Endoscopic ultrasound artificial intelligence-assisted for prediction of gastrointestinal stromal tumors diagnosis: A systematic review and meta-analysis

Abstract

BACKGROUND Subepithelial lesions (SELs) are gastrointestinal tumors with heterogeneous malignant potential. Endoscopic ultrasonography (EUS) is the leading method for evaluation, but without histopathological analysis, precise differentiation of SEL risk is limited. Artificial intelligence (AI) is a promising aid for the diagnosis of gastrointestinal lesions in the absence of histopathology. AIM To determine the diagnostic accuracy of AI-assisted EUS in diagnosing SELs, especially lesions originating from the muscularis propria layer. METHODS Electronic databases including PubMed, EMBASE, and Cochrane Library were searched. Patients of any sex and > 18 years, with SELs assessed by EUS AI-assisted, with previous histopathological diagnosis, and presented sufficient data values which were extracted to construct a 2 × 2 table. The reference standard was histopathology. The primary outcome was the accuracy of AI for gastrointestinal stromal tumor (GIST). Secondary outcomes were AI-assisted EUS diagnosis for GIST vs gastrointestinal leiomyoma (GIL), the diagnostic performance of experienced endoscopists for GIST, and GIST vs GIL. Pooled sensitivity, specificity, positive, and negative predictive values were calculated. The corresponding summary receiver operating characteristic curve and post-test probability were also analyzed. RESULTS Eight retrospective studies with a total of 2355 patients and 44154 images were included in this meta-analysis. The AI-assisted EUS for GIST diagnosis showed a sensitivity of 92% [95% confidence interval (CI): 0.89-0.95; P < 0.01), specificity of 80% (95%CI: 0.75-0.85; P < 0.01), and area under the curve (AUC) of 0.949. For diagnosis of GIST vs GIL by AI-assisted EUS, specificity was 90% (95%CI: 0.88-0.95; P = 0.02) and AUC of 0.966. The experienced endoscopists’ values were sensitivity of 72% (95%CI: 0.67-0.76; P < 0.01), specificity of 70% (95%CI: 0.64-0.76; P < 0.01), and AUC of 0.777 for GIST. Evaluating GIST vs GIL, the experts achieved a sensitivity of 73% (95%CI: 0.65-0.80; P < 0.01) and an AUC of 0.819. CONCLUSION AI-assisted EUS has high diagnostic accuracy for fourth-layer SELs, especially for GIST, demonstrating superiority compared to experienced endoscopists’ and improving their diagnostic performance in the absence of invasive procedures.

Diagnostic Accuracy of Artificial Intelligence in Endoscopy: Umbrella Review

“…These included 10 studies pertaining to upper gastrointestinal endoscopy[ 9 , 18-26 ], 5 studies focusing on colonoscopy [ 27-31 ], and 4 studies on capsule endoscopy [ 32-35 ]. Additionally, there was 1 study about endoscopic ultrasound (EUS) and 1 study about laryngoscopy [ 36 37 ]. Detail can be seen in Figure 1 .…”

Artificial Intelligence-Based Diagnosis of Gastric Mesenchymal Tumors Using Digital Endosonography Image Analysis

“…In a recent meta-analysis involving eight retrospective studies including 2,355 patients, AI-assisted EUS models demonstrated a sensitivity of 92% (95% CI, 89-95%), specificity of 80% (95% CI, 75-85%), and AUC value of 0.949 for diagnosing GISTs [16]. However, experienced endoscopists demonstrated a sensitivity of 72% (95% CI, 67-76%), specificity of 70% (95% CI, 64-76%), and AUC value of 0.777 for diagnosing GISTs.…”

“…Consequently, EUS is regarded as the most valuable diagnostic tool for evaluating gastric SETs. However, the diagnosis of SETs by EUS is operator-dependent; thus, interobserver variability and sometimes intraobserver variability are major limitations [12][13][14][15][16]. Accordingly, tissue acquisition using EUS guide, such as EUS-guided fine-needle aspiration (EUS-FNA) and EUS-guided fine-needle biopsy (EUS-FNB), is employed to establish a definitive histopathological diagnosis in patients with SETs.…”

“…AI-assisted EUS diagnostic tools have been introduced in gastric SETs to overcome the limitations of the current diagnostic modalities [18,28]. They have demonstrated excellent diagnostic performance in diagnosing GI SETs in a recent meta-analysis [16]. However, the current AI-assisted EUS diagnostic tools also have limitations.…”