A Cox-based Model for Predicting the Risk of Cardiovascular Disease

This research is aimed to develop a 10-year risk prediction model and identify key contributing Cardiovascular Disease (CVD) risk factors. A Cox proportional hazard regression method was adopted to design and develop the risk model. We used Framingham Original Cohort dataset of 5079 men and women aged 30 62 years, who had no overt symptoms of CVD at the baseline. Out of them, 3189 (62.78%) had an actual CVD event. A 10-year CVD risk model based on multiple risk factors (such as age, sex, body mass index (BMI), hypertension, systolic blood pressure, cigarettes per day, pulse rate, and diabetes) was developed in which heart rate was identified as one of the novel contributing risk factors. We validated the model via statistical and empirical validation methods. The proposed model achieved an acceptable discrimination and calibration with C-index (receiver operating characteristic (ROC)) being 0.71 from the validation dataset.

[1]  Maria Lindén,et al.  A Systematic Review of Wearable Patient Monitoring Systems – Current Challenges and Opportunities for Clinical Adoption , 2017, Journal of Medical Systems.

[2]  Dong Zhao,et al.  Cardiovascular risk assessment: a global perspective , 2015, Nature Reviews Cardiology.

[3]  Rod Jackson,et al.  Web-based assessment of cardiovascular disease risk in routine primary care practice in New Zealand: the first 18,000 patients (PREDICT CVD-1). , 2006, The New Zealand medical journal.

[4]  D.,et al.  Regression Models and Life-Tables , 2022 .

[5]  L. J. Wei,et al.  The Robust Inference for the Cox Proportional Hazards Model , 1989 .

[6]  John P. A. Ioannidis,et al.  Opportunities and challenges in developing risk prediction models with electronic health records data: a systematic review , 2017, J. Am. Medical Informatics Assoc..

[7]  A. Alavi,et al.  Opportunities and Challenges , 1998, In Vitro Diagnostic Industry in China.

[8]  Naveen Garg,et al.  Comparison of different cardiovascular risk score calculators for cardiovascular risk prediction and guideline recommended statin uses , 2017, Indian heart journal.

[9]  Gary S Collins,et al.  Sample size considerations for the external validation of a multivariable prognostic model: a resampling study , 2015, Statistics in medicine.

[10]  V. Fuster,et al.  Global burden of CVD: focus on secondary prevention of cardiovascular disease. , 2015, International journal of cardiology.

[11]  Heye Zhang,et al.  Assessment of Biofeedback Training for Emotion Management Through Wearable Textile Physiological Monitoring System , 2015, IEEE Sensors Journal.

[12]  M. Pencina,et al.  General Cardiovascular Risk Profile for Use in Primary Care: The Framingham Heart Study , 2008, Circulation.

[13]  J. Nacházel,et al.  Chronic renal disease. , 1963, Marquette medical review.

[14]  G. Kitas,et al.  Prediction of cardiovascular risk in rheumatoid arthritis: performance of original and adapted SCORE algorithms , 2015, Annals of the rheumatic diseases.

[15]  M. Pencina,et al.  Relation of corneal arcus to cardiovascular disease (from the Framingham Heart Study data set). , 2009, The American journal of cardiology.

[16]  Xingwei Tong,et al.  Inference for proportional hazard model with propensity score , 2018 .

[17]  W. D. Ray.  4. Modelling Survival Data in Medical Research , 1995 .

[18]  J. Gardin,et al.  Usefulness of Left Ventricular Mass and Geometry for Determining 10-Year Prediction of Cardiovascular Disease in Adults Aged >65 Years (from the Cardiovascular Health Study). , 2016, The American journal of cardiology.

[19]  G. Karthikeyni S. Arulmurugan.  Low-Power Wearable ECG Monitoring System for Multiple Patient Remote Monitoring , 2018 .

[20]  Jukka Vanhala,et al.  The electrical impedance measurements of dry electrode materials for the ECG measuring after repeated washing , 2017 .

[21]  S. Gabriel,et al.  Challenges of developing a cardiovascular risk calculator for patients with rheumatoid arthritis , 2017, PloS one.

[22]  J. Kai,et al.  Can machine-learning improve cardiovascular risk prediction using routine clinical data? , 2017, PloS one.

[23]  R. Stevens,et al.  Chronic renal disease is not chronic kidney disease: implications for use of the QRISK and Joint British Societies risk scores. , 2016, Family practice.

[24]  Maria Lindén,et al.  Machine learning-based clinical decision support system for early diagnosis from real-time physiological data , 2016, 2016 IEEE Region 10 Conference (TENCON).

[25]  J. Rottenberg,et al.  Cardiovascular Recovery From Psychological and Physiological Challenge and Risk for Adverse Cardiovascular Outcomes and All-Cause Mortality , 2015, Psychosomatic medicine.

[26]  R. Kronmal,et al.  10-Year Coronary Heart Disease Risk Prediction Using Coronary Artery Calcium and Traditional Risk Factors: Derivation in the MESA (Multi-Ethnic Study of Atherosclerosis) With Validation in the HNR (Heinz Nixdorf Recall) Study and the DHS (Dallas Heart Study). , 2015, Journal of the American College of Cardiology.

[27]  D. Spiegelhalter,et al.  Associations Between Fine Particulate Matter Components and Daily Mortality in Nagoya, Japan , 2015, Journal of epidemiology.