Colorectal cancer (CRC) is a significant global health issue where early detection is crucial for improving treatment outcomes and survival rates. This comprehensive review assesses the utility of stool-based tests in CRC screening, including traditional fecal occult blood tests (FOBT), both chemical (gFOBT) and immunochemical techniques (FIT), as well as multitarget stool DNA (mt-sDNA) as a novel and promising biomarker. The advancements, limitations and the impact of false positives and negatives of these methods are examined. The review analyzed various studies on current screening methods, focusing on laboratory tests and biomarkers. Findings indicate that while FIT and mt-sDNA tests offer enhanced sensitivity and specificity over traditional guaiac-based FOBT, they also come with higher costs and potential for increased false positives. FIT shows better patient adherence due to its ease to use, but incorrect usage and interpretation of FOBT can lead to significant diagnostic errors. In conclusion, despite the improvements in FOBT methods like FIT in CRC detection, careful consideration of each method’s benefits and drawbacks is essential. Effective CRC screening programs should combine various methods tailored to specific population needs, aiming for early detection and reduced mortality rates.

Cholecystectomy and Metabolic-associated steatotic liver disease (MASLD) are prevalent conditions in gastroenterology, frequently co-occurring in clinical practice. Cholecystectomy has been shown to have metabolic consequences, sharing similar pathological mechanisms with MASLD. A database of MASLD patients who underwent cholecystectomy was analysed. This study aimed to develop a tool to identify the risk of liver fibrosis after cholecystectomy. For this purpose, the extreme gradient boosting (XGB) algorithm was used to construct an effective predictive model. The factors associated with a better predictive method were platelet level, followed by dyslipidaemia and type-2 diabetes (T2DM). Compared to other ML methods, our proposed method, XGB, achieved higher accuracy values. The XGB method had the highest balanced accuracy (93.16%). XGB outperformed KNN in accuracy (93.16% vs. 84.45%) and AUC (0.92 vs. 0.84). These results demonstrate that the proposed XGB method can be used as an automatic diagnostic aid for MASLD patients based on machine-learning techniques.

Acute diverticulitis (AD) is a common gastrointestinal condition that has seen a significant rise in incidence and prevalence, largely due to the aging population and the increasing prevalence of obesity. Historically, routine colonoscopy was recommended after every episode of AD, but recent studies and meta-analyses have questioned this practice. Evidence now supports a more selective approach, suggesting that colonoscopy should only be performed in patients with complicated AD, persistent alarm symptoms (abdominal pain, weight loss, altered bowel habits, blood in stool, or iron-deficiency anemia), or imaging findings suggestive of neoplasia. For uncomplicated AD without alarm symptoms, routine colonoscopy is not justified, as it may lead to unnecessary complications and overuse of healthcare resources. Current guidelines reflect this shift, recommending individualized decision-making based on the patient’s clinical history and risk factors. Emerging non-invasive diagnostic tools, such as fecal immunochemical tests (FIT) and artificial intelligence (AI)-based models, hold promise for improving risk stratification and potentially reducing the need for invasive procedures. This narrative review, based on a structured literature search, synthesizes the evolution of post-AD colonoscopy recommendations, presents current evidence, and highlights future research directions on alternative diagnostic methods and their potential to optimize patient care and clinical decision-making.