic Bubble Scale (CEBuS), ADR, CIR, and the intraprocedural use of simethicone were recorded.

Results

We included 191 and 197 patients in the PEG + simethicone group and the PEG group, respectively. When comparing the PEG + simethicone group versus the PEG group, no significant differences in adequate bowel preparation rates (97% vs. 93%; p = 0.11) were found. However, the bubble scale score was significantly lower in the PEG + simethicone group (0 [0] versus 2 [5], p < 0.01), as well as intraprocedural use of simethicone (7% vs. 37%; p < 0.01). ADR (62% vs. 61%; p = 0.86) and CIR (98% vs. 96%, p = 0.14) did not differ between both groups.

Conclusion

Adding oral simethicone to a split-bowel preparation resulted in a lower incidence of bubbles and a lower intraprocedural use of simethicone but no further improvement on the preparation quality or ADR.

Endoscopist's Satisfaction with the Insertion Phase of Colonoscopy Is a Potential Quality Indicator for Colorectal Polyp Detection: A Propensity Score Matching Study

Quality indicators during the insertion phase of colonoscopy require exploration. Unsatisfactory insertion experiences cause endoscopist psychophysiological fatigue and affect the quality of their inspection. This comparative study used propensity score matching (PSM) to determine whether endoscopist satisfaction during scope insertion was related to polyp detection rate (PDR). Patients who underwent colonoscopy screening between April 2019 and December 2022 were enrolled in this study. The endoscopist satisfaction score (high and low) during the insertion phase in each examination was recorded based on the level of fatigue and presence of paradoxical scope movement. All examinations were classified into 2 groups: a high and a low satisfaction score group. After PSM with potential confounding factors related to polyp detection (endoscopist, insertion and withdrawal time, and sedative agent use), the PDR and adenoma detection rate (ADR) were compared. Overall, 4142 patients (average age, 54.1 years old; 54.4% male) underwent colonoscopies performed by twelve experienced endoscopists. Analysis using a logistic regression model revealed that a high satisfaction score during the insertion phase was an independent predictor of polyp detection (P < .001, odds ratio 1.79, 95% CI 1.41-2.33), whereas insertion time was not. After PSM, 513 patients from both groups were eligible for comparison. Polyp detection rate and ADR were significantly higher in the high-satisfaction group than in the low-satisfaction group (49.5% vs. 36.6%, P < .001; 35.1% vs. 27.1%, P = .007). The endoscopists' level of satisfaction with the insertion phase was shown to be a potential predictor of PDR in screening colonoscopy.

A Framework for the Evaluation of Human Machine Interfaces of Robot-Assisted Colonoscopy

The Human Machine Interface (HMI) of intraluminal robots has a crucial impact on the clinician's performance. It increases or decreases the difficulty of the tasks, and is connected to the users' physical and mental stress.

OBJECTIVE

This article presents a framework to compare and evaluate different HMIs for robotic colonoscopy, with the objective of identifying the optimal HMI that minimises the clinician's effort and maximises the clinical outcomes.

METHODS

The framework comprises a 1) a virtual simulator (clinically validated), 2) wearable sensors measuring the cognitive load, 3) a data collection unit of metrics correlated to the clinical performance, and 4) questionnaires exploring the users' impressions and perceived stress. The framework was tested with 42 clinicians investigating the optimal device for tele-operated control of robotic colonoscopes. Two control devices were selected and compared: a haptic serial-kinematic device and a standard videogame joypad.

RESULTS

The haptic device was preferred by the endoscopists, but the joypad enabled better clinical performance and reduced cognitive and physical load.

CONCLUSION

The framework can be used to evaluate different aspects of a HMI, both hardware and software, and determine the optimal HMI that can reduce the burden on clinicians while improving the clinical outcome.

SIGNIFICANCE

The findings of this study, and of future studies performed with this framework, can inform the design and development of HMIs for intraluminal robots, leading to improved clinical performance, reduced physical and mental stress for clinicians, and ultimately better patient outcomes.

Scoping review: autonomous endoscopic navigation

This is a scoping review of artificial intelligence (AI) in flexible endoscopy (FE), encompassing both computer vision (CV) and autonomous actions (AA). While significant progress has been made in AI and FE, particularly in polyp detection and malignancy prediction, resulting in several available market products, these achievements only scratch the surface potential of AI in flexible endoscopy. Many doctors still do not fully grasp that contemporary robotic FE systems, which operate the endoscope through telemanipulation, represent the most basic autonomy level, specifically categorized as level 1. Although these console systems allow remote control, they lack the more sophisticated forms of autonomy. This manuscript aims to review the current examples of AI applications in FE and hopefully act as a stimulus for more advanced AA in FE.

