Development and internal validation of a Nomogram-based risk prediction model for post-stroke cognitive impairment

i

This article has been updated. A Correction to this article was published on .

i

The Original Article was published on

i

The Original Article was published on

i

This article has been updated

i

This article was retracted on

i

This article has been updated

Abstract

Background: Post-stroke cognitive impairment (PSCI) severely affects patients' quality of life and survival, and no curative treatment is currently available. Therefore, early detection and prevention are crucial.
Objective: To develop and internally validate a nomogram for predicting the risk of PSCI within 6 months after stroke.
Study design: Bidirectional observational cohort study.
Methods: Demographic, clinical, and cognitive data were collected from patients with stroke treated at the First Affiliated Hospital of Air Force Medical University between January 2019 and January 2024, within 40 days of stroke onset. Six-month cognitive outcomes were obtained from medical records for the retrospective component (January 2019 to August 2023), while patients in the prospective component (August 2023 to January 2024) were followed up for 6 months. Patients were categorized into PSCI and non-PSCI groups based on the 6-month cognitive assessment. The least absolute shrinkage and selection operator regression and multivariable logistic regression were used to identify independent predictors and construct the prediction model. Model accuracy was evaluated and validated internally using the bootstrap method.
Results: Of 286 patients with stroke assessed, 107 presented with PSCI at the 6-month follow-up. The key predictors identified were baseline Mini-Mental State Examination score, time from lesion to rehabilitation facility, lesion location, and hypoalbuminemia. The risk prediction model using these factors showed strong performance, with an apparent area under the curve (AUC) of 0.940 (95% confidence interval [CI], 0.913-0.967), indicating good discrimination. The mean apparent AUC across 1000 bootstrap training samples was 0.947 (95% CI: 0.918-0.970). After optimism correction, the internally validated AUC was 0.937 (mean optimism = 0.003), indicating minimal overfitting.
Conclusion: The developed nomogram-based model predicted the risk of PSCI. It may aid in counseling patients with stroke and their families, and help clinicians identify high-risk patients for early intervention to improve outcomes.

Keywords

post-stroke cognitive impairment / stroke / risk prediction / nomogram

CHANGE HISTORY

A Correction to this paper has been published:
https://doi.org

The Retraction Note was updated to reflect reception of statements of disagreement from all authors.

This article has been retracted.Please see the Retraction Notice for more detail:
https://doi.org

References

[1] Ye S, Pan HQ, Li WJ, Wang B, Xing JJ, Xu L. High serum amyloid A predicts risk of cognitive impairment after lacunar infarction: development and validation of a nomo-gram. Front Neurol. 2022; 13:972771. https://doi.org/10.3389/fneur.2022.972771

[2] Huang YY, Chen SD, Leng XY, et al. Post-stroke cognitive impairment: epidemiology, risk factors, and management. J Alzheimers Dis. 2022; 86(3):983-999. https://doi.org/10.3233/JAD-215644

[3] He A, Wang Z, Wu X, et al. Incidence of post-stroke cognitive impairment in patients with first-ever ischemic stroke: a multicenter cross-sectional study in China. Lancet Reg Health West Pac. 2023; 33:100687. https://doi.org/10.1016/j.lanwpc.2023.100687

[4] Lee M, Yeo NY, Ahn HJ, et al.Prediction of post-stroke cognitive impairment after acute ischemic stroke using machine learning. Alzheimers Res Ther. 2023; 15(1):147. https://doi.org/10.1186/s13195-023-01289-4

[5] Yuan X, Zhang L, Sui R, Wang Z. A risk prediction model of post-stroke cognitive impairment based on magnetic resonance spectroscopy imaging. Neurol Res. 2021; 43(8):642-652. https://doi.org/10.1080/01616412.2021.1908659

[6] Dowling NM, Johnson S, Nadareishvili Z. Poststroke cognitive impairment and the risk of recurrent stroke and mortality: systematic review and meta-analysis. J Am Heart Assoc. 2024; 13(18):e33807. https://doi.org/10.1161/JAHA.123.033807

