Comparison of adenoma miss rate and adenoma detection rate between conventional colonoscopy and colonoscopy with second generation distal attachment cuff: a multicenter, randomized, back-to-back trial.

BACKGROUND AND AIMS: Endocuff VisionTM has been designed to enhance mucosal visualization thereby improving detection of (pre-)malignant colorectal lesions. This multicenter, international, back-to-back, randomized colonoscopy trial compared adenoma detection rate (ADR) and adenoma miss rate (AMR) between Endocuff Vision-assisted colonoscopy (EVC) and conventional colonoscopy (CC). METHODS: Patients aged 40-75 years referred for non-immunochemical fecal occult blood test-based screening, surveillance, or diagnostic colonoscopy were included at ten hospitals and randomized into four groups: Group 1; 2xCC, Group 2; CC followed by EVC, Group 3; EVC followed CC and Group 4; 2xEVC. Primary outcomes included ADR and AMR. RESULTS: A total of 717 patients were randomized of which 661 patients (92.2%) had one and 646 (90.1%) patients had two completed back-to-back colonoscopies. EVC did not significantly improve ADR compared to CC (41.1% [95%-CI;36.1-46.3] versus 35.5% [95%-CI;30.7-40.6], respectively, P=0.125), but EVC did reduced AMR by 11.7% (29.6% [95%-CI;23.6-36.5] versus 17.9% [95%-CI;12.5-23.5], respectively, P=0.049). AMR of 2xCC compared to 2xEVC was also not significantly different (25.9% [95%-CI;19.3-33.9] versus 18.8% [95%-CI;13.9-24.8], respectively, P=0.172). Only 3.7% of the polyps missed during the first procedures had advanced pathologic features. Factors affecting risk of missing adenomas were age (P=0.002), Boston Bowel Preparation Scale (P=0.008) and region where colonoscopy was performed (P<0.001). CONCLUSIONS: Our trial shows that EVC reduces the risk of missing adenomas but does not lead to a significant improved ADR. Remarkably, 25% of adenomas are still missed during conventional colonoscopies, which is not different from miss rates reported 25 years ago; reassuringly, advanced features were only found in 3.7% of these missed lesions. TRAIL REGISTRATION NUMBER: NCT03418948.

The use of magnet-controlled capsule endoscopy as the initial diagnostic tool in patients with acute upper gastrointestinal bleeding.

BACKGROUND: The latest magnet-controlled capsule endoscopy (MCCE) system can examine the water-distended stomach, duodenum, and the small bowel. We assessed the use of MCCE as the first diagnostic tool in patients with acute upper gastrointestinal bleeding (AUGIB). METHODS: This was a prospective cohort study that enrolled patients admitted with AUGIB from two teaching hospitals. Patients underwent MCCE as the initial diagnostic modality. Our primary endpoint was the diagnostic yield of MCCE. The subsequent care of these patients was guided by MCCE findings. RESULTS: Of 100 enrolled patients, 99 (mean age 54 years, 70.7% men) with a median Glasgow-Blatchford score of 6 (IQR 3-9) underwent MCCE. In three patients, MCCE found active bleeding (two duodenal ulcers and Dieulafoy's lesion). The overall diagnostic yield of MCCE was 95.8% (92 lesions in 96 patients); five in the esophagus (Mallory Weiss tears 2, varices 1, and esophagitis 2), 51 in the stomach (gastric erosions 26, gastric ulcers 14, cancer 3, GIST 3, gastric polyps 3, antral vascular ectasia 1,angiodysplasia 1), 32 in the duodenum (ulcers 28, erosions 3, polyp 1), and four in the small bowel (ulcers 2, an erosion with a nonbleeding vessel 1, Meckel's diverticulum 1). Fifty-two (52.5%) patients were discharged without endoscopy. Forty-five (45.5%) patients underwent inpatient esophagogastroduodenoscopy (EGD), which found an antral ulcer and six duodenal ulcers in addition. CONCLUSIONS: In stable patients with AUGIB, MCCE can be used as a diagnostic tool. EGD should follow in patients with an inadequate view of the duodenum.

