Machine learning in predicting immediate and long-term outcomes of myocardial revascularization: a systematic review

Гельцер, Б. И.; Рублев, В. Ю.; Циванюк, М. М.; Шахгельдян, К. И.

doi:10.15829/1560-4071-2021-4505

Cited by 3 publications

(1 citation statement)

References 56 publications

(45 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Обсуждение Одним из наиболее востребованных и перспективных направлений Национального проекта "Здраво охранение" является создание информационных систем оценки рисков сердечно-сосудистых заболеваний и их осложнений, в т.ч. ассоциированных с реваскуляризацией миокарда [10][11][12][13]. Реализация этой задачи базируется на применении современных методов МО, с помощью которых осуществляется интеллектуальный анализ больших данных и разрабатываются модели для предсказания неблагоприятных событий в послеоперационном периоде и смертности на различных горизонтах наблюдения.…”

Section: материал и методыunclassified

Phenotyping of risk factors and prediction of inhospital mortality in patients with coronary artery disease after coronary artery bypass grafting based on explainable artificial intelligence methods

Geltser,

Shakhgeldyan,

Rublev

et al. 2023

Russ J Cardiol

Self Cite

View full text Add to dashboard Cite

Aim. To develop predictive models of inhospital mortality (IHM) in patients with coronary artery disease after coronary artery bypass grafting (CABG), taking into account the results of phenotyping of preoperative risk factors.Material and methods. This retrospective study was conducted based on the data of 999 electronic health records of patients (805 men, 194 women) aged 35 to 81 years with a median (Me) of 63 years who underwent on-pump elective isolated CABG. Two groups of patients were distinguished, the first of which was represented by 63 (6,3%) patients who died in the hospital during the first 30 days after CABG, the second — 936 (93,7%) with a favorable outcome. Preoperative clinical and functional status was assessed using 102 factors. Chi-squares, Fisher, Mann-Whitney methods were used for data processing and analysis. Threshold values of predictors were determined by methods, including maximizing the ratio of true positive IHM cases to false positive ones. Multivariate logistic regression (MLR) was used to develop predictive models. Model accuracy was assessed using 3 following metrics: area under the ROC curve (AUC), sensitivity (Sens), and specificity (Spec).Results. An analysis of preoperative status of patients made it possible to identify 28 risk factors for IHM, combined into 7 phenotypes. The latter formed the feature space of IHM prognostic model, in which each feature demonstrates the patient’s compliance with a certain risk factor phenotype. The author’s MLR model had high quality metrics (AUC-0,91; Sen-0,9 and Spec-0,85).Conclusion. The developed data processing and analysis algorithm ensured high quality of preoperative risk factors identification and IHM prediction after CABG. Prospects for further research on this issue are related to the improvement of explainable artificial intelligence technologies, which allow developing information systems for managing clinical practice risks.

show abstract

Section: материал и методыunclassified

Phenotyping of risk factors and prediction of inhospital mortality in patients with coronary artery disease after coronary artery bypass grafting based on explainable artificial intelligence methods

Geltser,

Shakhgeldyan,

Rublev

et al. 2023

Russ J Cardiol

Self Cite

View full text Add to dashboard Cite

show abstract

Prediction of in-hospital mortality in patients with ST-segment elevation acute myocardial infarction after percutaneous coronary intervention

