Machine Learning Approach to Extract Diagnostic and Prognostic Thresholds: Application in Prognosis of Cardiovascular Mortality

Mena, Luis J.; Orozco, Eber E.; Felix, Vanessa G.; Ostos, Rodolfo; Melgarejo, Jesus; Maestre, Gladys E.
January 2012
Computational & Mathematical Methods in Medicine;Jan2012, p1
Academic Journal
Machine learning has become a powerful tool for analysing medical domains, assessing the importance of clinical parameters, and extracting medical knowledge for outcomes research. In this paper, we present a machine learning method for extracting diagnostic and prognostic thresholds, based on a symbolic classification algorithm called REMED.We evaluated the performance of our method by determining new prognostic thresholds for well-known and potential cardiovascular risk factors that are used to support medical decisions in the prognosis of fatal cardiovascular diseases. Our approach predicted 36% of cardiovascular deaths with 80% specificity and 75% general accuracy. The new method provides an innovative approach that might be useful to support decisions about medical diagnoses and prognoses.


Related Articles

  • Training in nuclear cardiology: What's new? Hage, Fadi; Hage, Fadi G // Journal of Nuclear Cardiology;Oct2015, Vol. 22 Issue 5, p861 

    No abstract available.

  • Diagnosis, Prognosis and Therapeutic Role of Circulating miRNAs in Cardiovascular Diseases. Sayed, Ali Sheikh Md; Xia, Ke; Salma, Umme; Yang, Tianlun; Peng, Jun // Heart, Lung & Circulation;Jun2014, Vol. 23 Issue 6, p503 

    Cardiovascular diseases (CVD) are the leading cause of morbidity and mortality in the world. Although much progress has been made for cardiovascular diseases in diagnosis, treatment and prognosis during the past two decades, the clinical need for a novel diagnostic biomarker and new therapeutic...

  • ECG BASELINE WANDER REMOVAL USING EMPIRICAL MODE DECOMPOSITION. Rohila, Ashish; Giri, V. K. // Far East Journal of Electronics & Communications;Dec2015, Vol. 15 Issue 2, p121 

    Electrocardiogram (ECG) is a widely used non invasive method for diagnosis of cardiovascular diseases. While recording, baseline wander enters in ECG signals due to movement of electrodes and respiration. In order to extract clinical information with high accuracy, there is a need to pre-process...

  • High sensitivity cardiac troponin T in patients with immunoglobulin light chain amyloidosis. Dispenzieri, A.; Gertz, M. A.; Kumar, S. K.; Lacy, M. Q.; Kyle, R. A.; Saenger, A. K.; Grogan, M.; Zeldenrust, S. R.; Hayman, S. R.; Buadi, F.; Greipp, P. R.; Leung, N.; Russell, S. R.; Dingli, D.; Lust, J. A.; Rajkumar, S. V.; Jaffe, A. S. // Heart;Mar2014, Vol. 100 Issue 5, p383 

    Objectives: To define whether the high sensitivity cardiac troponin T (hs-cTnT) assay in patients with immunoglobulin light chain amyloidosis (AL) improves risk prediction. Background: Cardiac involvement is the major cause of death in patients with AL amyloidosis. Risk stratification is...

  • Diagnosis and Prognosis of Cardiovascular Diseases on the Basis of Neural Networks. Yasnitsky, L.; Dumler, A.; Bogdanov, K.; Poleschuk, A.; Cherepanov, F.; Makurina, T.; Chugaynov, S. // Biomedical Engineering;Sep2013, Vol. 47 Issue 3, p160 

    A neural expert network system for diagnosis and prognosis of cardiovascular diseases was developed. Computer experiments using the system revealed that the current medical practice of recommending hypocholesteric diet, avoidance of pernicious habits, limitation in consumption of coffee and...

  • Whole-grain consumption and the risk of all-cause, CVD and cancer mortality: a meta-analysis of prospective cohort studies – CORRIGENDUM. Wei, Honglei; Gao, Zong; Liang, Rui; Li, Zengqiang; Hao, Hong; Liu, Xu // British Journal of Nutrition;9/14/2016, Vol. 116 Issue 5, p952 

    A correction to the article "Whole-grain Consumption and the Risk of All-Cause, CVD and Cancer Mortality: A Meta-Analysis of Prospective Cohort Studies" by Honglei Wei and colleagues is presented.

  • ADAPTIVE MODEL FOR SEMI-AUTOMATIC MEDICAL DATA ANALYSIS. Andreeva, Plamena; Sotirov, Tihomir; Lahtchev, Lubomir; Dimitrova, Maya // Proceedings of the International Conference on Information Techn;2008, Vol. 2, p275 

    The proposed adaptive model makes diagnosis on the basis of semi-automatic data analysis with recent machine learning methods. The objective is to provide an intelligent computer-based support for medical specialists. Adaptive systems can act in a robust way and obtain flexible diagnosis based...

  • Diagnosis and management of acute heart failure. Ural, Dilek; Çavuşoğlu, Yüksel; Eren, Mehmet; Karaüzüm, Kurtuluş; Temizhan, Ahmet; Yılmaz, Mehmet Birhan; Zoghi, Mehdi; Ramassubu, Kumudha; Bozkurt, Biykem // Anatolian Journal of Cardiology / Anadolu Kardiyoloji Dergisi;Nov2015, Vol. 15 Issue 11, p860 

    Acute heart failure (AHF) is a life threatening clinical syndrome with a progressively increasing incidence in general population. Turkey is a country with a high cardiovascular mortality and recent national statistics show that the population structure has turned to an 'aged' population. As a...

  • Learning Tract Variables with Distal Supervised Learning Model. Ying Chen; Shaobai Zhang // Journal of Networks;Feb2013, Vol. 8 Issue 2, p397 

    This paper compared the performance of tract variables (TVs) estimation with pellet trajectory estimation by using the trajectory mixture density networks (TMDN), and the result indicated that TVs can be estimated more accurately than the pellet trajectories. We used eight tract variables as...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics