Cargando…
Comparison of risk models for mortality and cardiovascular events between machine learning and conventional logistic regression analysis
AIMS: Non-linear models by machine learning may identify different risk factors with different weighting in comparison to conventional linear models. METHODS AND RESULTS: The analyses were performed in 15,933 patients included in the Shinken Database (SD) 2004–2014 (n = 22,022) for whom baseline dat...
Autores principales: | , , , , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2019
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6733605/ https://www.ncbi.nlm.nih.gov/pubmed/31499517 http://dx.doi.org/10.1371/journal.pone.0221911 |
_version_ | 1783450006215196672 |
---|---|
author | Suzuki, Shinya Yamashita, Takeshi Sakama, Tsuyoshi Arita, Takuto Yagi, Naoharu Otsuka, Takayuki Semba, Hiroaki Kano, Hiroto Matsuno, Shunsuke Kato, Yuko Uejima, Tokuhisa Oikawa, Yuji Matsuhama, Minoru Yajima, Junji |
author_facet | Suzuki, Shinya Yamashita, Takeshi Sakama, Tsuyoshi Arita, Takuto Yagi, Naoharu Otsuka, Takayuki Semba, Hiroaki Kano, Hiroto Matsuno, Shunsuke Kato, Yuko Uejima, Tokuhisa Oikawa, Yuji Matsuhama, Minoru Yajima, Junji |
author_sort | Suzuki, Shinya |
collection | PubMed |
description | AIMS: Non-linear models by machine learning may identify different risk factors with different weighting in comparison to conventional linear models. METHODS AND RESULTS: The analyses were performed in 15,933 patients included in the Shinken Database (SD) 2004–2014 (n = 22,022) for whom baseline data of blood sampling and ultrasound cardiogram and follow-up data at 2 years were available. Using non-linear models with machine learning software, 118 risk factors and their weighting of risk for all-cause mortality, heart failure (HF), acute coronary syndrome (ACS), ischemic stroke (IS), and intracranial hemorrhage (ICH) were identified, where the top two risk factors were albumin/hemoglobin, left ventricular ejection fraction/history of HF, history of ACS/anti-platelet use, history of IS/deceleration time, and history of ICH/warfarin use. The areas under the curve of the developed models for each event were 0.900, 0.912, 0.879, 0.758, and 0.753, respectively. CONCLUSION: Here, we described our experience with the development of models for predicting cardiovascular prognosis by machine learning. Machine learning could identify risk predicting models with good predictive capability and good discrimination of the risk impact. |
format | Online Article Text |
id | pubmed-6733605 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2019 |
publisher | Public Library of Science |
record_format | MEDLINE/PubMed |
spelling | pubmed-67336052019-09-20 Comparison of risk models for mortality and cardiovascular events between machine learning and conventional logistic regression analysis Suzuki, Shinya Yamashita, Takeshi Sakama, Tsuyoshi Arita, Takuto Yagi, Naoharu Otsuka, Takayuki Semba, Hiroaki Kano, Hiroto Matsuno, Shunsuke Kato, Yuko Uejima, Tokuhisa Oikawa, Yuji Matsuhama, Minoru Yajima, Junji PLoS One Research Article AIMS: Non-linear models by machine learning may identify different risk factors with different weighting in comparison to conventional linear models. METHODS AND RESULTS: The analyses were performed in 15,933 patients included in the Shinken Database (SD) 2004–2014 (n = 22,022) for whom baseline data of blood sampling and ultrasound cardiogram and follow-up data at 2 years were available. Using non-linear models with machine learning software, 118 risk factors and their weighting of risk for all-cause mortality, heart failure (HF), acute coronary syndrome (ACS), ischemic stroke (IS), and intracranial hemorrhage (ICH) were identified, where the top two risk factors were albumin/hemoglobin, left ventricular ejection fraction/history of HF, history of ACS/anti-platelet use, history of IS/deceleration time, and history of ICH/warfarin use. The areas under the curve of the developed models for each event were 0.900, 0.912, 0.879, 0.758, and 0.753, respectively. CONCLUSION: Here, we described our experience with the development of models for predicting cardiovascular prognosis by machine learning. Machine learning could identify risk predicting models with good predictive capability and good discrimination of the risk impact. Public Library of Science 2019-09-09 /pmc/articles/PMC6733605/ /pubmed/31499517 http://dx.doi.org/10.1371/journal.pone.0221911 Text en © 2019 Suzuki et al http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. |
