The Combination of Whole-Brain Features and Local-Lesion Features in DSC-PWI May Improve Ischemic Stroke Outcome Prediction
Abstract
:1. Introduction
2. Materials and Methods
2.1. Materials
2.2. Methods
2.2.1. Preprocessing Datasets
2.2.2. Segmentation of the Whole Brain and Ischemic Lesion
2.2.3. Calculating DRFs and Selecting Significant Radiomics Features by t-Test Analysis
2.2.4. Feature Selection and Combination
2.2.5. Ischemic Stroke Outcome Prediction
- (1)
- Experiments
- (2)
- Evaluating the Performance of Outcome Prediction
3. Results
3.1. Computed DRFs and Selected Significant DRFs
3.1.1. Computed DRFs
3.1.2. Selected Significant DRF of Whole Brain and Local Lesions
3.2. Selected Outstanding DRF and Combined DRF
3.3. Performance of Four Groups of DRFs for Predicting Ischemic Stroke Outcome
4. Discussion
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Campbell, B.C.; De Silva, D.A.; Macleod, M.R.; Coutts, S.B.; Schwamm, L.H.; Davis, S.M.; Donnan, G.A. Ischaemic stroke. Nat. Rev. Dis. Prim. 2019, 5, 70. [Google Scholar] [CrossRef] [PubMed]
- Liu, Z.; Xin, H.; Chopp, M. Axonal remodeling of the corticospinal tract during neurological recovery after stroke. Neural Regen. Res. 2021, 16, 939. [Google Scholar] [CrossRef] [PubMed]
- Modrau, B.; Winder, A.; Hjort, N.; Johansen, M.N.; Andersen, G.; Fiehler, J.; Vorum, H.; Forkert, N.D. Machine Learning-Based Prediction of Brain Tissue Infarction in Patients with Acute Ischemic Stroke Treated with Theophylline as an Add-On to Thrombolytic Therapy: A Randomized Clinical Trial Subgroup Analysis. Front. Neurol. 2021, 12, 613029. [Google Scholar] [CrossRef] [PubMed]
- Demel, S.L.; Stanton, R.; Aziz, Y.N.; Adeoye, O.; Khatri, P. Reflection on the past, present, and future of thrombolytic therapy for acute ischemic stroke. Neurology 2021, 97 (Suppl. 2), S170–S177. [Google Scholar] [CrossRef]
- Cheng, Q.; Tree, K. Systematic review of thrombolysis therapy in the management of non-cirrhosis-related portal vein thrombosis. J. Gastrointest. Surg. 2021, 25, 1579–1590. [Google Scholar] [CrossRef]
- Tilley, B.C.; Palesch, Y. Conduct of stroke-related clinical trials. In Stroke; Churchill Livingstone: London, UK, 2004; pp. 1187–1207. [Google Scholar]
- Lea-Pereira, M.C.; Amaya-Pascasio, L.; Martínez-Sánchez, P.; Rodríguez Salvador, M.D.M.; Galván-Espinosa, J.; Téllez-Ramírez, L.; Reche-Lorite, F.; Sánchez, M.J.; García-Torrecillas, J.M. Predictive Model and Mortality Risk Score during Admission forIschaemic Stroke with Conservative treatment. Int. J. Environ. Res. Public Health 2022, 19, 3182. [Google Scholar] [CrossRef]
- Tang, S.; Xiong, L.; Fan, Y.; Mok, V.C.; Wong, K.S.; Leung, T.W. Stroke Outcome Prediction by Blood Pressure Variability, Heart Rate Variability, and Baroreflex Sensitivity. Stroke 2020, 51, 1317–1320. [Google Scholar] [CrossRef]
- Xie, Y.; Jiang, B.; Gong, E.; Li, Y.; Zhu, G.; Michel, P.; Wintermark, M.; Zaharchuk, G. Use of gradient boosting machine learning to predict patient outcome in acute ischemic stroke on the basis of imaging, demographic, and clinical information. Am. J. Roentgenol. 2019, 212, 44–51. [Google Scholar] [CrossRef]
