Artificial intelligence-assisted optical diagnosis for the resect-and-discard strategy in clinical practice: the Artificial intelligence BLI Characterization (ABC) study.

BACKGROUND: Optical diagnosis of colonic polyps is poorly reproducible outside of high volume referral centers. The present study aimed to assess whether real-time artificial intelligence (AI)-assisted optical diagnosis is accurate enough to implement the leave-in-situ strategy for diminutive (≤ 5 mm) rectosigmoid polyps (DRSPs). METHODS: Consecutive colonoscopy outpatients with ≥ 1 DRSP were included. DRSPs were categorized as adenomas or nonadenomas by the endoscopists, who had differing expertise in optical diagnosis, with the assistance of a real-time AI system (CAD-EYE). The primary end point was ≥ 90 % negative predictive value (NPV) for adenomatous histology in high confidence AI-assisted optical diagnosis of DRSPs (Preservation and Incorporation of Valuable endoscopic Innovations [PIVI-1] threshold), with histopathology as the reference standard. The agreement between optical- and histology-based post-polypectomy surveillance intervals (≥ 90 %; PIVI-2 threshold) was also calculated according to European Society of Gastrointestinal Endoscopy (ESGE) and United States Multi-Society Task Force (USMSTF) guidelines. RESULTS: Overall 596 DRSPs were retrieved for histology in 389 patients; an AI-assisted high confidence optical diagnosis was made in 92.3 %. The NPV of AI-assisted optical diagnosis for DRSPs (PIVI-1) was 91.0 % (95 %CI 87.1 %-93.9 %). The PIVI-2 threshold was met with 97.4 % (95 %CI 95.7 %-98.9 %) and 92.6 % (95 %CI 90.0 %-95.2 %) of patients according to ESGE and USMSTF, respectively. AI-assisted optical diagnosis accuracy was significantly lower for nonexperts (82.3 %, 95 %CI 76.4 %-87.3 %) than for experts (91.9 %, 95 %CI 88.5 %-94.5 %); however, nonexperts quickly approached the performance levels of experts over time. CONCLUSION: AI-assisted optical diagnosis matches the required PIVI thresholds. This does not however offset the need for endoscopists' high level confidence and expertise. The AI system seems to be useful, especially for nonexperts.

Artificial intelligence and colonoscopy experience: lessons from two randomised trials.

BACKGROUND AND AIMS: Artificial intelligence has been shown to increase adenoma detection rate (ADR) as the main surrogate outcome parameter of colonoscopy quality. To which extent this effect may be related to physician experience is not known. We performed a randomised trial with colonoscopists in their qualification period (AID-2) and compared these data with a previously published randomised trial in expert endoscopists (AID-1). METHODS: In this prospective, randomised controlled non-inferiority trial (AID-2), 10 non-expert endoscopists (<2000 colonoscopies) performed screening/surveillance/diagnostic colonoscopies in consecutive 40-80 year-old subjects using high-definition colonoscopy with or without a real-time deep-learning computer-aided detection (CADe) (GI Genius, Medtronic). The primary outcome was ADR in both groups with histology of resected lesions as reference. In a post-hoc analysis, data from this randomised controlled trial (RCT) were compared with data from the previous AID-1 RCT involving six experienced endoscopists in an otherwise similar setting. RESULTS: In 660 patients (62.3±10 years; men/women: 330/330) with equal distribution of study parameters, overall ADR was higher in the CADe than in the control group (53.3% vs 44.5%; relative risk (RR): 1.22; 95% CI: 1.04 to 1.40; p<0.01 for non-inferiority and p=0.02 for superiority). Similar increases were seen in adenoma numbers per colonoscopy and in small and distal lesions. No differences were observed with regards to detection of non-neoplastic lesions. When pooling these data with those from the AID-1 study, use of CADe (RR 1.29; 95% CI: 1.16 to 1.42) and colonoscopy indication, but not the level of examiner experience (RR 1.02; 95% CI: 0.89 to 1.16) were associated with ADR differences in a multivariate analysis. CONCLUSIONS: In less experienced examiners, CADe assistance during colonoscopy increased ADR and a number of related polyp parameters as compared with the control group. Experience appears to play a minor role as determining factor for ADR. TRIAL REGISTRATION NUMBER: NCT:04260321.

Efficacy of a computer-aided detection system in a fecal immunochemical test-based organized colorectal cancer screening program: a randomized controlled trial (AIFIT study).

