Determinants of In‐Hospital Mortality After Percutaneous Coronary Intervention: A Machine Learning Approach
Background The ability to accurately predict the occurrence of in‐hospital death after percutaneous coronary intervention is important for clinical decision‐making. We sought to utilize the New York Percutaneous Coronary Intervention Reporting System in order to elucidate the determinants of in‐hosp...
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2019-03-01
|
| Series: | Journal of the American Heart Association: Cardiovascular and Cerebrovascular Disease |
| Subjects: | |
| Online Access: | https://www.ahajournals.org/doi/10.1161/JAHA.118.011160 |
| _version_ | 1818775831865982976 |
|---|---|
| author | Subhi J. Al'Aref Gurpreet Singh Alexander R. van Rosendael Kranthi K. Kolli Xiaoyue Ma Gabriel Maliakal Mohit Pandey Bejamin C. Lee Jing Wang Zhuoran Xu Yiye Zhang James K. Min S. Chiu Wong Robert M. Minutello |
| author_facet | Subhi J. Al'Aref Gurpreet Singh Alexander R. van Rosendael Kranthi K. Kolli Xiaoyue Ma Gabriel Maliakal Mohit Pandey Bejamin C. Lee Jing Wang Zhuoran Xu Yiye Zhang James K. Min S. Chiu Wong Robert M. Minutello |
| author_sort | Subhi J. Al'Aref |
| collection | DOAJ |
| description | Background The ability to accurately predict the occurrence of in‐hospital death after percutaneous coronary intervention is important for clinical decision‐making. We sought to utilize the New York Percutaneous Coronary Intervention Reporting System in order to elucidate the determinants of in‐hospital mortality in patients undergoing percutaneous coronary intervention across New York State. Methods and Results We examined 479 804 patients undergoing percutaneous coronary intervention between 2004 and 2012, utilizing traditional and advanced machine learning algorithms to determine the most significant predictors of in‐hospital mortality. The entire data were randomly split into a training (80%) and a testing set (20%). Tuned hyperparameters were used to generate a trained model while the performance of the model was independently evaluated on the testing set after plotting a receiver‐operator characteristic curve and using the output measure of the area under the curve (AUC) and the associated 95% CIs. Mean age was 65.2±11.9 years and 68.5% were women. There were 2549 in‐hospital deaths within the patient population. A boosted ensemble algorithm (AdaBoost) had optimal discrimination with AUC of 0.927 (95% CI 0.923–0.929) compared with AUC of 0.913 for XGBoost (95% CI 0.906–0.919, P=0.02), AUC of 0.892 for Random Forest (95% CI 0.889–0.896, P<0.01), and AUC of 0.908 for logistic regression (95% CI 0.907–0.910, P<0.01). The 2 most significant predictors were age and ejection fraction. Conclusions A big data approach that utilizes advanced machine learning algorithms identifies new associations among risk factors and provides high accuracy for the prediction of in‐hospital mortality in patients undergoing percutaneous coronary intervention. |
| first_indexed | 2024-12-18T11:03:18Z |
| format | Article |
| id | doaj.art-fa191a01361c45a281cb592c6c90ee52 |
| institution | Directory Open Access Journal |
| issn | 2047-9980 |
| language | English |
| last_indexed | 2024-12-18T11:03:18Z |
| publishDate | 2019-03-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of the American Heart Association: Cardiovascular and Cerebrovascular Disease |
| spelling | doaj.art-fa191a01361c45a281cb592c6c90ee522022-12-21T21:10:10ZengWileyJournal of the American Heart Association: Cardiovascular and Cerebrovascular Disease2047-99802019-03-018510.1161/JAHA.118.011160Determinants of In‐Hospital Mortality After Percutaneous Coronary Intervention: A Machine Learning ApproachSubhi J. Al'Aref0Gurpreet Singh1Alexander R. van Rosendael2Kranthi K. Kolli3Xiaoyue Ma4Gabriel Maliakal5Mohit Pandey6Bejamin C. Lee7Jing Wang8Zhuoran Xu9Yiye Zhang10James K. Min11S. Chiu Wong12Robert M. Minutello13Dalio Institute of Cardiovascular Imaging New York‐Presbyterian Hospital New York NYDalio Institute of Cardiovascular Imaging New York‐Presbyterian Hospital New York NYDalio Institute of Cardiovascular Imaging New York‐Presbyterian Hospital New York NYDalio Institute of Cardiovascular Imaging New York‐Presbyterian Hospital New York NYDalio Institute of Cardiovascular Imaging New York‐Presbyterian Hospital New York NYDalio Institute of Cardiovascular Imaging New York‐Presbyterian Hospital New York NYDalio Institute of Cardiovascular Imaging New York‐Presbyterian Hospital New York NYDalio Institute of Cardiovascular Imaging New York‐Presbyterian Hospital New York NYDalio Institute of Cardiovascular Imaging New York‐Presbyterian Hospital New York NYDalio Institute of Cardiovascular Imaging New York‐Presbyterian Hospital New York NYDivision of Health Informatics Weill Cornell Graduate School of Medical Sciences New York NYDalio Institute of Cardiovascular Imaging New York‐Presbyterian Hospital New York NYDivision of Cardiology Department of Medicine Weill Cornell Medicine