Publications by authors named "Back Kim"
Article Synopsis
- Preoperative templating for total knee arthroplasty (TKA) is crucial for surgical preparation, but it currently lacks automation; this study developed an AI model to automate the prediction of implant sizes.
- The model was trained on over 13,000 knee radiographs and combines predictions from both anteroposterior and lateral views, validating results against actual TKA outcomes to assess accuracy.
- Results showed the AI model achieved an exact prediction rate of 39.5% for femoral components and 43.2% for tibial components, with an overall accuracy of 88.9% when allowing for a one-size margin of error; this indicates the model is reliable and could speed up the templating process for surgeons.
Objective: Delirium is commonly reported from the inpatients with Coronavirus disease 2019 (COVID-19) infection. As delirium is closely associated with adverse clinical outcomes, prediction and prevention of delirium is critical. We developed a machine learning (ML) model to predict delirium in hospitalized patients with COVID-19 and to identify modifiable factors to prevent delirium.
View Article and Find Full Text PDF: The number of patients who undergo multiple operations on a knee is increasing. The objective of this study was to develop a deep learning algorithm that could detect 17 different surgical implants on plain knee radiographs. : An internal dataset consisted of 5206 plain knee antero-posterior X-rays from a single, tertiary institute for model development.
View Article and Find Full Text PDF