BACKGROUND: Computer-aided detection (CADe) increases adenoma detection in primary screening colonoscopy. The potential benefit of CADe in a fecal immunochemical test (FIT)-based colorectal cancer (CRC) screening program is unknown. This study assessed whether use of CADe increases the adenoma detection rate (ADR) in a FIT-based CRC screening program. METHODS: In a multicenter, randomized trial, FIT-positive individuals aged 50-74 years undergoing colonoscopy, were randomized (1:1) to receive high definition white-light (HDWL) colonoscopy, with or without a real-time deep-learning CADe by endoscopists with baseline ADR > 25 %. The primary outcome was ADR. Secondary outcomes were mean number of adenomas per colonoscopy (APC) and advanced adenoma detection rate (advanced-ADR). Subgroup analysis according to baseline endoscopists' ADR (≤ 40 %, 41 %-45 %, ≥ 46 %) was also performed. RESULTS: 800 individuals (median age 61.0 years [interquartile range 55-67]; 409 men) were included: 405 underwent CADe-assisted colonoscopy and 395 underwent HDWL colonoscopy alone. ADR and APC were significantly higher in the CADe group than in the HDWL arm: ADR 53.6 % (95 %CI 48.6 %-58.5 %) vs. 45.3 % (95 %CI 40.3 %-50.45 %; RR 1.18; 95 %CI 1.03-1.36); APC 1.13 (SD 1.54) vs. 0.90 (SD 1.32; P  = 0.03). No significant difference in advanced-ADR was found (18.5 % [95 %CI 14.8 %-22.6 %] vs. 15.9 % [95 %CI 12.5 %-19.9 %], respectively). An increase in ADR was observed in all endoscopist groups regardless of baseline ADR. CONCLUSIONS: Incorporating CADe significantly increased ADR and APC in the framework of a FIT-based CRC screening program. The impact of CADe appeared to be consistent regardless of endoscopist baseline ADR.

Oral mannitol for bowel preparation: a dose-finding phase II study.

BACKGROUND: Successful bowel preparation (BP) for colonoscopy depends on the instructions, diet, the laxative product, and patient adherence, which all affect colonoscopy quality. Nevertheless, there are no laxatives which combine effectiveness, safety, easy self-administration, good patient acceptance, and low cost. However, mannitol, a sugar alcohol, could be an attractive candidate for use in clinical practice if it is shown to demonstrate adequate efficacy and safety. AIMS: The present phase II dose-finding study compared three doses of mannitol (50, 100, and 150 g) to identify the best dose to be used in a subsequent phase III study. METHODS: The Boston Bowel Preparation Scale, caecal intubation rate, adherence, acceptability, and safety profile, including measurement of potentially dangerous colonic gas concentrations (CH4, H2, O2), were considered in all patients. A weighted algorithm was used to identify the best mannitol dose for use in the subsequent study. RESULTS: The per-protocol population included 60 patients in the 50 g group, 54 in the 100 g group, and 49 in the 150 g group. The 100 g dose was the best as it afforded optimal colon cleansing efficacy (94.4% of patients had adequate BP), adherence, acceptability, and safety, including negligible gas concentrations. CONCLUSIONS: The present study demonstrated that the colon cleansing efficacy and safety of mannitol were dose dependent. Conversely, gas concentrations were not dose dependent and negligible in all patients. Combined evaluation of efficacy, tolerability, and safety, using a weighted algorithm, determined that mannitol 100 g was the best dose for the phase III study.

The combination of PIVKA-II and AFP improves the detection accuracy for HCC in HBV caucasian cirrhotics on long-term oral therapy.

BACKGROUND & AIMS: Protein induced by vitamin K absence or antagonist-II (PIVKA-II) has been suggested as a serum biomarker for hepatocellular carcinoma (HCC) in Asian hepatitis B virus (HBV)-treated subjects but no studies tested it in Caucasian cirrhotics long-term nucleos(t)ide analogues (NUCs)-treated. We assessed the detection accuracy of PIVKA-II alone or in combination with alpha-foetoprotein (AFP) in patients under surveillance. METHODS: This cross-sectional, single centre case-control study was conducted in 212 NUC-treated cirrhotics: 64 HCC and 148 HCC-free controls for 84 (60-107) months. PIVKA-II was determined by a CMIA immunoassay (Abbott; limit of quantification: 8.2 mAU/mL). RESULTS: Protein induced by vitamin K absence or agonist II (PIVKA-II) and AFP levels were significantly higher in HCC patients [Barcelona Clinic Liver Cancer staging system stage 0/A in 91%, diameter 20 (6-50) mm] compared to controls: 109 (17-12 157) vs 31 (13-82) mAU/mL and 5 (1-1163) vs 2 (1-7) ng/mL (P < .001 for both markers), with a cut-off of 48 mAU/mL and 4.2 ng/mL by AUROC analysis. The PIVKA-II 82 mAU/mL and AFP 7 ng/mL cut-offs showed 100% specificity, with the former more sensitive (54% vs 42%), accurate (86% vs 83%), with higher negative predictive value (80% vs 76%) compared to AFP for HCC detection. PIVKA-II more frequently than AFP levels exceeded the cut-off 6-18 months before HCC diagnosis. Combining PIVKA-II with AFP increased sensitivity, accuracy and negative predictive values to 67%, 90% and 85%, preserving 100% specificity. PIVKA-II was associated with lesions >20 mm or neoplastic thrombosis. CONCLUSIONS: Combination of PIVKA-II and AFP increases the detection rate for HCC in NUC-treated HBV Caucasian cirrhotics, a potential new approach for surveillance.

