Frame-by-Frame Analysis of a Commercially Available Artificial Intelligence Polyp Detection System in Full-Length Colonoscopies.

INTRODUCTION: Computer-aided detection (CADe) helps increase colonoscopic polyp detection. However, little is known about other performance metrics like the number and duration of false-positive (FP) activations or how stable the detection of a polyp is. METHODS: 111 colonoscopy videos with total 1,793,371 frames were analyzed on a frame-by-frame basis using a commercially available CADe system (GI-Genius, Medtronic Inc.). Primary endpoint was the number and duration of FP activations per colonoscopy. Additionally, we analyzed other CADe performance parameters, including per-polyp sensitivity, per-frame sensitivity, and first detection time of a polyp. We additionally investigated whether a threshold for withholding CADe activations can be set to suppress short FP activations and how this threshold alters the CADe performance parameters. RESULTS: A mean of 101 ± 88 FPs per colonoscopy were found. Most of the FPs consisted of less than three frames with a maximal 66-ms duration. The CADe system detected all 118 polyps and achieved a mean per-frame sensitivity of 46.6 ± 26.6%, with the lowest value for flat polyps (37.6 ± 24.8%). Withholding CADe detections up to 6 frames length would reduce the number of FPs by 87.97% (p < 0.001) without a significant impact on CADe performance metrics. CONCLUSIONS: The CADe system works reliable but generates many FPs as a side effect. Since most FPs are very short, withholding short-term CADe activations could substantially reduce the number of FPs without impact on other performance metrics. Clinical practice would benefit from the implementation of customizable CADe thresholds.

When and how to use direct oral anticoagulants in patients with advanced chronic liver disease?

Direct oral anticoagulants (DOACs) emerged as effective and safe alternatives to traditional anticoagulants for the prevention and treatment of venous thromboembolic disease and the prevention of stroke in non-valvular atrial fibrillation. Patients with advanced chronic liver disease (ACLD) have a higher risk of thromboembolism and bleeding than patients with normal liver function. Therefore, anticoagulation and, in particular, direct oral anticoagulants play a central role. Portal vein thrombosis is a relatively frequent complication in patients with ACLD, but its treatment remains challenging. DOACs have been introduced in clinical practice and demonstrated similar efficacy and safety profiles compared with vitamin K antagonist and heparins. However, further data about the use of DOACs in patients suffering from ACLD are needed. This review summarizes current knowledge in terms of anticoagulation in patients with ACLD and focuses on the available data about the use of DOACs in this population.

Course of oesophageal varices and performance of noninvasive predictors following Hepatitis C Virus clearance in compensated advanced chronic liver disease.

BACKGROUND: In patients with hepatitis C virus (HCV) and compensated advanced chronic liver disease (cACLD), there is evidence that sustained virological response (SVR) to direct-acting antivirals (DAA) may ameliorate portal hypertension, although both the course of oesophageal varices and the performance of their noninvasive predictors following DAA-induced SVR are less defined. In this study, our aim was to assess the variation in oesophageal varices status in HCV patients with cACLD who obtained an SVR to DAAs and to evaluate the diagnostic performance of noninvasive predictors of varices after HCV cure. MATERIAL AND METHODS: Sixty-three HCV patients with cACLD and SVR to DAAs were prospectively followed up, and oesophageal varices surveillance was carried out according to the Baveno VI indications. Appearance and disappearance of varices, accuracy performance of their noninvasive predictors (Baveno/expanded Baveno VI criteria, platelet count/spleen diameter ratio) and number of endoscopies spared with their application were calculated. RESULTS: Following SVR, varices developed or disappeared in 12.1% and 17.4% of patients, respectively. The negative predictive value for varices of the Baveno VI, expanded Baveno VI criteria and platelet count/spleen diameter ratio following SVR was 88.2% (65.6-96.7), 83.3% (66.3-92.7) and 80.7% (67.1-89.5), respectively. Their application would have saved 30.4%, 42.9% and 55.4% of endoscopies, with no varices needing treatment missed using both Baveno VI criteria. CONCLUSIONS: In HCV patients with cACLD, following SVR to DAA, the expanded Baveno VI criteria provide the best balance between utility (diagnostic accuracy and endoscopies avoided) and safety (varices needing treatment missed) for varices surveillance.

Pathophysiology, diagnosis, and pharmacological treatment of gastro-esophageal reflux disease.

