Jiang Lei, Liu Shankai, Kong Hongyang
Department of Orthopedics, The Affiliated Taizhou People's Hospital of Nanjing Medical University, Taizhou, CHN.
Department of Interventional Radiology, The Affiliated Taizhou People's Hospital of Nanjing Medical University, Taizhou, CHN.
Cureus. 2024 Nov 10;16(11):e73402. doi: 10.7759/cureus.73402. eCollection 2024 Nov.
Knee osteoarthritis (OA) is a widespread chronic degenerative condition that may experience slow or rapid deterioration. The gut-joint axis represents a bidirectional relationship in OA onset and progression. This study aimed to establish and validate a prediction model of knee OA disease progression.
This prospective cohort investigation involved 296 patients diagnosed with knee OA using X-ray and CT scans at Taizhou People's Hospital from January 2020 to January 2022. Fecal samples and general information were collected for gut microbiota analysis. Least absolute shrinkage and selection operator (LASSO) regression and various prediction models, including microbiome-augmented models, were employed for knee OA risk prediction. The models predicting Kellgren-Lawrence classification one year later were evaluated by accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and area under the curve (AUC).
A total of 270 patients were involved in our study. After random assignment, 214 patients belonged to the training set and 56 patients belonged to the test set. The final intestinal flora included in the analysis included the following 12 species. Shannon index of patients with a Grade I Kellgren-Lawrence Classification after one year was lower than those with a Grade II/III after one year (P=0.018). The best model was the microbiome-augmented model built by Light GBM (LGBM). The AUC of this model in the training set was 0.812 (0.754-0.870), the sensitivity was 0.804 (0.725-0.883), the specificity was 0.744 (0.664-0.823), the PPV was 0.722 (0.638-0.807), the NPV was 0.821 (0.748-0.894), and the accuracy was 0.771 (0.715-0.827). The AUC of this model in the testing set was 0.876 (0.781-0.972), the sensitivity was 0.759 (0.603-0.914), the specificity was 0.917 (0.806-1.000), the PPV was 0.917 (0.806-1.000), the NPV was 0.759 (0.603-0.914), and the accuracy was 0.830 (0.729-0.931). Conclusion: One year later, the microbiome-augmented model constructed by LGBM for knee OA patients based on general and gut microbiota data using the Kellgren-Lawrence classification demonstrated the highest performance. This approach could aid in identifying patients at risk of rapid disease progression, facilitating early intervention and personalized treatments. Furthermore, it offers a novel perspective on the gut-joint axis's role in OA.
膝关节骨关节炎（OA）是一种广泛存在的慢性退行性疾病，其病情可能缓慢或快速恶化。肠-关节轴在OA的发病和进展中呈现双向关系。本研究旨在建立并验证膝关节OA疾病进展的预测模型。
这项前瞻性队列研究纳入了2020年1月至2022年1月在泰州市人民医院通过X线和CT扫描诊断为膝关节OA的296例患者。收集粪便样本和一般信息用于肠道微生物群分析。采用最小绝对收缩和选择算子（LASSO）回归以及各种预测模型，包括微生物群增强模型，对膝关节OA风险进行预测。通过准确性、敏感性、特异性、阳性预测值（PPV）、阴性预测值（NPV）和曲线下面积（AUC）对预测一年后Kellgren-Lawrence分级的模型进行评估。
共有270例患者参与本研究。随机分配后，214例患者属于训练集，56例患者属于测试集。分析中最终纳入的肠道菌群包括以下12个物种。一年后Kellgren-Lawrence分级为I级的患者的香农指数低于一年后为II/III级的患者（P=0.018）。最佳模型是由Light GBM（LGBM）构建的微生物群增强模型。该模型在训练集中的AUC为0.812（0.754-0.870），敏感性为0.804（0.725-0.883），特异性为0.744（0.664-0.823），PPV为0.722（0.638-0.807），NPV为0.821（0.748-0.894），准确性为0.771（0.715-0.827）。该模型在测试集中的AUC为0.876（0.781-0.972），敏感性为0.759（0.603-0.914），特异性为0.917（0.806-1.000），PPV为0.917（0.806-1.000），NPV为0.759（0.603-0.914），准确性为0.830（0.729-0.931）。结论：一年后，基于一般和肠道微生物群数据，采用Kellgren-Lawrence分级法，由LGBM为膝关节OA患者构建的微生物群增强模型表现最佳。这种方法有助于识别疾病快速进展风险的患者，便于早期干预和个性化治疗。此外，它为肠-关节轴在OA中的作用提供了新的视角。