- Brugnara, G.; Neuberger, U.; Mahmutoglu, M.A.; Foltyn, M.; Herweh, C.; Nagel, S.; Schönenberger, S.; Heiland, S.; Ulfert, C.; Ringleb, P.A.; et al. Multimodal Predictive Modeling of Endovascular Treatment Outcome for Acute Ischemic Stroke Using Machine-Learning. Stroke 2020, 51, 3541–3551. [Google Scholar] [CrossRef]
- Alaka, S.A.; Menon, B.K.; Brobbey, A.; Williamson, T.; Goyal, M.; Demchuk, A.M.; Hill, M.D.; Sajobi, T.T. Functional outcome prediction in ischemic stroke: A comparison of machine learning algorithms and regression models. Front. Neurol. 2020, 11, 889. [Google Scholar] [CrossRef]
- Li, X.D.; Li, M.M. A novel nomogram to predict mortality in patients with stroke: A survival analysis based on the MIMIC-III clinical database. BMC Med. Inform. Decis. Mak. 2022, 22, 92. [Google Scholar] [CrossRef] [PubMed]
- Osama, S.; Zafar, K.; Sadiq, M.U. Predicting Clinical Outcome in Acute Ischemic Stroke Using Parallel Multi-Parametric Feature Embedded Siamese Network. Diagnostics 2020, 10, 858. [Google Scholar] [CrossRef] [PubMed]
- Winzeck, S.; Hakim, A.; McKinley, R.; Pinto, J.A.; Alves, V.; Silva, C.; Pisov, M.; Krivov, E.; Belyaev, M.; Monteiro, M.; et al. Isles 2016 and 2017-benchmarking ischemic stroke lesion outcome prediction based on multispectral MRI. Front. Neurol. 2018, 9, 679. [Google Scholar] [CrossRef] [PubMed]
- Choi, Y.; Kwon, Y.; Lee, H.; Kim, B.J.; Paik, M.C.; Won, J.H. Ensemble of deep convolutional neural networks for prognosis of ischemic stroke. In Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries; Springer: Berlin/Heidelberg, Germany, 2016; Volume 10154, pp. 231–243. [Google Scholar]
- Maas, M.B.; Lev, M.H.; Ay, H.; Singhal, A.B.; Greer, D.M.; Smith, W.S.; Harris, G.J.; Halpern, E.; Kemmling, A.; Koroshetz, W.J.; et al. Collateral vessels on CT angiography predict outcome in acute ischemic stroke. Stroke 2009, 40, 3001–3005. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Van Seeters, T.; Biessels, G.J.; van der Schaaf, I.C.; Dankbaar, J.W.; Horsch, A.D.; Luitse, M.J.; Niesten, J.M.; Mali, W.P.; Kappelle, L.J.; van der Graaf, Y.; et al. Prediction of outcome in patients with suspected acute ischaemic stroke with CT perfusion and CT angiography: The Dutch acute stroke trial (DUST) study protocol. BMC Neurol. 2014, 14, 37. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Barrett, K.M.; Ding, Y.H.; Wagner, D.P.; Kallmes, D.F.; Johnston, K.C. Change in diffusion-weighted imaging infarct volume predicts neurologic outcome at 90 days: Results of the Acute Stroke Accurate Prediction (ASAP) trial serial imaging substudy. Stroke 2009, 40, 2422–2427. [Google Scholar] [CrossRef] [Green Version]
- Wang, H.; Song, B.; Ye, N.; Ren, J.; Sun, X.; Dai, Z.; Zhang, Y.; Chen, B.T. Machine learning-based multiparametric MRI radiomics for predicting the aggressiveness of papillary thyroid carcinoma. Eur. J. Radiol. 2020, 122, 108755. [Google Scholar] [CrossRef] [Green Version]
