Machine learning based model for risk prediction after ST-Elevation myocardial infarction: Insights from the North India ST elevation myocardial infarction (NORIN-STEMI) registry

Shetty, Manu Kumar; Kunal, Shekhar; Mp, Girish; Qamar, Arman; Arora, Sameer; Hendrickson, Michael; Mohanan, Padhinhare P.; Gupta, Puneet; Ramakrishnan, S; Yadav, Rakesh Kumar; Bansal, Ankit; Zachariah, George; Batra, Vishal; Bhatt, Deepak L.; Gupta, Anubha; Gupta, Mohit

doi:10.1016/j.ijcard.2022.05.023

Cited by 7 publications

(8 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We focused on the prediction in patients with STEMI undergoing PCI to understand the residual risk after revascularization. Several investigations have focused on risk stratification in patients with STEMI using ML algorithms ( 41 , 42 ). Nevertheless, only a few studies have focused on the long-term risk following MACEs ( 43 , 44 ).…”

Section: Discussionmentioning

confidence: 99%

Prediction models for major adverse cardiovascular events following ST-segment elevation myocardial infarction and subgroup-specific performance

Chen

Tan

et al. 2023

Front. Cardiovasc. Med.

View full text Add to dashboard Cite

BackgroundST-segment elevation myocardial infarction (STEMI) patients are at a high residual risk of major adverse cardiovascular events (MACEs) after revascularization. Risk factors modify prognostic risk in distinct ways in different STEMI subpopulations. We developed a MACEs prediction model in patients with STEMI and examined its performance across subgroups.MethodsMachine-learning models based on 63 clinical features were trained in patients with STEMI who underwent PCI. The best-performing model (the iPROMPT score) was further validated in an external cohort. Its predictive value and variable contribution were studied in the entire population and subgroups.ResultsOver 2.56 and 2.84 years, 5.0% and 8.33% of patients experienced MACEs in the derivation and external validation cohorts, respectively. The iPROMPT score predictors were ST-segment deviation, brain natriuretic peptide (BNP), low-density lipoprotein cholesterol (LDL-C), estimated glomerular filtration rate (eGFR), age, hemoglobin, and white blood cell (WBC) count. The iPROMPT score improved the predictive value of the existing risk score, with an increase in the area under the curve to 0.837 [95% confidence interval (CI): 0.784–0.889] in the derivation cohort and 0.730 (95% CI: 0.293–1.162) in the external validation cohort. Comparable performance was observed between subgroups. The ST-segment deviation was the most important predictor, followed by LDL-C in hypertensive patients, BNP in males, WBC count in females with diabetes mellitus, and eGFR in patients without diabetes mellitus. Hemoglobin was the top predictor in non-hypertensive patients.ConclusionThe iPROMPT score predicts long-term MACEs following STEMI and provides insights into the pathophysiological mechanisms for subgroup differences.

show abstract

Section: Discussionmentioning

confidence: 99%

Prediction models for major adverse cardiovascular events following ST-segment elevation myocardial infarction and subgroup-specific performance

Chen

Tan

et al. 2023

Front. Cardiovasc. Med.

View full text Add to dashboard Cite

show abstract

“…Consequently, machine learning algorithms are the best in terms of developing even more advanced models for risk predictability, since those algorithms are able to harvest and process a great number of variables, which are not necessarily preselected, as well as eliminating any assumptions for precision purposes. Moreover, in a recent study published by (Shetty et al, 2022), the authors brie y discussed an experiment that was carried out in developing countries, where machine learning models including Decision Tree, XGBoost, Random Forest and Naïve Bayes were used for cardiac risk predictability after certain patients have gone through ST-elevation myocardial infarction. The results of the experiment were astounding, when they concluded that the models had a far better 30 days mortality predictions as opposed to the conventional regression-driven models.…”

Section: Cardiologymentioning

confidence: 99%

Accelerating Change in Healthcare: Leveraging Kotter's Model for a Successful Integration of Artificial Intelligence.

Alrabie

2023

Preprint

View full text Add to dashboard Cite

Artificial intelligence in healthcare has a significant potential to deliver more efficient and effective medical services, as opposed to the current conventional practices. Although the transitioning into an artificial intelligence-based healthcare is considerably challenging, numerous cases around the world proven efficient and effective. The objective of this paper is to investigate why Kotter’s change management model is the favourable model for said change. In order to achieve that objective, a qualitative set of data has been collected and analysed. Kotter’s model has been validated based on a comparative review as well as models analysis counting in the most commonly used change management models. The paper concludes the necessity for a change management model, considering the magnitude and novelty of the change, which consequently indicates that in order to improve the delivery of medical services, by reducing cost, increasing accuracy and precision, an artificial intelligence initiative must be put in place, aided by change management. The paper also offers a framework to aid with mitigating and overcoming failures and setbacks when implementing the model.

show abstract

“…Since ML algorithms can use far larger number of variables, does not require preselection of important variables, and avoids prior assumptions, it is best suited for development of clinical risk prediction models. 4 ML models can incorporate both traditional as well as nontraditional and unknown risk factors for proper risk stratification. Multiple ML models such as Naïve Bayes, k-nearest neighbors (KNN), decision tree, random forest and XGBoost have been used previously for risk prediction of adverse cardiac events following STEMI.…”

Section: Ai In Preventive Cardiologymentioning

confidence: 99%

“… 5 The recently proposed MERC model among patients with STEMI in low-and-middle income countries had an improved 30-day mortality prediction as compared to traditional logistic regression-based models. 4 …”

Section: Ai In Preventive Cardiologymentioning

confidence: 99%

Artificial intelligence in cardiology: The past, present and future

Gupta

Kunal

et al. 2022

Indian Heart Journal

Self Cite

View full text Add to dashboard Cite

Machine learning based model for risk prediction after ST-Elevation myocardial infarction: Insights from the North India ST elevation myocardial infarction (NORIN-STEMI) registry

Cited by 7 publications

References 27 publications

Prediction models for major adverse cardiovascular events following ST-segment elevation myocardial infarction and subgroup-specific performance

Prediction models for major adverse cardiovascular events following ST-segment elevation myocardial infarction and subgroup-specific performance

Accelerating Change in Healthcare: Leveraging Kotter's Model for a Successful Integration of Artificial Intelligence.

Artificial intelligence in cardiology: The past, present and future

Contact Info

Product

Resources

About