Design and validation of an artificial intelligence system to detect the quality of colon cleansing before colonoscopy / Diseño y validación de un sistema de inteligencia artificial para detectar la calidad de la limpieza del colon previa a la realización de la colonoscopia

Background and aims Patients’ perception of their bowel cleansing quality may guide rescue cleansing strategies before colonoscopy. The main aim of this study was to train and validate a convolutional neural network (CNN) for classifying rectal effluent during bowel preparation intake as “adequate” or “inadequate” cleansing before colonoscopy.Patients and methodsPatients referred for outpatient colonoscopy were asked to provide images of their rectal effluent during the bowel preparation process. The images were categorized as adequate or inadequate cleansing based on a predefined 4-picture quality scale. A total of 1203 images were collected from 660 patients. The initial dataset (799 images), was split into a training set (80%) and a validation set (20%). The second dataset (404 images) was used to develop a second test of the CNN accuracy. Afterward, CNN prediction was prospectively compared with the Boston Bowel Preparation Scale (BBPS) in 200 additional patients who provided a picture of their last rectal effluent.ResultsOn the initial dataset, a global accuracy of 97.49%, a sensitivity of 98.17% and a specificity of 96.66% were obtained using the CNN model. On the second dataset, an accuracy of 95%, a sensitivity of 99.60% and a specificity of 87.41% were obtained. The results from the CNN model were significantly associated with those from the BBPS (P<0.001), and 77.78% of the patients with poor bowel preparation were correctly classified.ConclusionThe designed CNN is capable of classifying “adequate cleansing” and “inadequate cleansing” images with high accuracy. (AU)

Antecedentes y objetivos La percepción de los pacientes sobre la calidad de su limpieza intestinal puede guiar las estrategias de limpieza de rescate antes de una colonoscopia. El objetivo principal de este estudio fue entrenar y validar una red neuronal convolucional (CNN) para clasificar el efluente rectal durante la preparación intestinal como «adecuado» o «inadecuado».Pacientes y métodosPacientes no seleccionados proporcionaron imágenes del efluente rectal durante el proceso de preparación intestinal. Las imágenes fueron categorizadas como una limpieza adecuada o inadecuada según una escala de calidad de 4 imágenes predefinida. Se recopilaron un total de 1.203 imágenes de 660 pacientes. El conjunto de datos inicial (799 imágenes) se dividió en un conjunto de entrenamiento (80%) y un conjunto de validación (20%). Un segundo conjunto de datos (404 imágenes) se utilizó para evaluar la precisión de la CNN. Posteriormente, la predicción de la CNN se comparó prospectivamente con la escala de preparación colónica de Boston (BBPS) en 200 pacientes que proporcionaron una imagen de su último efluente rectal.ResultadosEn el conjunto de datos inicial, la precisión global fue del 97,49%, la sensibilidad del 98,17% y la especificidad del 96,66%. En el segundo conjunto de datos, se obtuvo una precisión del 95%, una sensibilidad del 99,60% y una especificidad del 87,41%. Los resultados del modelo de CNN se asociaron significativamente con la escala de preparación colónica de Boston (p<0,001), y el 77,78% de los pacientes con una preparación intestinal deficiente fueron clasificados correctamente.ConclusiónLa CNN diseñada es capaz de clasificar imágenes de «limpieza adecuada» y «limpieza inadecuada» con alta precisión. (AU)

Postcolonoscopy colorectal cancer: Prevalence, categorization and root-cause analysis based on the World Endoscopic Organization systemCáncer colorrectal poscolonoscopia / Prevalencia, categorización y análisis de las causas subyacentes basado en las recomendaciones de la Organización Mundial de Endoscopia

