METHODS: This study reviews the use of DL for Anterior Cruciate Ligament (ACL) tear diagnosis. A comprehensive search was performed in PubMed, Embase, and Web of Science databases from 2018 to 2024. The included study criteria used MRI images to evaluate ACL tears, and the diagnosis of ACL tears was performed using the DL model. We summarized the paper by reporting their model accuracy, model comparison with arthroscopy, and explainable.
RESULTS: AI implementation in tabular format; we conclude that many medical professionals believe that arthroscopic diagnosis is the most reliable method for diagnosing ACL tears. However, due to its intrusive treatment, CAD is projected to be able to produce similar outcomes from MRI scan results. To gain the trust of physicians and meet the demand for reliable knee injury detection systems, an algorithm for CAD should also meet several criteria, such as being transparent, interpretable, explainable, and easy to use. Therefore, future works should consider creating an Explainable DL model for ACL tear diagnosis. It is also essential to evaluate the performance of this Explainable DL model compared to the gold standard of arthroscopy diagnosis.
CONCLUSION: There are issues regarding the need for Explainable DL in CAD to increase confidence in its result while also highlighting the importance of the involvement of medical practitioners in system design. There is no funding for this work.
MATERIALS AND METHODS: A retrospective study was carried out on 318 subjects with hypochromic anaemia, which comprised 162 IDA and 156 thalassaemia trait subjects with α-thalassemia, β-thalassemia and HbE trait. Optimal cut-off value, sensitivity and specificity of M/H ratio for thalassaemia trait discrimination was determined using Receiver Operating Characteristic (ROC) analysis.
RESULTS: Subjects with thalassaemia trait showed higher MicroR compared to IDA ( p< 0.001) while subjects with IDA demonstrated higher Hypo-He than thalassaemia trait (p < 0.001). M/H ratio was significantly higher in thalassaemia trait compared to IDA, with medians of 3.77 (interquartile range: 2.57 - 6.52) and 1.73 (interquartile range: 1.27 - 2.38), respectively (p < 0.001). M/H ratio ≥ 2.25 was the optimal cut-off value for discriminating thalassaemia trait from IDA in hypochromic anaemia, with the area under ROC curve (AUC) of 0.83, sensitivity of 80.8% and specificity of 71.6%.
CONCLUSIONS: M/H ratio is a useful discriminant index to distinguish thalassaemia trait from IDA in hypochromic anaemia prior to diagnostic analysis for thalassaemia confirmation. High M/H ratio is suggestive of thalassaemia trait than of IDA. However, more studies are required to establish the role of M/H ratio as a screening tool for thalassaemia discrimination in hypochromic anaemia.