Is neural network better than logistic regression in death prediction in patients after ST-segment elevation myocardial infarction?

Abstract

Background: There is a need to develop patient classification methods and adjust post-discharge care to improve survival after ST-segment elevation myocardial infarction (STEMI). Aims:The study aimed to determine whether a neural network (NN) is better than logistic regression (LR) in mortality prediction in STEMI patients. Methods:The study included patients from the Polish Registry of Acute Coronary Syndromes (PL--ACS). Patients with the first anterior STEMI treated with the primary percutaneous coronary intervention (pPCI) of the left anterior descending (LAD) artery between 2009 and 2015 and discharged alive were included in the study. Patients were randomly divided into three groups: learning (60%), validation (20%), and test group (20%). Two models (LR and NN) were developed to predict 6-month all-cause mortality. The predictive values of LR and NN were evaluated with the Area Under the Receiver Operating Characteristics Curve (AUROC), and the comparison of AUROC for learning and test groups was performed. Validation of both methods was performed in the same group.Results: Out of 175 895 patients with acute coronary syndrome, 17 793 were included in the study. The 6-month all-cause mortality was 5.9%. Both NN and LR had good predictive values. Better results were obtained in the NN approach regarding the statistical quality of the models -AUROC 0.8422 vs. 0.8137 for LR (P <0.0001). AUROCs in the test groups were 0.8103 and 0.7939, respectively (P = 0.037). Conclusions:The neural network may have a better predictive value for mortality than logistic regression in patients after the first STEMI.

Digital tools in cardiac reperfusion pathways: A systematic review

“…For example, Niedziela et al retrospectively applied both a neural network and a logistic regression model to 175,895 patients recorded in the Polish Registry of Acute Coronary Syndromes (PL-ACS) between 2009 and 2015. 19 These patients, split into three groups (60% learning, 20% validation and 20% test) were used to model 6-month all-cause mortality rates. Subsequent analysis showed the neural network to have higher accuracy in predicting mortality, with an area under the curve (AUROC) of 0.8103 versus 0.7939 for the logistic regression model (p=0.037).…”

“… 15 AI models in their data-processing capability proved superior to conventional clinical algorithms in predicting hospital readmission rates or perioperative morbidity, in part because of their ability to include a far greater number of patient variables in their analysis. 19 …”

Impact of Air Pollution and COVID-19 Infection on Periprocedural Death in Patients with Acute Coronary Syndrome

“…An even more interesting statistical tool for the analysis of large amounts of data with the use of long-term databases is the creation of neural networks. Niedziela et al compared the creation and use of a neural network in predicting the risk of death in STEMI patients [ 50 ]. Li et al also used a mathematical model of neural networks to study heavy metal air pollution in major Chinese cities [ 51 ].…”

Answering Clinical Questions Using Machine Learning: Should We Look at Diastolic Blood Pressure When Tailoring Blood Pressure Control?

“…ML prediction results are now widely used in consumer and medical decision-making algorithms, showing high efficiency. In the field of cardiology and imaging medicine, practitioners use ML algorithms [30][31][32][33][34]; yet, clinical study data are not often analyzed in that way [35,36]. It has been changing, though.…”