The adoption of artificial intelligence assisted endoscopy in the Middle East: challenges and future potential

The use of artificial intelligence (AI) in endoscopy has shown immense potential to enhance diagnostic accuracy, streamline procedures, and improve patient outcomes. There are potential uses in every field of endoscopy, from improving adenoma detection rate (ADR) in colonoscopy to reducing read time in capsule endoscopy or minimizing blind spots in gastroscopy. Indeed, some of these systems are already licensed and in commercial use across the world. In the Middle East, where healthcare systems are rapidly evolving, there is a growing interest in adopting AI technologies to revolutionise endoscopic practices. This article provides an overview of the advancements, potential opportunities and challenges associated with the implementation of AI in endoscopy within the Middle East region. Our aim is to contribute to the ongoing dialogue surrounding the implementation of AI in endoscopy and consider some of the factors that are particularly relevant in the Middle Eastern context, including the need to train the models for local populations, cost and training, as well as trying to ensure equity of access for patients. It provides valuable insights for healthcare professionals, policymakers, and researchers interested in leveraging AI to enhance endoscopic procedures, improve patient care, and address the unique healthcare needs of the Middle East population.

Artificial Intelligence Applied to Colonoscopy: Is It Time to Take a Step Forward?

Growing evidence indicates that artificial intelligence (AI) applied to medicine is here to stay. In gastroenterology, AI computer vision applications have been stated as a research priority. The two main AI system categories are computer-aided polyp detection (CADe) and computer-assisted diagnosis (CADx). However, other fields of expansion are those related to colonoscopy quality, such as methods to objectively assess colon cleansing during the colonoscopy, as well as devices to automatically predict and improve bowel cleansing before the examination, predict deep submucosal invasion, obtain a reliable measurement of colorectal polyps and accurately locate colorectal lesions in the colon. Although growing evidence indicates that AI systems could improve some of these quality metrics, there are concerns regarding cost-effectiveness, and large and multicentric randomized studies with strong outcomes, such as post-colonoscopy colorectal cancer incidence and mortality, are lacking. The integration of all these tasks into one quality-improvement device could facilitate the incorporation of AI systems in clinical practice. In this manuscript, the current status of the role of AI in colonoscopy is reviewed, as well as its current applications, drawbacks and areas for improvement.

The Role of an Artificial Intelligence Method of Improving the Diagnosis of Neoplasms by Colonoscopy

BACKGROUND

Colorectal cancer (CRC) is the third most common cancer worldwide. Colonoscopy is the gold standard examination that reduces the morbidity and mortality of CRC. Artificial intelligence (AI) could be useful in reducing the errors of the specialist and in drawing attention to the suspicious area.

METHODS

A prospective single-center randomized controlled study was conducted in an outpatient endoscopy unit with the aim of evaluating the usefulness of AI-assisted colonoscopy in PDR and ADR during the day time. It is important to understand how already available CADe systems improve the detection of polyps and adenomas in order to make a decision about their routine use in practice. In the period from October 2021 to February 2022, 400 examinations (patients) were included in the study. One hundred and ninety-four patients were examined using the ENDO-AID CADe artificial intelligence device (study group), and 206 patients were examined without the artificial intelligence (control group).

RESULTS

None of the analyzed indicators (PDR and ADR during morning and afternoon colonoscopies) showed differences between the study and control groups. There was an increase in PDR during afternoon colonoscopies, as well as ADR during morning and afternoon colonoscopies.

CONCLUSIONS

Based on our results, the use of AI systems in colonoscopies is recommended, especially in circumstances of an increase of examinations. Additional studies with larger groups of patients at night are needed to confirm the already available data.

Assessment of the Role of Artificial Intelligence in the Association Between Time of Day and Colonoscopy Quality

IMPORTANCE

Time of day was associated with a decline in adenoma detection during colonoscopy. Artificial intelligence (AI) systems are effective in improving the adenoma detection rate (ADR), but the performance of AI during different times of the day remains unknown.

OBJECTIVE

To validate whether the assistance of an AI system could overcome the time-related decline in ADR during colonoscopy.

DESIGN, SETTING, AND PARTICIPANTS

This cohort study is a secondary analysis of 2 prospective randomized controlled trials (RCT) from Renmin Hospital of Wuhan University. Consecutive patients undergoing colonoscopy were randomly assigned to either the AI-assisted group or unassisted group from June 18, 2019, to September 6, 2019, and July 1, 2020, to October 15, 2020. The ADR of early and late colonoscopy sessions per half day were compared before and after the intervention of the AI system. Data were analyzed from March to June 2022.

EXPOSURE

Conventional colonoscopy or AI-assisted colonoscopy.

MAIN OUTCOMES AND MEASURES

Adenoma detection rate.

RESULTS

A total of 1780 patients (mean [SD] age, 48.61 [13.35] years, 837 [47.02%] women) were enrolled. A total of 1041 procedures (58.48%) were performed in early sessions, with 357 randomized into the unassisted group (34.29%) and 684 into the AI group (65.71%). A total of 739 procedures (41.52%) were performed in late sessions, with 263 randomized into the unassisted group (35.59%) and 476 into the AI group (64.41%). In the unassisted group, the ADR in early sessions was significantly higher compared with that of late sessions (13.73% vs 5.70%; P = .005; OR, 2.42; 95% CI, 1.31-4.47). After the intervention of the AI system, as expected, no statistically significant difference was found (22.95% vs 22.06%, P = .78; OR, 0.96; 95% CI; 0.71-1.29). Furthermore, the AI systems showed better assistance ability on ADR in late sessions compared with early sessions (odds ratio, 3.81; 95% CI, 2.10-6.91 vs 1.60; 95% CI, 1.10-2.34).

CONCLUSIONS AND RELEVANCE

In this cohort study, AI systems showed higher assistance ability in late sessions per half day, which suggests the potential to maintain high quality and homogeneity of colonoscopies and further improve endoscopist performance in large screening programs and centers with high workloads.

Scoping out the future: The application of artificial intelligence to gastrointestinal endoscopy

Artificial intelligence (AI) is a quickly expanding field in gastrointestinal endoscopy. Although there are a myriad of applications of AI ranging from identification of bleeding to predicting outcomes in patients with inflammatory bowel disease, a great deal of research has focused on the identification and classification of gastrointestinal malignancies. Several of the initial randomized, prospective trials utilizing AI in clinical medicine have centered on polyp detection during screening colonoscopy. In addition to work focused on colorectal cancer, AI systems have also been applied to gastric, esophageal, pancreatic, and liver cancers. Despite promising results in initial studies, the generalizability of most of these AI systems have not yet been evaluated. In this article we review recent developments in the field of AI applied to gastrointestinal oncology.

Factors Associated with Withdrawal Time in European Colonoscopy Practice: Findings of the European Colonoscopy Quality Investigation (ECQI) Group

The European Colonoscopy Quality Investigation (ECQI) Group aims to raise awareness for improvement in colonoscopy standards across Europe. We analyzed data collected on a sample of procedures conducted across Europe to evaluate the achievement of the European Society of Gastrointestinal Endoscopy (ESGE) mean withdrawal time (WT) target. We also investigated factors associated with WT, in the hope of establishing areas that could lead to a quality improvement.

METHODS

6445 form completions from 12 countries between 2 June 2016 and 30 April 2018 were considered for this analysis. We performed an exploratory analysis looking at WT according to the ESGE definition. Stepwise multivariable logistic regression analysis was conducted to determine the most influential associated factors after adjusting for the other pre-specified variables.

RESULTS

In 1150 qualifying colonoscopies, the mean WT was 7.8 min. Stepwise analysis, including 587 procedures where all inputs were known, found that the variables most associated with mean WT were a previous total colonoscopy in the last five years (p = 0.0011) and the time of day the colonoscopy was performed (p = 0.0192). The main factor associated with a WT < 6 min was the time of day that a colonoscopy was performed. Use of sedation was the main factor associated with a higher proportion of WT > 10 min, along with a previous colonoscopy.

CONCLUSIONS

On average, the sample of European practice captured by the ECQI survey met the minimum standard set by the ESGE. However, there was variation and potential for improvement.

Effects of a novel endoscopic reporting system with voice recognition on the endoscopic procedure time and report preparation time: propensity score matching analysis

BACKGROUND

With the increase in endoscopic procedures, endoscopists are spending more time creating reports. Although medical reports have largely become electronic, most of the current reporting systems require manual operation. This study aimed to evaluate the efficacy of a novel endoscopic reporting system that uses voice recognition (VR) technology.