[7] El Husseini N, Katzan IL, Rost NS, et al. Cognitive impairment after ischemic and hemorrhagic stroke: a scientific statement from the American Heart Association/ American Stroke Association. Stroke. 2023; 54(6):e272-e291. https://doi.org/10.1161/STR.0000000000000430

[8] Weaver NA, Kuijf HJ, Aben HP, et al. Strategic infarct locations for post-stroke cognitive impairment: a pooled analysis of individual patient data from 12 acute ischaemic stroke cohorts. Lancet Neurol. 2021; 20(6):448-459. https://doi.org/10.1016/S1474-4422(21)00060-0

[9] Filler J, Georgakis MK, Dichgans M. Risk factors for cognitive impairment and de-mentia after stroke: a systematic review and meta-analysis. Lancet Healthy Longev. 2024; 5(1):e31-e44. https://doi.org/10.1016/s2666-7568(23)00217-9

[10] Kandiah N, Chander RJ, Lin X, et al. Cognitive impairment after mild stroke: de-velopment and validation of the SIGNAL 2 risk score. J Alzheimers Dis. 2016; 49(4):1169-1177. https://doi.org/10.3233/JAD-150736

[11] Chander RJ, Lam BYK, Lin X, et al. Development and validation of a risk score (CHANGE) for cognitive impairment after ischemic stroke. Sci Rep. 2017; 7(1):12441. https://doi.org/10.1038/s41598-017-12755-z

[12] Wu XB, Xi X, Xu ML, et al. Prediction of early bladder outcomes after spinal cord injury: the HALT score. CNS Neurosci Ther. 2024; 30(2):e14628. https://doi.org/10.1111/cns.14628

[13] Wang Y, Liu H, Zhao JY, et al. Effectiveness of technology-assisted cognitive inter-ventions for post-stroke cognitive impairment: a systematic review and meta-ana-lysis. Syst Rev. 2026; 15(1):107. https://doi.org/10.1186/s13643-026-03076-2

[14] Zhang KX, Wang HW, Wang X, et al. Neuroimaging prognostic factors for treatment response to motor imagery training after stroke. Cereb Cortex. 2023; 33(16):9504-9513. https://doi.org/10.1093/cercor/bhad220

[15] Geiger LS, Klütz S, Mychajliw C, et al. Cognitive recovery after poststroke delirium (RECOVER): protocol for a longitudinal multimodal study on cognitive assessment in patients with stroke. JMIR Res Protoc. 2026; 15:e77508. https://doi.org/10.2196/77508

[16] Austin PC, Steyerberg EW. Events per variable (EPV) and the relative performance of different strategies for estimating the out-of-sample validity of logistic regression models. Stat Methods Med Res. 2017; 26(2):796-808. https://doi.org/10.1177/0962280214558972

[17] Ma YX, Yang YF, Wang XY, et al. Prevalence and risk factors of poststroke cognitive impairment: a systematic review and meta-analysis. Public Health Nurs. 2025; 42(2):1047-1059. https://doi.org/10.1111/phn.13503

[18] Zhong Y, Lin M, Zhou XL, et al. ABO exon polymorphisms are related to ischemic stroke in a Chinese Han population. BMC Med Genom. 2025; 18(1):102. https://doi.org/10.1186/s12920-025-02170-z

[19] Ji YY, Wang XL, Zheng K, et al. Incidence and influencing factors of post-stroke cognitive impairment in convalescent young patients with first-ever stroke. J Stroke Cerebrovasc Dis. 2024; 33(1):107511. https://doi.org/10.1016/j.jstrokecerebrovasdis.2023.107511

[20] Zha F, Zhao JJ, Chen C, et al. A high neutrophil-to-lymphocyte ratio predicts higher risk of poststroke cognitive impairment: development and validation of a clinical prediction model. Front Neurol. 2022; 12:755011. https://doi.org/10.3389/fneur.2021.755011

