Sex-specific Predictors of Mortality in Patients with Heart Failure in Intensive Care Units Using Machine Learning

Xinhui Tian

doi:10.62051/ijcsit.v5n2.14

Authors

Xinhui Tian

DOI:

https://doi.org/10.62051/ijcsit.v5n2.14

Keywords:

Intensive Care Units, Machine Learning Models, Risk Factors, Explainability Analysis

Abstract

This retrospective cohort study analyzed congestive heart failure (HF) patients from MIMIC-IV and eICU-CRD. Statistical tests described patient characteristics, while machine learning models (CART, RF, XGBoost, LightGBM) ranked sex-specific predictors, with SHAP used for interpretation. Among 30,411 patients, 3,840 died (men: 12.7%, mean age 69.50; women: 12.6%, mean age 73.02). Systolic blood pressure (SBP) was more critical for mortality in women, while body temperature, blood urea nitrogen (BUN), and creatinine was more significant in men. This is the first machine learning study to explore sex-specific in-hospital mortality predictors in ICU HF patients, identifying both known and potentially important risk factors.

Downloads

Download data is not yet available.

References

Alper AB, Campbell RC, Anker SD et al. A propensity-matched study of low serum potassium and mortality in older adults with chronic heart failure. Int J Cardiol 2009;137:1–8.

[2] Braunwald E. The war against heart failure: the Lancet lecture. Lancet (London, England) 2015;385:812–24.

[3] Arata A, Ricci F, Khanji MY et al. Sex Differences in Heart Failure: What Do We Know? J Cardiovasc Dev Dis 2023;10, DOI: 10.3390/JCDD10070277.

[4] Timmis A, Vardas P, Townsend N et al. European Society of Cardiology: cardiovascular disease statistics 2021. Eur Heart J 2022;43:716–99.

[5] Nguyen QD, Peters E, Wassef A, Desmarais P, Rémillard-Labrosse D, Tremblay-Gravel M. Evolution of Age and Female Representation in the Most-Cited Randomized Controlled Trials of Cardiology of the Last 20 Years. Circ Cardiovasc Qual Outcomes 2018;11, DOI: 10.1161/CIRCOUTCOMES.118.004713.

[6] Agarwala A, Michos ED, Samad Z, Ballantyne CM, Virani SS. The Use of Sex-Specific Factors in the Assessment of Women’s Cardiovascular Risk. Circulation 2020;141:592–9.

[7] Roger VL. Epidemiology of Heart Failure. Circ Res 2013;113:646–59.

[8] Cannatà A, Fabris E, Merlo M et al. Sex Differences in the Long-term Prognosis of Dilated Cardiomyopathy. Can J Cardiol 2020;36:37–44.

[9] Mansur A de P, Pereira-Barretto AC, del Carlo CH et al. Sex Differences in Prognosis of Heart Failure Due to Ischemic and Nonischemic Cardiomyopathy. J Clin Med 2023;12, DOI: 10.3390/JCM12165323.

[10] Raafs A, Verdonschot J, Ferreira JP et al. Identification of sex-specific biomarkers predicting new-onset heart failure. ESC Hear Fail 2021;8:3512–20.

[11] Han D, Xu F, Zhang L et al. Early prediction of in-hospital mortality in patients with congestive heart failure in intensive care unit: a retrospective observational cohort study. BMJ Open 2022;12:1–11.

[12] Johnson AEW, Bulgarelli L, Shen L et al. Author Correction: MIMIC-IV, a freely accessible electronic health record dataset. Sci Data 2023 101 2023;10:1–1.

[13] Pollard TJ, Johnson AEW, Raffa JD, Celi LA, Mark RG, Badawi O. The eICU collaborative research database, a freely available multi-center database for critical care research. Sci Data 2018;5:1–13.

[14] Gradus JL, Rosellini AJ, Horváth-Puhó E et al. Prediction of Sex-Specific Suicide Risk Using Machine Learning and Single-Payer Health Care Registry Data from Denmark. JAMA Psychiatry 2020;77:25–34.

[15] Pedregosa F, Varoquaux G, Gramfort A et al. Scikit-learn: Machine Learning in {P}ython. J Mach Learn Res 2011;12: 2825--2830.

[16] Murdoch WJ, Singh C, Kumbier K, Abbasi-Asl R, Yu B. Definitions, methods, and applications in interpretable machine learning. Proc Natl Acad Sci U S A 2019;116:22071–80.

