Comparison of Machine Learning Techniques for Prediction of Hospitalization in Heart Failure Patients
The present study aims to compare the performance of eight Machine Learning Techniques (MLTs) in the prediction of hospitalization among patients with heart failure, using data from the Gestione Integrata dello Scompenso Cardiaco (GISC) study. The GISC project is an ongoing study that takes place in...
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-08-01
|
Series: | Journal of Clinical Medicine |
Subjects: | |
Online Access: | https://www.mdpi.com/2077-0383/8/9/1298 |
id |
doaj-efa965fcecb644508a699d4c65557135 |
---|---|
record_format |
Article |
spelling |
doaj-efa965fcecb644508a699d4c655571352020-11-25T01:08:14ZengMDPI AGJournal of Clinical Medicine2077-03832019-08-0189129810.3390/jcm8091298jcm8091298Comparison of Machine Learning Techniques for Prediction of Hospitalization in Heart Failure PatientsGiulia Lorenzoni0Stefano Santo Sabato1Corrado Lanera2Daniele Bottigliengo3Clara Minto4Honoria Ocagli5Paola De Paolis6Dario Gregori7Sabino Iliceto8Franco Pisanò9Unit of Biostatistics, Epidemiology and Public Health, Department of Cardiac, Thoracic, Vascular Sciences and Public Health, University of Padova, Via Loredan, 18, 35131 Padova, ItalyMediaSoft, via Sonzini, 25, 73013 Galatina (Le), ItalyUnit of Biostatistics, Epidemiology and Public Health, Department of Cardiac, Thoracic, Vascular Sciences and Public Health, University of Padova, Via Loredan, 18, 35131 Padova, ItalyUnit of Biostatistics, Epidemiology and Public Health, Department of Cardiac, Thoracic, Vascular Sciences and Public Health, University of Padova, Via Loredan, 18, 35131 Padova, ItalyUnit of Biostatistics, Epidemiology and Public Health, Department of Cardiac, Thoracic, Vascular Sciences and Public Health, University of Padova, Via Loredan, 18, 35131 Padova, ItalyUnit of Biostatistics, Epidemiology and Public Health, Department of Cardiac, Thoracic, Vascular Sciences and Public Health, University of Padova, Via Loredan, 18, 35131 Padova, ItalyAUSL/Lecce, Zona Draghi, 73039 Tricase (Le), ItalyUnit of Biostatistics, Epidemiology and Public Health, Department of Cardiac, Thoracic, Vascular Sciences and Public Health, University of Padova, Via Loredan, 18, 35131 Padova, ItalyCardiology Unit, Department of Cardiac, Thoracic, Vascular Sciences and Public Health, University of Padova, Via Giustiniani, 2, 35128 Padova, ItalyAUSL/Lecce, Zona Draghi, 73039 Tricase (Le), ItalyThe present study aims to compare the performance of eight Machine Learning Techniques (MLTs) in the prediction of hospitalization among patients with heart failure, using data from the Gestione Integrata dello Scompenso Cardiaco (GISC) study. The GISC project is an ongoing study that takes place in the region of Puglia, Southern Italy. Patients with a diagnosis of heart failure are enrolled in a long-term assistance program that includes the adoption of an online platform for data sharing between general practitioners and cardiologists working in hospitals and community health districts. Logistic regression, generalized linear model net (GLMN), classification and regression tree, random forest, adaboost, logitboost, support vector machine, and neural networks were applied to evaluate the feasibility of such techniques in predicting hospitalization of 380 patients enrolled in the GISC study, using data about demographic characteristics, medical history, and clinical characteristics of each patient. The MLTs were compared both without and with missing data imputation. Overall, models trained without missing data imputation showed higher predictive performances. The GLMN showed better performance in predicting hospitalization than the other MLTs, with an average accuracy, positive predictive value and negative predictive value of 81.2%, 87.5%, and 75%, respectively. Present findings suggest that MLTs may represent a promising opportunity to predict hospital admission of heart failure patients by exploiting health care information generated by the contact of such patients with the health care system.https://www.mdpi.com/2077-0383/8/9/1298heart failuremachine learning techniqueshospitalization |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Giulia Lorenzoni Stefano Santo Sabato Corrado Lanera Daniele Bottigliengo Clara Minto Honoria Ocagli Paola De Paolis Dario Gregori Sabino Iliceto Franco Pisanò |