Comparison of Over-the-Scope Clips to Standard Endoscopic Treatment as the Initial Treatment in Patients With Bleeding From a Nonvariceal Upper Gastrointestinal Cause : A Randomized Controlled Trial.

BACKGROUND: Current endoscopic methods in the control of acute nonvariceal bleeding have a small but clinically significant failure rate. The role of over-the-scope clips (OTSCs) as the first treatment has not been defined. OBJECTIVE: To compare OTSCs with standard endoscopic hemostatic treatments in the control of bleeding from nonvariceal upper gastrointestinal causes. DESIGN: A multicenter, randomized controlled trial. (ClinicalTrials.gov: NCT03216395). SETTING: University teaching hospitals in Hong Kong, China, and Australia. PATIENTS: 190 adult patients with active bleeding or a nonbleeding visible vessel from a nonvariceal cause on upper gastrointestinal endoscopy. INTERVENTION: Standard hemostatic treatment (n = 97) or OTSC (n = 93). MEASUREMENTS: The primary outcome was 30-day probability of further bleeds. Other outcomes included failure to control bleeding after assigned endoscopic treatment, recurrent bleeding after initial hemostasis, further intervention, blood transfusion, and hospitalization. RESULTS: The 30-day probability of further bleeding in the standard treatment and OTSC groups was 14.6% (14 of 97) and 3.2% (3 of 93), respectively (risk difference, 11.4 percentage points [95% CI, 3.3 to 20.0 percentage points]; P = 0.006). Failure to control bleeding after assigned endoscopic treatment in the standard treatment and OTSC groups was 6 versus 1 (risk difference, 5.1 percentage points [CI, 0.7 to 11.8 percentage points]), respectively, and 30-day recurrent bleeding was 8 versus 2 (risk difference, 6.6 percentage points [CI, -0.3 to 14.4 percentage points]), respectively. The need for further interventions was 8 versus 2, respectively. Thirty-day mortality was 4 versus 2, respectively. In a post hoc analysis with a composite end point of failure to successfully apply assigned treatment and further bleeds, the event rate was 15 of 97 (15.6%) and 6 of 93 (6.5%) in the standard and OTSC groups, respectively (risk difference, 9.1 percentage points [CI, 0.004 to 18.3 percentage points]). LIMITATION: Clinicians were not blinded to treatment and the option of crossover treatment. CONCLUSION: Over-the-scope clips, as an initial treatment, may be better than standard treatment in reducing the risk for further bleeding from nonvariceal upper gastrointestinal causes that are amenable to OTSC placement. PRIMARY FUNDING SOURCE: General Research Fund to the University Grant Committee, Hong Kong SAR Government.

Artificial Intelligence-Assisted Colonoscopy for Colorectal Cancer Screening: A Multicenter Randomized Controlled Trial.

