Machine learning in the integration of simple variables for identifying patients with myocardial ischemia
| Autor: | Juhani Knuuti, O. Martinez-Manzanera, Luis Eduardo Juarez-Orozco, Remco J.J. Knol, Carlos A. Sánchez-Catasús, Friso M. van der Zant |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Male
Myocardial ischemia PREDICTION FLOW Ischemia 030204 cardiovascular system & hematology Logistic regression Machine learning computer.software_genre GUIDELINES DIAGNOSIS 030218 nuclear medicine & medical imaging 03 medical and health sciences 0302 clinical medicine POSITRON-EMISSION-TOMOGRAPHY Predictive Value of Tests risk of MACE REGRESSION medicine Humans Radiology Nuclear Medicine and imaging cardiovascular diseases Aged Retrospective Studies Nitrogen Radioisotopes Receiver operating characteristic business.industry Myocardial Perfusion Imaging Pet imaging Middle Aged Perfusion reserve medicine.disease myocardial ischemia PET ROC Curve Patient classification Positron-Emission Tomography Feasibility Studies CORONARY-ARTERY-DISEASE Female Artificial intelligence PERFUSION SPECT Cardiology and Cardiovascular Medicine business computer Mace |
| Zdroj: | Journal of Nuclear Cardiology, 27(1), 147-155. SPRINGER |
| ISSN: | 1071-3581 |
| Popis: | Background A significant number of variables are obtained when characterizing patients suspected with myocardial ischemia or at risk of MACE. Guidelines typically use a handful of them to support further workup or therapeutic decisions. However, it is likely that the numerous available predictors maintain intrinsic complex interrelations. Machine learning (ML) offers the possibility to elucidate complex patterns within data to optimize individual patient classification. We evaluated the feasibility and performance of ML in utilizing simple accessible clinical and functional variables for the identification of patients with ischemia or an elevated risk of MACE as determined through quantitative PET myocardial perfusion reserve (MPR). Methods 1,234 patients referred to Nitrogen-13 ammonia PET were analyzed. Demographic (4), clinical (8), and functional variables (9) were retrieved and input into a cross-validated ML workflow consisting of feature selection and modeling. Two PET-defined outcome variables were operationalized: (1) any myocardial ischemia (regional MPR |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink