scholarly journals A Feature-Driven Decision Support System for Heart Disease Prediction Based on Fisher's Discriminant Ratio and Backpropagation Algorithm

2020 ◽  
Vol 11 (2) ◽  
pp. 65
Author(s):  
Muh Dimas Yudianto ◽  
Tresna Maulana Fahrudin ◽  
Aryo Nugroho

Coronary heart disease included a group of cardiovascular, and it is a leading cause of death in low and middle-income countries. Risk factors for coronary heart disease are divided into two, namely primary and secondary risk factors. The need to identify characteristics or risk factors in heart disease patients by making the classification model. The modeling of heart disease classification to know how the system can able to reach the best prediction accuracy. Fisher's Discriminant Ratio is one of the methods for feature selection, which is used to get high discriminant features. While Backpropagation is one of the classification models to recognize patterns in heart disease patients. The experiment results showed that the accuracy of the classification model using 13 original features reached 92%. By reducing the features based on the score of the feature selection, then the lowest feature was removed from original features and left there were 12 features involved in the classification model which the accuracy increased to 93%. Furthermore, the results of determining the threshold (accuracy does not decrease continuously) and consider the effect of eliminating the lowest features that are considered quite fluctuating on accuracy. The accuracy reached 90% by eliminating the five lowest features and left eight existing features.

2020 ◽  
Author(s):  
Paul Novosad ◽  
Radhika Jain ◽  
Alison Campion ◽  
Sam Asher

ABSTRACTObjectiveTo model how known COVID-19 comorbidities will affect mortality rates and the age distribution of mortality in a large lower middle income country (India), as compared with a high income country (England), and to identify which health conditions drive any differences.DesignModelling study.SettingEngland and India.Participants1,375,548 respondents aged 18 to 99 to the District Level Household Survey-4 and Annual Health Survey in India. Additional information on health condition prevalence on individuals aged 18 to 99 was obtained from the Health Survey for England and the Global Burden of Diseases, Risk Factors, and Injuries Studies (GBD).Main outcome measuresThe primary outcome was the proportional increase in age-specific mortality in each country due to the prevalence of each COVID-19 mortality risk factor (diabetes, hypertension, obesity, chronic heart disease, respiratory illness, kidney disease, liver disease, and cancer, among others). The combined change in overall mortality and the share of deaths under 60 from the combination of risk factors was estimated in each country.ResultsRelative to England, Indians have higher rates of diabetes (10.6% vs. 8.5%), chronic respiratory disease (4.8% vs. 2.5%), and kidney disease (9.7% vs. 5.6%), and lower rates of obesity (4.4% vs. 27.9%), chronic heart disease (4.4% vs. 5.9%), and cancer (0.3% vs. 2.8%). Population COVID-19 mortality in India relative to England is most increased by diabetes (+5.4%) and chronic respiratory disease (+2.3%), and most reduced by obesity (−9.7%), cancer (−3.2%), and chronic heart disease (−1.9%). Overall, comorbidities lower mortality in India relative to England by 9.7%. Accounting for demographics and population health explains a third of the difference in share of deaths under age 60 between the two countries.ConclusionsKnown COVID-19 health risk factors are not expected to have a large effect on aggregate mortality or its age distribution in India relative to England. The high share of COVID-19 deaths from people under 60 in low- and middle-income countries (LMICs) remains unexplained. Understanding mortality risk associated with health conditions prevalent in LMICs, such as malnutrition and HIV/AIDS, is essential for understanding differential mortality.SUMMARY BOXWhat is already known on this topicCOVID-19 infections in low- and middle-income countries (LMICs) are rising rapidly, with the burden of mortality concentrated at much younger ages than in rich countries.A range of pre-existing health conditions can increase the severity of COVID-19 infections.It is feared that poor population health may worsen the severity of the pandemic in LMICs.What this study addsThe COVID-19 comorbidities that have been studied to date may have only a very small effect on aggregate mortality in India relative to England and do not shift the mortality burden toward lower ages at all.India’s younger demographics can explain only a third of the substantial difference in the share of deaths under age 60 between India and England.However, mortality risk associated with health conditions prevalent in LMICs, such as malnutrition and HIV/AIDS, is unknown and research on this topic is urgently needed.


2010 ◽  
Vol 35 (2) ◽  
pp. 72-115 ◽  
Author(s):  
Thomas A. Gaziano ◽  
Asaf Bitton ◽  
Shuchi Anand ◽  
Shafika Abrahams-Gessel ◽  
Adrianna Murphy

2021 ◽  
pp. 413-428
Author(s):  
Ana Rita Antunes ◽  
Lino A. Costa ◽  
Ana Maria A. C. Rocha ◽  
Ana Cristina Braga

Author(s):  
Chenran Wang ◽  
Yanghua Sun ◽  
Di Jiang ◽  
Chunping Wang ◽  
Shiwei Liu