Aims: The World Endoscopy Organization (WEO) recommends that endoscopy units implement a process to identify postcolonoscopy colorectal cancer (PCCRC). The aims of this study were to assess the 3-year PCCRC rate and to perform root-cause analyses and categorization in accordance with the WEO recommendations.Patients and methods: Cases of colorectal cancers (CRCs) in a tertiary care center were retrospectively included from January 2018 to December 2019. The 3-year and 4-year PCCRC rates were calculated. A root-cause analysis and categorization of PCCRCs (interval and type A, B, C noninterval PCCRCs) were performed. The level of agreement between two expert endoscopists was assessed. Results: A total of 530 cases of CRC were included. A total of 33 were deemed PCCRCs (age 75.8±9.5 years; 51.5% women). The 3-year and 4-year PCCRC rates were 3.4% and 4.7%, respectively. The level of agreement between the two endoscopists was acceptable either for the root-cause analysis (k=0.958) or for the categorization (k=0.76). The most plausible explanations of the PCCRCs were 8 “likely new PCCRCs”, 1 (4%) “detected, not resected”, 3 (12%) “detected, incomplete resection”, 8 (32%) “missed lesion, inadequate examination”, and 13 (52%) “missed lesion, adequate examination”. Most PCCRCs were deemed noninterval Type C PCCRCs (N=17, 51.5%). Conclusion: WEO recommendations for root-cause analysis and categorization are useful to detect areas for improvement. Most PCCRCs were avoidable and were likely due to missed lesions during an otherwise adequate examination.(AU)

Objetivo: La Organización Mundial de Endoscopia recomienda que las unidades de endoscopia implementen procedimientos para identificar el cáncer colorrectal poscolonoscopia (CCRPC). Los objetivos de este estudio fueron evaluar la tasa de CCRPCP a los 3 y 4 años, realizar un análisis de causalidad potencial y categorización siguiendo las recomendaciones de la Organización Mundial de Endoscopia.Pacientes y métodos: Se incluyeron retrospectivamente los cánceres colorrectales diagnosticados de enero de 2018 a diciembre de 2019 en un hospital de tercer nivel. Se calculó la tasa de CCRPC a 3 años. Se realizó un análisis de causalidad potencial y categorización de los CCRPC (intervalo y CCRPC de no intervalo tipo A, B, C). Se evaluó la concordancia entre dos endoscopistas expertos. Resultados: Se incluyeron 530 cánceres colorrectales. Un total de 33 se consideraron CCRPC (edad 75,8±9,5 años; 51,5% mujeres). La tasa de CCRPC a 3 y 4 años fue del 3,4% y 4,7% respectivamente. La concordancia entre los dos endoscopistas fue aceptable para el análisis de causalidad (k=0,958) y para la categorización (k=0,76). La explicación probable de los CCRPC fue: 8 «probable CCRPC de novo», 1 (4%) «detectado, no resecado», 3 (12%) «detectado, resección incompleta», 8 (32%) «no detectado, examen inadecuado» y 13 (52%) «no detectado, examen adecuado». La mayoría de los CCRPC se consideraron de no intervalo tipo C (N=17, 51,5%). Conclusión: Las recomendaciones de la Organización Mundial de Endoscopia para el análisis de causalidad y la categorización son útiles para detectar áreas de mejora. La mayoría de los CCRPC eran evitables debido a lesiones no detectadas a pesar de realizar un examen adecuado.(AU)

Restrictive diets are unnecessary for colonoscopy: Non-inferiority randomized trial.

Background and study aims In colonoscopy, preparation is often regarded as the most burdensome part of the intervention. Traditionally, specific diets have been recommended, but the evidence to support this policy is insufficient. The aim of this study was to evaluate the impact of the decision not to follow a restrictive diet on bowel preparation and colonoscopy outcomes. Patients and methods This was a multicenter, controlled, non-inferiority randomized trial with FIT-positive screening colonoscopy. The subjects were assigned to follow the current standard (1-day low residue diet [LRD]) or a liberal diet. The allocation was balanced for the risk of inadequate cleansing using the Dik et al. score. All participants received the same instructions for morning colonoscopy preparation. The primary outcome was the rate of adequate preparations as defined by the Boston Bowel Preparation Scale. Secondary outcomes included tolerability and measures of colonoscopy performance and quality. Results A total of 582 subjects were randomized. Of these, 278 who received the liberal diet and 275 who received the 1-day LRD were included in the intent-to-treat analysis. Non-inferiority was demonstrated with adequate preparation rates of 97.8% in the 1-day LRD and 96.4% in the liberal diet group. Tolerability was higher with the liberal diet (94.7% vs. 83.2%). No differences were found with respect to cecal intubation time, aspirated volume, or length of the examination. Global and right colon average adenoma detection rates per colonoscopy were similar. Conclusions The liberal diet was non-inferior to the 1-day LRD, and increased tolerability. Colonoscopy performance and quality were not affected. (NCT05032794).

Agreement between the perception of colon cleansing reported by patients and colon cleansing assessed by a validated colon cleansing scale / Concordancia entre la percepción de limpieza colónica referida por los pacientes y la limpieza colónica evaluada mediante una escala de limpieza validada

Aims Patients’ perception of their cleansing quality can guide strategies to improve cleansing during colonoscopy. There are no studies assessing the agreement between the quality of cleansing perceived by patients and cleansing quality assessed during colonoscopy using validated bowel preparation scales. The main aim of this study was to compare the cleansing quality reported by patients with the quality during colonoscopy using the Boston Bowel Preparation Scale (BBPS). Patients and methods Consecutive patients referred to an outpatient colonoscopy were included. Four drawings representing different degrees of cleansing were designed. Patients chose the drawing that most resembled the last stool. The predictive ability of the patient's perception and agreement between the patient's perception and the BBPS were calculated. A BBPS score of <2 points in any segment was considered inadequate. Results Six hundred and thirty-three patients were included (age: 62.8 ± 13.7 years, male: 53.4%). Overall, 107 patients (16.9%) had inadequate cleansing during colonoscopy, and in 12.2% of cases, the patient's perception was poor. The patient's perception compared to the quality of cleanliness during colonoscopy presented a positive and negative predictive value of 54.6% and 88.3%, respectively. The agreement between patient perception and the BBPS was significant (P < 0.001), although fair (k = 0.37). The results were similar in a validation cohort of 378 patients (k = 0.41). Conclusions The cleanliness perceived by the patient and the quality of cleanliness using a validated scale were correlated, although fair. However, this measure satisfactorily identified patients with adequate preparation. Cleansing rescue strategies may target patients who self-report improper cleaning (AU)

Objetivos La percepción de los pacientes sobre su calidad de limpieza previa a la colonoscopia puede guiar estrategias de rescate para mejorar la limpieza durante la colonoscopia. El objetivo fue evaluar la concordancia entre la calidad de limpieza percibida por los pacientes con la calidad durante la colonoscopia utilizando la escala de preparación colónica de Boston (BBPS). Pacientes y métodos Se incluyeron pacientes consecutivos remitidos a una colonoscopia ambulatoria. Se diseñó un set de 4 imágenes representativas de diferentes grados de limpieza. Los pacientes elegían la imagen que se asemejaba más a la última deposición. Se calculó la concordancia entre la percepción del paciente y la BBPS. Una puntuación de la BBPS < 2 puntos en cualquier segmento se consideró una limpieza inadecuada. Resultados Se incluyeron 633 pacientes. Globalmente, 107 pacientes (16,9%) presentaron una limpieza inadecuada durante la colonoscopia, y en el 12,2% de los casos, la percepción del paciente fue de limpieza inadecuada. La percepción del paciente presentó un valor predictivo positivo y negativo de 54,6 y 88,3%, respectivamente, para predecir la calidad de limpieza mediante la BBPS. La concordancia entre la percepción del paciente y la BBPS fue significativa (p < 0,001), aunque aceptable (k = 0,37). Los resultados fueron similares en una cohorte de validación de 378 pacientes (k = 0,41). Conclusiones Existe concordancia entre la limpieza percibida por el paciente y la calidad de la limpieza mediante una escala validada, aunque esta fue aceptable. Estos resultados sustentan el uso de estrategias de rescate en los pacientes con percepción de una limpieza colónica inadecuada (AU)

Comparative Study of Predictive Models for the Detection of Patients at High Risk of Inadequate Colonic Cleansing.

