Efficiency of prognostic scores in predicting the new-onset atrial fibrillation in patients with ST-elevation myocardial infarction after percutaneous coronary intervention DOI Creative Commons
Raymond Pak, B. I. Geltser, K. I. Shakhgeldyan

et al.

Russian Journal of Cardiology, Journal Year: 2024, Volume and Issue: 29(12), P. 6125 - 6125

Published: Nov. 17, 2024

Aim . To compare the effectiveness of POAF, PAFAC, COM-AF, HATCH, ms2HEST and CHA 2 DS -VASc scores for predicting new-onset atrial fibrillation (AF) in patients with ST-elevation myocardial infarction (STEMI) after percutaneous coronary intervention (PCI), as well to develop novel prognostic models based on machine learning methods. Material methods This single-center retrospective study was conducted using data from 3449 electronic health records STEMI. Two groups individuals were identified, first which included 312 (9%) AF postoperative period PCI, second — 3139 (91%) without cardiac arrhythmia. predict AF, univariate multivariate logistic regression (ULR MLR), decision tree (DT), artificial neural networks (ANN) used. Results The results showed that 6 analyzed scores, only 4 (mc2HEST, HATCH) have an acceptable potential documented by AUC metrics ULR developed basis sum points each score (AUC 0,736, 0,731, 0,71 0,702, respectively). integrative ANN model, combining resource demonstrated higher accuracy than DT MLR 0,759 vs 0,745 0,755, p-value<0,0001). Conclusion Further studies aimed at improving quality STEMI PCI may involve searching predictors characterizing severity involvement its restoration, inflammatory response, electrophysiological status, etc.

Language: Английский

Efficiency of prognostic scores in predicting the new-onset atrial fibrillation in patients with ST-elevation myocardial infarction after percutaneous coronary intervention DOI Creative Commons
Raymond Pak, B. I. Geltser, K. I. Shakhgeldyan

et al.

Russian Journal of Cardiology, Journal Year: 2024, Volume and Issue: 29(12), P. 6125 - 6125

Published: Nov. 17, 2024

Aim . To compare the effectiveness of POAF, PAFAC, COM-AF, HATCH, ms2HEST and CHA 2 DS -VASc scores for predicting new-onset atrial fibrillation (AF) in patients with ST-elevation myocardial infarction (STEMI) after percutaneous coronary intervention (PCI), as well to develop novel prognostic models based on machine learning methods. Material methods This single-center retrospective study was conducted using data from 3449 electronic health records STEMI. Two groups individuals were identified, first which included 312 (9%) AF postoperative period PCI, second — 3139 (91%) without cardiac arrhythmia. predict AF, univariate multivariate logistic regression (ULR MLR), decision tree (DT), artificial neural networks (ANN) used. Results The results showed that 6 analyzed scores, only 4 (mc2HEST, HATCH) have an acceptable potential documented by AUC metrics ULR developed basis sum points each score (AUC 0,736, 0,731, 0,71 0,702, respectively). integrative ANN model, combining resource demonstrated higher accuracy than DT MLR 0,759 vs 0,745 0,755, p-value<0,0001). Conclusion Further studies aimed at improving quality STEMI PCI may involve searching predictors characterizing severity involvement its restoration, inflammatory response, electrophysiological status, etc.

Language: Английский

Citations

0