METHODS

We retrospectively reviewed consecutive patients who underwent esophagogastroduodenoscopy between September 2019 and March 2020 at a general hospital in Japan. The novel reporting system, used during endoscopic procedures, is equipped with VR and provides automatic responses by playing back recognized words. Differences in total time spent on the endoscopic procedure and report preparation between the manual entry (ME) and VR groups were evaluated using a propensity score matching method.

RESULTS

We enrolled 356 patients: 226 and 130 patients in the ME and VR groups, respectively. Propensity score matching created 101 matched pairs. After matching, the median report preparation time (311 vs. 383 s, P = 0.009) and median total time (765 vs. 842 s, P = 0.053) in the VR group were shorter than those in the ME group. The VR system independently shortened the total and report preparation times by 156 s (95% confidence interval, - 274 to - 37 s; P = 0.009) and 118 s (95% confidence interval, - 220 to - 15 s; P = 0.023), respectively, on multiple linear regression analysis.

CONCLUSIONS

The VR system could save the report preparation time and the total time. This novel system may improve the efficiency of endoscopy-related tasks.

Artificial Intelligence in Lower Gastrointestinal Endoscopy: The Current Status and Future Perspective

The present manuscript aims to review the history, recent advances, evidence, and challenges of artificial intelligence (AI) in colonoscopy. Although it is mainly focused on polyp detection and characterization, it also considers other potential applications (i.e., inflammatory bowel disease) and future perspectives. Some of the most recent algorithms show promising results that are similar to human expert performance. The integration of AI in routine clinical practice will be challenging, with significant issues to overcome (i.e., regulatory, reimbursement). Medico-legal issues will also need to be addressed. With the exception of an AI system that is already available in selected countries (GI Genius; Medtronic, Minneapolis, MN, USA), the majority of the technology is still in its infancy and has not yet been proven to reach a sufficient diagnostic performance to be adopted in the clinical practice. However, larger players will enter the arena of AI in the next few months.

Polyp detection algorithm can detect small polyps: Ex vivo reading test compared with endoscopists

BACKGROUND AND STUDY AIMS

Small polyps are occasionally missed during colonoscopy. This study was conducted to validate the diagnostic performance of a polyp-detection algorithm to alert endoscopists to unrecognized lesions.

METHODS

A computer-aided detection (CADe) algorithm was developed based on convolutional neural networks using training data from 1991 still colonoscopy images from 283 subjects with adenomatous polyps. The CADe algorithm was evaluated on a validation dataset including 50 short videos with 1-2 polyps (3.5 ± 1.5 mm, range 2-8 mm) and 50 videos without polyps. Two expert colonoscopists and two physicians in training separately read the same videos, blinded to the presence of polyps. The CADe algorithm was also evaluated using eight full videos with polyps and seven full videos without a polyp.

RESULTS

The per-video sensitivity of CADe for polyp detection was 88% and the per-frame false-positive rate was 2.8%, with a confidence level of ≥30%. The per-video sensitivity of both experts was 88%, and the sensitivities of the two physicians in training were 84% and 76%. For each reader, the frames with missed polyps appearing on short videos were significantly less than the frames with detected polyps, but no trends were observed regarding polyp size, morphology or color. For full video readings, per-polyp sensitivity was 100% with a per-frame false-positive rate of 1.7%, and per-frame specificity of 98.3%.

CONCLUSIONS

The sensitivity of CADe to detect small polyps was almost equivalent to experts and superior to physicians in training. A clinical trial using CADe is warranted.

Evolving Role and Future Directions of Natural Language Processing in Gastroenterology

In line with the current trajectory of healthcare reform, significant emphasis has been placed on improving the utilization of data collected during a clinical encounter. Although the structured fields of electronic health records have provided a convenient foundation on which to begin such efforts, it was well understood that a substantial portion of relevant information is confined in the free-text narratives documenting care. Unfortunately, extracting meaningful information from such narratives is a non-trivial task, traditionally requiring significant manual effort. Today, computational approaches from a field known as Natural Language Processing (NLP) are poised to make a transformational impact in the analysis and utilization of these documents across healthcare practice and research, particularly in procedure-heavy sub-disciplines such as gastroenterology (GI). As such, this manuscript provides a clinically focused review of NLP systems in GI practice. It begins with a detailed synopsis around the state of NLP techniques, presenting state-of-the-art methods and typical use cases in both clinical settings and across other domains. Next, it will present a robust literature review around current applications of NLP within four prominent areas of gastroenterology including endoscopy, inflammatory bowel disease, pancreaticobiliary, and liver diseases. Finally, it concludes with a discussion of open problems and future opportunities of this technology in the field of gastroenterology and health care as a whole.