spellingShingle |
Giulia Lorenzoni Stefano Santo Sabato Corrado Lanera Daniele Bottigliengo Clara Minto Honoria Ocagli Paola De Paolis Dario Gregori Sabino Iliceto Franco Pisanò Comparison of Machine Learning Techniques for Prediction of Hospitalization in Heart Failure Patients Journal of Clinical Medicine heart failure machine learning techniques hospitalization |
author_facet |
Giulia Lorenzoni Stefano Santo Sabato Corrado Lanera Daniele Bottigliengo Clara Minto Honoria Ocagli Paola De Paolis Dario Gregori Sabino Iliceto Franco Pisanò |
author_sort |
Giulia Lorenzoni |
title |
Comparison of Machine Learning Techniques for Prediction of Hospitalization in Heart Failure Patients |
title_short |
Comparison of Machine Learning Techniques for Prediction of Hospitalization in Heart Failure Patients |
title_full |
Comparison of Machine Learning Techniques for Prediction of Hospitalization in Heart Failure Patients |
title_fullStr |
Comparison of Machine Learning Techniques for Prediction of Hospitalization in Heart Failure Patients |
title_full_unstemmed |
Comparison of Machine Learning Techniques for Prediction of Hospitalization in Heart Failure Patients |
title_sort |
comparison of machine learning techniques for prediction of hospitalization in heart failure patients |
publisher |
MDPI AG |
series |
Journal of Clinical Medicine |
issn |
2077-0383 |
publishDate |
2019-08-01 |
description |
The present study aims to compare the performance of eight Machine Learning Techniques (MLTs) in the prediction of hospitalization among patients with heart failure, using data from the Gestione Integrata dello Scompenso Cardiaco (GISC) study. The GISC project is an ongoing study that takes place in the region of Puglia, Southern Italy. Patients with a diagnosis of heart failure are enrolled in a long-term assistance program that includes the adoption of an online platform for data sharing between general practitioners and cardiologists working in hospitals and community health districts. Logistic regression, generalized linear model net (GLMN), classification and regression tree, random forest, adaboost, logitboost, support vector machine, and neural networks were applied to evaluate the feasibility of such techniques in predicting hospitalization of 380 patients enrolled in the GISC study, using data about demographic characteristics, medical history, and clinical characteristics of each patient. The MLTs were compared both without and with missing data imputation. Overall, models trained without missing data imputation showed higher predictive performances. The GLMN showed better performance in predicting hospitalization than the other MLTs, with an average accuracy, positive predictive value and negative predictive value of 81.2%, 87.5%, and 75%, respectively. Present findings suggest that MLTs may represent a promising opportunity to predict hospital admission of heart failure patients by exploiting health care information generated by the contact of such patients with the health care system. |
topic |
heart failure machine learning techniques hospitalization |
url |
https://www.mdpi.com/2077-0383/8/9/1298 |
work_keys_str_mv |
AT giulialorenzoni comparisonofmachinelearningtechniquesforpredictionofhospitalizationinheartfailurepatients AT stefanosantosabato comparisonofmachinelearningtechniquesforpredictionofhospitalizationinheartfailurepatients AT corradolanera comparisonofmachinelearningtechniquesforpredictionofhospitalizationinheartfailurepatients AT danielebottigliengo comparisonofmachinelearningtechniquesforpredictionofhospitalizationinheartfailurepatients AT claraminto comparisonofmachinelearningtechniquesforpredictionofhospitalizationinheartfailurepatients AT honoriaocagli comparisonofmachinelearningtechniquesforpredictionofhospitalizationinheartfailurepatients AT paoladepaolis comparisonofmachinelearningtechniquesforpredictionofhospitalizationinheartfailurepatients AT dariogregori comparisonofmachinelearningtechniquesforpredictionofhospitalizationinheartfailurepatients AT sabinoiliceto comparisonofmachinelearningtechniquesforpredictionofhospitalizationinheartfailurepatients AT francopisano comparisonofmachinelearningtechniquesforpredictionofhospitalizationinheartfailurepatients |
_version_ |
1725183598704721920 |