Endocuff With or Without Artificial Intelligence-Assisted Colonoscopy in Detection of Colorectal Adenoma: A Randomized Colonoscopy Trial.

INTRODUCTION: Both artificial intelligence (AI) and distal attachment devices have been shown to improve adenoma detection rate and reduce miss rate during colonoscopy. We studied the combined effect of Endocuff and AI on enhancing detection rates of various colonic lesions. METHODS: This was a 3-arm prospective randomized colonoscopy study involving patients aged 40 years or older. Participants were randomly assigned in a 1:1:1 ratio to undergo Endocuff with AI, AI alone, or standard high-definition (HD) colonoscopy. The primary outcome was adenoma detection rate (ADR) between the Endocuff-AI and AI groups while secondary outcomes included detection rates of polyp (PDR), sessile serrated lesion (sessile detection rate [SDR]), and advanced adenoma (advanced adenoma detection rate) between the 2 groups. RESULTS: A total of 682 patients were included (mean age 65.4 years, 52.3% male), with 53.7% undergoing diagnostic colonoscopy. The ADR for the Endocuff-AI, AI, and HD groups was 58.7%, 53.8%, and 46.3%, respectively, while the corresponding PDR was 77.0%, 74.0%, and 61.2%. A significant increase in ADR, PDR, and SDR was observed between the Endocuff-AI and AI groups (ADR difference: 4.9%, 95% CI: 1.4%-8.2%, P = 0.03; PDR difference: 3.0%, 95% CI: 0.4%-5.8%, P = 0.04; SDR difference: 6.4%, 95% CI: 3.4%-9.7%, P < 0.01). Both Endocuff-AI and AI groups had a higher ADR, PDR, SDR, and advanced adenoma detection rate than the HD group (all P < 0.01). DISCUSSION: Endocuff in combination with AI further improves various colonic lesion detection rates when compared with AI alone.

Blue-light imaging or narrow-band imaging for proximal colonic lesions: a prospective randomized tandem colonoscopy study.

BACKGROUND AND AIMS: Blue-light imaging (BLI) is a new image-enhanced endoscopy with a wavelength filter similar to narrow-band imaging (NBI). We compared the 2 with white-light imaging (WLI) on proximal colonic lesion detection and miss rates. METHODS: In this 3-arm prospective randomized study with tandem examination of the proximal colon, we enrolled patients aged ≥40 years. Eligible patients were randomized in 1:1:1 ratio to receive BLI, NBI, or WLI during the first withdrawal from the proximal colon. The second withdrawal was performed using WLI in all patients. Primary outcomes were proximal polyp (pPDRs) and adenoma (pADRs) detection rates. Secondary outcomes were miss rates of proximal lesions found on tandem examination. RESULTS: Of 901 patients included (mean age, 64.7 years; 52.9% men), 48.1% underwent colonoscopy for screening or surveillance. The corresponding pPDRs of the BLI, NBI, and WLI groups were 45.8%, 41.6, and 36.6%, whereas the corresponding pADRs were 36.6%, 33.8%, and 28.3%. There was a significant difference in pPDR and pADR between BLI and WLI groups (difference, 9.2% [95% confidence interval {CI}, 3.3-16.9] and 8.3% [95% CI, 2.7-15.9]) and between NBI and WLI groups (difference, 5.0% [95% CI, 1.4-12.9] and 5.6% [95% CI, 2.1-13.3]). Proximal adenoma miss rates were significantly lower with BLI (19.4%) than with WLI (27.4%; difference, -8.0%; 95% CI, -15.8 to -.1) but not between NBI (27.2%) and WLI. CONCLUSIONS: Both BLI and NBI were superior to WLI on detecting proximal colonic lesions, but only BLI had lower proximal adenoma miss rates than WLI. (Clinical trial registration number: NCT03696992.).

Machine learning models in the prediction of 1-year mortality in patients with advanced hepatocellular cancer on immunotherapy: a proof-of-concept study.

INTRODUCTION: Immunotherapy is a new promising treatment for patients with advanced hepatocellular carcinoma (HCC), but is costly and potentially associated with considerable side effects. This study aimed to evaluate the role of machine learning (ML) models in predicting the 1-year cancer-related mortality in advanced HCC patients treated with immunotherapy. METHOD: 395 HCC patients who had received immunotherapy (including nivolumab, pembrolizumab or ipilimumab) between 2014 and 2019 in Hong Kong were included. The whole data sets were randomly divided into training (n = 316) and internal validation (n = 79) set. The data set, including 47 clinical variables, was used to construct six different ML models in predicting the risk of 1-year mortality. The performances of ML models were measured by the area under receiver operating characteristic curve (AUC) and their performances were compared with C-Reactive protein and Alpha Fetoprotein in ImmunoTherapY score (CRAFITY) and albumin-bilirubin (ALBI) score. The ML models were further validated with an external cohort between 2020 and 2021. RESULTS: The 1-year cancer-related mortality was 51.1%. Of the six ML models, the random forest (RF) has the highest AUC of 0.92 (95% CI 0.87-0.98), which was better than logistic regression (0.82, p = 0.01) as well as the CRAFITY (0.68, p < 0.01) and ALBI score (0.84, p = 0.04). RF had the lowest false positive (2.0%) and false negative rate (5.2%), and performed better than CRAFITY score in the external validation cohort (0.91 vs 0.66, p < 0.01). High baseline AFP, bilirubin and alkaline phosphatase were three common risk factors identified by all ML models. CONCLUSION: ML models could predict 1-year cancer-related mortality in HCC patients treated with immunotherapy, which may help to select patients who would benefit from this treatment.

Feasibility study of a single-use balloon-assisted robotic colonoscope in healthy volunteers.

Background and study aims Despite its widespread adoption, colonoscope still has its limitations. Advancement is often limited by the looping of colon. The isolation of SARS-CoV-2 in stool raises concern for the risk of disease transmission. A single-use robotic colonoscope, the NISInspire-C System, that features a balloon-suction anchorage mechanism was developed to address these. Methods The NISInspire-C balloons are designed to provide anchorage for straightening of the colon during advancement. Angulation at the bending section is tendon-wire driven by servo mechanisms integrated into a robotic control console. This was a pilot, prospective trial to evaluate the safety and feasibility of this system. Healthy volunteers underwent examination with the NISInspire-C, followed by the conventional colonoscope. The procedure time, cecal intubation rates (CIR), complications, and level of pain were measured. Results A total of 19 subjects underwent the examination. The cecal intubation rate was 89.5 % (17/19) and the overall time-to-cecum was 26.3 minutes (SD: 17.9 mins). There were no procedure-related complications. Polyps were detected in seven of 19 (36.8 %) subjects during the NISInspire-C procedure. Three more subjects were found to have adenomatous polyps with the conventional colonoscope. There was minimal variation in level of pain during the procedures with the two colonoscopes. Conclusion The single-use robotic colonoscope NISInspire-C is a safe and feasible alternative to the conventional colonoscope. Further technical refinement is needed to improve the CIR. This study was limited by its small sample size.