Background Ischemic heart disease (IHD) imposes the greatest disease burden globally, especially in low‐ and middle‐income countries (LMICs). We aim to examine the population‐attributable fraction and risk‐attributable death and disability‐adjusted life years (DALYs) for IHD in 137 low‐ and middle‐income countries. Methods and Results Using comparative risk assessment framework from the 2019 Global Burden of Disease study, the population‐attributable fraction and IHD burden (death and DALYs) attributable to risk factors in low‐income countries, lower‐middle‐income countries (LMCs), and upper‐middle‐income countries were assessed from 2000 to 2019. In 2019, the population‐attributable fraction (%) of IHD deaths in relation to all modifiable risk factors combined was highest in lower‐middle‐income countries (94.2; 95% uncertainty interval, 91.9–96.2), followed by upper‐middle‐income countries (93.5; 90.4–95.8) and low‐income countries (92.5; 90.0–94.7). There was a >13‐fold difference between Peru and Uzbekistan in age‐standardized rates (per 100 000) of attributable death (44.3 versus 660.4) and DALYs (786.7 versus 10506.1). Dietary risks accounted for the largest proportion of IHD’s behavioral burden in low‐ and middle‐income countries, primarily attributable to diets low in whole grains. High systolic blood pressure and high low‐density lipoprotein cholesterol remained the 2 leading causes of DALYs, with the former topping the list in 116 countries, while the latter led in 21 of the 137 countries. Compared with 2000 to 2010, the increases in risk‐attributable deaths and DALYs among upper‐middle income countries were slower from 2010 to 2019, while the trends in low‐income countries and lower‐middle income countries were opposite. Conclusions IHD’s attributable burden remains high in low‐ and middle‐income countries. Considerable heterogeneity was observed among different income‐classified regions and countries.


2019 ◽  
Author(s):  
Carmen Arroyo-Quiroz ◽  
Tonatiuh Barrientos-Gutierrez ◽  
Martin O'Flaherty ◽  
Maria Guzman-Castillo ◽  
Lina Sofia Palacio Mejia ◽  
...  

Abstract Background : Coronary heart disease (CHD) mortality rates have decreased in most countries but increased in low and middle-income countries. Few studies have analyzed CHD mortality trends in Latin America, specifically trends in young-adults and the effect of correcting these comparisons for nonspecific causes of death (garbage codes).Objective: To describe and compare standardized, age-specific, and garbage-code corrected mortality trends for CHD from 1985 to 2015 in Argentina, Colombia and Mexico. Methods: CHD deaths were grouped by country, year of registration, sex and 10-year age bands to calculate age-adjusted and age and sex specific rates for adults aged ≥25. We corrected for garbage-codes using the Global Burden of Disease methodology. Finally, we fitted Joinpoint regression models.Results: In 1985, age-standardized mortality rates per 100,000 were 136.6 in Argentina, 160.6 in Colombia and 87.51 in Mexico. Compared to 2015, mortality fell in Argentina and Colombia (51% and 6.5% respectively) and increased by 61% in Mexico. The steepest decline was observed in Argentinian women, and the sharpest increment in Mexican men. There has been an upward trend in young Mexicans since 1985. Garbage-code corrections produced increases in mortality rates, particularly in Argentina: approximately 80 additional deaths per 100,000 (14 in Colombia and 13 in Mexico). Conclusions: Latin American countries are at different stages of the epidemic. The disease burdens are bigger after correcting for misclassification. Although CHD mortality is falling in Argentina, the modest falls in Colombia and substantial rises in Mexico highlight the region’s need for effective, population-wide prevention policies.


2019 ◽  
Author(s):  
Carmen Arroyo-Quiroz ◽  
Tonatiuh Barrientos-Gutierrez ◽  
Martin O'Flaherty ◽  
Maria Guzman-Castillo ◽  
Lina Sofia Palacio Mejia ◽  
...  

Abstract Background: Coronary heart disease (CHD) mortality rates have decreased in most countries, but increased in low and middle-income countries. Few studies have analyzed CHD mortality trends in Latin America, specifically the trends in young-adults and the effect of correcting these comparisons for nonspecific causes of death (garbage codes). Objective: To describe and compare standardized, age-specific, and garbage-code corrected mortality trends for CHD from 1985 to 2015 in Argentina, Colombia, and Mexico. Methods: CHD deaths were grouped by country, year of registration, sex, and 10-year age bands to calculate age-adjusted and age and sex specific rates for adults aged ≥25. We corrected for garbage-codes using the Global Burden of Disease methodology. Finally, we fitted Joinpoint regression models. Results: In 1985, age-standardized mortality rates per 100,000 were 136.6 in Argentina, 160.6 in Colombia and 87.51 in Mexico. Compared to 2015, mortality fell in Argentina and Colombia (51% and 6.5% respectively) and increased by 61% in Mexico. The steepest decline was observed in Argentinian women and the sharpest increment in Mexican men. There has been an upward trend in young Mexicans since 1985. Garbage-code corrections produced increases in mortality rates, particularly in Argentina: approximately 80 additional deaths per 100,000 (14 in Colombia and 13 in Mexico). Conclusions: Latin American countries are at different stages of the epidemic. The disease burdens are bigger after correcting for misclassification. Although CHD mortality is falling in Argentina, the modest falls in Colombia and substantial rises in Mexico highlight the region’s need for effective, population-wide prevention policies.


Sign in / Sign up

Export Citation Format

Share Document