New York NYDivision of Cardiology Department of Medicine Weill Cornell Medicine New York NYBackground The ability to accurately predict the occurrence of in‐hospital death after percutaneous coronary intervention is important for clinical decision‐making. We sought to utilize the New York Percutaneous Coronary Intervention Reporting System in order to elucidate the determinants of in‐hospital mortality in patients undergoing percutaneous coronary intervention across New York State. Methods and Results We examined 479 804 patients undergoing percutaneous coronary intervention between 2004 and 2012, utilizing traditional and advanced machine learning algorithms to determine the most significant predictors of in‐hospital mortality. The entire data were randomly split into a training (80%) and a testing set (20%). Tuned hyperparameters were used to generate a trained model while the performance of the model was independently evaluated on the testing set after plotting a receiver‐operator characteristic curve and using the output measure of the area under the curve (AUC) and the associated 95% CIs. Mean age was 65.2±11.9 years and 68.5% were women. There were 2549 in‐hospital deaths within the patient population. A boosted ensemble algorithm (AdaBoost) had optimal discrimination with AUC of 0.927 (95% CI 0.923–0.929) compared with AUC of 0.913 for XGBoost (95% CI 0.906–0.919, P=0.02), AUC of 0.892 for Random Forest (95% CI 0.889–0.896, P<0.01), and AUC of 0.908 for logistic regression (95% CI 0.907–0.910, P<0.01). The 2 most significant predictors were age and ejection fraction. Conclusions A big data approach that utilizes advanced machine learning algorithms identifies new associations among risk factors and provides high accuracy for the prediction of in‐hospital mortality in patients undergoing percutaneous coronary intervention.https://www.ahajournals.org/doi/10.1161/JAHA.118.011160big data analyticsin‐hospital mortalitymachine learningpercutaneous coronary intervention |
| spellingShingle | Subhi J. Al'Aref Gurpreet Singh Alexander R. van Rosendael Kranthi K. Kolli Xiaoyue Ma Gabriel Maliakal Mohit Pandey Bejamin C. Lee Jing Wang Zhuoran Xu Yiye Zhang James K. Min S. Chiu Wong Robert M. Minutello Determinants of In‐Hospital Mortality After Percutaneous Coronary Intervention: A Machine Learning Approach Journal of the American Heart Association: Cardiovascular and Cerebrovascular Disease big data analytics in‐hospital mortality machine learning percutaneous coronary intervention |
| title | Determinants of In‐Hospital Mortality After Percutaneous Coronary Intervention: A Machine Learning Approach |
| title_full | Determinants of In‐Hospital Mortality After Percutaneous Coronary Intervention: A Machine Learning Approach |
| title_fullStr | Determinants of In‐Hospital Mortality After Percutaneous Coronary Intervention: A Machine Learning Approach |
| title_full_unstemmed | Determinants of In‐Hospital Mortality After Percutaneous Coronary Intervention: A Machine Learning Approach |
| title_short | Determinants of In‐Hospital Mortality After Percutaneous Coronary Intervention: A Machine Learning Approach |
| title_sort | determinants of in hospital mortality after percutaneous coronary intervention a machine learning approach |
| topic | big data analytics in‐hospital mortality machine learning percutaneous coronary intervention |
| url | https://www.ahajournals.org/doi/10.1161/JAHA.118.011160 |
| work_keys_str_mv | AT subhijalaref determinantsofinhospitalmortalityafterpercutaneouscoronaryinterventionamachinelearningapproach AT gurpreetsingh determinantsofinhospitalmortalityafterpercutaneouscoronaryinterventionamachinelearningapproach AT alexanderrvanrosendael determinantsofinhospitalmortalityafterpercutaneouscoronaryinterventionamachinelearningapproach AT kranthikkolli determinantsofinhospitalmortalityafterpercutaneouscoronaryinterventionamachinelearningapproach AT xiaoyuema determinantsofinhospitalmortalityafterpercutaneouscoronaryinterventionamachinelearningapproach AT gabrielmaliakal determinantsofinhospitalmortalityafterpercutaneouscoronaryinterventionamachinelearningapproach AT mohitpandey determinantsofinhospitalmortalityafterpercutaneouscoronaryinterventionamachinelearningapproach AT bejaminclee determinantsofinhospitalmortalityafterpercutaneouscoronaryinterventionamachinelearningapproach AT jingwang determinantsofinhospitalmortalityafterpercutaneouscoronaryinterventionamachinelearningapproach AT zhuoranxu determinantsofinhospitalmortalityafterpercutaneouscoronaryinterventionamachinelearningapproach AT yiyezhang determinantsofinhospitalmortalityafterpercutaneouscoronaryinterventionamachinelearningapproach AT jameskmin determinantsofinhospitalmortalityafterpercutaneouscoronaryinterventionamachinelearningapproach AT schiuwong determinantsofinhospitalmortalityafterpercutaneouscoronaryinterventionamachinelearningapproach AT robertmminutello determinantsofinhospitalmortalityafterpercutaneouscoronaryinterventionamachinelearningapproach |