Machine learning models in the prediction of chronic or shunt-dependent hydrocephalus following subarachnoid hemorrhage: A systematic review and meta-analysis
Restricted accessReview articleFirst published online February, 2026
Machine learning models in the prediction of chronic or shunt-dependent hydrocephalus following subarachnoid hemorrhage: A systematic review and meta-analysis
Chronic or shunt-dependent hydrocephalus is a frequent consequence of subarachnoid hemorrhage (SAH) with an unclear pathophysiology, making treatment challenging. Despite favorable outcomes following cerebrospinal fluid (CSF) diversion, high-risk surgical interventions remain necessary in some cases. Accurate prediction of chronic or shunt-dependent hydrocephalus in SAH patients can play an important role in their management. This systematic review and meta-analysis assessed the predictive performance of machine learning (ML) models in forecasting chronic or shunt-dependent hydrocephalus following SAH.
Methods
A systematic search of PubMed, Embase, Scopus, and Web of Science was conducted. ML or deep learning (DL)-based models that predicted chronic or shunt-dependent hydrocephalus following SAH were included. To avoid bias, only the data of the best-performance model, which was defined by the highest area under the curve (AUC) of the models, were extracted. The pooled AUC, accuracy (ACC), sensitivity, specificity, and diagnostic odds ratio (DOR) were calculated using the R program.
Results
Six studies with 2096 individuals were included. The AUC, ACC, sensitivity, and specificity ranged from 0.8 to 0.92, 0.72 to 0.9, 0.73 to 0.85, and 0.7 to 0.92. The meta-analysis showed a pooled AUC of 0.83 (95%CI: 0.81–0.84) and ACC of 0.79 (95%CI: 0.66–0.91). The meta-analysis revealed a pooled sensitivity of 0.8 (95%CI: 0.73–0.85), specificity of 0.79 (95%CI: 0.68–0.86), and DOR of 12.13 (95%CI: 8.2–17.96) for predictive performance of these models.
Conclusion
ML-based models showed encouraging predictive performance in forecasting chronic or shunt-dependent hydrocephalus following SAH.
Ahmadi KoupaeiSRZiaeeMBaharvahdatH, et al.An epidemiological investigation on patients with non-traumatic subarachnoid hemorrhage from 2010 to 2020. Bull Emerg Trauma2024; 12: 35–41.
2.
MohammadzadehINiroomandBShahnazianZ, et al.Machine learning for predicting poor outcomes in aneurysmal subarachnoid hemorrhage: a systematic review and meta-analysis involving 8445 participants. Clin Neurol Neurosurg2024; 249: 108668.
3.
EtminanNChangH-SHackenbergK, et al.Worldwide incidence of aneurysmal subarachnoid hemorrhage according to region, time period, blood pressure, and smoking prevalence in the population: a systematic review and meta-analysis. JAMA Neurol2019; 76: 588–597.
4.
RagagliniCFoschiMDe SantisF, et al.Epidemiology and treatment of atraumatic subarachnoid hemorrhage over 10 years in a population-based registry. Eur Stroke J2024; 9: 200–208.
5.
NussbaumESMikoffNParanjapeGS. Cognitive deficits among patients surviving aneurysmal subarachnoid hemorrhage. A contemporary systematic review. Br J Neurosurg2021; 35: 384–401.
6.
ChenLMengYXueQ, et al.Risk factors of shunt-dependent hydrocephalus after subarachnoid hemorrhage: a systematic review and meta-analysis based on observational cohort studies. Neurosurg Rev2024; 47: 421.
7.
WuC-RChenJ-SChenY-S, et al.Nomogram for the prediction of shunt-dependent hydrocephalus in patients with aneurysmal subarachnoid hemorrhage: a single-institute experience. bioRxiv. DOI: 10.1101/2022.12.31.22283967, Epub ahead of print 3 January 2023.
8.
SunZXueFWangK, et al.A nomogram model for predicting postoperative prognosis in patients with aneurysmal subarachnoid hemorrhage using preoperative biochemical indices. BMC Neurol2024; 24: 270.
9.