BACKGROUND AND AIMS: Artificial intelligence (AI)-assisted colonoscopy improves polyp detection and characterization in colonoscopy. However, data from large-scale multicenter randomized controlled trials (RCT) in an asymptomatic population are lacking. METHODS: This multicenter RCT aimed to compare AI-assisted colonoscopy with conventional colonoscopy for adenoma detection in an asymptomatic population. Asymptomatic subjects 45-75 years of age undergoing colorectal cancer screening by direct colonoscopy or fecal immunochemical test were recruited in 6 referral centers in Hong Kong, Jilin, Inner Mongolia, Xiamen, and Beijing. In the AI-assisted colonoscopy, an AI polyp detection system (Eagle-Eye) with real-time notification on the same monitor of the endoscopy system was used. The primary outcome was overall adenoma detection rate (ADR). Secondary outcomes were mean number of adenomas per colonoscopy, ADR according to endoscopist's experience, and colonoscopy withdrawal time. This study received Institutional Review Board approval (CRE-2019.393). RESULTS: From November 2019 to August 2021, 3059 subjects were randomized to AI-assisted colonoscopy (n = 1519) and conventional colonoscopy (n = 1540). Baseline characteristics and bowel preparation quality between the 2 groups were similar. The overall ADR (39.9% vs 32.4%; P < .001), advanced ADR (6.6% vs 4.9%; P = .041), ADR of expert (42.3% vs 32.8%; P < .001) and nonexpert endoscopists (37.5% vs 32.1%; P = .023), and adenomas per colonoscopy (0.59 ± 0.97 vs 0.45 ± 0.81; P < .001) were all significantly higher in the AI-assisted colonoscopy. The median withdrawal time (8.3 minutes vs 7.8 minutes; P = .004) was slightly longer in the AI-assisted colonoscopy group. CONCLUSIONS: In this multicenter RCT in asymptomatic patients, AI-assisted colonoscopy improved overall ADR, advanced ADR, and ADR of both expert and nonexpert attending endoscopists. (ClinicalTrials.gov, Number: NCT04422548).

Identification of Tissue Types and Gene Mutations From Histopathology Images for Advancing Colorectal Cancer Biology.

Objective: Colorectal cancer (CRC) patients respond differently to treatments and are sub-classified by different approaches. We evaluated a deep learning model, which adopted endoscopic knowledge learnt from AI-doscopist, to characterise CRC patients by histopathological features. Results: Data of 461 patients were collected from TCGA-COAD database. The proposed framework was able to 1) differentiate tumour from normal tissues with an Area Under Receiver Operating Characteristic curve (AUROC) of 0.97; 2) identify certain gene mutations (MYH9, TP53) with an AUROC > 0.75; 3) classify CMS2 and CMS4 better than the other subtypes; and 4) demonstrate the generalizability of predicting KRAS mutants in an external cohort. Conclusions: Artificial intelligent can be used for on-site patient classification. Although KRAS mutants were commonly associated with therapeutic resistance and poor prognosis, subjects with predicted KRAS mutants in this study have a higher survival rate in 30 months after diagnoses.

Nurse-led reinforced education by mobile messenger improves the quality of bowel preparation of colonoscopy in a population-based colorectal cancer screening program: A randomized controlled trial.

BACKGROUND: Adequate bowel preparation is an important colonoscopy quality indicator. Reinforced education is effective in improving bowel preparation quality of colonoscopy with mixed indications. However, it remains unclear whether such improvement can be consistently observed in pre- and post-irrigation during colonoscopy in screening population. OBJECTIVE: We aimed to study the effectiveness of nurse-led reinforced education delivered via mobile messenger (WhatsApp Messenger) on pre- and post-irrigation bowel preparation adequacy in colonoscopies for positive fecal immunochemical test in a population-based colorectal cancer screening program. DESIGN: Randomized controlled trial. SETTING: A hospital-based endoscopy centre in Hong Kong, China. PARTICIPANTS: Patients undergoing colonoscopy for positive fecal immunochemical test in a population-based colorectal cancer screening program. METHODS: The recruited patients were randomized to receive either WhatsApp Reinforced Education (WRE) or No Reinforced Education (NRE) (1:1). Patients in WRE group received one-off reinforced education of bowel preparation in text and video formats via WhatsApp Messenger four days prior to colonoscopy sent by investigator while NRE group received standard-of-care only. Primary outcome was the bowel preparation adequacy rate as evaluated by Aronchick Scale. Secondary outcomes included bowel preparation adequacy rate as evaluated by Boston Bowel Preparation Scale, adenoma detection rate and risk factors of bowel preparation inadequacy. Continuous variables were described as means with standard deviation (SD) and analyzed with Student's t-test. The Pearson Chi Square Test or Fisher Exact Test was used to assess categorical variables when appropriate. Risk factors were determined by logistic regression. RESULTS: From July 2017 to April 2019, 685 eligible patients were randomized to WRE (n = 343) and NRE (n = 342) groups. Patients in WRE group had higher bowel preparation adequacy rate as evaluated by Aronchik Scale (83.4% vs 75.4%, p = 0.010) and Boston Bowel Preparation Scale (94.2% vs 88.9%, p = 0.013). Adenoma detection rate was higher in WRE group but without statistical significance (71.4% vs 67.5%, p = 0.27). In logistic regression, WhatsApp Reinforced Education reduced the inadequate bowel preparation risk (Adjusted odds ratio: 0.564; 95% confidence interval: 0.371-0.856, p = 0.007). Male gender (Adjusted odds ratio [AOR]: 1.638; 95% confidence interval [CI]: 1.054-2.546, p = 0.028) and diabetes (AOR: 2.062; 95% CI: 1.215-3.497, p = 0.007) were risk factors of bowel preparation inadequacy. CONCLUSIONS: Nurse-led mobile messenger-initiated reinforced education improves both pre- and post-irrigation bowel preparation quality of screening colonoscopy following positive fecal immunochemical test. It is readily incorporable in clinical practice because of its low setup cost. REGISTRATION NUMBER: Registered on 4 July 2017 on https://clinicaltrials.gov/ (NCT03209739).

