Machine ​learning algorithms for claims data‐based prediction of in‐hospital mortality in patients with heart failure

Abstract Aims Models predicting mortality in heart failure (HF) patients are often limited with regard to performance and applicability. The aim of this study was to develop a reliable algorithm to compute expected in‐hospital mortality rates in HF cohorts on a population level based on administrati...

Full description

Bibliographic Details
Main Authors: Sebastian König, Vincent Pellissier, Sven Hohenstein, Andres Bernal, Laura Ueberham, Andreas Meier‐Hellmann, Ralf Kuhlen, Gerhard Hindricks, Andreas Bollmann
Format: Article
Language:English
Published: Wiley 2021-08-01
Series:ESC Heart Failure
Subjects:
Online Access:https://doi.org/10.1002/ehf2.13398
id doaj-fc20fb60518d4ecaacbc3099e1da3b26
record_format Article
spelling doaj-fc20fb60518d4ecaacbc3099e1da3b262021-07-28T18:55:36ZengWileyESC Heart Failure2055-58222021-08-01843026303610.1002/ehf2.13398Machine ​learning algorithms for claims data‐based prediction of in‐hospital mortality in patients with heart failureSebastian König0Vincent Pellissier1Sven Hohenstein2Andres Bernal3Laura Ueberham4Andreas Meier‐Hellmann5Ralf Kuhlen6Gerhard Hindricks7Andreas Bollmann8Department of Electrophysiology Heart Center Leipzig at University of Leipzig Strümpellstraße 39 Leipzig 04289 GermanyLeipzig Heart Institute Leipzig GermanyLeipzig Heart Institute Leipzig GermanyLeipzig Heart Institute Leipzig GermanyDepartment of Electrophysiology Heart Center Leipzig at University of Leipzig Strümpellstraße 39 Leipzig 04289 GermanyHelios Hospitals Berlin GermanyHelios Health Berlin GermanyDepartment of Electrophysiology Heart Center Leipzig at University of Leipzig Strümpellstraße 39 Leipzig 04289 GermanyDepartment of Electrophysiology Heart Center Leipzig at University of Leipzig Strümpellstraße 39 Leipzig 04289 GermanyAbstract Aims Models predicting mortality in heart failure (HF) patients are often limited with regard to performance and applicability. The aim of this study was to develop a reliable algorithm to compute expected in‐hospital mortality rates in HF cohorts on a population level based on administrative data comparing regression analysis with different machine learning (ML) models. Methods and results Inpatient cases with primary International Statistical Classification of Diseases and Related Health Problems (ICD‐10) encoded discharge diagnosis of HF non‐electively admitted to 86 German Helios hospitals between 1 January 2016 and 31 December 2018 were identified. The dataset was randomly split 75%/25% for model development and testing. Highly unbalanced variables were removed. Four ML algorithms were applied, and all algorithms were tuned using a grid search with multiple repetitions. Model performance was evaluated by computing receiver operating characteristic areas under the curve. In total, 59 125 cases (69.8% aged 75 years or older, 51.9% female) were investigated, and in‐hospital mortality was 6.20%. Areas under the curve of all ML algorithms outperformed regression analysis in the testing dataset with values of 0.829 [95% confidence interval (CI) 0.814–0.843] for logistic regression, 0.875 (95% CI 0.863–0.886) for random forest, 0.882 (95% CI 0.871–0.893) for gradient boosting machine, 0.866 (95% CI 0.854–0.878) for single‐layer neural networks, and 0.882 (95% CI 0.872–0.893) for extreme gradient boosting. Brier scores demonstrated a good calibration especially of the latter three models. Conclusions We introduced reliable models to calculate expected in‐hospital mortality based only on administrative routine data using ML algorithms. A broad application could supplement quality measurement programs and therefore improve future HF patient care.https://doi.org/10.1002/ehf2.13398Mortality predictionPrediction modelsMachine learningIn‐hospital mortalityHeart failure
collection DOAJ
language English
format Article
sources DOAJ
author Sebastian König
Vincent Pellissier
Sven Hohenstein
Andres Bernal
Laura Ueberham
Andreas Meier‐Hellmann
Ralf Kuhlen
Gerhard Hindricks
Andreas Bollmann
spellingShingle Sebastian König
Vincent Pellissier
Sven Hohenstein
Andres Bernal
Laura Ueberham
Andreas Meier‐Hellmann
Ralf Kuhlen
Gerhard Hindricks
Andreas Bollmann
Machine ​learning algorithms for claims data‐based prediction of in‐hospital mortality in patients with heart failure
