Development of a preoperative index-based nomogram for the prediction of hypokalemia in patients with pituitary adenoma: a retrospective cohort study

Figures

• 

  Figure 1. Feature selection using the least absolute shrinkage and selection operator (LASSO) binary logistic regression model. (A) Model LASSO. Color lines represent the preoperative indices associated with postoperative hypokalemia. The x-axis represents the alpha (cutoff), and the y-axis represents the shrink effect value. LASSO coefficient profiles of the 103 texture features. A coefficient profile plot was produced against the log (λ) sequence. A vertical line was drawn at the value selected using 10-fold cross-validation, where optimal λ resulted in 10 nonzero coefficients. (B) Tuning parameter (lambda) selection in the LASSO model used 10-fold cross-validation via minimum criteria for risk of postoperative hypokalemia. The area under the receiver operating characteristic (AUC) curve was plotted versus log (λ). Dotted vertical lines were drawn at the optimal values by using the minimum criteria. A λ value of 0.074, with log (λ), −2.603, was chosen (1 standard deviation) according to 10-fold cross-validation.

• 

  Figure 2. Multivariable logistic regression models restricted cubic spline analysis the selected variables by LASSO regression analyses on a continuous scale and risk for prevalence postoperative hypokalemia. Odds ratios are represented by a solid line, and the 95% confidence intervals are represented by the pink area. (A) to (I) were restricted cubic spline modeling of the association of age, weight, APTT, serum potassium, urea, CK, HCT, EOS, and PCT with risk of postoperative hypokalemia adjusted by types of pituitary adenomas and the other eight indices.

• 

  Figure 3. Developed and validated preoperative indices nomogram. The preoperative indices nomogram was developed with age, type of pituitary adenoma, weight, APTT, serum potassium, urea, CK, HCT, EOS, and PCT.

• 

  Figure 4. Receiver operating characteristic curves (ROC) for the preoperative index’s prediction model predicting postoperative hypokalemia in training and validation sets. AUC, area under the curve.

• 

  Figure 5. Calibration curve of the preoperative indices’ nomogram. The y-axis represents the actual postoperative hypokalemia rate. The x-axis represents the predicted postoperative hypokalemia risk. The diagonal dotted represents a perfect prediction by an ideal model. The dotted line represents the performance of the nomogram, of which a closer fit to the diagonal dotted line represents a better prediction.