Reviews on Imaging-based Risk Prediction Models for Ischemic Stroke

doi:10.37015/AUDT.2025.240018

Abstract

Abstract:

Stroke significantly impacts national health due to its high incidence, disability, mortality, and recurrence rates, resulting in a substantial economic burden. Risk prediction models for ischemic stroke help identify high-risk populations for early prevention, diagnosis, and treatment. Various risk-scoring models have been developed for primary and secondary prevention of ischemic stroke, estimating the probability of cardiovascular events over a specified timeframe based on the presence of known risk factors. However, these risk-scoring models often lack precision for cardiovascular disease risk assessments across diverse baseline risk conditions. Integrating image-based biomarkers into existing risk-prediction models may enhance risk stratification accuracy. This review presents the most used models for ischemic stroke prediction and underscores the clinical utility of biomarkers in the management of ischemic stroke.

Key words: Ischemic stroke; Imaging biomarkers; Stroke prevention; Risk assessment

Cui Liuping, Liu Ran, Liu Yumei, Zhou Fubo, Tao Yunlu, Xing Yingqi. Reviews on Imaging-based Risk Prediction Models for Ischemic Stroke. Advanced Ultrasound in Diagnosis and Therapy, 2025, 9(2): 117-126.

Figures/Tables 7

Table 1

Table 2

Table 3

Figure 1

Figure 2

Figure 3

Figure 4

References 51

[1]	Goldsborough E, 3rd , Osuji N, Blaha MJ. Assessment of cardiovascular disease risk: A 2022 update. Endocrinology & Metabolism Clinics of North America 2022;51:483-509.
[2]	Jiang L, Zhou Y, Zhang L, Wu L, Shi H, He B, et al. Stroke health management: novel strategies for the prevention of recurrent ischemic stroke. Front Neurol 2022;13:1018794.
[3]	Khanna NN, Jamthikar AD, Gupta D, Nicolaides A, Araki T, Saba L, et al. Performance evaluation of 10-year ultrasound image-based dtroke/cardiovascular (Cv) risk calculator by comparing against ten conventional Cv risk calculators: A diabetic study. Computers in Biology & Medicine 2019;105:125-143.
[4]	Khanna NN, Jamthikar AD, Gupta D, Araki T, Piga M, Saba L, et al. Effect of carotid image-based phenotypes on cardiovascular risk calculator: Aecrs1.0. Medical & Biological Engineering & Computing 2019;57:1553-1566.
[5]	Jamthikar A, Gupta D, Khanna NN, Saba L, Araki T, Viskovic K, et al. A low-cost machine learning-based cardiovascular/stroke risk assessment system: Integration of conventional factors with image phenotypes. Cardiovasc Diagn Ther 2019;9:420-430.
[6]	Wolf PA, D’Agostino RB, Belanger AJ, Kannel WB. Probability of Stroke: A risk profile from the framingham study. Stroke 1991;22:312-318.
[7]	D’Agostino RB, Wolf PA, Belanger AJ, Kannel WB. Stroke risk profile: adjustment for antihypertensive medication. The framingham study. Stroke 1994;25:40-43.
[8]	Huang JY, Cao YF, Guo JP, Guan YT, Wang Y, Yang YJ, et al. Modified framingham stroke profile in the predicition of the risk of stroke among Chinese. Chin J Cerebrovasc Dis 2013;10:228-232.
[9]	Naqvi TZ, Mendoza F, Rafii F, Gransar H, Guerra M, Lepor N, et al. High prevalence of ultrasound detected carotid atherosclerosis in subjects with low framingham risk score: Potential implications for screening for subclinical atherosclerosis. J Am Soc Echocardiogr 2010;23:809-815.
[10]	Ziegelbauer K, Schaefer C, Steinmetz H, Sitzer M, Lorenz MW. Clinical usefulness of carotid ultrasound to improve stroke risk assessment: Ten-year results from the carotid atherosclerosis progression study (Caps). Eur J Prev Cardiol 2013;20:837-843.
[11]	Den Ruijter HM, Peters SA, Anderson TJ, Britton AR, Dekker JM, Eijkemans MJ, et al. Common carotid intima-media thickness measurements in cardiovascular risk prediction: A meta-analysis. JAMA 2012;308:796-803.
[12]	Polak JF, Szklo M, Kronmal RA, Burke GL, Shea S, Zavodni AE, O’Leary DH.The value of carotid artery plaque and intima-media thickness for incident cardiovascular disease: the multi-ethnic study of atherosclerosis. J Am Heart Assoc 2013;2:e000087.
