Random Forest for Automatic Feature Importance Estimation and Selection for Explainable Postural Stability of a Multi-Factor Clinical Test

Machine learning algorithms for integrating clinical features to predict intracranial hemorrhage in patients with acute leukemia

BACKGROUND

Intracranial hemorrhage (ICH) in acute leukemia (AL) patients leads to high morbidity and mortality, treatment approaches for ICH are generally ineffective. Thus, early identification of which subjects are at high risk of ICH is of key importance. Currently, machine learning can achieve well predictive capability through constructing algorithms that simultaneously exploit the information coming from clinical features.

METHODS

After rigid data preprocessing, 42 different clinical features from 948 AL patients were used to train different machine learning algorithms. We used the feature selection algorithms to select the top 10 features from 42 clinical features. To test the performance of the machine learning algorithms, we calculated area under the curve (AUC) values from receiver operating characteristic (ROC) curves along with 95% confidence intervals (CIs) by cross-validation.

RESULTS

With the 42 features, RF exhibited the best predictive power. After feature selection, the top 10 features were international normalized ratio (INR), prothrombin time (PT), creatinine (Cr), indirect bilirubin (IBIL), albumin (ALB), monocyte (MONO), platelet (PLT), lactic dehydrogenase (LDH), fibrinogen (FIB) and prealbumin (PA). Among the top 10 features, INR, PT, Cr, IBIL and ALB had high predictive performance with an AUC higher than 0.8 respectively.

CONCLUSIONS

The RF algorithm exhibited a higher cross-validated performance compared with the classical algorithms, and the selected important risk features should help in individualizing aggressive treatment in AL patients to prevent ICH. Efforts that will be made to test and optimize in independent samples will warrant the application of such algorithm and predictors in the future.