- Zhou, M.; Scott, J.; Chaudhury, B.; Hall, L.; Goldgof, D.; Yeom, K.; Iv, M.; Ou, Y.; Kalpathy-Cramer, J.; Napel, S.; et al. Radiomics in Brain Tumor: Image Assessment, Quantitative Feature Descriptors, and Machine-Learning Approaches. Am. J. Neuroradiol. 2017, 39, 208–216. [Google Scholar] [CrossRef] [Green Version]
- Pinker-Domenig, K.; Chin, J.; Melsaether, A.N.; Morris, E.A.; Moy, L. Precision Medicine and Radiogenomics in Breast Cancer: New Approaches toward Diagnosis and Treatment. Radiology 2018, 287, 732–747. [Google Scholar] [CrossRef]
- Wang, H.; Sun, Y.; Ge, Y.; Wu, P.-Y.; Lin, J.; Zhao, J.; Song, B. A Clinical-Radiomics Nomogram for Functional Outcome Predictions in Ischemic Stroke. Neurol. Ther. 2021, 10, 819–832. [Google Scholar] [CrossRef]
- Tang, T.-Y.; Jiao, Y.; Cui, Y.; Zhao, D.-L.; Zhang, Y.; Wang, Z.; Meng, X.-P.; Yin, X.-D.; Yang, Y.-J.; Teng, G.-J.; et al. Penumbra-based radiomics signature as prognostic biomarkers for thrombolysis of acute ischemic stroke patients: A multicenter cohort study. J. Neurol. 2020, 267, 1454–1463. [Google Scholar] [CrossRef] [PubMed]
- Cui, H.; Wang, X.; Bian, Y.; Song, S.; Feng, D.D. Ischemic stroke clinical outcome prediction based on image signature selection from multimodality data. Conf. Proc. IEEE Eng. Med. Biol. Soc. 2018, 2018, 722–725. [Google Scholar]
- Guo, Y.; Yang, Y.; Cao, F.; Li, W.; Wang, M.; Luo, Y.; Guo, J.; Zaman, A.; Zeng, X.; Miu, X.; et al. Novel Survival Features Generated by Clinical Text Information and Radiomics Features May Improve the Prediction of Ischemic Stroke Outcome. Diagnostics 2022, 12, 1664. [Google Scholar] [CrossRef] [PubMed]
- Love, T.; Swinney, D.; Wong, E.; Buxton, R. Perfusion imaging and stroke: A more sensitive measure of the brain bases of cognitive deficits. Aphasiology 2002, 16, 873–883. [Google Scholar] [CrossRef] [PubMed]
- Lev, M.H.; Segal, A.Z.; Farkas, J.; Hossain, S.T.; Putman, C.; Hunter, G.J.; Budzik, R.; Harris, G.J.; Buonanno, F.S.; Ezzeddine, M.A.; et al. Utility of perfusion-weighted CT imaging in acute middle cerebral artery stroke treated with intra-arterial thrombolysis: Prediction of final infarct volume and clinical outcome. Stroke 2001, 32, 2021–2028. [Google Scholar] [CrossRef] [Green Version]
- Guo, Y.; Yang, Y.; Cao, F.; Wang, M.; Luo, Y.; Guo, J.; Liu, Y.; Zeng, X.; Miu, X.; Zaman, A.; et al. A Focus on the Role of DSC-PWI Dynamic Radiomics Features in Diagnosis and Outcome Prediction of Ischemic Stroke. J. Clin. Med. 2022, 11, 5364. [Google Scholar] [CrossRef]
- Zhu, H.; Jiang, L.; Zhang, H.; Luo, L.; Chen, Y.; Chen, Y. An automatic machine learning approach for ischemic stroke onset time identification based on DWI and FLAIR imaging. NeuroImage Clin. 2021, 31, 102744. [Google Scholar] [CrossRef] [PubMed]
- Gillies, R.J.; Kinahan, P.E.; Hricak, H. Radiomics: Images Are More than Pictures, They Are Data. Radiology 2016, 278, 563–577. [Google Scholar] [CrossRef] [Green Version]
