Diagnostic accuracy of artificial intelligence for detecting gastrointestinal luminal pathologies: A systematic review and meta-analysis.

Background: Artificial Intelligence (AI) holds considerable promise for diagnostics in the field of gastroenterology. This systematic review and meta-analysis aims to assess the diagnostic accuracy of AI models compared with the gold standard of experts and histopathology for the diagnosis of various gastrointestinal (GI) luminal pathologies including polyps, neoplasms, and inflammatory bowel disease. Methods: We searched PubMed, CINAHL, Wiley Cochrane Library, and Web of Science electronic databases to identify studies assessing the diagnostic performance of AI models for GI luminal pathologies. We extracted binary diagnostic accuracy data and constructed contingency tables to derive the outcomes of interest: sensitivity and specificity. We performed a meta-analysis and hierarchical summary receiver operating characteristic curves (HSROC). The risk of bias was assessed using Quality Assessment for Diagnostic Accuracy Studies-2 (QUADAS-2) tool. Subgroup analyses were conducted based on the type of GI luminal disease, AI model, reference standard, and type of data used for analysis. This study is registered with PROSPERO (CRD42021288360). Findings: We included 73 studies, of which 31 were externally validated and provided sufficient information for inclusion in the meta-analysis. The overall sensitivity of AI for detecting GI luminal pathologies was 91.9% (95% CI: 89.0-94.1) and specificity was 91.7% (95% CI: 87.4-94.7). Deep learning models (sensitivity: 89.8%, specificity: 91.9%) and ensemble methods (sensitivity: 95.4%, specificity: 90.9%) were the most commonly used models in the included studies. Majority of studies (n = 56, 76.7%) had a high risk of selection bias while 74% (n = 54) studies were low risk on reference standard and 67% (n = 49) were low risk for flow and timing bias. Interpretation: The review suggests high sensitivity and specificity of AI models for the detection of GI luminal pathologies. There is a need for large, multi-center trials in both high income countries and low- and middle- income countries to assess the performance of these AI models in real clinical settings and its impact on diagnosis and prognosis. Systematic review registration: [https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=288360], identifier [CRD42021288360].

Malnutrition and liver disease in a developing country.

Malnutrition is a highly prevalent and under recognized condition in developing countries of South Asia. The presence of malnutrition causes a severe impact on patients with liver cirrhosis. The etiology of cirrhosis differs in the South Asian region compared to the West, with hepatitis B and C still being the leading causes and the prevalence of nonalcoholic fatty liver disease increasing over time. Comorbid malnutrition worsens outcomes for cirrhosis patients. Urgent attention to address malnutrition is needed to improve patient outcomes. The etiology and pathophysiology of malnutrition in liver diseases is multifactorial, as reduction in liver function affects both macronutrients and micronutrients. A need for nutritional status assessment for liver disease patients exists in all parts of the world. There are many widely studied tools in use to perform a thorough nutritional assessment, of which some tools are low cost and do not require extensive training. These tools can be studied and evaluated for use in the resource limited setting of a country like Pakistan. Treatment guidelines for proper nutrition maintenance in chronic liver disease exist for all parts of the world, but the knowledge and practice of nutritional counseling in Pakistan is poor, both amongst patients and physicians. Emphasis on assessment for nutritional status at the initial visit with recording of vital signs is needed. Simultaneously, treating physicians need to be made aware of the misconceptions surrounding nutritional restrictions in cirrhosis so that patient education is done correctly based on proper scientific evidence.

Infiltrative gallbladder tuberculosis versus locally infiltrating tumour of the gallbladder: a diagnostic dilemma unmasked by histopathology.

Gallbladder tuberculosis (TB) as an isolated infection and is an extremely rare entity even in parts of the world with endemicity. Though it has myriad ways of presentation, it can be cured successfully. We present a case of a 53-year-old man who presented with epigastric fullness and bloating with on and off low-grade fever for 2 months and significant weight loss. He underwent a CT scan, which showed a soft tissue gallbladder mass causing mural thickening of the antrum and lesser curvature. This was followed by a CT-guided core biopsy and gastric antrum biopsy via gastroscopy. Histopathology revealed chronic granulomatous inflammation in both samples. Various clinical presentations of gallbladder TB have been reported in literature, but to the best of our knowledge, the present case has a unique presentation and has never been reported before.