Frailty is one of the most important geriatric syndromes, which can be associated with increased risk for incident disability and hospitalization. Developing a real-time classification model of elderly frailty level could be beneficial for designing a clinical predictive assessment tool. Hence, the objective of this study was to predict the elderly frailty level utilizing the machine learning approach on skeleton data acquired from a Kinect sensor. Seven hundred and eighty-seven community elderly were recruited in this study. The Kinect data were acquired from the elderly performing different functional assessment exercises including: (1) 30-s arm curl; (2) 30-s chair sit-to-stand; (3) 2-min step; and (4) gait analysis tests. The proposed methodology was successfully validated by gender classification with accuracies up to 84 percent. Regarding frailty level evaluation and prediction, the results indicated that support vector classifier (SVC) and multi-layer perceptron (MLP) are the most successful estimators in prediction of the Fried’s frailty level with median accuracies up to 97.5 percent. The high level of accuracy achieved with the proposed methodology indicates that ML modeling can identify the risk of frailty in elderly individuals based on evaluating the real-time skeletal movements using the Kinect sensor.
The locking compression plate (LCP) system has several advantages in fracture fixation combining angular stability with the use of locking screws with traditional fixation techniques. However, the system is complex and requiring careful attention to biomechanical principles and good surgical technique. Due to the set of complicate stresses and strains in the LCP system after implantation, the material, which is being used here, is deemed important. However, so far the materials have been limited to the stainless steel (SS) or titanium (Ti). This study was therefore aimed at investigate the biomechanical performance of the internal tibial locked plates at different material properties, including SS, Ti, carbon/polyether ether ketone (PEEK) composite, in treating medial tibial fracture using patient-specific finite element (FE) model of the human tibia. The carbon/PEEK composite materials were used at three different fiber plies configurations. Simulated loading was applied at 60:40 ratios on the medial:lateral aspect. The model was fixed distally in all degrees of freedom. The results revealed the highest stress (307.10 MPa) and the lowest strain (0.14%) at Ti LCP system. The carbon/PEEK LCP system at configuration I and III showed low stress (∼60 MPa) and high strain (0.70%), which are suitable points for designing of an internal LCP system. On the other hand, the highest value of stress in callus region was 4.78 MPa (Carbon PEEK/Configuration I) and the strain variations of callus region were between 1.46% and 3.82% among all materials. These results implied the advantage of carbon/PEEK composite materials in LCP system as they can tolerate higher strains at lower stresses.
1 November 2021 in Computer Methods and Programs in Biomedicine