Modeling Mortality in Heart Failure Patients: Considering Time-Varying Effects - A Bayesian Survival Analysis Utilizing Bayesian AFT Model with the INLA Method

Document Type : Original Research Articles

Authors
VIJAYAN S
KAVITHA S
Saranya V
Department of Statistics, Periyar University, Salem, Tamil Nadu, India
10.22059/jsciences.2025.379754.1007872
Abstract
Heart failure and disease ranks among the most common illnesses globally. Heart failure is a condition where the heart cannot pump blood efficiently, posing a growing global public health challenge with a high mortality rate. This study aimed to identify factors influencing the survival time of heart failure patients. Using secondary data, 299 heart failure patients were studied based on medical records from a 12-month enrollment period. The analysis employed Kaplan-Meier plots and Bayesian parametric survival models, utilizing SPSS and R software, with Integrated Nested Laplace Approximation methods. The Bayesian lognormal accelerated failure time model was deemed appropriate based on model selection criteria. The results indicated that factors such as age, gender, height, systolic and diastolic blood pressure, smoking, alcohol consumption, and the presence of heart disease significantly affected survival times. Cholesterol levels notably impacted survival outcomes in older patients. The Bayesian Weibull accelerated failure time model also described the survival data well. The study's findings suggested that the age groups 59 to 95 and above were most affected by heart failure, significantly impacting survival time.
Keywords
Heart Failure
Kaplan-Meier
Bayesian
survival time
INLA
Subjects
  1. Ahmad T, Munir A, Bhatti SH, Aftab M, Raza MA. Survival analysis of heart failure patients: A case study. PloS One. 2017 Jul 20;12(7):e0181001.
  2. Akerkar R, Martino S, Rue H. Implementing approximate Bayesian inference for survival analysis using integrated nested Laplace approximations. Prepr Stat Nor Univ Sci Technol. 2010 Jan 13; 1:1-38.
  3. Hailay A, Kebede E, Mohammed K. Survival during treatment period of patients with severe heart failure admitted to intensive care unit (ICU) at gondar university hospital (GUH), Gondar, Ethiopia. American Journal of Health Research. 2015 Jul;3(5):257-69.
  4. Tamrat Befekadu Abebe TB, Eyob Alemayehu Gebreyohannes EA, Yonas Getaye Tefera YG, Tadesse Melaku Abegaz TM. Patients with HFpEF and HFrEF have different clinical characteristics but similar prognosis: a retrospective cohort study.
  5. Benjamin EJ, Muntner P, Alonso A, Bittencourt MS, Callaway CW, Carson AP, Chamberlain AM, Chang AR, Cheng S, Das SR, Delling FN. Heart disease and stroke statistics—2019 update: a report from the American Heart Association. Circulation. 2019 Mar 5;139(10):e56-2.
  6. Habte B, Alemseged F, Tesfaye D. The pattern of cardiac diseases at the cardiac clinic of Jimma University specialised hospital, South West Ethiopia. Ethiopian journal of health sciences. 2010;20(2).
  7. Weng SF, Reps J, Kai J, Garibaldi JM, Qureshi N. Can machine learning improve cardiovascular risk prediction using routine clinical data? PloS one. 2017 Apr 4;12(4):e0174944.
  8. Gottlieb SS. Prognostic indicators: useful for clinical care?. Journal of the American College of Cardiology. 2009 Jan 27;53(4):343-4.
  9. Boqué P, Saez M, Serra L. Need to go further: using INLA to discover limits and chances of burglaries’ spatiotemporal prediction in heterogeneous environments. Crime Science. 2022 Sep 10;11(1):7.

10.Ashine T, Tadesse Likassa H, Chen DG. Estimating Time-to-Death and Determining Risk Predictors for Heart Failure Patients: Bayesian AFT Shared Frailty Models with the INLA Method. Stats. 2024 Sep 23;7(3):1066-83.        

  1. Aalen OO. Survival and Event History Analysis: A Process Point of View. Springer-Verlag; 2008.
  2. Maller RA, Zhou X. Survival analysis with long-term survivors. (No Title). 1996.
  3. Anderka R, Deisenroth MP, Takao S. Iterated INLA for State and Parameter Estimation in Nonlinear Dynamical Systems. arXiv preprint arXiv:2402.17036. 2024 Feb 26.
  4. Gelman A, Hwang J, Vehtari A. Understanding predictive information criteria for Bayesian models. Statistics and computing. 2014 Nov; 24:997-1016.
  5. Núñez J, Garcia S, Núñez E, Bonanad C, Bodí V, Miñana G, Santas E, Escribano D, Bayes-Genis A, Pascual-Figal D, Chorro FJ. Early serum creatinine changes and outcomes in patients admitted for acute heart failure: the cardio-renal syndrome revisited. European Heart Journal: Acute Cardiovascular Care. 2017 Aug 1;6(5):430-40.
  6. Morales-Otero M, Gómez-Rubio V, Núñez-Antón V. Fitting double hierarchical models with the integrated nested Laplace approximation. Statistics and Computing. 2022 Aug;32(4):62.
  7. Chopin N. Approximate Bayesian inference for latent Gaussian models by using integrated nested Laplace. JR Stat. Soc. Ser. B Stat. Methodol. 2009 Apr;71:319-92.
  8. Tripoliti EE, Papadopoulos TG, Karanasiou GS, Naka KK, Fotiadis DI. Heart failure: diagnosis, severity estimation and prediction of adverse events through machine learning techniques. Computational and structural biotechnology journal. 2017 Jan 1;15:26-47.
  9. van Niekerk J, Rue H. Use of the INLA approach for the analysis of interval-censored data. InEmerging topics in modeling interval-censored survival data 2022 Jul 15 (pp. 123-140). Cham: Springer International Publishing.
  10. Watanabe S, Opper M. Asymptotic equivalence of Bayes cross validation and widely applicable information criterion in singular learning theory. Journal of machine learning research. 2010 Dec 1;11(12).

 
  1. Yancy CW, Jessup M, Bozkurt B, Butler J, Casey DE, Drazner MH, Fonarow GC, Geraci SA, Horwich T, Januzzi JL, Johnson MR. 2013 ACCF/AHA guideline for the management of heart failure: executive summary: a report of the American College of Cardiology Foundation/American Heart Association Task Force on practice guidelines. Journal of the American College of Cardiology. 2013 Oct 15;62(16):1495-539.of Cardiology, 62(16), e147-e239.
Journal of Sciences, Islamic Republic of Iran
Volume 35, Issue 4
Autumn 2024
Pages 341-349