Robust prognostic prediction model developed with integrated biological markers for acute myocardial infarction.
Commonly used prediction methods for acute myocardial infarction (AMI) were created before contemporary percutaneous coronary intervention was recognized as the primary therapy. Although several studies have used machine learning techniques for prognostic prediction of patients with AMI, its clinica...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2022-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0277260 |
| _version_ | 1797984286569136128 |
|---|---|
| author | Masahiro Nishi Eiichiro Uchino Yasushi Okuno Satoaki Matoba |
| author_facet | Masahiro Nishi Eiichiro Uchino Yasushi Okuno Satoaki Matoba |
| author_sort | Masahiro Nishi |
| collection | DOAJ |
| description | Commonly used prediction methods for acute myocardial infarction (AMI) were created before contemporary percutaneous coronary intervention was recognized as the primary therapy. Although several studies have used machine learning techniques for prognostic prediction of patients with AMI, its clinical application has not been achieved. Here, we developed an online application tool using a machine learning model to predict in-hospital mortality in patients with AMI. A total of 2,553 cases of ST-elevation AMI were assigned to 80% training subset for cross validation and 20% test subset for model performance evaluation. We implemented random forest classifier for the binary classification of in-hospital mortality. The selected best feature set consisted of ten clinical and biological markers including max creatine phosphokinase, hemoglobin, heart rate, creatinine, systolic blood pressure, blood sugar, age, Killip class, white blood cells, and c-reactive protein. Our model achieved high performance: the area under the curve of the receiver operating characteristic curve for the test subset, 0.95: sensitivity, 0.89: specificity, 0.91: precision, 0.43: accuracy, 0.91 respectively, which outperformed common scoring methods. The freely available application tool for prognostic prediction can contribute to risk triage and decision-making in patient-centered modern clinical practice for AMI. |
| first_indexed | 2024-04-11T07:00:20Z |
| format | Article |
| id | doaj.art-a5633ea99eee4bc1985aca66a8b2865d |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-04-11T07:00:20Z |
| publishDate | 2022-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-a5633ea99eee4bc1985aca66a8b2865d2022-12-22T04:38:49ZengPublic Library of Science (PLoS)PLoS ONE1932-62032022-01-011711e027726010.1371/journal.pone.0277260Robust prognostic prediction model developed with integrated biological markers for acute myocardial infarction.Masahiro NishiEiichiro UchinoYasushi OkunoSatoaki MatobaCommonly used prediction methods for acute myocardial infarction (AMI) were created before contemporary percutaneous coronary intervention was recognized as the primary therapy. Although several studies have used machine learning techniques for prognostic prediction of patients with AMI, its clinical application has not been achieved. Here, we developed an online application tool using a machine learning model to predict in-hospital mortality in patients with AMI. A total of 2,553 cases of ST-elevation AMI were assigned to 80% training subset for cross validation and 20% test subset for model performance evaluation. We implemented random forest classifier for the binary classification of in-hospital mortality. The selected best feature set consisted of ten clinical and biological markers including max creatine phosphokinase, hemoglobin, heart rate, creatinine, systolic blood pressure, blood sugar, age, Killip class, white blood cells, and c-reactive protein. Our model achieved high performance: the area under the curve of the receiver operating characteristic curve for the test subset, 0.95: sensitivity, 0.89: specificity, 0.91: precision, 0.43: accuracy, 0.91 respectively, which outperformed common scoring methods. The freely available application tool for prognostic prediction can contribute to risk triage and decision-making in patient-centered modern clinical practice for AMI.https://doi.org/10.1371/journal.pone.0277260 |
| spellingShingle | Masahiro Nishi Eiichiro Uchino Yasushi Okuno Satoaki Matoba Robust prognostic prediction model developed with integrated biological markers for acute myocardial infarction. PLoS ONE |
| title | Robust prognostic prediction model developed with integrated biological markers for acute myocardial infarction. |
| title_full | Robust prognostic prediction model developed with integrated biological markers for acute myocardial infarction. |
| title_fullStr | Robust prognostic prediction model developed with integrated biological markers for acute myocardial infarction. |
| title_full_unstemmed | Robust prognostic prediction model developed with integrated biological markers for acute myocardial infarction. |
| title_short | Robust prognostic prediction model developed with integrated biological markers for acute myocardial infarction. |
| title_sort | robust prognostic prediction model developed with integrated biological markers for acute myocardial infarction |
| url | https://doi.org/10.1371/journal.pone.0277260 |
| work_keys_str_mv | AT masahironishi robustprognosticpredictionmodeldevelopedwithintegratedbiologicalmarkersforacutemyocardialinfarction AT eiichirouchino robustprognosticpredictionmodeldevelopedwithintegratedbiologicalmarkersforacutemyocardialinfarction AT yasushiokuno robustprognosticpredictionmodeldevelopedwithintegratedbiologicalmarkersforacutemyocardialinfarction AT satoakimatoba robustprognosticpredictionmodeldevelopedwithintegratedbiologicalmarkersforacutemyocardialinfarction |