Development and validation of a new nomogram for self-reported OA based on machine learning: a cross-sectional study

Figures

• 

  Fig. 1. Flow chart of sample selection.

• 

  Fig. 2. Selection of main predictors of OA. (A) Selection of the tuning parameter lambda in the LASSO regression via 10-fold cross-validation based on minimum criteria. Misclassification error from the LASSO regression cross-validation procedure was plotted as a function of log lambda. The y-axis indicates the misclassification error. The x-axis indicates the log lambda. (B) The LASSO coefficient profiles of clinical features. The dotted vertical line was plotted at the value selected using 10-fold cross-validation in A. The resulting variables with non-zero coefficients are indicated in the plot. (C) Importance ranking of 7 variables by LASSO regression. (D) Importance ranking of 15 variables via 10-fold cross-validation and assessment of feature importance by XGBoost algorithm. (E) Selection of variables by RF algorithm. Mean decrease accuracy and mean decrease gini from the RF algorithm cross-validation procedure was plotted. (F) Importance ranking of 15 variables via assessment of feature importance by RF algorithm. (G) Intersection of variables obtained from the three algorithms, and come out with 5 main predictors of OA.

• 

  Fig. 3. The nomogram represents the predicted probability of OA on a scale of 0 to 200. For each predictor, draw a vertical line straight up to the point axis and note the corresponding points. Sum the points from each predictor, and the total score corresponding to a predicted probability of OA can be found at the bottom of the nomogram.

• 

  Fig. 4. The performance of the new nomogram for predicting OA. A ROC curve in the training cohort. The x-axis is 1-Specifcity; the y-axis is the Sensitivity. B Calibration curve in the training cohort. The x-axis is the nomogram predicted probability of OA; the y-axis is actual probability. C ROC curve in the validation cohort. D Calibration curve in the validation cohort.

• 

  Fig. 5. The clinical utility of the nomogram was evaluated by DCA. A Decision curve in the training cohort. B Decision curve in the validation cohort. The x-axis represents the threshold probability. The y-axis represents net benefits.