Additional file 3 of A novel method to predict the haemoglobin concentration after kidney transplantation based on machine learning: prediction model establishment and method optimization

Additional file 3 of A novel method to predict the haemoglobin concentration after kidney transplantation based on machine learning: prediction model establishment and method optimization

Supplementary Material 3

محفوظ في:

التفاصيل البيبلوغرافية
المؤلف الرئيسي:	Songping He (21683753) (author)
مؤلفون آخرون:	Xiangxi Li (21683756) (author), Fangyu Peng (156188) (author), Jiazhi Liao (17661417) (author), Xia Lu (1370136) (author), Hui Guo (110581) (author), Xin Tan (721363) (author), Yanyan Chen (527430) (author)
منشور في:	2025
الموضوعات:	Artificial Intelligence and Image Processing Kidney transplantation Machine learning Clinical prediction Missing value imputation Error-correcting output codes
الوسوم:	إضافة وسم لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!

مواد مشابهة

Additional file 2 of A novel method to predict the haemoglobin concentration after kidney transplantation based on machine learning: prediction model establishment and method optimization
حسب: Songping He (21683753)
منشور في: (2025)

Details on imputation methods in R or python.
حسب: Elena Albu (15181070)
منشور في: (2025)

Pseudocode for the missForestPredict algorithm.
حسب: Elena Albu (15181070)
منشور في: (2025)

Pseudocode for the missForestPredict algorithm - new observation.
حسب: Elena Albu (15181070)
منشور في: (2025)

Prediction performance for datasets with missing values and categorical outcome (BSS).
حسب: Elena Albu (15181070)
منشور في: (2025)

The above figure provides a rough summary of the five methods we examine with respect to their quality in predicting systematically missing values.
حسب: Anja Mühlemann (18510195)
منشور في: (2025)

Cronbach’s Alpha for Imputation Methods.
حسب: Ayman Omar Baniamer (21222249)
منشور في: (2025)

Flowchart for the data generation and analysis method.
حسب: Ayman Omar Baniamer (21222249)
منشور في: (2025)

Prediction performance for datasets with simulated missingness (BSS for categorical outcomes and R squared for continuous outcomes).
حسب: Elena Albu (15181070)
منشور في: (2025)

Cumulative total variance for components of imputation methods.
حسب: Ayman Omar Baniamer (21222249)
منشور في: (2025)

Prediction performance (BSS) for simulated datasets with simulated missingness: high correlation (0.7) and high AUROC (0.9).
حسب: Elena Albu (15181070)
منشور في: (2025)

Prediction performance (BSS) for simulated datasets with simulated missingness: high correlation (0.7) and low AUROC (0.75).
حسب: Elena Albu (15181070)
منشور في: (2025)

Prediction performance (BSS) for simulated datasets with simulated missingness: low correlation (0.1) and high AUROC (0.9).
حسب: Elena Albu (15181070)
منشور في: (2025)

Prediction performance (BSS) for simulated datasets with simulated missingness: low correlation (0.1) and low AUROC (0.75).
حسب: Elena Albu (15181070)
منشور في: (2025)

Absolute difference between missing rates as compared with ZERO rate of missing due to imputation method.
حسب: Ayman Omar Baniamer (21222249)
منشور في: (2025)

Confusion matrix for the point estimate methods I1-I3.
حسب: Anja Mühlemann (18510195)
منشور في: (2025)

Table 1_A random forest dynamic threshold imputation method for handling missing data in cognitive diagnosis assessments.pdf
حسب: Xiaofeng You (21987266)
منشور في: (2025)

ORIGINAL_data.sav
حسب: ayman baniamer (20678483)
منشور في: (2025)

Dispersion between observed ET<sub>o</sub> values and those imputed by the NIPALS-PCA, EM-PCA and IM methods (50% scenario).
حسب: Valter Cesar de Souza (20489819)
منشور في: (2024)

A multiple imputation method using population information
حسب: Tadayoshi Fushiki (20353)
منشور في: (2025)

Dispersion between observed ET<sub>o</sub> values and those imputed by the NIPALS-PCA, EM-PCA and IM methods (30% and 40% scenarios).
حسب: Valter Cesar de Souza (20489819)
منشور في: (2024)

Dispersion between observed ET<sub>o</sub> values and those imputed by the NIPALS-PCA, EM-PCA and IM methods (10% and 20% scenarios).
حسب: Valter Cesar de Souza (20489819)
منشور في: (2024)

Classification for risk below and above 5% under a cut-off-probability of <i>α</i> for method I5.
حسب: Anja Mühlemann (18510195)
منشور في: (2025)

Classification for risk below and above 5% under a cut-off-probability of <i>α</i> for method I4.
حسب: Anja Mühlemann (18510195)
منشور في: (2025)

Data Sheet 1_Predicting carbohydrate quality in a global database of packaged foods.docx
حسب: Eric Antoine Scuccimarra (20864336)
منشور في: (2025)

<i>Eigenvalues for the first three components, through CIM, EM, and MI imputations methods, through different missing data ratios.</i>: Eigenvalues for the first component, : the ratio between the first and the second components eigenvalues, : the ratio between the difference of the first and second eigenvalues and the difference of the second and third eigenvalues.
حسب: Ayman Omar Baniamer (21222249)
منشور في: (2025)

Median object size of the imputation object in MB (the Q1 - Q3 range is presented in the shiny app).
حسب: Elena Albu (15181070)
منشور في: (2025)

Median runtime in seconds for building imputation models and imputing the training set (the Q1 - Q3 range is presented in the shiny app).
حسب: Elena Albu (15181070)
منشور في: (2025)

Mean number of completely missing observations over all train/test splits for datasets with simulated missingness (amputation).
حسب: Elena Albu (15181070)
منشور في: (2025)

Comparison procedure steps.
حسب: Elena Albu (15181070)
منشور في: (2025)

Amputation mechanisms.
حسب: Elena Albu (15181070)
منشور في: (2025)

Real datasets description.
حسب: Elena Albu (15181070)
منشور في: (2025)

Simulated datasets description.
حسب: Elena Albu (15181070)
منشور في: (2025)

Proportion of original (non-missing) and imputed values for categorical variables.
حسب: Elena Albu (15181070)
منشور في: (2025)

Distribution of original (non-missing) and imputed values for continuous variables.
حسب: Elena Albu (15181070)
منشور في: (2025)

Errors (deviations from true values); median and IQR bars.
حسب: Elena Albu (15181070)
منشور في: (2025)

NMSE errors (deviations from true values) on test sets for simulated datasets with simulated missingness: high correlation (0.7) and high AUROC (0.9).
حسب: Elena Albu (15181070)
منشور في: (2025)

NMSE errors (deviations from true values) on test sets for simulated datasets with simulated missingness: high correlation (0.7) and low AUROC (0.75).
حسب: Elena Albu (15181070)
منشور في: (2025)

NMSE errors (deviations from true values) on test sets for simulated datasets with simulated missingness: low correlation (0.1) and high AUROC (0.9).
حسب: Elena Albu (15181070)
منشور في: (2025)

NMSE errors (deviations from true values) on test sets for simulated datasets with simulated missingness: low correlation (0.1) and low AUROC (0.75).
حسب: Elena Albu (15181070)
منشور في: (2025)

Cannot write session to /tmp/vufind_sessions/sess_tuhi0pe18h10c3pjeqi7dqab6i