- Smith, S.M.; Jenkinson, M.; Woolrich, M.W.; Beckmann, C.F.; Behrens, T.E.; Johansen-Berg, H.; Bannister, P.R.; De Luca, M.; Drobnjak, I.; Flitney, D.E.; et al. Advances in functional and structural MR image analysis and implementation as FSL. Neuroimage 2004, 23, S208–S219. [Google Scholar] [CrossRef] [Green Version]
- Lansberg, M.G.; Lee, J.; Christensen, S.; Straka, M.; De Silva, D.A.; Mlynash, M.; Campbell, B.C.; Bammer, R.; Olivot, J.M.; Desmond, P.; et al. RAPID automated patient selection for reperfusion therapy: A pooled analysis of the Echoplanar Imaging Thrombolytic Evaluation Trial (EPITHET) and the Diffusion and Perfusion Imaging Evaluation for Understanding Stroke Evolution (DEFUSE) Study. Stroke 2011, 42, 1608–1614. [Google Scholar] [CrossRef] [Green Version]
- Van Griethuysen, J.J.; Fedorov, A.; Parmar, C.; Hosny, A.; Aucoin, N.; Narayan, V.; Beets-Tan, R.G.; Fillion-Robin, J.C.; Pieper, S.; Aerts, H.J. Computational Radiomics System to Decode the Radiographic Phenotype. Cancer Res. 2017, 77, e104–e107. [Google Scholar] [CrossRef] [PubMed]
- Zhang, Y.; Zhang, B.; Liang, F.; Liang, S.; Zhang, Y.; Yan, P.; Ma, C.; Liu, A.; Guo, F.; Jiang, C. Radiomics features on non-contrast-enhanced CT scan can precisely classify AVM-related hematomas from other spontaneous intraparenchymal hematoma types. Eur. Radiol. 2019, 29, 2157–2165. [Google Scholar] [CrossRef] [PubMed]
- Ghosh, P.; Azam, S.; Jonkman, M.; Karim, A.; Shamrat, F.J.M.; Ignatious, E.; Shultana, S.; Beeravolu, A.R.; De Boer, F. Efficient prediction of cardiovascular disease using machine learning algorithms with relief and LASSO feature selection techniques. IEEE Access 2021, 9, 19304–19326. [Google Scholar] [CrossRef]
- Muthukrishnan, R.; Rohini, R. LASSO: A feature selection technique in predictive modeling for machine learning. In Proceedings of the 2016 IEEE International Conference on Advances in Computer Applications (ICACA), Coimbatore, India, 24 October 2016; IEEE: Piscataway, NJ, USA, 2016; pp. 18–20. [Google Scholar]
- Zou, H.; Chen, C.; Zha, M.; Zhou, K.; Xiao, R.; Feng, Y.; Qiu, L.; Zhang, X.; Wang, Z. A Neural Regression Model for Predicting Thermal Conductivity of CNT Nanofluids with Multiple Base Fluids. J. Therm. Sci. 2021, 30, 1908–1916. [Google Scholar] [CrossRef]
- Kotsiantis, S.B.; Zaharakis, I.D.; Pintelas, P.E. Machine learning: A review of classification and combining techniques. Artif. Intell. Rev. 2006, 26, 159–190. [Google Scholar] [CrossRef]
- Kotsiantis, S.B.; Zaharakis, I.; Pintelas, P. Supervised machine learning: A review of classification techniques. Emerg. Artif. Intell. Appl. Comput. Eng. 2007, 160, 3–24. [Google Scholar]
- Song, X.; Tong, W.; Lei, C.; Huang, J.; Fan, X.; Zhai, G.; Zhou, H. A clinical decision model based on machine learning for ptosis. BMC Ophthalmol. 2021, 21, 169. [Google Scholar] [CrossRef]
- Goyal, M.; Ospel, J.M.; Kappelhof, M.; Ganesh, A. Challenges of outcome prediction for acute stroke treatment decisions. Stroke 2021, 52, 1921–1928. [Google Scholar] [CrossRef]