Scheduled second look endoscopy after endoscopic hemostasis to patients with high risk bleeding peptic ulcers: a Randomized Controlled Trial.

BACKGROUND: The recommendation of second look endoscopy (SLOGD) in selected patients at high risk for rebleeding has been inconclusive. This study aimed to evaluate the benefit of SLOGD in selected patients predicted at high risk of recurrent bleeding. METHODS: From a cohort of 939 patients with bleeding peptic ulcers who underwent endoscopic hemostasis, we derived a 9-point risk score (age > 60, Male, ulcer ≥ 2 cm in size, posterior bulbar or lesser curve gastric ulcer, Forrest I bleeding, haemoglobin < 8 g/dl) to predict recurrent bleeding. We then validated the score in another cohort of 1334 patients (AUROC 0.77). To test the hypothesis that SLOGD in high-risk patients would improve outcomes, we did a randomized controlled trial to compare scheduled SLOGD with observation alone in those predicted at high risk of rebleeding (a score of ≥ 5). The primary outcome was clinical bleeding within 30 days of the index bleed. RESULTS: Of 314 required, we enrolled 157 (50%) patients (SLOGD n = 78, observation n = 79). Nine (11.8%) in SLOGD group and 14 (18.2%) in observation group reached primary outcome (absolute difference 6.4%, 95% CI - 5.0% to 17.8%). Twenty-one of 69 (30.4%) patients who underwent SLOGD needed further endoscopic treatment. No surgery for bleeding control was needed. There were 6 vs. 3 of 30-day deaths in either group (p = 0.285, log rank). No difference was observed regarding blood transfusion and hospitalization. CONCLUSIONS: In this aborted trial that enrolled patients with bleeding peptic ulcers at high-risk of recurrent bleeding, scheduled SLOGD did not significantly improve outcomes. CLINICALTRIALS: gov:NCT02352155.

Two vs One Forward View Examination of Right Colon on Adenoma Detection: An International Multicenter Randomized Trial.

