Fig. 2 | Scientific Reports

Fig. 2

From: Research on multi-algorithm and explainable AI techniques for predictive modeling of acute spinal cord injury using multimodal data

Fig. 2

Data Preprocessing and Feature Selection Process (A-D) Density distribution plots of variables after multiple imputation of missing values using the MICE package. (E) Lasso regression coefficient path illustrating the trajectories of each variable’s coefficients with changes in the regularization parameter Log Lambda. (F) Deviation diagnosis plot of the Lasso regression model showing changes in deviation with different Log(λ) values. IMLL, Intramedullary lesion length; RBC, Red blood cell; FDP, Fibrinogen degradation products; K, Kalium; Cl, Chlorine; Na, Natrium; BMI, Body Mass Index; P-LCR, Platelet-large cell ratio, MPV, Mean platelet volume; PDW, Platelet distribution width; PCT, Plateletcrit.

Back to article page