- Wang, C.; Miao, P.; Liu, J.; Li, Z.; Wei, Y.; Wang, Y.; Zhang, Y.; Wang, K.; Cheng, J. Validation of cerebral blood flow connectivity as imaging prognostic biomarker on subcortical stroke. J. Neurochem. 2021, 159, 172–184. [Google Scholar] [CrossRef]
- Hernandez, D.A.; Bokkers, R.P.; Mirasol, R.V.; Luby, M.; Henning, E.C.; Merino, J.G.; Warach, S.; Latour, L. Pseudocontinuous arterial spin labeling quantifies relative cerebral blood flow in acute stroke. Stroke 2012, 43, 753–758. [Google Scholar] [CrossRef] [Green Version]
- Wang, C.; Miao, P.; Liu, J.; Wei, S.; Guo, Y.; Li, Z.; Zheng, D.; Cheng, J. Cerebral blood flow features in chronic subcortical stroke: Lesion location-dependent study. Brain Res. 2019, 1706, 177–183. [Google Scholar] [CrossRef] [PubMed]
- Grefkes, C.; Fink, G.R. Connectivity-based approaches in stroke and recovery of function. Lancet Neurol. 2014, 13, 206–216. [Google Scholar] [CrossRef]
- Giacalone, M.; Rasti, P.; Debs, N.; Frindel, C.; Cho, T.H.; Grenier, E.; Rousseau, D. Local spatio-temporal encoding of raw perfusion MRI for the prediction of final lesion in stroke. Med. Image Anal. 2018, 50, 117–126. [Google Scholar] [CrossRef] [PubMed]
- Rava, R.A.; Snyder, K.V.; Mokin, M.; Waqas, M.; Zhang, X.; Podgorsak, A.R.; Allman, A.B.; Senko, J.; Bhurwani, M.M.S.; Hoi, Y.; et al. Assessment of computed tomography perfusion software in predicting spatial location and volume of infarct in acute ischemic stroke patients: A comparison of Sphere, Vitrea, and RAPID. J. NeuroInterv. Surg. 2021, 13, 130–135. [Google Scholar] [CrossRef] [PubMed]
- Lu, S.S.; Zhang, X.; Xu, X.Q.; Cao, Y.Z.; Liu, Q.H.; Wu, F.Y.; Liu, S.; Shi, H.B. Comparison of CT angiography collaterals for predicting target perfusion profile and clinical outcome in patients with acute ischemic stroke. Eur. Radiol. 2019, 29, 4922–4929. [Google Scholar] [CrossRef] [PubMed]
- Kao, H.W.; Tsai, F.Y.; Hasso, A.N. Predicting stroke evolution: Comparison of susceptibility-weighted MR imaging with MR perfusion. Eur. Radiol. 2012, 22, 1397–1403. [Google Scholar] [CrossRef]
- Appelros, P.; Stegmayr, B.; Terént, A. A review on sex differences in stroke treatment and outcome. Acta Neurol. Scand. 2010, 121, 359–369. [Google Scholar] [CrossRef]
- Shobha, N.; Sylaja, P.N.; Kapral, M.K.; Fang, J.; Hill, M.D. Differences in stroke outcome based on sex. Neurology 2010, 74, 767–771. [Google Scholar] [CrossRef]
Item | Parameter | |
---|---|---|
Patient information | Patients | 78 |
Male | 61 (78.21%) | |
Age | 71.68 ± 10.66 | |
90-day mRS | 2.60 ± 2.34 | |
DSC-PWI images | Matrix | 256 |
Slices | 20 | |
Number of measurements | 50 | |
Thickness | 6.5 mm |
Classifier | Implementation in Python 3.6 |
---|---|
NB | sklearn.naive_bayes. GaussianNB() |
LR | sklearn.linear_model.logisticRegressionCV(max_iter = 100,000, solver = “liblinear”) |
DT | sklearn.tree. DecisionTreeClassifier() |
GBDT | sklearn.ensemble.GradientBoostingClassifier() |
nn | sklearn.neural_network. MLPClassifier (hidden_layer_sizes = (400, 100), alpha = 0.01, max_iter = 10,000) |
KNN | sklearn.neighbors. sklearn.neighbors() |
Ada | sklearn.ensemble.AdaBoostClassifier() |