[13]	Gardin JM, Bartz TM, Polak JF, O'Leary DH, Wong ND. What do carotid intima-media thickness and plaque add to the prediction of stroke and cardiovascular disease risk in older adults? The cardiovascular health study. J Am Soc Echocardiogr 2014;27:998-1005.
[14]	Yang X, Li J, Hu D, Chen J, Li Y, Huang J, et al. Predicting the 10-year risks of atherosclerotic cardiovascular disease in Chinese population: The China-Par Project (Prediction for Ascvd Risk in China). Circulation 2016;134:1430-1440.
[15]	Tang X, Zhang DD, Liu XF, Liu QP, Cao Y, Li N, et al. Application of the China-ParStroke risk equations in a rural northern Chinese population. J Peking University (Medical Edition) 2020;52:444-450.
[16]	Xing X, Yang X, Liu F, Li J, Chen J, Liu X, Cao J, et al. Predicting 10-year and lifetime stroke risk in Chinese population. Stroke 2019;50:2371-2378.
[17]	Liu X, Shen P, Zhang D, Sun Y, Chen Y, Liang J, et al. Evaluation of atherosclerotic cardiovascular risk prediction models in China: Results from the Cherry study. JACC Asia 2022;2:33-43
[18]	Li S, Tang M. The prevalence and prognosis of asymptomatic intracranial atherosclerosis in a community-based population: results based on high-resolution magnetic resonance imaging. Eur J Neurol 2023;30:3761-3771.
[19]	Brunner G, Virani SS, Sun W, Liu L, Dodge RC, Nambi V, et al. Associations between carotid artery plaque burden, plaque characteristics, and cardiovascular events: the aric carotid magnetic resonance imaging study. JAMA Cardiol 2021;6:79-86.
[20]	Bos D, Arshi B, van den Bouwhuijsen QJA, Ikram MK, Selwaness M, Vernooij MW, et al. Atherosclerotic carotid plaque composition and incident stroke and coronary events. J Am Coll Cardiol 2021;77:1426-1435.
[21]	Rothwell PM, Giles MF, Flossmann E, Lovelock CE, Redgrave JN, Warlow CP. A simple score (Abcd) to identify individuals at high early risk of stroke after transient ischaemic attack. Lancet 2005;366:29-36.
[22]	Johnston SC, Rothwell PM, Nguyen-Huynh MN, Giles MF, Elkins JS, Bernstein AL, et al. Validation and refinement of scores to predict very early stroke risk after transient ischaemic attack. Lancet 2007;369:283-292.
[23]	Amarenco P, Lavallée PC, Labreuche J, Albers GW, Bornstein NM, Canhão P, et al. One-year risk of tsroke after transient ischemic attack or minor stroke. N Engl J Med 2016;374:1533-1542.
[24]	Amin HP, Madsen TE, Bravata DM, Wira CR, Johnston SC, Ashcraft S, et al. Diagnosis, workup, risk reduction of transient ischemic attack in the emergency department setting: A scientific statement from the American Heart Association. Stroke2023;54:e109-e121.
[25]	Ottaviani M, Vanni S, Moroni F, Peiman N, Boddi M, Grifoni S. Urgent carotid duplex and head computed tomography versus Abcd² score for risk stratification of patients with transient ischemic attack. Eur J Emerg Med 2016;23:19-23.
[26]	Giles MF, Albers GW, Amarenco P, Arsava MM, Asimos A, Ay H, et al. Addition of brain infarction to the Abcd² score (Abcd²i): A collaborative analysis of unpublished data on 4574 patients. Stroke 2010;41:1907-1913.
[27]	Merwick A, Albers GW, Amarenco P, Arsava EM, Ay H, Calvet D, et al. Addition of brain and carotid imaging to the Abcd² score to identify patients at early risk of stroke after transient ischaemic attack: A multicentre observational study. Lancet Neurol 2010;9:1060-1069.
[28]	Weng JX, Gu HQ. External validation of Abcd series scores for predicting early stroke events following transient ischemic attack in a large nationwide registry. Eur Stroke J 2022;7:439-446.
[29]	Jing J, Suo Y, Wang A, Zuo Y, Jiang Y, Liu L, et al. Imaging parameters predict recurrence after transient ischemic attack or minor stroke stratified by ABCD² score. Stroke 2021;52:2007-2015.
[30]	Tian Y, Pan Y, Wang M, Meng X, Zhao X, Liu L, et al. The combination of heart rate variability and ABCD² score portends adverse outcomes after minor stroke or transient ischemic attack. J Neurol Sci 2023;445:120522.
[31]	Chaudhary D, Abedi V, Li J, Schirmer CM, Griessenauer CJ, Zand R.Clinical risk score for predicting recurrence following a cerebral ischemic event. Front Neurol 2019;10:1106.
