Development and Validation of a Novel Score for Predicting Long-Term Mortality After an Acute Ischemic Stroke

Overview

Journal Int J Environ Res Public Health

Publisher MDPI

Specialties Environmental Health
Public Health

Date 2023 Feb 25

PMID 36833741

Authors

Ching-Heng Lin

Ya-Wen Kuo

Yen-Chu Huang

Meng Lee

Yi-Wei Huang

Chang-Fu Kuo

Jiann-Der Lee

Affiliations

Soon will be listed here.

Abstract

Background: Long-term mortality prediction can guide feasible discharge care plans and coordinate appropriate rehabilitation services. We aimed to develop and validate a prediction model to identify patients at risk of mortality after acute ischemic stroke (AIS).

Methods: The primary outcome was all-cause mortality, and the secondary outcome was cardiovascular death. This study included 21,463 patients with AIS. Three risk prediction models were developed and evaluated: a penalized Cox model, a random survival forest model, and a DeepSurv model. A simplified risk scoring system, called the C-HAND (history of Cancer before admission, Heart rate, Age, eNIHSS, and Dyslipidemia) score, was created based on regression coefficients in the multivariate Cox model for both study outcomes.

Results: All experimental models achieved a concordance index of 0.8, with no significant difference in predicting poststroke long-term mortality. The C-HAND score exhibited reasonable discriminative ability for both study outcomes, with concordance indices of 0.775 and 0.798.

Conclusions: Reliable prediction models for long-term poststroke mortality were developed using information routinely available to clinicians during hospitalization.

Citing Articles

Development and Validation of a Predictive Score for Three-Year Mortality in Acute Ischemic Stroke Patients.

Barsan I, Ilut S, Tohanean N, Pop R, Vesa S, Perju-Dumbrava L Medicina (Kaunas). 2024; 60(9).

PMID: 39336454 PMC: 11434564. DOI: 10.3390/medicina60091413.

A Systematic Review of Artificial Intelligence Models for Time-to-Event Outcome Applied in Cardiovascular Disease Risk Prediction.

Teshale A, Htun H, Vered M, Owen A, Freak-Poli R J Med Syst. 2024; 48(1):68.

PMID: 39028429 PMC: 11271333. DOI: 10.1007/s10916-024-02087-7.

A comparison of random survival forest and Cox regression for prediction of mortality in patients with hemorrhagic stroke.

Wang Y, Deng Y, Tan Y, Zhou M, Jiang Y, Liu B BMC Med Inform Decis Mak. 2023; 23(1):215.

PMID: 37833724 PMC: 10576378. DOI: 10.1186/s12911-023-02293-2.

References

Mogensen U, Gerds T . A random forest approach for competing risks based on pseudo-values. Stat Med. 2013; 32(18):3102-14. DOI: 10.1002/sim.5775. View

Papavasileiou V, Milionis H, Michel P, Makaritsis K, Vemmou A, Koroboki E . ASTRAL score predicts 5-year dependence and mortality in acute ischemic stroke. Stroke. 2013; 44(6):1616-20. DOI: 10.1161/STROKEAHA.113.001047. View

Saposnik G, Kapral M, Liu Y, Hall R, ODonnell M, Raptis S . IScore: a risk score to predict death early after hospitalization for an acute ischemic stroke. Circulation. 2011; 123(7):739-49. DOI: 10.1161/CIRCULATIONAHA.110.983353. View

Peng S, Chuang Y, Kang T, Tseng K . Random forest can predict 30-day mortality of spontaneous intracerebral hemorrhage with remarkable discrimination. Eur J Neurol. 2010; 17(7):945-50. DOI: 10.1111/j.1468-1331.2010.02955.x. View

ODonnell M, Fang J, DUva C, Saposnik G, Gould L, McGrath E . The PLAN score: a bedside prediction rule for death and severe disability following acute ischemic stroke. Arch Intern Med. 2012; 172(20):1548-56. DOI: 10.1001/2013.jamainternmed.30. View

Ntaios G, Faouzi M, Ferrari J, Lang W, Vemmos K, Michel P . An integer-based score to predict functional outcome in acute ischemic stroke: the ASTRAL score. Neurology. 2012; 78(24):1916-22. DOI: 10.1212/WNL.0b013e318259e221. View