Background: Various predictive models have been published to identify outpatients with inadequate colonic cleansing who may benefit from intensified preparations to improve colonoscopy quality. The main objective of this study was to compare the accuracy of three predictive models for identifying poor bowel preparation in outpatients undergoing colonoscopy. Methods: This cross-sectional study included patients scheduled for outpatient colonoscopy over a 3-month period. We evaluated and compared three predictive models (Models 1-3). The quality of colonic cleansing was assessed using the Boston Bowel Preparation Scale. We calculated the area under the curve (AUC) and the corresponding 95% confidence interval for each model. Additionally, we performed simple and multiple logistic regression analyses to identify variables associated with inadequate colonic cleansing and developed a new model. Results: A total of 649 consecutive patients were included in the study, of whom 84.3% had adequate colonic cleansing quality. The AUCs of Model 1 (AUC = 0.67, 95% CI [0.63-0.70]) and Model 2 (AUC = 0.62, 95% CI [0.58-0.66]) were significantly higher than that of Model 3 (AUC = 0.54, 95% CI [0.50-0.58]; p < 0.001). Moreover, Model 1 outperformed Model 2 (p = 0.013). However, the new model did not demonstrate improved accuracy compared to the older models (AUC = 0.671). Conclusions: Among the three compared models, Model 1 showed the highest accuracy for predicting poor bowel preparation in outpatients undergoing colonoscopy and could be useful in clinical practice to decrease the percentage of inadequately prepared patients.

Agreement between the perception of colon cleansing reported by patients and colon cleansing assessed by a validated colon cleansing scale.

AIMS: Patients' perception of their cleansing quality can guide strategies to improve cleansing during colonoscopy. There are no studies assessing the agreement between the quality of cleansing perceived by patients and cleansing quality assessed during colonoscopy using validated bowel preparation scales. The main aim of this study was to compare the cleansing quality reported by patients with the quality during colonoscopy using the Boston Bowel Preparation Scale (BBPS). PATIENTS AND METHODS: Consecutive patients referred to an outpatient colonoscopy were included. Four drawings representing different degrees of cleansing were designed. Patients chose the drawing that most resembled the last stool. The predictive ability of the patient's perception and agreement between the patient's perception and the BBPS were calculated. A BBPS score of <2 points in any segment was considered inadequate. RESULTS: Six hundred and thirty-three patients were included (age: 62.8±13.7 years, male: 53.4%). Overall, 107 patients (16.9%) had inadequate cleansing during colonoscopy, and in 12.2% of cases, the patient's perception was poor. The patient's perception compared to the quality of cleanliness during colonoscopy presented a positive and negative predictive value of 54.6% and 88.3%, respectively. The agreement between patient perception and the BBPS was significant (P<0.001), although fair (k=0.37). The results were similar in a validation cohort of 378 patients (k=0.41). CONCLUSIONS: The cleanliness perceived by the patient and the quality of cleanliness using a validated scale were correlated, although fair. However, this measure satisfactorily identified patients with adequate preparation. Cleansing rescue strategies may target patients who self-report improper cleaning. Registration number of the trial: NCT03830489.

Postcolonoscopy colorectal cancer: Prevalence, categorization and root-cause analysis based on the World Endoscopic Organization system.

AIMS: The World Endoscopy Organization (WEO) recommends that endoscopy units implement a process to identify postcolonoscopy colorectal cancer (PCCRC). The aims of this study were to assess the 3-year PCCRC rate and to perform root-cause analyses and categorization in accordance with the WEO recommendations. PATIENTS AND METHODS: Cases of colorectal cancers (CRCs) in a tertiary care center were retrospectively included from January 2018 to December 2019. The 3-year and 4-year PCCRC rates were calculated. A root-cause analysis and categorization of PCCRCs (interval and type A, B, C noninterval PCCRCs) were performed. The level of agreement between two expert endoscopists was assessed. RESULTS: A total of 530 cases of CRC were included. A total of 33 were deemed PCCRCs (age 75.8±9.5 years; 51.5% women). The 3-year and 4-year PCCRC rates were 3.4% and 4.7%, respectively. The level of agreement between the two endoscopists was acceptable either for the root-cause analysis (k=0.958) or for the categorization (k=0.76). The most plausible explanations of the PCCRCs were 8 "likely new PCCRCs", 1 (4%) "detected, not resected", 3 (12%) "detected, incomplete resection", 8 (32%) "missed lesion, inadequate examination", and 13 (52%) "missed lesion, adequate examination". Most PCCRCs were deemed noninterval Type C PCCRCs (N=17, 51.5%). CONCLUSION: WEO recommendations for root-cause analysis and categorization are useful to detect areas for improvement. Most PCCRCs were avoidable and were likely due to missed lesions during an otherwise adequate examination.

Design and validation of an artificial intelligence system to detect the quality of colon cleansing before colonoscopy.

