Meet Inspiring Speakers and Experts at our 3000+ Global Conference Series Events with over 1000+ Conferences, 1000+ Symposiums
and 1000+ Workshops on Medical, Pharma, Engineering, Science, Technology and Business.

Explore and learn more about Conference Series : World's leading Event Organizer

Back

Tatjana Gligorijevic

Tatjana Gligorijevic

University of Belgrade, Serbia

Title: Follow up and risk assessment using artificial neural networks in patients with myocardial infarction

Biography

Biography: Tatjana Gligorijevic

Abstract

Artificial Neural Networks (ANN) is learning models that mimic the principles of morphological and functional organization of biological neurons, which has the capacity to promote and facilitate current statistical methods. The aim of this paper is to identify individuals with high risk of all causes of mortality after acute myocardial infarction using ANN, and to assess their survival rates. A total of 1,705 consecutive patients who underwent 24-hour ECG monitoring, short ECG analysis, non-invasive beat-to-beat heart rate variability and baroreflex sensitivity were followed for 3 years; of these, 286 patients died. Depressed baroreflex sensitivity BRS (≤5.33 ms/mmHg) was independently related to increased risk of mortality. The proposed neural network classifier showed good performance for survival prediction. Neural network architecture with 25 neurons in the first hidden layer and 30 neurons in the second hidden layer showed the best classification performance 88% accuracy, 81% sensitivity, 93% specificity and 0.85 F-measure. The error threshold value of 0.03 showed the nest results. These findings support the theory that patients with high sympathetic activity have an increased risk of mortality independent of other risk factors. The artificial intelligence infrastructure can reliably identify individuals with higher risk.

Figure-1: Kaplan-Meier survival curves for cardiac death in patients with reduced BRS at or below 5.33 ms/mmHg in early phase after acute myocardial infarction.

References

1.  Bigi R, Gregori D, Cortigiani L, Desideri A, Chiarotto F A and Toffolo G M (2005) Artificial neural networks and robust Bayesian classifiers for risk stratification following uncomplicated myocardial infarction. International Journal of Cardiology; 101(3): 481-487.

2. Choi W S, Cho Y, Kim N Y, Kang J K, Kim K H, Park, S H and Jun J E (2010) Prognostic value of standard electrocardiographic parameters for predicting major adverse cardiac events after acute myocardial infarction. Circulation; 122: 21.

3. Exner D V (2009) Noninvasive risk stratification after myocardial infarction: rationale, current evidence and the need for definitive trials. Canadian Journal of Cardiology; 25, 21A: 27A.

4. Lin J F, Hsu S Y, Wu S, Teng M S, Chou H H, Cheng S T and Ko Y L (2015) QT interval independently predicts mortality and heart failure in patients with ST-elevation myocardial Infarction. International Journal of Medical Sciences; 12(12): 968.

5. Raji C G and Chandra S V (2016) Graft survival prediction in liver transplantation using artificial neural network models. Journal of Computational Science; 16, 72-78.