Geltser,

Shahgeldyan,

Domzhalov

et al. 2023

Russ J Cardiol

Self Cite

View full text Add to dashboard Cite

Aim. Development of models for predicting in-hospital mortality (IHM) in patients with ST-segment elevation myocardial infarction (STEMI) after percutaneous coronary intervention (PCI) based on multivariate logistic regression (MLR).Material and methods. This retrospective cohort study of 4735 electronic health records of patients (3249 men and 1486 women) with STEMI aged 26 to 93 years with a median of 63 years who underwent PCI was performed. Two groups of persons were identified, the first of which consisted of 321 (6,8%) patients who died in the hospital, while the second — 4413 (93,2%) patients with a favorable PCI outcome. To develop predictive models, univariate logistic regression (ULR) and MLR were used. Model accuracy was assessed using 3 following metrics: area under the ROC curve (AUC), sensitivity, and specificity. The end point was represented by the IHM score in STEMI patients after PCI.Results. Statistical analysis made it possible to identify factors that are linearly associated with IHM. ULR was used to determine their weight coefficients characterizing the predictive potential. IHM predictive algorithms based on GRACE scale predictors, represented both by ULR model and by 5 factors in continuous MLR model, had acceptable predictive accuracy (AUC — 0,83 and 0,86, respectively). The MLR model had the best quality metrics, the structure of which, in addition to 5 GRACE factors, included left ventricular ejection fraction (LVEF) parameters and white blood cell (WBC) count (AUC — 0,93, sensitivity — 0,87, specificity — 0,86) . The greatest contribution to endpoint was associated with the Killip class and LVEF, and the smallest contribution was associated with WBC and the age of patients.Conclusion. The predictive accuracy of the developed MLR models was higher than that of the GRACE score. The model with the structure represented by 5 factors GRACE, LV EF and WBC had the highest quality metrics.

show abstract

Elements of artificial intelligence in a predictive personalized model of pharmacotherapy choice in patients with heart failure with mildly reduced ejection fraction of ischemic origin

Osipova,

Kontsevaya,

Demko

et al. 2023

Cardiovasc Ther Prev

View full text Add to dashboard Cite

Aim. To create and train a neural network (NN) of a predictive personalized model of pharmacotherapy choice in patients with heart failure with mildly reduced ejection fraction (HFmrEF) of ischemic origin.Material and methods. The study included 170 people with HFmrEF of ischemic origin, who on the background standard pharmacotherapy, received a beta-blocker (BB) or BB+mineralocorticoid receptor antagonist eplerenone (EP): bisoprolol (BIS); BIS+EP; nebivolol (NEB); NEB+EP. Patients underwent echocardiography and were analyzed for serum aldosterone (AL), tumor necrosis factor-α (TNF-α), matrix metalloproteinase 9 (MMP-9). To create the NN model, the following approximate predictive function of parameters was used: age, AL, TNF-α, MMP-9, sphericity index (SI), type of pharmacotherapy. The result of this function is a parameter vector: AL, TNF-α, MMP-9, SI and quality of life (QOL). The designed NN model is implemented in the Matlab software package for solving machine learning and Data Science problems. The NN model is represented as a connected graph and NN function. Dichotomous analysis was used to compare the effect of treatment types in pairs. For intergroup comparison of therapy, the Wilcoxon W test method. The critical significance (p) was considered <0,05.Results. As a result of model inference, the predicted clinical parameters of patients were obtained, depending on the influence of pharmacotherapy type on the levels of AL, TNF-α, MMP-9, and SI. Function approximation of the distribution was constructed. Determination coefficient R2 of approximating functions was ≥0,92. The calculated values for the BIS therapy groups were obtained; BIS+EP — 169,59, 82,30, 15,26 and 52,92; NEB — 186,42, 87,65, 16,10 and 57,22; NEB+EP — 171,17, 71,90, 14,22 and 58,68, respectively. There were following mean values in the vector of initial states (before therapy): AL, MMP-9, TNF-α, and QOL — 205,84, 174,16, 18,32, and 50,71, respectively. The greatest negative changes of AL, MMP-9, TNF-α (p<0,05) was observed in the NEP+EP group.Conclusion. In the course of the study, using artificial intelligence, a predictive model of a personalized approach to pharmacotherapy choice in patients with HFmrEF of ischemic origin was developed and trained. It has been established that NEP+EP therapy has the greatest effect.

show abstract

Machine learning in predicting immediate and long-term outcomes of myocardial revascularization: a systematic review

Cited by 3 publications

References 56 publications

Phenotyping of risk factors and prediction of inhospital mortality in patients with coronary artery disease after coronary artery bypass grafting based on explainable artificial intelligence methods

Phenotyping of risk factors and prediction of inhospital mortality in patients with coronary artery disease after coronary artery bypass grafting based on explainable artificial intelligence methods

Prediction of in-hospital mortality in patients with ST-segment elevation acute myocardial infarction after percutaneous coronary intervention

Elements of artificial intelligence in a predictive personalized model of pharmacotherapy choice in patients with heart failure with mildly reduced ejection fraction of ischemic origin

Contact Info

Product

Resources

About