Figure 4 | Scientific Reports

Figure 4

From: Machine learning-based prediction models for parathyroid carcinoma using pre-surgery cognitive function and clinical features

Figure 4

(A, B, C) coefficients, cross-validation, and feature selection in LASSO regression. (A, B) We ensured optimal penalty parameter lambda (λ) at the minimum mean squared error value. (C) The coefficient of 6 variables including sex, MMSE, PTH, calcium, 25-hydroxy vitamin D, and phosphorous, log(λ) = − 2.171463896 (λ = 0.006738079091822886) when the error of the model is minimized, and 6 variables were selected for further regression analysis.

Back to article page