DA | sklearn.discriminant_analysis() |
RF | sklearn.ensemble.RandomForestClassifier(n_estimators = 200) |
SVM | sklearn.svm.SVC(kernel = ‘rbf’,probability = True) |
Item | First_Order | GLCM | GLDM | GLSZM | GLRLM | NGTDM | Sum |
---|---|---|---|---|---|---|---|
All DRF | 16,200 | 21,600 | 12,600 | 14,400 | 14,400 | 4500 | 83,700 |
T-test (WB) | 1410 | 1332 | 782 | 752 | 1000 | 288 | 5564 |
T-test (LL) | 4177 | 2445 | 1830 | 2303 | 3248 | 658 | 14,661 |
Lasso (WB) | 9 | 15 | 8 | 2 | 5 | 5 | 44 |
Lasso (LL) | 7 | 15 | 0 | 9 | 0 | 1 | 32 |
Combined DRFs | 10 | 16 | 5 | 8 | 2 | 4 | 45 |
DRFs | Group | Mean | Std | Sum | Minimum | Medium | Maximum |
---|---|---|---|---|---|---|---|
T-test (WB) | First_order | 0.024 | 0.015 | 33.57 | <0.0001 | 0.023 | 0.050 |
GLCM | 0.025 | 0.015 | 32.986 | <0.0001 | 0.025 | 0.050 | |
GLDM | 0.024 | 0.014 | 18.69 | <0.0001 | 0.023 | 0.050 | |
GLRLM | 0.025 | 0.015 | 18.538 | <0.0001 | 0.024 | 0.050 | |
GLSZM | 0.026 | 0.014 | 25.912 | <0.0001 | 0.026 | 0.050 | |
NGTDM | 0.025 | 0.012 | 7.322 | 0.002 | 0.025 | 0.050 | |
T-test (LL) | First_order | 0.020 | 0.014 | 84.315 | 0.000 | 0.016 | 0.050 |
GLCM | 0.026 | 0.013 | 63.610 | 0.001 | 0.026 | 0.050 | |
GLDM | 0.019 | 0.013 | 34.826 | 0.001 | 0.015 | 0.050 | |
GLRLM | 0.020 | 0.012 | 44.914 | 0.001 | 0.015 | 0.050 | |
GLSZM | 0.022 | 0.014 | 69.973 | 0.001 | 0.019 | 0.050 | |
NGTDM | 0.022 | 0.014 | 14.393 | 0.001 | 0.019 | 0.050 |
Models | Lasso (WB) | Lasso (LL) | Combined DRFs | Lasso (Combined) | CTI + survF in Ref. [26] |
---|---|---|---|---|---|
SVM | 0.907 | 0.857 | 0.923 | 0.948 | 0.897 |
nn | 0.923 | 0.844 | 0.923 | 0.971 | 0.882 |
RF | 0.802 | 0.784 | 0.801 | 0.801 | 0.949 |
DT | 0.729 | 0.659 | 0.676 | 0.556 | 0.890 |
KNN | 0.869 | 0.844 | 0.911 | 0.9 | 0.851 |
Ada | 0.698 | 0.753 | 0.738 | 0.718 | 0.918 |
LR | 0.936 | 0.882 | 0.923 | 0.971 | 0.892 |
NB | 0.886 | 0.857 | 0.936 | 0.942 | 0.821 |
GBDT | 0.74 | 0.744 | 0.722 | 0.691 | 0.908 |
DA | 0.772 | 0.798 | 0.643 | 0.879 | 0.790 |
Mean ± Std | 0.826 ± 0.088 | 0.802 ± 0.069 | 0.820 ± 0.117 | 0.838 ± 0.142 | 0.880 ± 0.047 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Guo, Y.; Yang, Y.; Wang, M.; Luo, Y.; Guo, J.; Cao, F.; Lu, J.; Zeng, X.; Miao, X.; Zaman, A.; et al. The Combination of Whole-Brain Features and Local-Lesion Features in DSC-PWI May Improve Ischemic Stroke Outcome Prediction. Life 2022, 12, 1847. https://doi.org/10.3390/life12111847
Guo Y, Yang Y, Wang M, Luo Y, Guo J, Cao F, Lu J, Zeng X, Miao X, Zaman A, et al. The Combination of Whole-Brain Features and Local-Lesion Features in DSC-PWI May Improve Ischemic Stroke Outcome Prediction. Life. 2022; 12(11):1847. https://doi.org/10.3390/life12111847
Chicago/Turabian StyleGuo, Yingwei, Yingjian Yang, Mingming Wang, Yu Luo, Jia Guo, Fengqiu Cao, Jiaxi Lu, Xueqiang Zeng, Xiaoqiang Miao, Asim Zaman, and et al. 2022. "The Combination of Whole-Brain Features and Local-Lesion Features in DSC-PWI May Improve Ischemic Stroke Outcome Prediction" Life 12, no. 11: 1847. https://doi.org/10.3390/life12111847