The study compares the diagnostic performance of deep learning (DL) with that of the former radiologist reading of the Kellgren–Lawrence (KL) grade and evaluates whether additional patient data can improve the diagnostic performance of DL. From March 2003 to February 2017, 3000 patients with 4366 knee AP radiographs were randomly selected. DL was trained using knee images and clinical information in two stages. In the first stage, DL was trained only with images and then in the second stage, it was trained with image data and clinical information. In the test set of image data, the areas under the receiver operating characteristic curve (AUC)s of the DL algorithm in diagnosing KL 0 to KL 4 were 0.91 (95% confidence interval (CI), 0.88–0.95), 0.80 (95% CI, 0.76–0.84), 0.69 (95% CI, 0.64–0.73), 0.86 (95% CI, 0.83–0.89), and 0.96 (95% CI, 0.94–0.98), respectively. In the test set with image data and additional patient information, the AUCs of the DL algorithm in diagnosing KL 0 to KL 4 were 0.97 (95% confidence interval (CI), 0.71–0.74), 0.85 (95% CI, 0.80–0.86), 0.75 (95% CI, 0.66–0.73), 0.86 (95% CI, 0.79–0.85), and 0.95 (95% CI, 0.91–0.97), respectively. The diagnostic performance of image data with additional patient information showed a statistically significantly higher AUC than image data alone in diagnosing KL 0, 1, and 2 (p-values were 0.008, 0.020, and 0.027, respectively).The diagnostic performance of DL was comparable to that of the former radiologist reading of the knee osteoarthritis KL grade. Additional patient information improved DL diagnosis in interpreting early knee osteoarthritis.

Lee KW, et al. Clin Orthop Surg. 2021 May;13:e50. https://doi.org/10.4055/cios20284

Background: The aims of this study were to evaluate the effects of correcting lower limb alignment by total knee arthroplasty (TKA) on the spinopelvic alignment and to identify patients with difference in the knee joint between clinically measured passive motion and the actual standing posture. Methods: In this retrospective study, 101 patients who underwent TKA and whose serial whole-body EOS X-ray were available were included. The relationship of the knee and spinopelvic alignment was analyzed by evaluating the parameters of standing anterior-posterior and lateral whole-body EOS X-ray. The differences between postoperative passive motion and weight-bearing posture in the knee joint were assessed in both coronal and sagittal planes. Furthermore, the causes of such differences were analyzed. Results: Significant correlations between Δpelvic obliquity and coronal ΔHip-Knee-Ankle (HKA)_Rt-Lt angle between the preoperative and 3-month and 1-year postoperative data (p < 0.001 and p < 0.005, respectively) and improved with coronal lower limb alignment close to neutral resulted in decreased pelvic obliquity (p < 0.001, ß = 0.085 and p = 0.005, ß = 0.065, respectively) were observed. The correlations between Δpelvic tilt (PT) and Δsacral slope (SS) and sagittal ΔHKA_Rt-Lt angle were statistically significant (PT: p < 0.001 and p < 0.045; SS: p = 0.002 and p < 0.001, respectively). The improved sagittal alignment close to neutral resulted in decreased PT and increased SS. The difference between postoperative passive motion and the weight-bearing posture of the knee joint was correlated with lumbar lordosis and sagittal C7 plumb line-sacrum distance (p = 0.042 and p < 0.001, respectively). Conclusions: The correction of lower limb alignment with TKA affected pelvic parameters dominantly; however, there was little effect on the spinal alignment. Additionally, patients with anterior stooping or lumbar flat back demonstrated difference in extension between passive knee motion and standing. Therefore, rather than only focusing on changes in the knee alignment correction, knee surgeons should also evaluate the spinopelvic alignment before surgery to consider the prognosis of the standing and predict the possible changes in the whole-body alignment. This preoperative assessment may improve the prognosis of TKA.

