RESUMEN
BACKGROUND: Osteoporosis is a significant health problem in the skeletal system, associated with bone tissue changes and its strength. Machine Learning (ML), on the other hand, has been accompanied by improvements in recent years and has been in the spotlight. This study is designed to investigate the Diagnostic Test Accuracy (DTA) of ML to detect osteoporosis through the hip dual-energy X-ray absorptiometry (DXA) images. METHODS: The ISI Web of Science, PubMed, Scopus, Cochrane Library, IEEE Xplore Digital Library, CINAHL, Science Direct, PROSPERO, and EMBASE were systematically searched until June 2023 for studies that tested the diagnostic precision of ML model-assisted for predicting an osteoporosis diagnosis. RESULTS: The pooled sensitivity of univariate analysis of seven studies was 0.844 (95% CI 0.791 to 0.885, I2 = 94% for 7 studies). The pooled specificity of univariate analysis was 0.781 (95% CI 0.732 to 0.824, I2 = 98% for 7 studies). The pooled diagnostic odds ratio (DOR) was 18.91 (95% CI 14.22 to 25.14, I2 = 93% for 7 studies). The pooled mean positive likelihood ratio (LR+) and the negative likelihood ratio (LR-) were 3.7 and 0.22, respectively. Also, the summary receiver operating characteristics (sROC) of the bivariate model has an AUC of 0.878. CONCLUSION: Osteoporosis can be diagnosed by ML with acceptable accuracy, and hip fracture prediction was improved via training in an Architecture Learning Network (ALN).
Asunto(s)
Fracturas de Cadera , Osteoporosis , Huesos Pélvicos , Humanos , Osteoporosis/diagnóstico por imagen , Algoritmos , Aprendizaje AutomáticoRESUMEN
ABSTRACT: Functional 1H magnetic resonance spectroscopy (fMRS) is a derivative of dynamic MRS imaging. This modality links physiologic metabolic responses with available activity and measures absolute or relative concentrations of various metabolites. According to clinical evidence, the mitochondrial glycolysis pathway is disrupted in many nervous system disorders, especially Alzheimer disease, resulting in the activation of anaerobic glycolysis and an increased rate of lactate production. Our study evaluates fMRS with J-editing as a cutting-edge technique to detect lactate in Alzheimer disease. In this modality, functional activation is highlighted by signal subtractions of lipids and macromolecules, which yields a much higher signal-to-noise ratio and enables better detection of trace levels of lactate compared with other modalities. However, until now, clinical evidence is not conclusive regarding the widespread use of this diagnostic method. The complex machinery of cellular and noncellular modulators in lactate metabolism has obscured the potential roles fMRS imaging can have in dementia diagnosis. Recent developments in MRI imaging such as the advent of 7 Tesla machines and new image reconstruction methods, coupled with a renewed interest in the molecular and cellular basis of Alzheimer disease, have reinvigorated the drive to establish new clinical options for the early detection of Alzheimer disease. Based on the latter, lactate has the potential to be investigated as a novel diagnostic and prognostic marker for Alzheimer disease.