Effect of successive endoscopic procedures in polyp and adenoma detection rates: Too early is not always too good

BACKGROUND AND AIMS: There is conflicting evidence regarding the impact of hypothetical cumulative fatigue after performing too many endoscopic procedures on both polyp and adenoma detection rates (PDR, and ADR, respectively). The aim of this study is to evaluate the effect of successive endoscopic procedures on PDR and ADR.

METHODS

A retrospective cross-sectional study was undertaken among consecutive patients on whom colonoscopy and/or esophagogastroduodenoscopy were performed between January 2012 and August 2014. Data regarding polyp and adenoma detection, cecal intubation, and bowel cleansing quality as well as demographical data of subjects were extracted. Endoscopic procedures were classified according to the time slots of the procedures throughout the endoscopy session in three groups: from the 1st to 4th endoscopy study (round 1), from the 5th to the 8th study (round 2), above the 9th study (round 3). We compared PDR and ADR among rounds.

RESULTS

Overall, 3388 patients were enrolled. Median age was 50 years (range 18-95) and 52.39% were female. There was a significant difference in terms of PDR among rounds (36.83%, 41.24%, and 43.38%, respectively, p = 0.007) and a non-significant numerical difference when ADR was compared (23.2%, 25.71%, and 26.78%, p = 0.07). On multivariate analysis, ADR was significantly associated with age (odds ratio [OR] 1.02 [1.01-1.03]), and male sex (OR 1.64 [1.38-1.94]).

CONCLUSION

Theoretical endoscopist's fatigue due to cumulative performance of endoscopies does not diminish colonoscopy quality. Both PDR and ADR seem to improve after endoscopist's cumulative rounds of performed endoscopies. This could be due to a "warm-up" effect.

Automated polyp detection in the colorectum: a prospective study (with videos)

BACKGROUND AND AIMS

Adenoma detection is a highly personalized task that differs markedly among endoscopists. Technical advances are therefore desirable for the improvement of the adenoma detection rate (ADR). An automated computer-driven technology would offer the chance to objectively assess the presence of colorectal polyps during colonoscopy. We present here the application of a real-time automated polyp detection software (APDS) under routine colonoscopy conditions.

METHODS

This was a prospective study at a university hospital in Germany. A prototype of a novel APDS ("KoloPol," Fraunhofer IIS, Erlangen, Germany) was used for automated image-based polyp detection. The software functions by highlighting structures of possible polyp lesions in a color-coded manner during real-time colonoscopy procedures. Testing the feasibility of APDS deployment under real-time conditions was the primary goal of the study. APDS polyp detection rates (PDRs) were defined as secondary endpoints provided that endoscopists' detection served as criterion standard.

RESULTS

The APDS was applied in 55 routine colonoscopies without the occurrence of any clinically relevant adverse events. Endoscopists' PDRs and ADRs were 56.4% and 30.9%, respectively. The PDRs and ADRs of the APDS were 50.9% and 29.1%, respectively. The APDS detected 55 of 73 polyps (75.3%). Smaller polyp size and flat polyp morphology were correlated with insufficient polyp detection by the APDS.

CONCLUSION

Computer-assisted automated low-delay polyp detection is feasible during real-time colonoscopy. Efforts should be undertaken to improve the APDS with respect to smaller and flat shaped polyps. (Clinical trial registration number: NCT02838888.).

Study on detection rate of polyps and adenomas in artificial-intelligence-aided colonoscopy

BACKGROUND/AIM

To study the impact of computer-aided detection (CADe) system on the detection rate of polyps and adenomas in colonoscopy.

MATERIALS AND METHODS

A total of 1026 patients were prospectively randomly scheduled for colonoscopy with (the CADe group, CADe) or without (the control group, CON) the aid of the CADe system, together with visual notification and voice alarm, so as to compare the detection rate of polyp.

RESULTS

Compared with group CON, the detection rate of adenomas increased in group CADe, the average number of adenomas increased, the number of small adenomas increased, the number of proliferative polyps increased, and the differences were statistically significant (P < 0.001), but the comparison for the number of larger adenomas showed no significant difference between the groups (P> 0.05).

CONCLUSIONS

The CADe system is feasible for increasing the detection of polyps and adenomas in colonoscopy.