[32]	Ay H, Gungor L, Arsava EM, Rosand J, Vangel M, Benner T, et al. A score to predict early risk of recurrence after ischemic stroke. Neurology 2010;74:128-135.
[33]	Arsava EM, Kim GM, Oliveira-Filho J, Gungor L, Noh HJ, Lordelo Mde J, et al. Prediction of early recurrence after acute ischemic stroke. JAMA Neurol 2016;73:396-401.
[34]	Hankey GJ, Wee CK. Predicting early recurrent stroke with the recurrence risk estimator. JAMA Neurol 2016;73:376-378.
[35]	CAPRIE Steering Committee. A randomised, blinded, trial of clopidogrel versus aspirin in patients at risk of ischaemic events (Caprie). Caprie Steering Committee. Lancet 1996;348:1329-1339.
[36]	Weimar C, Diener HC, Alberts MJ, Steg PG, Bhatt DL, Wilson PW, et al. The Essen stroke risk score predicts recurrent cardiovascular events: A validation within the reduction of atherothrombosis for continued health (Reach) registry. Stroke 2009;40:350-354.
[37]	Meng X, Wang Y, Zhao X, Wang C, Li H, Liu L, et al. Validation of the Essen stroke risk score and the stroke prognosis instrument Ⅱ in Chinese patients. Stroke 2011;42:3619-3620.
[38]	Zhang YM, Zheng ZL. The combination of logistic model evaluation of carotid plaque neovascularization grading and Essen score predicts the risk of recurrence of cerebral infarction. Chin J Ultrasound Med 2018;34:289-292.
[39]	Li F, Gu SY, Zhang LN, Chen J, Yao MH, Wu TT, et al. Carotid plaque score and ischemic stroke risk stratification through a combination of B-mode and contrast-enhanced ultrasound in patients with low and intermediate carotid stenosis. Front Cardiovasc Med 2023;10:1209855.
[40]	Li QQ, Zhang HR, Wu YJ, Yu H. The predictive value of ESRS combined with cranial magnetic resonance angiography score for recurrence in elderly patients with cerebral infarction. J Vas & Endovascular Surg 2021;7:1227-1230.
[41]	Yang LX, Jiang TA, Zhang L, He JF. The predictive value of carotid artery plaque properties, degree of intracranial artery stenosis combined with ESRS score for the recurrence of cerebral infarction. J Chin Modern Doctors 2023;61:46-50.
[42]	Kernan WN, Horwitz RI, Brass LM, Viscoli CM, Taylor KJ. A prognostic system for transient ischemia or minor stroke. Ann Intern Med 1991;114:552-557.
[43]	Kernan WN, Viscoli CM, Brass LM, Makuch RW, Sarrel PM, Roberts RS, et al. The Stroke Prognosis Instrument Ⅱ (SPI-Ⅱ) : A clinical prediction instrument for patients with transient ischemia and nondisabling ischemic stroke. Stroke 2000;31:456-462.
[44]	Saba L, Cau R, Murgia A, Nicolaides AN, Wintermark M, Castillo M, et al. Carotid plaque-rads: A novel stroke risk classification system. JACC Cardiovasc Imaging 2024;17:62-75.
[45]	Lin XM, Wang F, Wang J, Lu QL, Cao H, Dua KL, et al. Comparison of the predictive value of RRE-90, ESRS, and SPI-Ⅱ scores for the risk of recurrent ischemic stroke. J Shaanxi Med 2019;48:599-602.
[46]	Weimar C, Benemann J, Michalski D, Müller M, Luckner K, Katsarava Z, et al. Prediction of recurrent stroke and vascular death in patients with transient ischemic attack or nondisabling stroke: A prospective comparison of validated prognostic scores. Stroke 2010;41:487-493.
[47]	Kongwatcharapong J, Sornkhamphan A, Kaveeta C, Nathisuwan S. Validation and comparison of the stroke prognosis instrument (SPI-Ⅱ) and the essen stroke risk score (ESRS) in predicting stroke recurrence in Asian population. BMC Neurol 2023;23:287.
[48]	Raychev R, Nour M, Saver J, Liebeskind D, Penkov S, Angelov D,et al. Machine learning algorithms for autonomous detection of stroke symptoms and Bell’s palsy. Proceedings of the International Stroke Conference; 2024 Feb 7-9, Phoenix, AZ, USA.
[49]	Ben Alaya I, Limam H, Kraiem T. Applications of artificial intelligence for Dwi and Pwi data processing in acute ischemic stroke: Current practices and future directions. Clin Imaging 2022;81:79-86.
[50]	Czap AL, Bahr-Hosseini M, Singh N. Machine learning automated detection of large vessel occlusion from mobile stroke unit computed tomography angiography. Stroke 2022;53:1651-1656.
[51]	Lu J, Zhang M. Artificial intelligence in the imaging assessment of ischaemic stroke. Intern J Med Radiol 2024;47:133-136.