YangY-CYinC-HChenK-T, et al.Prognostic nomogram of predictors for shunt-dependent hydrocephalus in patients with aneurysmal subarachnoid hemorrhage receiving external ventricular drain insertion: a single-center experience and narrative review. World Neurosurg2021; 150: e12–e22.
10.
Raissi DehkordiNRaissi DehkordiNKarimi ToudeshkiK, et al.Artificial intelligence in diagnosis of long QT syndrome: a review of current state, challenges, and future perspectives. Mayo Clin Proc Digit Health2024; 2: 21–31.
11.
HajikarimlooBSabbagh AlvaniMKoohfarA, et al.Clinical application of artificial intelligence in prediction of intraoperative cerebrospinal fluid leakage in pituitary surgery: a systematic review and meta-analysis. World Neurosurg2024; 191: 303–313.e1.
12.
HajikarimlooBHabibiMAAlvaniMS, et al.Machine learning-based models for prediction of survival in medulloblastoma: a systematic review and meta-analysis. Neurol Sci2024; 46: 689–696.
13.
HajikarimlooBTosSMAlvaniMS, et al.Application of artificial intelligence in prediction of Ki-67 index in meningiomas: a systematic review and meta-analysis. World Neurosurg2025; 193: 226–235.
14.
HajikarimlooBMohammadzadehINazariMA, et al.Prediction of facial nerve outcomes after surgery for vestibular schwannoma using machine learning-based models: a systematic review and meta-analysis. Neurosurg Rev2025; 48: 79.
15.
ZhangFCaiX-FZhaoW, et al.A predictive model for chronic hydrocephalus after clipping aneurysmal subarachnoid hemorrhage. J Craniofac Surg2023; 34: 680–683.
16.
SchweingruberNBremerJWieheA, et al.Early prediction of ventricular peritoneal shunt dependency in aneurysmal subarachnoid haemorrhage patients by recurrent neural network-based machine learning using routine intensive care unit data. J Clin Monit Comput2024; 38: 1175–1186.
17.
RubinosCKwonSBMegjhaniM, et al.Predicting shunt dependency from the effect of cerebrospinal fluid drainage on ventricular size. Neurocrit Care2022; 37: 670–677.
18.
MuscasGMatteuzziTBecattiniE, et al.Development of machine learning models to prognosticate chronic shunt-dependent hydrocephalus after aneurysmal subarachnoid hemorrhage. Acta Neurochir2020; 162: 3093–3105.
19.
GollwitzerMSteindlMStrohN, et al.Machine learning-based prediction of chronic shunt-dependent hydrocephalus after spontaneous subarachnoid hemorrhage. World Neurosurg2024; 192: e124–e133.
20.
FreyDHilbertAFrühA, et al.Enhancing the prediction for shunt-dependent hydrocephalus after aneurysmal subarachnoid hemorrhage using a machine learning approach. Neurosurg Rev2023; 46: 206.
21.
PageMJMcKenzieJEBossuytPM, et al.The PRISMA 2020 statement: an updated guideline for reporting systematic reviews. BMJ2021; 372: n71.
22.
LuoDWanXLiuJ, et al.Optimally estimating the sample mean from the sample size, median, mid-range, and/or mid-quartile range. Stat Methods Med Res2018; 27: 1785–1805.
23.
StaffaSJZurakowskiD. Statistical development and validation of clinical prediction models. Anesthesiology2021; 135: 396–405.
24.
SunYYangJLiT, et al.Nomogram for predicting facial nerve outcomes after surgical resection of vestibular schwannoma. Front Neurol2021; 12: 817071.
25.
HarrisMKMacielakRJKaulVF, et al.A nomogram to predict long-term facial nerve function after vestibular schwannoma resection: a contemporary multi-institutional study. J Neurosurg2024; 141: 1667–1674.
26.
ShiXLiuYZhangZ, et al.The value of radiographic features in predicting postoperative facial nerve function in vestibular schwannoma patients: a retrospective study and nomogram analysis. CNS Neurosci Ther2024; 30: e14526.
27.