ESC Heart Failure
Mortality prediction
Prediction models
Machine learning
In‐hospital mortality
Heart failure
author_facet Sebastian König
Vincent Pellissier
Sven Hohenstein
Andres Bernal
Laura Ueberham
Andreas Meier‐Hellmann
Ralf Kuhlen
Gerhard Hindricks
Andreas Bollmann
author_sort Sebastian König
title Machine ​learning algorithms for claims data‐based prediction of in‐hospital mortality in patients with heart failure
title_short Machine ​learning algorithms for claims data‐based prediction of in‐hospital mortality in patients with heart failure
title_full Machine ​learning algorithms for claims data‐based prediction of in‐hospital mortality in patients with heart failure
title_fullStr Machine ​learning algorithms for claims data‐based prediction of in‐hospital mortality in patients with heart failure
title_full_unstemmed Machine ​learning algorithms for claims data‐based prediction of in‐hospital mortality in patients with heart failure
title_sort machine ​learning algorithms for claims data‐based prediction of in‐hospital mortality in patients with heart failure
publisher Wiley
series ESC Heart Failure
issn 2055-5822
publishDate 2021-08-01
description Abstract Aims Models predicting mortality in heart failure (HF) patients are often limited with regard to performance and applicability. The aim of this study was to develop a reliable algorithm to compute expected in‐hospital mortality rates in HF cohorts on a population level based on administrative data comparing regression analysis with different machine learning (ML) models. Methods and results Inpatient cases with primary International Statistical Classification of Diseases and Related Health Problems (ICD‐10) encoded discharge diagnosis of HF non‐electively admitted to 86 German Helios hospitals between 1 January 2016 and 31 December 2018 were identified. The dataset was randomly split 75%/25% for model development and testing. Highly unbalanced variables were removed. Four ML algorithms were applied, and all algorithms were tuned using a grid search with multiple repetitions. Model performance was evaluated by computing receiver operating characteristic areas under the curve. In total, 59 125 cases (69.8% aged 75 years or older, 51.9% female) were investigated, and in‐hospital mortality was 6.20%. Areas under the curve of all ML algorithms outperformed regression analysis in the testing dataset with values of 0.829 [95% confidence interval (CI) 0.814–0.843] for logistic regression, 0.875 (95% CI 0.863–0.886) for random forest, 0.882 (95% CI 0.871–0.893) for gradient boosting machine, 0.866 (95% CI 0.854–0.878) for single‐layer neural networks, and 0.882 (95% CI 0.872–0.893) for extreme gradient boosting. Brier scores demonstrated a good calibration especially of the latter three models. Conclusions We introduced reliable models to calculate expected in‐hospital mortality based only on administrative routine data using ML algorithms. A broad application could supplement quality measurement programs and therefore improve future HF patient care.
topic Mortality prediction
Prediction models
Machine learning
In‐hospital mortality
Heart failure
url https://doi.org/10.1002/ehf2.13398
work_keys_str_mv AT sebastiankonig machinelearningalgorithmsforclaimsdatabasedpredictionofinhospitalmortalityinpatientswithheartfailure
AT vincentpellissier machinelearningalgorithmsforclaimsdatabasedpredictionofinhospitalmortalityinpatientswithheartfailure
AT svenhohenstein machinelearningalgorithmsforclaimsdatabasedpredictionofinhospitalmortalityinpatientswithheartfailure
AT andresbernal machinelearningalgorithmsforclaimsdatabasedpredictionofinhospitalmortalityinpatientswithheartfailure
AT lauraueberham machinelearningalgorithmsforclaimsdatabasedpredictionofinhospitalmortalityinpatientswithheartfailure
AT andreasmeierhellmann machinelearningalgorithmsforclaimsdatabasedpredictionofinhospitalmortalityinpatientswithheartfailure
AT ralfkuhlen machinelearningalgorithmsforclaimsdatabasedpredictionofinhospitalmortalityinpatientswithheartfailure
AT gerhardhindricks machinelearningalgorithmsforclaimsdatabasedpredictionofinhospitalmortalityinpatientswithheartfailure
AT andreasbollmann machinelearningalgorithmsforclaimsdatabasedpredictionofinhospitalmortalityinpatientswithheartfailure
_version_ 1721265326056800256