目的：通过IOL Master 700观察白内障手术前后Chang-Warning弦(CW弦)的变化，并利用术前数据和人工智能预测模型预测术后CW弦。

方法：研究对象为304例白内障患者，分析其术前及术后的IOL Master 700测量数据，包括散光矢量值、角膜平均曲率、眼轴长度、前房深度、晶状体厚度、角膜中央厚度、白到白距离、浦肯野反射Ⅰ像相对于角膜中心的位置和瞳孔中心的位置、CW弦等。研究建立了基于SVR算法和BP神经网络算法的预测模型，通过术前CW弦及眼部生物参数来预测术后CW弦。

结果：相比于白内障手术前，手术后左、右眼CW弦X分量向颞侧有轻微偏移，Y分量变化不大。使用术前CW弦和其他术前眼部生物参数作为输入数据，相比于BP神经网络，SVR模型能够更准确的对术后CW弦的X分量和Y分量做出预测。

结论：CW弦可以用各种生物测量仪器、角膜地形图仪器或断层摄像仪器在同轴固定光下直接测量。使用SVR算法能够在白内障手术前较精准的对术后CW弦进行预测。

METHODS: The analysis was conducted on the preoperative and postoperative IOL Master 700 measurements of 304 cataract patients. This included astigmatism vector value, average keratometry, axial length, anterior chamber depth, lens thickness, corneal central thickness, white-to-white, the position of the Purkinje reflex I image relative to the corneal center and pupil center, and the CW chord. A prediction model based on the SVR algorithm and the BP neural network algorithm was established to predict the postoperative CW chord using the preoperative CW chord and ocular biological parameters.

RESULTS: The X component of the CW chord showed a slight shift in the temporal direction in both the left and right eyes after cataract surgery, while the Y component changed little. The SVR model, using the preoperative CW chord and other preoperative biometric parameters as input data, was able to predict the X and Y components of the CW chord more accurately than the BP neural network.

CONCLUSION: The CW chord can be directly measured with a coaxial fixation light using various biometers, corneal topographers, or tomographers. The use of the SVR algorithm can accurately predict the postoperative CW chord before cataract surgery.