[21] Ameli M, Grefkes C, Kemper F, et al. Differential effects of high-frequency repetitive transcranial magnetic stimulation over ipsilesional primary motor cortex in cortical and subcortical middle cerebral artery stroke. Ann Neurol. 2009; 66(3):298-309. https://doi.org/10.1002/ana.21725

[22] Sabanayagam C, He F, Chee ML, Cheng CY. Validity and reliability of self-reported prevalent and incident cardiovascular disease among asian adults. J Cardiovasc Dev Dis. 2024; 11(11):350. https://doi.org/10.3390/jcdd11110350

[23] Huang JF, Cheng AG, Kumar R, et al. Hypoalbuminemia predicts the outcome of COVID-19 independent of age and co-morbidity. J Med Virol. 2020; 92(10):2152-2158. https://doi.org/10.1002/jmv.26003

[24] Yu YT, Liu J, Hu B, et al. Expert consensus on the use of human serum albumin in critically ill patients. Chin Med J(Engl). 2021; 134(14):1639-1654. https://doi.org/10.1097/CM9.0000000000001661

[25] D’Oria M, Girardi L, Amgad A, et al. Expert-based narrative review on compression ultrasonography (CUS) for diagnosis and follow-up of deep venous thrombosis (DVT). Diagnostics(Basel). 2025; 15(1):82. https://doi.org/10.3390/diagnostics15010082

[26] Needleman L, Cronan JJ, Lilly MP, et al. Ultrasound for lower extremity deep venous thrombosis: multidisciplinary recommendations from the society of radiologists in ultrasound consensus conference. Circulation. 2018; 137(14):1505-1515. https://doi.org/10.1161/CIRCULATIONAHA.117.030687

[27] Quinn TJ, Richard E, Teuschl Y, et al. European Stroke Organisation and European Academy of Neurology joint guidelines on post-stroke cognitive impairment. Eur J Neurol. 2021; 28(12):3883-3920. https://doi.org/10.1111/ene.15068

[28] Zhao LQ, Leng YS, Hu YB, et al. Understanding decision curve analysis in clinical prediction model research. Postgrad Med J. 2024; 100(1185):512-515. https://doi.org/10.1093/postmj/qgae027

[29] Liu PP, Ding PA, Wu HT, et al. Prediction of occult peritoneal metastases or positive cytology using CT in gastric cancer. Eur Radiol. 2023; 33(12):9275-9285. https://doi.org/10.1007/s00330-023-09854-z

[30] Dong Y, Ding MY, Cui M, et al. Development and validation of a clinical model (DREAM-LDL) for post-stroke cognitive impairment at 6 months. Aging. 2021; 13(17):21628-21641. https://doi.org/10.18632/aging.203507

[31] Gallucci L, Sperber C, Monsch AU, Klöppel S, Arnold M, Umarova RM. Improving diagnostic accuracy of the Montreal Cognitive Assessment to identify post-stroke cognitive impairment. Sci Rep. 2024; 14(1):20125. https://doi.org/10.1038/s41598-024-71184-x

[32] Zhu YL, Zhao S, Fan ZQ, et al. Evaluation of the mini-mental state examination and the Montreal Cognitive Assessment for predicting post-stroke cognitive impairment during the acute phase in Chinese minor stroke patients. Front Aging Neurosci. 2020; 12:236. https://doi.org/10.3389/fnagi.2020.00236

[33] Salvadori E, Pantoni L, Società Italiana di NeuroGeriatria (SINEG). Teleneuropsychology for vascular cognitive impairment: which tools do we have? Cereb Circ Cogn Behav. 2023; 5:100173. https://doi.org/10.1016/j.cccb.2023.100173

[34] Gao Y, Qiu Y, Yang QY, et al. Repetitive transcranial magnetic stimulation combined with cognitive training for cognitive function and activities of daily living in patients with post-stroke cognitive impairment: a systematic review and meta-analysis. Ageing Res Rev. 2023; 87:101919. https://doi.org/10.1016/j.arr.2023.101919

