Machine Learning for Vestibular Schwannoma Diagnosis Using Audiometrie Data Alone.

OBJECTIVE: The aim of this study is to compare machine learning algorithms and established rule-based evaluations in screening audiograms for the purpose of diagnosing vestibular schwannomas. A secondary aim is to assess the performance of rule-based evaluations for predicting vestibular schwannomas using the largest dataset in the literature. STUDY DESIGN: Retrospective case-control study. SETTING: Tertiary referral center. PATIENTS: Seven hundred sixty seven adult patients with confirmed vestibular schwannoma and a pretreatment audiogram on file and 2000 randomly selected adult controls with audiograms. INTERVENTIONS: Audiometric data were analyzed using machine learning algorithms and standard rule-based criteria for defining asymmetric hearing loss. MAIN OUTCOME MEASURES: The primary outcome is the ability to identify patients with vestibular schwannomas based on audiometric data alone, using machine learning algorithms and rule-based formulas. The secondary outcome is the application of conventional rule-based formulas to a larger dataset using advanced computational techniques. RESULTS: The machine learning algorithms had mildly improved specificity in some fields compared with rule-based evaluations and had similar sensitivity to previous rule-based evaluations in diagnosis of vestibular schwannomas. CONCLUSIONS: Machine learning algorithms perform similarly to rule-based evaluations in identifying patients with vestibular schwannomas based on audiometric data alone. Performance of established rule-based formulas was consistent with earlier performance metrics, when analyzed using a large dataset.

On the heterogeneity of the femoral enthesis of the human ACL: microscopic anatomy and clinical implications.

BACKGROUND: Most ruptures of the native anterior cruciate ligament (ACL) and ACL graft occur at, or near, the femoral enthesis, with the posterolateral fibers of the native ligament being especially vulnerable during pivot landings. Characterizing the anatomy of the ACL femoral enthesis may help us explain injury patterns which, in turn, could help guide injury prevention efforts. It may also lead to improved anatomic reconstruction techniques given that the goal of such techniques is to replicate the knee's normal anatomy. Hence, the aim of this study was to investigate the microscopic anatomy of the ACL femoral enthesis and determine whether regional differences exist. METHODS: Fifteen human ACL femoral entheses were histochemically processed and sectioned along the longitudinal axis of the ACL at 20, 40, 60, and 80 % of the width of the enthesis. Four thick sections (100 µm) per enthesis were prepared, stained, and digitized. From these sections, regional variations in the quantity of calcified and uncalcified fibrocartilage, the angle at which the ligament originates from the bone, and the shape profile of the tidemark were quantified. RESULTS: At least 33 % more calcified fibrocartilage and 143 % more uncalcified fibrocartilage were found in the antero-inferior region, which corresponds to the inferior margin of the origin of the anteromedial ACL fibers, than all other regions (Ps < 0.05). In addition, the anteromedial fibers of the ACL originated from the femur at an angle six times greater than did its posterolateral fibers (P = 0.032). Finally, average entheseal tidemark profiles correlated bilaterally (Pearson's r = 0.79; P = 0.036), the most common profile being convex with a single re-entrant. CONCLUSIONS: Systematic regional differences were found in fibrocartilage quantity and collagen fiber attachment angles. The marked differences may reflect differences in the loading history of the various regions of the ACL femoral enthesis. These differences, which could affect the potential for injury, should also be considered when developing new ACL reconstruction approaches.

Quantitative comparison of the microscopic anatomy of the human ACL femoral and tibial entheses.

The femoral enthesis of the human anterior cruciate ligament (ACL) is known to be more susceptible to injury than the tibial enthesis. To determine whether anatomic differences might help explain this difference, we quantified the microscopic appearance of both entheses in 15 unembalmed knee specimens using light microscopy, toluidine blue stain and image analysis. The amount of calcified fibrocartilage and uncalcified fibrocartilage, and the ligament entheseal attachment angle were then compared between the femoral and tibial entheses via linear mixed-effects models. The results showed marked differences in anatomy between the two entheses. The femoral enthesis exhibited a 3.9-fold more acute ligament attachment angle than the tibial enthesis (p<0.001), a 43% greater calcified fibrocartilage tissue area (p<0.001), and a 226% greater uncalcified fibrocartilage depth (p<0.001), with the latter differences being particularly pronounced in the central region. We conclude that the ACL femoral enthesis has more fibrocartilage and a more acute ligament attachment angle than the tibial enthesis, which provides insight into why it is more vulnerable to failure.