BACKGROUND AND AIMS: Patients' perception of their bowel cleansing quality may guide rescue cleansing strategies before colonoscopy. The main aim of this study was to train and validate a convolutional neural network (CNN) for classifying rectal effluent during bowel preparation intake as "adequate" or "inadequate" cleansing before colonoscopy. PATIENTS AND METHODS: Patients referred for outpatient colonoscopy were asked to provide images of their rectal effluent during the bowel preparation process. The images were categorized as adequate or inadequate cleansing based on a predefined 4-picture quality scale. A total of 1203 images were collected from 660 patients. The initial dataset (799 images), was split into a training set (80%) and a validation set (20%). The second dataset (404 images) was used to develop a second test of the CNN accuracy. Afterward, CNN prediction was prospectively compared with the Boston Bowel Preparation Scale (BBPS) in 200 additional patients who provided a picture of their last rectal effluent. RESULTS: On the initial dataset, a global accuracy of 97.49%, a sensitivity of 98.17% and a specificity of 96.66% were obtained using the CNN model. On the second dataset, an accuracy of 95%, a sensitivity of 99.60% and a specificity of 87.41% were obtained. The results from the CNN model were significantly associated with those from the BBPS (P<0.001), and 77.78% of the patients with poor bowel preparation were correctly classified. CONCLUSION: The designed CNN is capable of classifying "adequate cleansing" and "inadequate cleansing" images with high accuracy.

Colon Bowel Preparation in the Era of Artificial Intelligence: Is There Potential for Enhancing Colon Bowel Cleansing?

BACKGROUND AND OBJECTIVES: Proper bowel preparation is of paramount importance for enhancing adenoma detection rates and reducing postcolonoscopic colorectal cancer risk. Despite recommendations from gastroenterology societies regarding the optimal rates of successful bowel preparation, these guidelines are frequently unmet. Various approaches have been employed to enhance the rates of successful bowel preparation, yet the quality of cleansing remains suboptimal. Intensive bowel preparation techniques, supplementary administration of bowel solutions, and educational interventions aimed at improving patient adherence to instructions have been commonly utilized, particularly among patients at a high risk of inadequate bowel preparation. Expedited strategies conducted on the same day as the procedure have also been endorsed by scientific organizations. More recently, the utilization of artificial intelligence (AI) has emerged for the preprocedural detection of inadequate bowel preparation, holding the potential to guide the preparation process immediately preceding colonoscopy. This manuscript comprehensively reviews the current strategies employed to optimize bowel cleansing, with a specific focus on patients with elevated risks for inadequate bowel preparation. Additionally, the prospective role of AI in this context is thoroughly examined. CONCLUSIONS: While a majority of outpatients may achieve cleanliness with standard cleansing protocols, dealing with hard-to-prepare patients remains a challenge. Rescue strategies based on AI are promising, but such evidence remains limited. To ensure proper bowel cleansing, a combination of strategies should be performed.

Role of colonoscopy in colorectal cancer screening: Available evidence.

Colonoscopy is the cornerstone examination for colorectal cancer (CRC) screening and it is recommended as the first examination in the context of individuals with high risk of CRC development. Thereby, this examination is of choice in the setting of patients with hereditary CRC syndromes or in patients with long-standing inflammatory bowel disease with colon involvement. However, its role is less clear in the average risk-risk population and in patients with family history of CRC not linked to hereditary CRC syndromes. Despite this, current guidelines, include colonoscopy as alternative for CRC screening either in average risk population with the same evidence level that other screening strategies or in the familial risk population. The present manuscript reviews the clinical evidence on the role of colonoscopy in preventing CRC in different screening settings.

Screening uptake of colonoscopy versus fecal immunochemical testing in first-degree relatives of patients with non-syndromic colorectal cancer: A multicenter, open-label, parallel-group, randomized trial (ParCoFit study).