ZhengHYanTHanY, et al.Nomograms for prognostic risk assessment in glioblastoma multiforme: applications and limitations. Clin Genet2022; 102: 359–368.
28.
GuoCCuiY. Machine learning exhibited excellent advantages in the performance simulation and prediction of free water surface constructed wetlands. J Environ Manage2022; 309: 114694.
29.
GilliesRJKinahanPEHricakH. Radiomics: images are more than pictures, they are data. Radiology2016; 278: 563–577.
30.
YatesLAAandahlZRichardsSA, et al.Cross validation for model selection: a review with examples from ecology. Ecol Monogr; 93: e1557.
31.
PianykhOSLangsGDeweyM, et al.Continuous learning AI in radiology: implementation principles and early applications. Radiology2020; 297: 6–14.
32.
KoçakB. Key concepts, common pitfalls, and best practices in artificial intelligence and machine learning: focus on radiomics. Diagn Interv Radiol2022; 28: 450–462.
33.
da CruzHFPfahringerBMartensenT, et al.Using interpretability approaches to update ‘black-box’ clinical prediction models: an external validation study in nephrology. Artif Intell Med2021; 111: 101982.
34.
RattiEGravesM. Explainable machine learning practices: opening another black box for reliable medical AI. AI Ethics2022; 2: 801–814.
35.
RaptisSIlioudisCTheodorouK. From pixels to prognosis: unveiling radiomics models with SHAP and LIME for enhanced interpretability. Biomed Phys Eng Express2024; 10: 035016.
36.
KantiPKSharmaPWanatasanappanVV, et al.Explainable machine learning techniques for hybrid nanofluids transport characteristics: an evaluation of shapley additive and local interpretable model-agnostic explanations. J Therm Anal Calorim2024; 149: 11599–11618.
37.
AhmedSShamim KaiserMHossainMS, et al. A comparative analysis of LIME and SHAP interpreters with explainable ML-based diabetes predictions. IEEE Access2024.
38.
ValenteFParedesSHenriquesJ, et al.Interpretability, personalization and reliability of a machine learning based clinical decision support system. Data Min Knowl Discov2022; 36: 1140–1173.
39.
NasarianEAlizadehsaniRAcharyaUR, et al.Designing interpretable ML system to enhance trust in healthcare: a systematic review to proposed responsible clinician-AI-collaboration framework. Inf Fusion2024; 108: 102412.
40.
DuchWSetionoRZuradaJM. Computational intelligence methods for rule-based data understanding. Proc IEEE2004; 92: 771–805.
41.
HanifAZhangXWoodS. A survey on explainable artificial intelligence techniques and challenges. IEEE 25th International Enterprise Distributed Object Computing Workshop (EDOCW). New York: IEEE, 2021, pp. 81–89.
42.
MarcinkevičsRVogtJE. Interpretable and explainable machine learning: a methods-centric overview with concrete examples. Wiley Interdiscip Rev Data Min Knowl Discov2023; 13: e1493.
43.
AnuyahSSinghMKNyavorH. Advancing clinical trial outcomes using deep learning and predictive modelling: bridging precision medicine and patient-centered care. arXiv2024. https://arxiv.org/abs/2412.07050
44.
AdeoyeSAdamsR. Leveraging artificial intelligence for predictive healthcare: a data-driven approach to early diagnosis and personalized treatment. Cognizance Journal of Multidisciplinary Studies2024; 4: 80–97.
45.
ShamsA. Leveraging state-of-the-art AI algorithms in personalized oncology: from transcriptomics to treatment. Diagnostics2024; 14: 2174.
46.
ShahS-C. Design of a machine learning-based intelligent middleware platform for a heterogeneous private edge cloud system. Sensors (Basel)2021; 21: 7701.
47.
HoffpauirKSimmonsJSchmidtN, et al.A survey on edge intelligence and lightweight machine learning support for future applications and services. ACM J Data Inf Qual2023; 15: 1–30.
48.
EssibayiMAIbrahim AbdallahOMortezaeiA, et al.Natural history, pathophysiology, and recent management modalities of intraventricular hemorrhage. J Intensive Care Med2024; 39: 813–819.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
