A nomogram for one-year risk of death after hip fracture

Figures

• 

  FIGURE 1. Flowchart of data screening and analysis.

• 

  FIGURE 2. Hotspot plot for correlation analysis of all variables. The vertical coordinates on the right side of Figure 2 represent the correlation coefficients, values greater than 0 indicate a positive correlation and are shown in blue in the figure, values less than 0 indicate a negative correlation and are shown in red in the figure. The names of the variables on the diagonal indicate the rows and columns corresponding to the variable, the area above the diagonal shows the correlation between the two variables in dots, and the area below the diagonal shows the specific value of the correlation between the two variables. An absolute value of more than 0.4 for the correlation coefficient indicates a significant correlation.

• 

  FIGURE 3. The potential risk factors were selected using the LASSO regression. (a) Graph of cross-validation results. The vertical line on the left side represents λ min, and the vertical line on the right side represents λ 1se. λ min refers to the λ value corresponding to the minimum mean squared error (MSE) among all λ values; λ 1se refers to the λ value corresponding to the simplest and best model obtained after cross-validation within a square difference range of λ min. (b) Trend graph of variance filter coefficients. Each color curve represents a trend in variance coefficient change.

• 

  FIGURE 4. Nomogram and dynamic web calculator to predict 1-year mortality after hip fracture in older adults. CHD: 1 means the patient has CHD; 0 means none. Surgery: 1 means the patient underwent surgery; 0 means no surgery. HB: 1 means the patient is anemic; 0 means no anemia. AST, BUN: 1 means the patient’s test result exceeds the upper limit of normal value; 0 means the upper limit of normal value is not exceeded. (a) Nomogram to predict 1-year mortality after hip fracture in the elderly. According to the patient’s status of each item, the first row of “Points” is selected, and the cumulative score of the six rows is recorded as “Total Points,” and the corresponding “1-year mortality” value is selected to represent the 1-year risk of death after hip fracture. (b) Dynamic web calculator to predict 1-year mortality after hip fracture in the elderly. Click on the “Predict” button and the “Graphical Summary” on the right shows the corresponding risk values (95% confidence interval) in graphical form, the “Numerical Summary” on the right shows the specific risk values (95% confidence interval), and the “Model Summary” on the right shows the specific information of the model.

• 

  FIGURE 5. The results of each performance evaluation of the nomogram. (a) ROC curve in the training set. (b) ROC curve in the validation set. (c) Calibration curve in the training set. (d) Calibration curve in the validation set. (e) DCA curve in the training set. (f) DCA curve in the validation set. (g) CIC in the training set. (h) CIC in the validation set.