BACKGROUND: Colonoscopy screening is underused by first-degree relatives (FDRs) of patients with non-syndromic colorectal cancer (CRC) with screening completion rates below 50%. Studies conducted in FDR referred for screening suggest that fecal immunochemical testing (FIT) was not inferior to colonoscopy in terms of diagnostic yield and tumor staging, but screening uptake of FIT has not yet been tested in this population. In this study, we investigated whether the uptake of FIT screening is superior to the uptake of colonoscopy screening in the familial-risk population, with an equivalent effect on CRC detection. METHODS AND FINDINGS: This open-label, parallel-group, randomized trial was conducted in 12 Spanish centers between February 2016 and December 2021. Eligible individuals included asymptomatic FDR of index cases <60 years, siblings or ≥2 FDR with CRC. The primary outcome was to compare screening uptake between colonoscopy and FIT. The secondary outcome was to determine the efficacy of each strategy to detect advanced colorectal neoplasia (adenoma or serrated polyps ≥10 mm, polyps with tubulovillous architecture, high-grade dysplasia, and/or CRC). Screening-naïve FDR were randomized (1:1) to one-time colonoscopy versus annual FIT during 3 consecutive years followed by a work-up colonoscopy in the case of a positive test. Randomization was performed before signing the informed consent using computer-generated allocation algorithm based on stratified block randomization. Multivariable regression analysis was performed by intention-to-screen. On December 31, 2019, when 81% of the estimated sample size was reached, the trial was terminated prematurely after an interim analysis for futility. Study outcomes were further analyzed through 2-year follow-up. The main limitation of this study was the impossibility of collecting information on eligible individuals who declined to participate. A total of 1,790 FDR of 460 index cases were evaluated for inclusion, of whom 870 were assigned to undergo one-time colonoscopy (n = 431) or FIT (n = 439). Of them, 383 (44.0%) attended the appointment and signed the informed consent: 147/431 (34.1%) FDR received colonoscopy-based screening and 158/439 (35.9%) underwent FIT-based screening (odds ratio [OR] 1.08; 95% confidence intervals [CI] [0.82, 1.44], p = 0.564). The detection rate of advanced colorectal neoplasia was significantly higher in the colonoscopy group than in the FIT group (OR 3.64, 95% CI [1.55, 8.53], p = 0.003). Study outcomes did not change throughout follow-up. CONCLUSIONS: In this study, compared to colonoscopy, FIT screening did not improve screening uptake by individuals at high risk of CRC, resulting in less detection of advanced colorectal neoplasia. Further studies are needed to assess how screening uptake could be improved in this high-risk group, including by inclusion in population-based screening programs. TRIAL REGISTRATION: This trial was registered with ClinicalTrials.gov (NCT02567045).

Endoscopic Vacuum Therapy for Upper Gastrointestinal Leaks and Perforations: Analysis From a Multicenter Spanish Registry.

INTRODUCTION: Endoscopic vacuum therapy (EVT) is a novel technique for closing upper gastrointestinal (UGI) defects. Available literature includes single-center retrospective cohort studies with small sample sizes. Furthermore, evidence about factors associated with EVT failure is scarce. We aimed to assess the efficacy and safety of EVT for the resolution of UGI defects in a multicenter study and to investigate the factors associated with EVT failure and in-hospital mortality. METHODS: This is a prospective cohort study in which consecutive EVT procedures for the treatment of UGI defects from 19 Spanish hospitals were recorded in the national registry between November 2018 and March 2022. RESULTS: We included 102 patients: 89 with anastomotic leaks and 13 with perforations. Closure of the defect was achieved in 84 cases (82%). A total of 6 patients (5.9%) had adverse events related to the EVT. The in-hospital mortality rate was 12.7%. A total of 6 patients (5.9%) died because of EVT failure and 1 case (0.9%) due to a fatal adverse event. Time from diagnosis of the defect to initiation of EVT was the only independent predictor for EVT failure (odds ratio [OR] 1.03, 95% confidence interval [CI] 1.01-1.05, P = 0.005). EVT failure (OR 24.5, 95% CI 4.5-133, P = 0.001) and development of pneumonia after EVT (OR 246.97, 95% CI 11.15-5,472.58, P = 0.0001) were independent predictors of in-hospital mortality. DISCUSSION: EVT is safe and effective in cases of anastomotic leak and perforations of the upper digestive tract. The early use of EVT improves the efficacy of this technique.

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.

Usefulness of a novel computer-aided detection system for colorectal neoplasia: a randomized controlled trial.