White light computer-aided optical diagnosis of diminutive colorectal polyps in routine clinical practice.

Background and study aims Artificial Intelligence (AI) systems could make the optical diagnosis (OD) of diminutive colorectal polyps (DCPs) more reliable and objective. This study was aimed at prospectively evaluating feasibility and diagnostic performance of AI-standalone and AI-assisted OD of DCPs in a real-life setting by using a white light-based system (GI Genius, Medtronic Co, Minneapolis, Minnesota, United States). Patients and methods Consecutive colonoscopy outpatients with at least one DCP were evaluated by 11 endoscopists (5 experts and 6 non-experts in OD). DCPs were classified in real time by AI (AI-standalone OD) and by the endoscopist with the assistance of AI (AI-assisted OD), with histopathology as the reference standard. Results Of the 480 DCPs, AI provided the outcome "adenoma" or "non-adenoma" in 81.4% (95% confidence interval [CI]: 77.5-84.6). Sensitivity, specificity, positive and negative predictive value, and accuracy of AI-standalone OD were 97.0% (95% CI 94.0-98.6), 38.1% (95% CI 28.9-48.1), 80.1% (95% CI 75.2-84.2), 83.3% (95% CI 69.2-92.0), and 80.5% (95% CI 68.7-82.8%), respectively. Compared with AI-standalone, the specificity of AI-assisted OD was significantly higher (58.9%, 95% CI 49.7-67.5) and a trend toward an increase was observed for other diagnostic performance measures. Overall accuracy and negative predictive value of AI-assisted OD for experts and non-experts were 85.8% (95% CI 80.0-90.4) vs. 80.1% (95% CI 73.6-85.6) and 89.1% (95% CI 75.6-95.9) vs. 80.0% (95% CI 63.9-90.4), respectively. Conclusions Standalone AI is able to provide an OD of adenoma/non-adenoma in more than 80% of DCPs, with a high sensitivity but low specificity. The human-machine interaction improved diagnostic performance, especially when experts were involved.

Scoring systems for risk stratification in upper and lower gastrointestinal bleeding.

Several scoring systems have been developed for both upper and lower GI bleeding to predict the bleeding severity and discriminate between low-risk patients, who may be suitable for outpatient management, and those who would likely need hospital-based interventions and are at high risk for adverse outcomes. Risk scores created to identify low-risk patients (namely the Glasgow Blatchford Score and the Oakland score) showed very good discriminative performances and their implementation has proven to be effective in reducing hospital admissions and healthcare burden. Conversely, the performances of risk scores in identifying specific adverse events to define high-risk patients are less accurate, and whether their integration into routine clinical practice has a tangible impact on patient management remains unproven. This review describes the existing risk score systems for GI bleeding, emphasizes key research findings, elucidates the circumstances in which their utilization can be beneficial, examines their constraints when considering routine clinical application, and discuss future development.

Factors influencing the presence of potentially explosive gases during colonoscopy: Results of the SATISFACTION study.

This study tested the hypothesis that bowel preparation with mannitol should not affect the colonic concentration of H2 and CH4 . Therefore, the SATISFACTION study, an international, multicenter, randomized, parallel-group phase II-III study investigated this issue. The phase II dose-finding part of the study evaluated H2 , CH4 , and O2 concentrations in 179 patients randomized to treatment with 50 g, 100 g, or 150 g mannitol. Phase III of the study compared the presence of intestinal gases in 680 patients randomized (1:1) to receive mannitol 100 g in single dose or a standard split-dose 2 L polyethylene glycol (PEG)-Asc preparation (2 L PEG-Asc). Phase II results showed that mannitol did not influence the concentration of intestinal gases. During phase III, no patient in either group had H2 or CH4 concentrations above the critical thresholds. In patients with H2 and/or CH4 levels above detectable concentrations, the mean values were below the risk thresholds by at least one order of magnitude. The results also highlighted the effectiveness of standard washing and insufflation maneuvers in removing residual intestinal gases. In conclusion, bowel cleansing with mannitol was safe as the concentrations of H2 and CH4 were the same as those found in patients prepared with 2 L PEG-Asc. In both groups, the concentrations of gases were influenced more by the degree of cleansing achieved and the insufflation and washing maneuvers performed than by the preparation used for bowel cleansing. The trial protocol was registered with ClinicalTrials.gov (https://clinicaltrials.gov/ct2/show/NCT04759885) and with EudraCT (eudract_number: 2019-002856-18).