Meniscal tear is a common reason for patients to undergo knee operation, and the medial meniscus posterior root tear (MMPRT) is one of the most frequent kinds of meniscal tears. The purpose of this study was to analyze participants’ factors (anthropometric and medical) to the fate of the MMPRT based on the treatment strategy. The hypothesis of this study was that treatment modalities from conservative treatment to final arthroplasty would be affected by participants’ affecting factors. From July 2003 to May 2018, 640 participants were included. Groups were categorized according to the treatment strategies such as conservative treatment, arthroscopic surgery, high tibial osteotomy (HTO) and arthroplasty surgery. Participants’ affecting factors were analyzed by one-way analysis of variance according to the four different treatment strategies and a correlation between affecting factors was also analyzed. Participants with K-L (Kellgren–Lawrence) Grade 4 and high BMI > 28.17 were appropriate candidates for arthroplasty, with K-L Grade 4 being a greater determining factor than high BMI. Participants with alignment factors such as low initial weight bearing line (WBL) (26.5%) and high delta WBL ratio (5.9%) were appropriate candidates for HTO, with the delta WBL ratio being a greater determining factor than initial WBL. Longer MRI-event times (1.44 year) and a lesser extent of meniscal extrusion (2.98 mm) were significantly associated with conservative treatment. Understanding the correlation of each affecting factor to the treatment strategy will help clinicians decide on the appropriate treatment for patients with MMPRT.

The purposes of this study were (1) to evaluate the relationship between lumbosacral flexibility and the effects of total knee arthroplasty (TKA) on whole-body alignment; and (2) to determine the prerequisites of the adjacent joints for successful TKA. A total of 116 patients (156 cases) who had whole-body X-ray and flexion-extension lumbar radiograph available were enrolled. For the sagittal alignment evaluation, hip–knee–ankle (HKA) angle, pelvic tilt (PT), sacral slope (SS), lumbar lordosis (LL), thoracic kyphosis (TK), and C7 plumb line-sacrum distance (SVA) were evaluated on the whole-body radiographs. Lumbar flexibility (LF) was evaluated using the flexion-extension lumbar radiographs, and pelvic flexibility (PF) was evaluated using the pelvic incidence (PI). The disparities in the knee joint between postoperative passive motion and weight-bearing posture were assessed. LF was significantly correlated with ΔLL and ΔSVA (LL: p = 0.039, SVA: p = 0.040; Pearson correlation coefficient (PCC): −0.206 and 0.205, respectively). There were correlations between PF and ΔSS (p < 0.001, PCC: −0.362), and between the disparity and LF (p = 0.005, PCC = −0.275). Linear regression analysis demonstrated that LF was significantly associated with the presence of disparity (p = 0.005, β = −0.205). LF is an important factor for improved spinal and lower limb alignment after TKA. Additionally, reduced LF may result in knee joint disparity between passive extension and standing extension status. Therefore, surgeons should consider spinopelvic alignment, including lower limb alignment preoperatively, to be able to predict possible changes in whole-body alignment following TKA.

This study aimed to validate the accuracy and prediction performance of machine learning (ML), deep learning (DL), and logistic regression methods in the treatment of medial meniscus posterior root tears (MMPRT). From July 2003 to May 2018, 640 patients diagnosed with MMPRT were included. First, the affecting factors for the surgery were evaluated using statistical analysis. Second, AI technology was introduced using X-ray and MRI. Finally, the accuracy and prediction performance were compared between ML&DL and logistic regression methods. Affecting factors of the logistic regression method corresponded well with the feature importance of the six top-ranked factors in the ML&DL method. There was no significant difference when comparing the accuracy, F1-score, and error rate between ML&DL and logistic regression methods (accuracy = 0.89 and 0.91, F1 score = 0.89 and 0.90, error rate = 0.11 and 0.09; p = 0.114, 0.422, and 0.119, respectively). The area under the curve (AUC) values showed excellent test quality for both ML&DL and logistic regression methods (AUC = 0.97 and 0.94, respectively) in the evaluation of prediction performance (p = 0.289). The affecting factors of the logistic regression method and the influence of the ML&DL method were not significantly different. The accuracy and performance of the ML&DL method in predicting the fate of MMPRT were comparable to those of the logistic regression method. Therefore, this ML&DL algorithm could potentially predict the outcome of the MMRPT in various fields and situations. Furthermore, our method could be efficiently implemented in current clinical practice.