[35] Harwood RH, Goldberg SE, Brand A, et al. Promoting activity, independence, and stability in early dementia and mild cognitive impairment (PrAISED): randomised controlled trial. BMJ. 2023; 382:e74787. https://doi.org/10.1136/bmj-2023-074787

[36] Hbid Y, Fahey M, Wolfe CDA, Obaid M, Douiri A. Risk prediction of cognitive decline after stroke. J Stroke Cerebrovasc Dis. 2021; 30(8):105849. https://doi.org/10.1016/j.jstrokecerebrovasdis.2021.105849

[37] Baccaro A, Wang YP, Candido M, et al. Post-stroke depression and cognitive impairment: Study design and preliminary findings in a Brazilian prospective stroke cohort (EMMA study). J Affect Disord. 2019; 245:72-81. https://doi.org/10.1016/j.jad.2018.10.003

[38] Baccaro A, Wang YP, Brunoni AR, et al. Does stroke laterality predict major de-pression and cognitive impairment after stroke? Two-year prospective evaluation in the EMMA study. Prog Neuropsychopharmacol Biol Psychiatry. 2019; 94:109639. https://doi.org/10.1016/j.pnpbp.2019.109639

[39] Toole JF, Bhadelia R, Williamson JD, Veltkamp R.Progressive cognitive impairment after stroke. J Stroke Cerebrovasc Dis. 2004; 13(3):99-103. https://doi.org/10.1016/j.jstrokecerebrovasdis.2004.03.005

[40] Singh V, Singh R, Singh G. Recent advances in speech areas and associated neural structures of the brain. J Anat Soc India. 2023; 72(4):281. https://doi.org/10.4103/jasi.jasi_124_23

[41] Hou SJ, Huang YR, Zhu J, et al. Mouse serum albumin induces neuronal apoptosis and tauopathies. Acta Neuropathol Commun. 2024; 12(1):66. https://doi.org/10.1186/s40478-024-01771-6

[42] Cao YR, Yao XR. Acute albumin administration as therapy for intracerebral hemor-rhage: A literature review. Heliyon. 2024; 10(1):e23946. https://doi.org/10.1016/j.heliyon.2023.e23946

[43] Shastri D, Raj V, Lee S. Revolutionizing Alzheimer's treatment: harnessing human serum albumin for targeted drug delivery and therapy advancements. Ageing Res Rev. 2024; 99:102379. https://doi.org/10.1016/j.arr.2024.102379

[44] Boada M, Anaya F, Ortiz P, et al. Efficacy and safety of plasma exchange with 5% albumin to modify cerebrospinal fluid and plasma Amyloid-β concentrations and cognition out-comes in Alzheimer's disease patients: a multicenter, randomized, controlled clinical trial. J Alzheimers Dis. 2017; 56(1):129-143. https://doi.org/10.3233/jad-160565

[45] Swartz RH, Longman RS, Lindsay MP, et al.Canadian stroke best practice recommenda-tions: vascular cognitive impairment, 7th edition practice guidelines update, 2024. Alzheimers Dement. 2025; 21(1):e14324. https://doi.org/10.1002/alz.14324

[46] Ding MY, Xu Y, Wang YZ, et al. Predictors of cognitive impairment after stroke: a prospective stroke cohort study. J Alzheimers Dis. 2019; 71(4):1139-1151. https://doi.org/10.3233/JAD-190382

[47] Gu YZ, Wang F, Gong L, Fang M, Liu XY. A nomogram incorporating red blood cell indices to predict post-stroke cognitive impairment in the intracerebral hemorrhage population. Front Aging Neurosci. 2022; 14:985386. https://doi.org/10.3389/fnagi.2022.985386

[48] Gong L, Wang HC, Zhu XF, et al. Nomogram to predict cognitive dysfunction after a minor ischemic stroke in hospitalized-population. Front Aging Neurosci. 2021; 13:637363. https://doi.org/10.3389/fnagi.2021.637363