Sensitivity and specificity of machine learning and deep learning algorithms in the diagnosis of thoracolumbar injuries resulting in vertebral fractures: A systematic review and meta-analysis

Hakija Bečulić; Emir Begagić; Amina Džidić-Krivić; Ragib Pugonja; Namira Softić; Binasa Bašić; Simon Balogun; Adem Nuhović; Emir Softić; Adnana Ljevaković; Haso Sefo; Sabina Šegalo; Rasim Skomorac; Mirza Pojskić

doi:10.1016/j.bas.2024.102809

Sensitivity and specificity of machine learning and deep learning algorithms in the diagnosis of thoracolumbar injuries resulting in vertebral fractures: A systematic review and meta-analysis

Brain Spine. 2024 Apr 17:4:102809. doi: 10.1016/j.bas.2024.102809. eCollection 2024.

Authors

Hakija Bečulić^{1

2}, Emir Begagić³, Amina Džidić-Krivić⁴, Ragib Pugonja², Namira Softić¹, Binasa Bašić⁵, Simon Balogun⁶, Adem Nuhović⁷, Emir Softić⁸, Adnana Ljevaković⁵, Haso Sefo⁹, Sabina Šegalo¹⁰, Rasim Skomorac^{2

11}, Mirza Pojskić¹²

Affiliations

¹ Department of Neurosurgery, Cantonal Hospital Zenica, Crkvice 67, 72000, Zenica, Bosnia and Herzegovina.
² Department of Anatomy, School of Medicine, University of Zenica, Travnička 1, 72000, Zenica, Bosnia and Herzegovina.
³ Department of General Medicine, School of Medicine, University of Zenica, Travnička 1, 72000, Zenica, Bosnia and Herzegovina.
⁴ Department of Neurology, Cantonal Hospital Zenica, Crkvice 67, 72000, Zenica, Bosnia and Herzegovina.
⁵ Department of Neurology, General Hospital Travnik, Kalibunar Bb, 72270, Travnik, Bosnia and Herzegovina.
⁶ Division of Neurosurgery, Department of Surgery, Obafemi Awolowo University Teaching Hospitals Complex, Ilesa Road PMB 5538, 220282, Ile-Ife, Nigeria.
⁷ Department of General Medicine, School of Medicine, University of Sarajevo, Univerzitetska 1, 71000, Sarajevo, Bosnia and Herzegovina.
⁸ Department of Patophysiology, School of Medicine, University of Zenica, Travnička 1, 72000, Zenica, Bosnia and Herzegovina.
⁹ Neurosurgery Clinic, University Clinical Center Sarajevo, Bolnička 25, 71000, Sarajevo, Bosnia and Herzegovina.
¹⁰ Department of Laboratory Technologies, Faculty of Health Siences, University of Sarajevo, Stjepana Tomića 1, 71000, Sarajevo, Bosnia and Herzegovina.
¹¹ Department of Surgery, School of Medicine, University of Zenica, Travnička 1, 72000, Zenica, Bosnia and Herzegovina.
¹² Department of Neurosurgery, University Hospital Marburg, Baldingerstr., 35033, Marburg, Germany.

Abstract

Introduction: Clinicians encounter challenges in promptly diagnosing thoracolumbar injuries (TLIs) and fractures (VFs), motivating the exploration of Artificial Intelligence (AI) and Machine Learning (ML) and Deep Learning (DL) technologies to enhance diagnostic capabilities. Despite varying evidence, the noteworthy transformative potential of AI in healthcare, leveraging insights from daily healthcare data, persists.

Research question: This review investigates the utilization of ML and DL in TLIs causing VFs.

Materials and methods: Employing Preferred Reporting Items for Systematic Reviews and Meta-Analyzes (PRISMA) methodology, a systematic review was conducted in PubMed and Scopus databases, identifying 793 studies. Seventeen were included in the systematic review, and 11 in the meta-analysis. Variables considered encompassed publication years, geographical location, study design, total participants (14,524), gender distribution, ML or DL methods, specific pathology, diagnostic modality, test analysis variables, validation details, and key study conclusions. Meta-analysis assessed specificity, sensitivity, and conducted hierarchical summary receiver operating characteristic curve (HSROC) analysis.

Results: Predominantly conducted in China (29.41%), the studies involved 14,524 participants. In the analysis, 11.76% (N = 2) focused on ML, while 88.24% (N = 15) were dedicated to deep DL. Meta-analysis revealed a sensitivity of 0.91 (95% CI = 0.86-0.95), consistent specificity of 0.90 (95% CI = 0.86-0.93), with a false positive rate of 0.097 (95% CI = 0.068-0.137).

Conclusion: The study underscores consistent specificity and sensitivity estimates, affirming the diagnostic test's robustness. However, the broader context of ML applications in TLIs emphasizes the critical need for standardization in methodologies to enhance clinical utility.

Keywords: Artificial intelligence; Deep learning; Machine learning; Thoracolumbar injuries; Vertebral fractures.

Publication types

Review