Diagnostic test accuracy of machine learning algorithms for the detection intracranial hemorrhage: a systematic review and meta-analysis study

• Published in: Biomedical engineering online Vol. 22; no. 1; pp. 114 - 23
• Main Authors: Maghami, Masoud, Sattari, Shahab Aldin, Tahmasbi, Marziyeh, Panahi, Pegah, Mozafari, Javad, Shirbandi, Kiarash
• Format: Journal Article
• Language: English
• Published: London BioMed Central 04.12.2023; BioMed Central Ltd; Springer Nature B.V; BMC
• Subjects: Accuracy; Algorithms; Artificial intelligence; Biomaterials; Biomedical Engineering and Bioengineering; Biomedical Engineering/Biotechnology; Biotechnology; Brain; Brain diseases; Cerebrovascular disorders; Computed tomography; Computer-aided medical diagnosis; CT imaging; Deep learning; Diagnostic imaging; Diagnostic systems; Diagnostic tests; Diagnostic Tests, Routine; Differential thermal analysis; Digital libraries; Digital systems; Engineering; Hemorrhage; Humans; Intracranial hemorrhages; Ischemia; Learning algorithms; Libraries; Machine Learning; Medical imaging equipment; Medical research; Medical tests; Medicine, Experimental; Meta-analysis; Methods; Neural networks; Older people; Prospective Studies; Retrospective Studies; Review; Sensitivity analysis; Sensitivity and Specificity; Stroke; Support vector machines; Systematic review; Iran; Deep learning; Cerebrovascular disorders; Intracranial hemorrhages; Machine learning; Artificial intelligence; Brain diseases; Meta-analysis
• ISSN: 1475-925X; 1475-925X
• DOI: 10.1186/s12938-023-01172-1

Background This systematic review and meta-analysis were conducted to objectively evaluate the evidence of machine learning (ML) in the patient diagnosis of Intracranial Hemorrhage (ICH) on computed tomography (CT) scans. Methods Until May 2023, systematic searches were conducted in ISI Web of Science, PubMed, Scopus, Cochrane Library, IEEE Xplore Digital Library, CINAHL, Science Direct, PROSPERO, and EMBASE for studies that evaluated the diagnostic precision of ML model-assisted ICH detection. Patients with and without ICH as the target condition who were receiving CT-Scan were eligible for the research, which used ML algorithms based on radiologists' reports as the gold reference standard. For meta-analysis, pooled sensitivities, specificities, and a summary receiver operating characteristics curve (SROC) were used. Results At last, after screening the title, abstract, and full paper, twenty-six retrospective and three prospective, and two retrospective/prospective studies were included. The overall (Diagnostic Test Accuracy) DTA of retrospective studies with a pooled sensitivity was 0.917 (95% CI 0.88–0.943, I 2  = 99%). The pooled specificity was 0.945 (95% CI 0.918–0.964, I 2  = 100%). The pooled diagnostic odds ratio (DOR) was 219.47 (95% CI 104.78–459.66, I 2  = 100%). These results were significant for the specificity of the different network architecture models ( p -value = 0.0289). However, the results for sensitivity ( p -value = 0.6417) and DOR ( p -value = 0.2187) were not significant. The ResNet algorithm has higher pooled specificity than other algorithms with 0.935 (95% CI 0.854–0.973, I 2  = 93%). Conclusion This meta-analysis on DTA of ML algorithms for detecting ICH by assessing non-contrast CT-Scans shows the ML has an acceptable performance in diagnosing ICH. Using ResNet in ICH detection remains promising prediction was improved via training in an Architecture Learning Network (ALN).