INTRODUCTION: Gastro-esophageal reflux disease (GERD) is a highly prevalent, chronic, relapsing disorder, whose knowledge has increased in last years thanks to the advent of new sophisticated techniques, such as 24-h impedance-pH monitoring and high-resolution manometry, for the study of esophageal functions. AREAS COVERED: This review provides an overview of our advancements in understanding the complex pathophysiology, improving the diagnosis and defining the modern pharmacological therapeutic approach to GERD. EXPERT OPINION: The growing clinical application of impedance-pH testing has allowed us to know the diversity of patients with non-erosive reflux disease (NERD), who nowadays represent about 70% of the whole population with reflux symptoms. We have realized that NERD has to be considered as an umbrella term covering various subgroups with different pathophysiologies. The development of new impedance metrics, in particular mean nocturnal baseline impedance, seems to be promising in the improvement of the diagnostic process of this disease. There are no particularly innovative features in the pharmacological therapy of GERD, unless the interest toward drugs is able to increase the defense properties of esophageal mucosa and/or its protection. These compounds can be of help in combination with proton pump inhibitors in NERD patients with partial response to antisecretory drugs alone.

High anti-TNF alfa drugs trough levels are not associated with the occurrence of adverse events in patients with inflammatory bowel disease.

Objectives: Up to 40% of inflammatory bowel disease (IBD) patients treated with anti-TNF drugs lose response within 1 year of treatment, therefore requiring drug optimization. Although higher drug trough levels (TLs) are associated with sustained clinical outcomes, there are concerns that they may be associated with a higher risk of adverse events (AEs). The aim was to evaluate the presence of a possible association between drug TLs and the occurrence of AEs in IBD patients treated with anti-TNF drugs.Methods: We retrospectively studied a cohort of 113 IBD patients treated with adalimumab or infliximab, of whom 27 were in combination therapy with immunosuppressants. TLs were measured using a homogeneous mobility shift assay.Results: During a median follow-up of 16 months (range 1-144), we observed 103 AEs occurring in 58 patients. We found no statistically significant difference (p = .21) in median TLs between patients who did 6.7 mcg/mL; range 0.0-36.2) or did not (7.7 mcg/mL; range 0.0-20.7) experience an AE. No difference was observed in the rate of AEs between patients in mono- or combination therapy (p = .38), as well as between elderly (i.e., >65 years) and younger patients (p = .32). Considering a TL cutoff of 7 mcg/mL for infliximab and 12 mcg/mL for adalimumab, or even double these TL values, we observed no statistically significant difference in the rate of AEs occurrence.Conclusion: Our study suggests that, when clinically required, anti-TNF drug dosage may be increased without particular concerns regarding the risk of AEs occurrence in IBD patients, even in patients on combination therapy and elderly ones.

Proton pump inhibitors: use and misuse in the clinical setting.

INTRODUCTION: The introduction of proton pump inhibitors (PPIs) into clinical practice has greatly improved our therapeutic approach to acid-related diseases for their efficacy and safety. Areas Covered: The following evidence-based indications for PPI use are acknowledged by many scientific societies: treatment of the various forms and complications of gastroesophageal reflux disease, eradication of H. pylori infection in combination with two or more antibiotics, short- and long-term therapy of H. pylori-negative peptic ulcers, healing, and prevention of NSAID/COXIB-associated gastric ulcers, co-therapy with endoscopic procedures to control upper digestive bleeding and medical treatment of Zollinger Ellison syndrome. Expert Commentary: Despite the above well-defined indications, however, the use of PPIs continues to grow every year in both western and eastern countries and the endless expansion of the PPI market has created important problems for many regulatory authorities for two relevant features: the progressive increase of the costs of therapy and the greater potential harms for the patients. The major reasons for the misuse of PPIs are the prevention of gastro-duodenal ulcers in patients without risk factors and the stress ulcer prophylaxis in non-intensive care units, steroid therapy alone, anti-platelet or anti-coagulant treatment in patients without risk of gastric injury and the overtreatment of functional dyspepsia.

The appropriate use of proton-pump inhibitors.