BACKGROUND & AIMS: Second forward view (SFV) examination of the right colon (RC) in colonoscopy was suggested to improve the adenoma detection rate (ADR), but multicenter data to inform its routine use remain limited. We performed an international multicenter randomized trial comparing SFV vs a standard single forward view examination of the RC on adenoma detection. METHODS: Asymptomatic individuals undergoing screening or surveillance colonoscopies from 6 Asia Pacific regions were invited for study. A forward view examination of the RC was first performed in all patients, followed by randomization at the hepatic flexure to either SFV examination of the RC and standard withdrawal examination from the hepatic flexure to rectum, or a standard withdrawal colonoscopy (SWC) examination from the hepatic flexure to rectum. The primary outcome was RC ADR. RESULTS: Between 2016 and 2019, there were 1011 patients randomized (SFV group, 502 patients; SWC group, 509 patients). Forty-five endoscopists performed the colonoscopies. The RC ADR was significantly higher in the SFV group than in the SWC group (27.1% vs 21.6%; P = .042). The whole-colon ADR was high in both groups (49.0% vs 45.0%; P =.201). The SFV examination identified 58 additional adenomas in 49 patients (9.8%), leading to a change in surveillance recommendations in 15 patients (3.0%). The median overall withdrawal time was 1.5 minutes longer in the SFV group (12.0 vs 10.5 min; P < .001). Older age, male sex, ever smoking, and longer RC withdrawal time were independent predictors of right-sided adenoma detection. CONCLUSIONS: In this multicenter trial, SFV examination significantly increased the RC ADR in screening and surveillance colonoscopies. Routine RC SFV examination should be considered. ClinicalTrials.gov ID: NCT03121495.

Timing of endoscopy for acute upper gastrointestinal bleeding: a territory-wide cohort study.

OBJECTIVE: While it is recommended that patients presenting with acute upper gastrointestinal bleeding (AUGIB) should receive endoscopic intervention within 24 hours, the optimal timing is still uncertain. We aimed to assess whether endoscopy timing postadmission would affect outcomes. DESIGN: We conducted a retrospective, territory-wide, cohort study with healthcare data from all public hospitals in Hong Kong. Adult patients (age ≥18) that presented with AUGIB between 2013 and 2019 and received therapeutic endoscopy within 48 hours (n=6474) were recruited. Patients were classified based on endoscopic timing postadmission: urgent (t≤6), early (6

Comparison of a Hemostatic Powder and Standard Treatment in the Control of Active Bleeding From Upper Nonvariceal Lesions : A Multicenter, Noninferiority, Randomized Trial.

BACKGROUND: The effectiveness of the hemostatic powder TC-325 as a single endoscopic treatment for acute nonvariceal upper gastrointestinal bleeding is uncertain. OBJECTIVE: To compare TC-325 with standard endoscopic hemostatic treatments in the control of active bleeding from nonvariceal upper gastrointestinal causes. DESIGN: One-sided, noninferiority, randomized, controlled trial. (ClinicalTrials.gov: NCT02534571). SETTING: University teaching hospitals in the Asia-Pacific region. PATIENTS: 224 adult patients with acute bleeding from a nonvariceal cause on upper gastrointestinal endoscopy. INTERVENTION: TC-325 (n = 111) or standard hemostatic treatment (n = 113). MEASUREMENTS: The primary outcome was control of bleeding within 30 days. Other outcomes included failure to control bleeding during index endoscopy, recurrent bleeding after initial hemostasis, further interventions, blood transfusion, hospitalization, and death. RESULTS: 224 patients were enrolled (136 with gastroduodenal ulcers [60.7%], 33 with tumors [14.7%], and 55 with other causes of bleeding [24.6%]). Bleeding was controlled within 30 days in 100 of 111 patients (90.1%) in the TC-325 group and 92 of 113 (81.4%) in the standard treatment group (risk difference, 8.7 percentage points [1-sided 95% CI, 0.95 percentage point]). There were fewer failures of hemostasis during index endoscopy with TC-325 (3 [2.7%] vs. 11 [9.7%]; odds ratio, 0.26 [CI, 0.07 to 0.95]). Recurrent bleeding within 30 days did not differ between groups (9 [8.1%] vs. 10 [8.8%]). The need for further interventions also did not differ between groups (further endoscopic treatment: 8 [7.2%] vs. 10 [8.8%]; angiography: 2 [1.8%] vs. 4 [3.5%]; surgery: 1 [0.9%] vs. 0). There were 14 deaths in each group (12.6% vs. 12.4%). LIMITATION: Clinicians were not blinded to treatment. CONCLUSION: TC-325 is not inferior to standard treatment in the endoscopic control of bleeding from nonvariceal upper gastrointestinal causes. PRIMARY FUNDING SOURCE: General Research Fund to the University Grants Committee, Hong Kong SAR Government.