spellingShingle | Research Article Suzuki, Shinya Yamashita, Takeshi Sakama, Tsuyoshi Arita, Takuto Yagi, Naoharu Otsuka, Takayuki Semba, Hiroaki Kano, Hiroto Matsuno, Shunsuke Kato, Yuko Uejima, Tokuhisa Oikawa, Yuji Matsuhama, Minoru Yajima, Junji Comparison of risk models for mortality and cardiovascular events between machine learning and conventional logistic regression analysis |
title | Comparison of risk models for mortality and cardiovascular events between machine learning and conventional logistic regression analysis |
title_full | Comparison of risk models for mortality and cardiovascular events between machine learning and conventional logistic regression analysis |
title_fullStr | Comparison of risk models for mortality and cardiovascular events between machine learning and conventional logistic regression analysis |
title_full_unstemmed | Comparison of risk models for mortality and cardiovascular events between machine learning and conventional logistic regression analysis |
title_short | Comparison of risk models for mortality and cardiovascular events between machine learning and conventional logistic regression analysis |
title_sort | comparison of risk models for mortality and cardiovascular events between machine learning and conventional logistic regression analysis |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6733605/ https://www.ncbi.nlm.nih.gov/pubmed/31499517 http://dx.doi.org/10.1371/journal.pone.0221911 |
work_keys_str_mv | AT suzukishinya comparisonofriskmodelsformortalityandcardiovasculareventsbetweenmachinelearningandconventionallogisticregressionanalysis AT yamashitatakeshi comparisonofriskmodelsformortalityandcardiovasculareventsbetweenmachinelearningandconventionallogisticregressionanalysis AT sakamatsuyoshi comparisonofriskmodelsformortalityandcardiovasculareventsbetweenmachinelearningandconventionallogisticregressionanalysis AT aritatakuto comparisonofriskmodelsformortalityandcardiovasculareventsbetweenmachinelearningandconventionallogisticregressionanalysis AT yaginaoharu comparisonofriskmodelsformortalityandcardiovasculareventsbetweenmachinelearningandconventionallogisticregressionanalysis AT otsukatakayuki comparisonofriskmodelsformortalityandcardiovasculareventsbetweenmachinelearningandconventionallogisticregressionanalysis AT sembahiroaki comparisonofriskmodelsformortalityandcardiovasculareventsbetweenmachinelearningandconventionallogisticregressionanalysis AT kanohiroto comparisonofriskmodelsformortalityandcardiovasculareventsbetweenmachinelearningandconventionallogisticregressionanalysis AT matsunoshunsuke comparisonofriskmodelsformortalityandcardiovasculareventsbetweenmachinelearningandconventionallogisticregressionanalysis AT katoyuko comparisonofriskmodelsformortalityandcardiovasculareventsbetweenmachinelearningandconventionallogisticregressionanalysis AT uejimatokuhisa comparisonofriskmodelsformortalityandcardiovasculareventsbetweenmachinelearningandconventionallogisticregressionanalysis AT oikawayuji comparisonofriskmodelsformortalityandcardiovasculareventsbetweenmachinelearningandconventionallogisticregressionanalysis AT matsuhamaminoru comparisonofriskmodelsformortalityandcardiovasculareventsbetweenmachinelearningandconventionallogisticregressionanalysis AT yajimajunji comparisonofriskmodelsformortalityandcardiovasculareventsbetweenmachinelearningandconventionallogisticregressionanalysis |