Muscari A, Puddu G, Santoro N, Zoli M . A simple scoring system for outcome prediction of ischemic stroke. Acta Neurol Scand. 2011; 124(5):334-42. DOI: 10.1111/j.1600-0404.2010.01479.x. View

Flint A, Faigeles B, Cullen S, Kamel H, Rao V, Gupta R . THRIVE score predicts ischemic stroke outcomes and thrombolytic hemorrhage risk in VISTA. Stroke. 2013; 44(12):3365-9. DOI: 10.1161/STROKEAHA.113.002794. View

Wang W, Kiik M, Peek N, Curcin V, Marshall I, Rudd A . A systematic review of machine learning models for predicting outcomes of stroke with structured data. PLoS One. 2020; 15(6):e0234722. PMC: 7292406. DOI: 10.1371/journal.pone.0234722. View

10.

Aronsson L, Andersson R, Ansari D . Artificial neural networks versus LASSO regression for the prediction of long-term survival after surgery for invasive IPMN of the pancreas. PLoS One. 2021; 16(3):e0249206. PMC: 7993879. DOI: 10.1371/journal.pone.0249206. View

11.

Hartmann A, Rundek T, Mast H, Paik M, Boden-Albala B, Mohr J . Mortality and causes of death after first ischemic stroke: the Northern Manhattan Stroke Study. Neurology. 2001; 57(11):2000-5. DOI: 10.1212/wnl.57.11.2000. View

12.

Saposnik G, Raptis S, Kapral M, Liu Y, Tu J, Mamdani M . The iScore predicts poor functional outcomes early after hospitalization for an acute ischemic stroke. Stroke. 2011; 42(12):3421-8. DOI: 10.1161/STROKEAHA.111.623116. View

13.

Austin P, Lee D, DAgostino R, Fine J . Developing points-based risk-scoring systems in the presence of competing risks. Stat Med. 2016; 35(22):4056-72. PMC: 5084773. DOI: 10.1002/sim.6994. View

14.

Saposnik G, Guzik A, Reeves M, Ovbiagele B, Johnston S . Stroke Prognostication using Age and NIH Stroke Scale: SPAN-100. Neurology. 2012; 80(1):21-8. PMC: 3589202. DOI: 10.1212/WNL.0b013e31827b1ace. View

15.

Liu C, Lin J, Liou C, Lee J, Peng T, Lee M . Causes of Death in Different Subtypes of Ischemic and Hemorrhagic Stroke. Angiology. 2017; 69(7):582-590. DOI: 10.1177/0003319717738687. View

16.

Celik G, Baykan O, Kara Y, Tireli H . Predicting 10-day mortality in patients with strokes using neural networks and multivariate statistical methods. J Stroke Cerebrovasc Dis. 2014; 23(6):1506-12. DOI: 10.1016/j.jstrokecerebrovasdis.2013.12.018. View

17.

Hong K, Yegiaian S, Lee M, Lee J, Saver J . Declining stroke and vascular event recurrence rates in secondary prevention trials over the past 50 years and consequences for current trial design. Circulation. 2011; 123(19):2111-9. PMC: 3118516. DOI: 10.1161/CIRCULATIONAHA.109.934786. View

18.

Yeramaneni S, Kleindorfer D, Sucharew H, Alwell K, Moomaw C, Flaherty M . Hyperlipidemia is associated with lower risk of poststroke mortality independent of statin use: A population-based study. Int J Stroke. 2016; 12(2):152-160. PMC: 5346890. DOI: 10.1177/1747493016670175. View

19.

Moons K, Harrell F, Steyerberg E . Should scoring rules be based on odds ratios or regression coefficients?. J Clin Epidemiol. 2002; 55(10):1054-5. DOI: 10.1016/s0895-4356(02)00453-5. View

20.

Sung S, Hsieh C, Lin H, Chen Y, Chen C, Kao Yang Y . Validity of a stroke severity index for administrative claims data research: a retrospective cohort study. BMC Health Serv Res. 2016; 16(1):509. PMC: 5034530. DOI: 10.1186/s12913-016-1769-8. View