The surgical installation accuracy of the components in unicompartmental knee arthroplasty (UKA) is an important factor affecting the joint function and the implant life. Taking the ratio of the medial-lateral position of the femoral component relative to the tibial insert (a/A) as a parameter, and considering nine installation conditions of the femoral component, this study established the musculoskeletal multibody dynamics models of UKA to simulate the patients’ walking gait, and investigated the influences of the medial-lateral installation positions of the femoral component in UKA on the contact force, joint motion and ligament force of the knee joint. The results showed that, with the increase of a/A ratio, the medial contact force of the UKA implant was decreased and the lateral contact force of the cartilage was increased; the varus rotation, external rotation and posterior translation of the knee joint were increased; and the anterior cruciate ligament force, posterior cruciate ligament force and medial collateral ligament force were decreased. The medial-lateral installation positions of the femoral component in UKA had little effect on knee flexion-extension movement and lateral collateral ligament force. When the a/A ratio was less than or equalled to 0.375, the femoral component collided with the tibia. In order to prevent the overload on the medial implant and lateral cartilage, the excessive ligament force, and the collision between the femoral component and the tibia, it is suggested that the a/A ratio should be controlled within the range of 0.427−0.688 when the femoral component is installed in UKA. This study provides a reference for the accurate installation of the femoral component in UKA.
Objective To construct large medical model named by "Huaxi HongYi"and explore its application effectiveness in assisting medical record generation. Methods By the way of a full-chain medical large model construction paradigm of "data annotation - model training - scenario incubation", through strategies such as multimodal data fusion, domain adaptation training, and localization of hardware adaptation, "Huaxi HongYi" with 72 billion parameters was constructed. Combined with technologies such as speech recognition, knowledge graphs, and reinforcement learning, an application system for assisting in the generation of medical records was developed. ResultsTaking the assisted generation of discharge records as an example, in the pilot department, after using the application system, the average completion times of writing a medical records shortened (21 min vs. 5 min) with efficiency increased by 3.2 time, the accuracy rate of the model output reached 92.4%. Conclusion It is feasible for medical institutions to build independently controllable medical large models and incubate various applications based on these models, providing a reference pathway for artificial intelligence development in similar institutions.