[17] Knaus WA, Draper EA, Wagner DP, Zimmerman JE. APACHE II: a severity of disease classification system. Crit Care Med 1985;13:818–29.

[18] Aoyama D, Morishita T, Uzui H et al. Sequential organ failure assessment score on admission predicts long-term mortality in acute heart failure patients. ESC Hear Fail 2020;7:245–53.

[19] Butler J, Kalogeropoulos AP, Georgiopoulou V V. et al. Systolic blood pressure and incident heart failure in the elderly. The Cardiovascular Health Study and the Health, Ageing and Body Composition Study. Heart 2011; 97: 1304–11.

[20] Ji H, Niiranen TJ, Rader F et al. Sex Differences in Blood Pressure Associations With Cardiovascular Outcomes. Circulation 2021;143:761–3.

[21] Ji H, Kim A, Ebinger JE et al. Sex Differences in Blood Pressure Trajectories Over the Life Course. JAMA Cardiol 2020;5:255–62.

[22] Lévy P, Naughton MT, Tamisier R, Cowie MR, Bradley TD. Sleep apnoea and heart failure. Eur Respir J 2022;59, DOI: 10.1183/13993003.01640-2021.

[23] Natarajan A, Su HW, Heneghan C, Blunt L, O’Connor C, Niehaus L. Measurement of respiratory rate using wearable devices and applications to COVID-19 detection. NPJ Digit Med 2021;4, DOI: 10.1038/S41746-021-00493-6.

[24] Payvar S, Spertus JA, Miller AB et al. Association of low body temperature and poor outcomes in patients admitted with worsening heart failure: a substudy of the Efficacy of Vasopressin Antagonism in Heart Failure Outcome Study with Tolvaptan (EVEREST) trial. Eur J Heart Fail 2013;15:1382–9.

[25] Xu H, Xie Y, Sun X, Feng N. Association between first 24-h mean body temperature and mortality in patients with diastolic heart failure in intensive care unit: A retrospective cohort study. Front Med 2022;9, DOI: 10.3389/ FMED. 2022. 1028122/FULL.

[26] Waalen J, Buxbaum JN. Is Older Colder or Colder Older? The Association of Age With Body Temperature in 18,630 Individuals. Journals Gerontol Ser A Biol Sci Med Sci 2011;66A:487.

[27] Van Veldhuisen DJ, Ruilope LM, Maisel AS, Damman K. Biomarkers of renal injury and function: diagnostic, prognostic and therapeutic implications in heart failure. Eur Heart J 2016;37:2577–85.

[28] Arihan O, Wernly B, Lichtenauer M et al. Blood Urea Nitrogen (BUN) is independently associated with mortality in critically ill patients admitted to ICU. PLoS One 2018;13, DOI: 10.1371/JOURNAL.PONE.0191697.

[29] Hong C, Zhu H, Zhou X et al. Association of Blood Urea Nitrogen with Cardiovascular Diseases and All-Cause Mortality in USA Adults: Results from NHANES 1999-2006. Nutrients 2023;15, DOI: 10.3390/NU15020461.

[30] Xu Z-R, Zhang Q, Chen L-F et al. Characteristics of hyperuricemia in older adults in China and possible associations with sarcopenia. Aging Med 2018;1:23.

[31] Huang AA, Huang SY. Dendrogram of transparent feature importance machine learning statistics to classify associations for heart failure: A reanalysis of a retrospective cohort study of the Medical Information Mart for Intensive Care III (MIMIC-III) database. PLoS One 2023;18, DOI: 10.1371/JOURNAL.PONE.0288819.

[32] Rathod KS, Kapil V, Velmurugan S et al. Accelerated resolution of inflammation underlies sex differences in inflammatory responses in humans. J Clin Invest 2017;127:169.

[33] Lippi G, Salvagno GL, Guidi GC. Red blood cell distribution width is significantly associated with aging and gender. Clin Chem Lab Med 2014;52:e197–9.

[34] Murphy WG. The sex difference in haemoglobin levels in adults — Mechanisms, causes, and consequences. Blood Rev 2014;28:41–7.

[35] Cai A, Qiu W, Xia S et al. Sex-specific characteristics and outcomes in hospitalized heart failure with preserved ejection fraction: the China Cardiovascular Association Database-Heart Failure Center Registry. Eur Heart J 2023;44:4715–8.

[36] Suthahar N, Lau ES, Blaha MJ et al. Sex-Specific Associations of Cardiovascular Risk Factors and Biomarkers With Incident Heart Failure. J Am Coll Cardiol 2020;76:1455.