The introduction of proton-pump inhibitors (PPIs) into clinical practice since about thirty years has greatly improved our therapeutic approach to acid-related diseases for their well recognized efficacy and safety. Accordingly, the role of surgery has been enormously reduced in this field. The main indications for PPI use are universally acknowledged by many scientific societies and are the following: treatment of gastroesophageal reflux disease in its various forms and complications, eradication of H. pylori infection in combination with two or more antibiotics, therapy of H. pylori-negative peptic ulcers, healing and prevention of NSAID-associated gastric ulcers, co-therapy with endoscopic procedures to control upper digestive bleeding and medical treatment of Zollinger-Ellison Syndrome. Despite the above well-defined indications, however, the use of PPIs continues to grow every year in both Western and Eastern countries and this phenomenon poses serious queries about the appropriate prescription of these drugs worldwide. In fact, the endless expansion of PPI market has created important problems for many regulatory authorities for two relevant features: the progressive and irreversible increase of the costs of therapy with this class of drugs and the greater potential harms for the patients. So, there is the need for a reappraisal of PPI correct indications for both general practitioners and various specialists in order to re-establish a correct use of these effective drugs in daily clinical practice, according to the best evidence-based guidelines.

Anti-TNF therapy is able to stabilize bowel damage progression in patients with Crohn's disease. A study performed using the Lémann Index.

AIMS: The Lémann Index (LI) was developed to assess the cumulative structural damage of the intestinal tract in patients with Crohn's Disease (CD) independently of clinical and biochemical activity. Recently, the goal of CD focused on obtaining mucosal healing and deep remission rather than simple symptom control. These new therapeutic aims emphasize the need to prevent progression of bowel damage. In this study we aimed to evaluate the influence of different treatments on structural damage progression, assessed by means of LI in a series of CD patients consistently treated with various drugs. METHODS: The LI was calculated at inclusion and at the end of follow-up in 104 CD patients subdivided according to treatments received: biological drugs (n=40, 38.4%), azathioprine (n=19, 18.3%), and mesalazine (n=45, 43.3%). RESULTS: The median follow-up was 29 months, with no difference among groups. During follow-up, the median LI was stable in the biological group [from 6.3 (range, 0.6-37.3) to 6.4 (range, 0.6-37.6), P=0.543], whereas it significantly increased from 4.1 (range, 0.6-30) to 8.3 (range, 0.6-31.8) in the azathioprine group (P=0.0006), and from 2.4 (range, 0.6-25.8) to 4.1 (range, 0.6-28.8) in the mesalazine group (P<0.0001). Also during follow-up the LI increased significantly (P=0.004) in the azathioprine (68.4%) and mesalazine (60.0%) groups as compared with the biological therapy group (30.0%). CONCLUSIONS: In CD patients the LI tends to increase over time, although the use of biological drugs rather than azathioprine or mesalazine seems to be able to reduce the progressive bowel damage.

Adalimumab trough serum levels and anti-adalimumab antibodies in the long-term clinical outcome of patients with Crohn's disease.

OBJECTIVE: Few data are available on the relevance of adalimumab (ADA) trough serum levels and anti-ADA antibodies (AAA) during long-term follow-up of patients with Crohn's Disease (CD), and their association with disease outcome. In this study, our aim was to assess ADA trough serum levels and the presence of AAA according to disease activity and clinical response during long-term follow-up in a series of patients with CD treated with ADA monotherapy. MATERIAL AND METHODS: We prospectively evaluated 23 consecutive, infliximab-naïve CD patients who achieved clinical remission/response after induction and were in maintenance treatment with ADA, and who were followed-up for at least 72 weeks. Blood samples were drawn at standardized time points to assess ADA through levels, AAA. RESULTS: At week 48, we found significantly (p = 0.027) different ADA trough serum levels in patients in remission (10.1 mcg/mL), mild (7.4 mcg/mL), and moderate/severe disease (4.5 mcg/mL). Median ADA trough levels were significantly lower in patients with AAA (3.7 mcg/mL versus 9.3 mcg/mL, p = 0.006). At the end of follow-up (median 102 weeks, range 73-112 weeks), ADA trough serum concentrations were significantly higher (11.9 mcg/mL) as compared to patients with mild and moderate/severe disease (5.5 mcg/mL, p = 0.0002). Furthermore, median ADA trough concentrations showed a trend towards lower levels in AAA positive patients (5.2 mcg/mL versus 7.2 mcg/mL, p = 0.371). CONCLUSIONS: Our results emphasize the relevance of therapeutic drug monitoring in CD patients on biologic treatment. ADA trough serum levels and the presence of AAA are important features in the management of patients on ADA treatment.