BACKGROUND AND AIMS: Artificial intelligence-based computer-aid detection (CADe) devices have been recently tested in colonoscopies, increasing the adenoma detection rate (ADR), mainly in Asian populations. However, evidence for the benefit of these devices in the occidental population is still low. We tested a new CADe device, namely, ENDO-AID (OIP-1) (Olympus, Tokyo, Japan), in clinical practice. METHODS: This randomized controlled trial included 370 consecutive patients who were randomized 1:1 to CADe (n = 185) versus standard exploration (n = 185) from November 2021 to January 2022. The primary endpoint was the ADR. Advanced adenoma was defined as ≥10 mm, harboring high-grade dysplasia, or with a villous pattern. Otherwise, the adenoma was nonadvanced. ADR was assessed in both groups stratified by endoscopist ADR and colon cleansing. RESULTS: In the intention-to-treat analysis, the ADR was 55.1% (102/185) in the CADe group and 43.8% (81/185) in the control group (P = .029). Nonadvanced ADRs (54.8% vs 40.8%, P = .01) and flat ADRs (39.4 vs 24.8, P = .006), polyp detection rate (67.1% vs 51%; P = .004), and number of adenomas per colonoscopy were significantly higher in the CADe group than in the control group (median [25th-75th percentile], 1 [0-2] vs 0 [0-1.5], respectively; P = .014). No significant differences were found in serrated ADR. After stratification by endoscopist and bowel cleansing, no statistically significant differences in ADR were found. CONCLUSIONS: Colonoscopy assisted by ENDO-AID (OIP-1) increases ADR and number of adenomas per colonoscopy, suggesting it may aid in the detection of colorectal neoplastic lesions, especially because of its detection of diminutive and flat adenomas. (Clinical trial registration number: NCT04945044.).

Predictive factors for inadequate bowel cleansing in colon capsule endoscopy / Factores predictores de limpieza colónica inadecuada en exploraciones con cápsula endoscópica de colon

Background and aims: Achieving adequate bowel cleansing is of utmost importance for the efficiency of colon capsule endoscopy (CCE). However, information about predictive factors is lacking. The aim of this study was to assess the predictive factors of poor bowel cleansing in the CCE setting. Methods: In this observational study, 126 patients who underwent CCE at two tertiary care hospitals were included between June 2017 and January 2020. Participants prepared for bowel cleansing with a 1-day clear liquid diet, a 4-L split-dose polyethylene glycol regimen and boosters with sodium phosphate, sodium amidotrizoate and meglumine amidotrizoate. Domperidone tablets and bisacodyl suppositories were administered when needed. Overall and per-segment bowel cleansing was evaluated using a CCE cleansing score. Simple and multiple logistic regression analysis were carried out to assess poor bowel cleansing and excretion rate predictors. Results: Overall bowel cleansing was optimal in 53 patients (50.5%). Optimal per-segment bowel cleansing was achieved as follows: cecum (86 patients; 74.8%), transverse colon (91 patients; 81.3%), distal colon (81 patients; 75%) and rectum (64 patients; 66.7%). In the univariate analysis, elderly (OR, 1.03; 95% CI (1.01–1.076)) and constipation (OR, 3.82; 95% CI (1.50–9.71)) were associated with poor bowel cleansing. In the logistic regression analysis, constipation (OR, 3.77; 95% CI (1.43–10.0)) was associated with poor bowel cleansing. No variables were significantly associated with the CCE device excretion rate. Conclusion: Our results suggest that constipation is the most powerful predictor of poor bowel cleansing in the CCE setting. Tailored cleansing protocols should be recommended for these patients.(AU)

Antecedentes y objetivos Lograr una limpieza intestinal adecuada es de gran importancia para la eficiencia de la cápsula endoscópica de colon (CEC). Se carece de información sobre factores predictivos. El objetivo fue evaluar los factores predictivos de la limpieza colónica deficiente en pacientes con CEC. Métodos: Ciento veintiséis pacientes fueron sometidos a CEC en dos hospitales de tercer nivel entre junio de 2017 y enero de 2020. La preparación consistió en un día de dieta líquida, y 4 l de polietilenglicol (dosis fraccionada), fosfato sódico, amidotrizoato de sodio y meglumina amidotrizoato. Ocasionalmente se administró domperidona y supositorios de bisacodilo. Se evaluó limpieza total y por segmentos. Se realizó un análisis de regresión logística simple y múltiple para evaluar factores de limpieza deficiente y de excreción de la CEC. Resultados: La limpieza intestinal fue óptima en 53 pacientes (50,5%). Por segmentos fue: ciego y ascendente (86 pacientes; 74,8%), transverso (91 pacientes; 81,3%), distal (81 pacientes; el 75%) y recto (64 pacientes; 66,7%). En la regresión simple, la edad avanzada (OR, 1,03, IC 95% [1,01-1,076]) y el estreñimiento (OR, 3,82; IC 95% [1,50-9,71]) se asociaron con una limpieza deficiente. El estreñimiento (OR, 3,77; IC del 95% [1,43-10,0]) fue el único factor asociado de forma independiente. Ninguna variable se asoció a la tasa de excreción de la CEC. Conclusión: Nuestros resultados sugieren que el estreñimiento es el factor más potente de la limpieza deficiente colónica en el estudio endoscópico con CEC. Protocolos de limpieza adaptados se deben recomendar en estos pacientes.(AU)