Acute gastrointestinal bleeding: proposed study outcomes for new randomised controlled trials.

BACKGROUND: Acute gastrointestinal bleeding (GIB) remains a common cause of hospitalisation. However, interpretation and comparisons of published studies in GIB have been hampered by disparate study methodology. AIMS: To make recommendations about outcome measures to be used in future randomised controlled trials (RCTs) of patients with acute bleeding from any GI source (nonvariceal UGI, variceal, small bowel, or colon) and suggest new RCTs in acute GIB for future peer-reviewed funding. METHODS: As part of a National Institutes of Health conference entitled "Hemostatic Outcomes in Clinical Trials", a group of GIB experts performed targeted critical reviews of available evidence with the goal of proposing a bleeding outcome that could potentially be applied to different disciplines. In addition, the panel sought to develop a clinically meaningful primary endpoint specifically for acute GIB, potentially allowing a more contemporary regrouping of clinically relevant outcomes. RESULTS: The primary endpoint proposed was a composite outcome of further bleeding within 30 days after randomisation leading to red blood cell transfusion, urgent intervention (repeat endoscopy; interventional radiology or surgery), or death. Secondary outcomes may include the individual components of the primary outcome, length of hospitalisation, serious adverse events, and health care resource utilisation. CONCLUSION: The proposed endpoint may help move the GIB field forward by focusing on the most clinically relevant outcomes for patients with acute GIB of all types and informing study design and importance of sample size determination for future RCTs in GIB.

Short Message Service reminders reduce outpatient colonoscopy nonattendance rate: A randomized controlled study.

BACKGROUND AND AIM: Nonattendance of outpatient colonoscopy leads to inefficient use of health-care resources. We aimed to study the effectiveness of using Short Message Service (SMS) reminder prior in patients scheduled for outpatient colonoscopy on their nonattendance rate. METHODS: Patients who scheduled for an outpatient colonoscopy and had access of SMS were recruited from three clinics in Hong Kong. Patients were randomized to SMS group and standard care (SC) group. All patients were given a written appointment slip on the booking date. In addition, patients in the SMS group received an SMS reminder 7-10 days before their colonoscopy appointment. Patients' demographics, attendance, colonoscopy completion, and bowel preparation quality were recorded. Logistic regression was performed to identify predictors of nonattendance. RESULTS: From November 2013 to October 2019, a total of 2225 eligible patients were recruited. A total of 1079 patients were allocated to the SMS group and 1146 to the SC group. The nonattendance rate of patients in the SMS group was significantly lower than that in the SC group (8.9% vs 11.9%, P = 0.022). There were no significant differences in their baseline characteristics and colonoscopy completion rate and bowel preparation quality. A trend towards a higher rate of adequate bowel preparation was observed in the SMS group when compared with the SC group (69.9% vs 65.8%, P = 0.053). Independent predictors for nonattendance included younger age, underprivilege, and existing diabetes. CONCLUSIONS: An SMS reminder for outpatient colonoscopy is effective in reducing the nonattendance rate and may potentially improve the bowel preparation quality.

Endoscopic ultrasound-guided cyanoacrylate injection to prevent rebleeding in hepatocellular carcinoma patients with variceal hemorrhage.

