Artificial Intelligence in the Diagnosis of Upper Gastrointestinal Diseases

Abstract

Artificial intelligence (AI) has enormous potential to support clinical routine workflows and therefore is gaining increasing popularity among medical professionals. In the field of gastroenterology, investigations on AI and computer-aided diagnosis (CAD) systems have mainly focused on the lower gastrointestinal (GI) tract. However, numerous CAD tools have been tested also in upper GI disorders showing encouraging results. The main application of AI in the upper GI tract is endoscopy; however, the need to analyze increasing loads of numerical and categorical data in short times has pushed researchers to investigate applications of AI systems in other upper GI settings, including gastroesophageal reflux disease, eosinophilic esophagitis, and motility disorders. AI and CAD systems will be increasingly incorporated into daily clinical practice in the coming years, thus at least basic notions will be soon required among physicians. For noninsiders, the working principles and potential of AI may be as fascinating as obscure. Accordingly, we reviewed systematic reviews, meta-analyses, randomized controlled trials, and original research articles regarding the performance of AI in the diagnosis of both malignant and benign esophageal and gastric diseases, also discussing essential characteristics of AI.

Global research trends of artificial intelligence applied in esophageal carcinoma: A bibliometric analysis (2000-2022) via CiteSpace and VOSviewer

“…Computer-aided diagnosis ( 79 ) and computer-aided therapy ( 80 ) have become the main application directions, and deep learning (#5) has emerged as the name of specific methods of artificial intelligence with the highest word frequency13.89 ( Figure 8D ). Specifically, deep learning plays a role in early detection ( 81 ), accurate differentiation of precancerous lesions from tumor lesions ( 82 ), determination of invasive tumor margins during surgical treatment ( 83 ), monitoring of disease progression and acquired drug resistance ( 84 ), and prediction of tumor aggressiveness ( 85 ), metastasis pattern ( 86 ) and recurrence risk ( 87 ). The innovation of esophageal imaging recognition and cancer marker screening technology provides the possibility for esophageal cancer detection, treatment and monitoring.…”

Clinical use of mean nocturnal baseline impedance and post-reflux swallow-induced peristaltic wave index for the diagnosis of gastro-esophageal reflux disease

“…Although the calculation of MNBI is reproducible and takes a few minutes [65,71], it currently needs to be performed manually. However, AI tools for automated calculation of novel MII-pH metric are being developed [72]. In this regard, Rogers et al developed an AI system which autonomously evaluated MII-pH tracings with an accuracy of 88.5% compared to human reviewers.…”

“…Additionally, the ratio of upright baseline impedance divided by the recumbent baseline impedance (U:R AIBI ratio) could segregate responders to treatment from controls and nonresponders regardless of treatment status upon MII-pH recording. The U:R AIBI ratio at 5 cm above the LES performed better than AET in predicting response to medical therapy in those with conclusively abnormal AET as per the Lyon Consensus [72,73]. Finally, MNBI is currently considered the most representative measure of baseline impedance [74] but novel techniques for the measurement of mucosal impedance have been recently proposed, including endoscopy ad hoc probes [75] and balloon catheter systems [76].…”

Applications of Artificial Intelligence to Eosinophilic Esophagitis

“…Artificial intelligence (AI) has been applied to many other diseases in gastroenterology and is well suited to revolutionize the management of EoE [11]. AI is a branch of computer science which tries to imitate the way humans learn and solve problems using large datasets.…”