Prevalence of missed lesions in patients with inadequate bowel preparation through a very early repeat colonoscopy.

OBJECTIVES: When bowel preparation (BP) is inadequate, international guidelines recommend repeating the colonoscopy within 1 year to avoid missing clinically relevant lesions. We aimed to determine the rate of missed lesions in patients with inadequate BP through a very early repeat colonoscopy with adequate BP. METHODS: Post hoc analysis was conducted using data collected from a prospective multicenter randomized clinical trial including patients with inadequate BP and then repeat colonoscopy. Inadequate BP was defined as the Boston Bowel Preparation Scale (BBPS) score <2 points in any segment. We included patients with any indication for colonoscopy. The adenoma detection rate (ADR), advanced ADR (AADR), and serrated polyp detection rate (SPDR) were calculated for index and repeat colonoscopies. RESULTS: Of the 651 patients with inadequate BP from the original trial, 413 (63.4%) achieved adequate BP on repeat colonoscopy. The median interval between index and repeat colonoscopies was 28 days. On repeat colonoscopy, the ADR was 45.3% (95% confidence interval [CI] 40.5-50.1%), the AADR was 10.9% (95% CI 8.1-14.3%), and the SPDR was 14.3% (95% CI 10.9-17.7%). Cancer was discovered in four patients (1%; 95% CI 0.2-2.5%). A total of 60.2% of all advanced adenoma (AA) were discovered on repeat colonoscopy. A colon segment scored BBPS = 0 had most AA (66.1%) and all four cancers. CONCLUSION: Patients with inadequate BP present a high rate of AAs on repeat colonoscopy. When a colonoscopy has a colon segment score BBPS = 0, we recommend repeating the colonoscopy as soon as possible.

Predictive factors for inadequate bowel cleansing in colon capsule endoscopy.

BACKGROUND AND AIMS: Achieving adequate bowel cleansing is of utmost importance for the efficiency of colon capsule endoscopy (CCE). However, information about predictive factors is lacking. The aim of this study was to assess the predictive factors of poor bowel cleansing in the CCE setting. METHODS: In this observational study, 126 patients who underwent CCE at two tertiary care hospitals were included between June 2017 and January 2020. Participants prepared for bowel cleansing with a 1-day clear liquid diet, a 4-L split-dose polyethylene glycol regimen and boosters with sodium phosphate, sodium amidotrizoate and meglumine amidotrizoate. Domperidone tablets and bisacodyl suppositories were administered when needed. Overall and per-segment bowel cleansing was evaluated using a CCE cleansing score. Simple and multiple logistic regression analysis were carried out to assess poor bowel cleansing and excretion rate predictors. RESULTS: Overall bowel cleansing was optimal in 53 patients (50.5%). Optimal per-segment bowel cleansing was achieved as follows: cecum (86 patients; 74.8%), transverse colon (91 patients; 81.3%), distal colon (81 patients; 75%) and rectum (64 patients; 66.7%). In the univariate analysis, elderly (OR, 1.03; 95% CI (1.01-1.076)) and constipation (OR, 3.82; 95% CI (1.50-9.71)) were associated with poor bowel cleansing. In the logistic regression analysis, constipation (OR, 3.77; 95% CI (1.43-10.0)) was associated with poor bowel cleansing. No variables were significantly associated with the CCE device excretion rate. CONCLUSION: Our results suggest that constipation is the most powerful predictor of poor bowel cleansing in the CCE setting. Tailored cleansing protocols should be recommended for these patients.