BACKGROUND AND AIM: Secondary prophylaxis (SP) of variceal rebleeding was reported to improve outcomes of hepatocellular carcinoma (HCC) patients, but the optimal endoscopic approach is not well defined. We compared outcomes in HCC patients who underwent SP by endoscopic ultrasound-guided cyanoacrylate obturation (EUS-CYA) versus no SP. METHODS: Between 2014 and 2018, 30 consecutive patients with inoperable HCC and recent endoscopically controlled variceal bleeding were prospectively recruited. Twenty-seven patients with persistent varices ≥ 3 mm on endoscopic ultrasound underwent EUS-CYA for SP. Thirty-three HCC patients treated by esophagogastroduodenoscopy-guided CYA obturation (EGD-CYA) alone for acute variceal bleeding between 2009 and 2013 were identified from a prospective gastrointestinal bleed registry as standard of care controls for comparison. Outcome measures were death-adjusted cumulative incidence of rebleeding, bleeding-free survival, technical success, and procedure-related adverse events of EUS-CYA. RESULTS: The majority of patients in both groups had advanced HCC, portal vein thrombosis, and Child-Pugh B cirrhosis. EUS-CYA was successful in all 27 patients with no radiographic evidence of cyanoacrylate-lipiodol embolization. Significantly lower 30- and 90-day death-adjusted cumulative incidence of rebleeding (14.8% vs 42.4%, P = 0.023 and 18.5% vs 60.6%, P = 0.002, respectively) and significantly higher variceal bleeding-free survival at 3 and 6 months (51.9% vs 21.2%, P = 0.009, 40.7% vs 15.2%, P = 0.010, respectively) were observed in the EUS-CYA group when compared with standard of care group. CONCLUSIONS: Secondary prophylaxis by EUS-CYA reduced rebleeding rate and improved variceal bleeding-free survival in patients with inoperable HCC and variceal bleeding when compared with no SP. Randomized studies are needed to confirm the benefits of EUS-CYA for this difficult-to-treat population.

AI-doscopist: a real-time deep-learning-based algorithm for localising polyps in colonoscopy videos with edge computing devices.

We have designed a deep-learning model, an "Artificial Intelligent Endoscopist (a.k.a. AI-doscopist)", to localise colonic neoplasia during colonoscopy. This study aims to evaluate the agreement between endoscopists and AI-doscopist for colorectal neoplasm localisation. AI-doscopist was pre-trained by 1.2 million non-medical images and fine-tuned by 291,090 colonoscopy and non-medical images. The colonoscopy images were obtained from six databases, where the colonoscopy images were classified into 13 categories and the polyps' locations were marked image-by-image by the smallest bounding boxes. Seven categories of non-medical images, which were believed to share some common features with colorectal polyps, were downloaded from an online search engine. Written informed consent were obtained from 144 patients who underwent colonoscopy and their full colonoscopy videos were prospectively recorded for evaluation. A total of 128 suspicious lesions were resected or biopsied for histological confirmation. When evaluated image-by-image on the 144 full colonoscopies, the specificity of AI-doscopist was 93.3%. AI-doscopist were able to localise 124 out of 128 polyps (polyp-based sensitivity = 96.9%). Furthermore, after reviewing the suspected regions highlighted by AI-doscopist in a 102-patient cohort, an endoscopist has high confidence in recognizing four missed polyps in three patients who were not diagnosed with any lesion during their original colonoscopies. In summary, AI-doscopist can localise 96.9% of the polyps resected by the endoscopists. If AI-doscopist were to be used in real-time, it can potentially assist endoscopists in detecting one more patient with polyp in every 20-33 colonoscopies.

Patient-derived tumor organoid predicts drugs response in glioblastoma: A step forward in personalized cancer therapy?

Despite significant medical advances, glioblastoma multiforme (GBM) remains a formidable therapeutic challenge. Advent of targeted capture sequencing and patients-derived organoid cultures may hold the key to scientifically sound individualized treatment approaches. We report on our initial experience of using the combination of these two technologies to create a tailored approach of systemic therapies for a patient with GBM, which challenges the conventional treatment paradigm, as well as specifically highlighting the complexities of such an approach and the potential for a more favorable treatment outcome.