Continuous clinical remission with biologics in ulcerative colitis: the 'AURORA' comparison study.

OBJECTIVES: Comparative trials among biological drugs for the treatment of ulcerative colitis (UC) provided conflicting results. After patent expire of infliximab originator, adalimumab, infliximab biosimilar, golimumab and vedolizumab have been approved in Italy.We compared the efficacy of these four biologics in UC according to the concept of continuous clinical remission (CCR). METHODS: In a retrospective, multicentre study, all UC patients treated with adalimumab, infliximab biosimilar, golimumab or vedolizumab between 2014 and 2019 were included. All drugs were compared to each other according to the 1-year CCR rate, defined as Mayo partial score ≤2, with bleeding subscore = 0, without any relapse or optimization with dose escalation, topical treatments or steroid use after first clinical remission. RESULTS: Four-hundred sixteen patients (adalimumab = 90, infliximab biosimilar = 105, golimumab = 79, vedolizumab = 142) were included. CCR was achieved in similar percentages among the groups (33%, 37%, 28%, 37%, respectively). All drugs were equivalent in biologic-naive patients, while vedolizumab was better than a second anti-TNFα in prior anti-TNFα agent failures. No differences were found according to type of adverse events or severe adverse events. CONCLUSIONS: Based on a strict definition of clinical remission, all biologics appear equally effective at 1 year. Changing to vedolizumab is more effective than switching to another anti-TNFα in TNFα failures.

Treatment options for localised renal cell carcinoma of the transplanted kidney.

Currently, there is no consensus among the transplant community about the treatment of renal cell carcinoma (RCC) of the transplanted kidney. Until recently, graftectomy was universally considered the golden standard, regardless of the characteristics of the neoplasm. Due to the encouraging results observed in native kidneys, conservative options such as nephron-sparing surgery (NSS) (enucleation and partial nephrectomy) and ablative therapy (radiofrequency ablation, cryoablation, microwave ablation, high-intensity focused ultrasound, and irreversible electroporation) have been progressively used in carefully selected recipients with early-stage allograft RCC. Available reports show excellent patient survival, optimal oncological outcome, and preserved renal function with acceptable complication rates. Nevertheless, the rarity and the heterogeneity of the disease, the number of options available, and the lack of long-term follow-up data do not allow to adequately define treatment-specific advantages and limitations. The role of active surveillance and immunosuppression management remain also debated. In order to offer a better insight into this difficult topic and to help clinicians choose the best therapy for their patients, we performed and extensive review of the literature. We focused on epidemiology, clinical presentation, diagnostic work up, staging strategies, tumour characteristics, treatment modalities, and follow-up protocols. Our research confirms that both NSS and focal ablation represent a valuable alternative to graftectomy for kidney transplant recipients with American Joint Committee on Cancer stage T1aN0M0 RCC. Data on T1bN0M0 lesions are scarce but suggest extra caution. Properly designed multi-centre prospective clinical trials are warranted.

Application of EASL 2017 criteria for switching hepatitis B patients from tenofovir disoproxil to entecavir or tenofovir alafenamide.

BACKGROUND: To overcome safety limitations of tenofovir-disoproxil, EASL guidelines proposed switching chronic hepatitis B patients older than 60 years or with bone or renal disease to tenofovir-alafenamide or entecavir. AIMS: To estimate the number of patients who would benefit from a treatment switch in a real-life setting. METHODS: Consecutive hepatitis B patients receiving tenofovir-disoproxil before 31 December 2017 were enrolled in a cross-sectional study in two European hospitals. Clinical and virological data were recorded; renal function was assessed by estimated glomerular filtrate rate, serum phosphate and creatinine, proteinuria, and albuminuria; bone involvement by spine and femur DEXA scan. RESULTS: In total, 565 patients included: 62 (18-91) years, 75% males, 92% Caucasian, 92% HBeAg-negative, 40% cirrhotic. Fifty-five percent of patients fulfilled age criterion (>60 years). Older patients had higher rates of cirrhosis (51% vs 26%, p<0.001), cardiovascular disease, and renal impairment. Thirty-six percent of patients met renal criteria, more commonly NA-experienced individuals (35% vs 21%, p=0.001); 17% had bone disease. Overall, 66% of patients had at least one criterion (71% if NA-experienced), 8% all three criteria, 28% age and renal criteria. CONCLUSIONS: Approximately two-thirds of patients receiving long-term tenofovir-disoproxil are candidates for an entecavir or tenofovir-alafenamide switch according to EASL recommendations.