Predicting in-hospital mortality of patients with febrile neutropenia using machine learning models

Abstract

Background: Febrile neutropenia (FN) has been associated with high mortality among adults with cancer. Current systems for early detection of inpatient FN mortality are based on scoring indexes that require intensive physicians' subjective evaluation.

Objective: In this study, we leveraged machine learning techniques to build a FN mortality risk evaluation tool focused on FN admissions without physicians' subjective evaluation.

Methods: We used the National Inpatient Sample and Nationwide Inpatient Sample (NIS) that included mortality data among adult inpatients who were diagnosed with FN during a hospital admission. Machine learning techniques that we compared included linear models (ridge logistic regression and linear support vector machine) and non-linear models (gradient boosting tree and neural network). The primary outcome for this study was death among individuals with a recorded FN admission. Model comparison was evaluated based on areas under the receiver operating characteristic curve (AUROC) and model performance was estimated using 30 % test set created via stratified split.

Results: Our analysis detected 126,013 adult admissions within the NIS data that were diagnosed with FN, among which 5,856 were declared as deceased (4.6 %). Our machine learning results demonstrate linear models and non-linear models achieved areas under the receiver operating characteristic (AUROC) around 92 % in survival prediction.

Conclusions: We developed machine learning models that do not require physicians' subjective evaluation for FN mortality risk prediction.

Keywords: Cancer; Febrile neutropenia; HCUP; Machine learning; Mortality.