Objective: The early symptoms of knee osteoarthritis ( KOA) are not obvious. therefore there are a large number of patients with knee joint lesions thai have not been detected. In order to screen high-risk groups or earlystage patients with KOA on a large scale, this study established a quantitative prediction model for the risk of KOA through simple and easy-to-measure indicators. Methods: According to age and sex proportion. 1045 residents from two streets in Nanjing were sampled for KOA diagnosis and physical fitness tests. The test indicators included gender, age, height, weight, BMI, thigh circumference, 30-second sitting and standing, knee joint flexion, single-leg standing with eyes c·losed. and time-up-and-go test. In GeNle 2.3 software, a mathematical mo(le[ between KOA and the al,ove indicators was established through Bayesian network learning. The modeling sleps include data discretization, structural learning using mountain climbing algorithm and K2 algorithm, parameter learning using Expectation-Maximization algorithm, model verification and sensitivity analysis. Results: Univariate analysis showed that there were statistically significant differences between the groups of "no KOA" and "KOA" in the 10 indicators (P<0.01 ). The established mathematical model included 11 nodes und 19 directed line segments. Determining the slate of any one or more nodes can predict the probability of KOA disease. In the model. gender, BMI. body weight, 30-sec·ond sitting and standing, and knee joint ile>don were nodes that were directly related to KOA or had higher sensitivity. These indicators had high predictive value. lhe accuracy of the. model was 78.9%, and the area inider the ROC curve was 0.722. ConcluMion: This study has constructed a Bayesian network model for quantitalively predicting the risk of developing KOA, which exhibits good predictive performance and has advantages for widespread application. [ABSTRACT FROM AUTHOR]