Models	Common risk factors	Male only	Female only
FSR	Age (0-10)	Antihypertensive treatment (2)	Diabetes (3)
	Systolic blood pressure (0-10)	Diabetes (2)	Cardiovascular disease (2)
	Smoking (3)	Cardiovascular disease (3)	Atrial fibrillation (6)
		Atrial fibrillation (4)	Left ventricular hypertrophy (4)
		Left ventricular hypertrophy (5)
China-PAR	Age; Treated or untreated systolic blood pressure; Total cholesterol; Current smoking; Diabetes	HDL; Geographic region; Urbanization; Family history of ASCVD	HDL; Waistline; Geographic region; Urbanization

ABCD²	RRE-90	ESRS	SPI-Ⅱ
Age > 60 years- 1;	Mutiple infarcts of different ages- 1;	Age	Age > 70 years- 2;
Hypertension- 1;	Simultaneous infarcts in different circulations- 1; Multiple acute infarcts- 1;	65-75 years- 1,	Hypertension- 1;
Clinical symptoms	Isolated cortical infarcts- 1;	> 75 years- 2;	Diabetes- 3;
speech disorders- 1, weakness of a limb on one side- 2;	History of TIA or stroke within the month preceding index stroke- 1;	Hypertension- 1;	Current ischemic stroke- 1;
Duration of symptom	Stroke subtype- 1.	Diabetes- 1;	Coronary artery disease- 1;
< 10 min- 0,		History of MI- 1;	Heart failure- 3;
10-60 min- 1,		Other cardiovascular disease- 1;	History of previous stroke -3.
> 60 min- 2;		Peripheral arterial disease- 1;
Diabetes- 1.		Smoking- 1;
		History of stroke or TIA- 1.

Models (Number)	Study population (Follow-up time)	Clinical outcome	Clinical value	Limitations
FSRP (5734)	Population aged 55-85 without a history of stroke (10-year)	Stroke	The most commonly used prediction model for elderly people	Relatively weak predictive ability for young people
China-PAR (21320)	Population aged 35-74 without a history of MI or stroke (12.3-year)	Non-fatal acute MI or death from CHD and stroke	Suitable for Chinese populations	Underestimating cardiovascular risk in high-risk populations
ABCD (209)	Initial TIA (7-day)	Stroke	ABCD² is the most commonly used short-term tool to assess the risk of stroke recurrence.	ABCD² may underestimate the risk of stroke recurrence
ABCD² (1916)	Initial TIA (2-day, 7-day, 90-day)	Stroke
ABCD²-I (3206)	Initial TIA (7-day, 90-day)	Stroke
RRE-90 (1458)	Stroke within 72 hours of onset (90-day)	Stroke	Effectively predicts the risk of stroke recurrence within 90 days	Imaging evaluation is time-consuming and not suitable for emergency units
ESRS (1681)	Ischemic stroke (1-year)	Stroke	ESRS and SPI-II can effectively predict long-term stroke recurrence (1 year)	Overall predictive performance is poor
SPI-Ⅰ (142)	TIA and MIS in the carotid distribution within 1 month (2 years)	Stroke or death		Only applicable to stroke in the carotid system
SPI-Ⅱ (525)	Women with TIA or non-disabling ischemic stroke (2 years)	Stroke or death