Identifying Neuroimaging Markers of Motor Disability in Acute Stroke by Machine Learning Techniques
The DOI matches its Crossref record; 71 of the 71 references it cites were found in a registry or an index.
Abstract
Conventional mass-univariate analyses have been previously used to test for group differences in neural signals. However, machine learning algorithms represent a multivariate decoding approach that may help to identify neuroimaging patterns associated with functional impairment in "individual" patients. We investigated whether fMRI allows classification of individual motor impairment after stroke using support vector machines (SVMs). Forty acute stroke patients and 20 control subjects underwent resting-state fMRI. Half of the patients showed significant impairment in hand motor function. Resting-state connectivity was computed by means of whole-brain correlations of seed time-courses in ipsilesional primary motor cortex (M1). Lesion location was identified using diffusion-weighted images. These features were used for linear SVM classification of unseen patients with respect to motor impairment. SVM results were compared with conventional mass-univariate analyses. Resting-state connectivity classified patients with hand motor deficits compared with controls and nonimpaired patients with 82.6-87.6% accuracy. Classification was driven by reduced interhemispheric M1 connectivity and enhanced connectivity between ipsilesional M1 and premotor areas. In contrast, lesion location provided only 50% sensitivity to classify impaired patients. Hence, resting-state fMRI reflects behavioral deficits more accurately than structural MRI. In conclusion, multivariate fMRI analyses offer the potential to serve as markers for endophenotypes of functional impairment.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Rehme et al used SVM in resting-state functional MRI data, by which endophenotypes of motor disability after stroke were identified and classified.50”
From Artificial intelligence in healthcare: past, present and future (2017) · cites this paper as [50]
In the citing paper
“SVM can correctly classify patients with stroke with 87.6% accuracy.”
From Artificial intelligence in healthcare: past, present and future (2017) · cites this paper as [50]
Citations
Cites
Cortes, C., & Vapnik, V. (1995) · Machine Learning · doi:10.1007/bf00994018 · Cited by 59,421
Cortes, C., & Vapnik, V. (1995) · Machine-mediated learning · doi:10.1023/a:1022627411411 · Cited by 48,445
LIBSVM: A library for support vector machines
Chang, C.-C., & Lin, C.-J. (2011) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/1961189.1961199 · Cited by 40,918
Functional connectivity in the motor cortex of resting human brain using echo‐planar mri
Biswal, B., Zerrin Yetkin, F., Haughton, V. M., & Hyde, J. S. (1995) · Magnetic Resonance in Medicine · doi:10.1002/mrm.1910340409 · Cited by 9,812
Ashburner, J., & Friston, K. J. (2005) · NeuroImage · doi:10.1016/j.neuroimage.2005.02.018 · Cited by 7,507 · cited 1×
“Then, all images were spatially normalized to the standard template of the Montreal Neurological Institute (MNI, Canada) using the unified segmentation approach with masked lesions (Ashburner and Friston 2005).”
Power, J. D., Barnes, K. A., Snyder, A. Z., Schlaggar, B. L., & Petersen, S. E. (2012) · NeuroImage · doi:10.1016/j.neuroimage.2011.10.018 · Cited by 7,429 · cited 1×
“We tested for group differences in head motion parameters from image realignment by comparing the framewise displacement and the root mean squared error (RMSE) (Power et al. 2012).”
MethodHeart Disease and Stroke Statistics—2013 Update: A Report From the American Heart Association
Go, A. S., Mozaffarian, D., Roger, V. L., Benjamin, E. J., Berry, J. D., Borden, W. B., Bravata, D. M., Dai, S., Ford, E. S., Fox, C. S., et al. (2013) · Circulation · doi:10.1161/cir.0b013e31828124ad · Cited by 5,292
Note on the Sampling Error of the Difference Between Correlated Proportions or Percentages
McNemar, Q. (1947) · Psychometrika · doi:10.1007/bf02295996 · Cited by 4,754
A component based noise correction method (CompCor) for BOLD and perfusion based fMRI
Behzadi, Y., Restom, K., Liau, J., & Liu, T. T. (2007) · NeuroImage · doi:10.1016/j.neuroimage.2007.04.042 · Cited by 4,502 · cited 1×
“Furthermore, the time-series was adjusted for the first 5 components of a principal component analysis (Behzadi et al. 2007; Chai et al. 2012).”
MethodA new SPM toolbox for combining probabilistic cytoarchitectonic maps and functional imaging data
Eickhoff, S. B., Stephan, K. E., Mohlberg, H., Grefkes, C., Fink, G. R., Amunts, K., & Zilles, K. (2005) · NeuroImage · doi:10.1016/j.neuroimage.2004.12.034 · Cited by 4,033 · cited 2×
“To this end, we used the same connectivity maps as for the SVM analysis consisting of positive correlations between seed voxel time-courses in ipsilesional M1 and wholebrain target voxels, which were transformed into Fisher Z-scores and then masked by frontoparietal sensorimotor areas (Eickhoff et al. 2005).”
MethodSelf-citation
Cited by
Artificial intelligence in healthcare: past, present and future
Jiang, F., Jiang, Y., Zhi, H., Dong, Y., Li, H., Ma, S., Wang, Y., Dong, Q., Shen, H., & Wang, Y. (2017) · Stroke and Vascular Neurology · doi:10.1136/svn-2017-000101 · Cited by 4,837
Disruptions of network connectivity predict impairment in multiple behavioral domains after stroke
Siegel, J. S., Ramsey, L. E., Snyder, A. Z., Metcalf, N. V., Chacko, R. V., Weinberger, K., Baldassarre, A., Hacker, C. D., Shulman, G. L., & Corbetta, M. (2016) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1521083113 · Cited by 656
Applications of machine learning to diagnosis and treatment of neurodegenerative diseases
Myszczynska, M. A., Ojamies, P. N., Lacoste, A. M. B., Neil, D., Saffari, A., Mead, R., Hautbergue, G. M., Holbrook, J. D., & Ferraiuolo, L. (2020) · Nature Reviews Neurology · doi:10.1038/s41582-020-0377-8 · Cited by 595
Recovery from stroke: current concepts and future perspectives
Grefkes, C., & Fink, G. R. (2020) · Neurological Research and Practice · doi:10.1186/s42466-020-00060-6 · Cited by 546
Self-citationBrain networks and their relevance for stroke rehabilitation
Guggisberg, A. G., Koch, P. J., Hummel, F. C., & Buetefisch, C. M. (2019) · Clinical Neurophysiology · doi:10.1016/j.clinph.2019.04.004 · Cited by 245
Restoring brain function after stroke — bridging the gap between animals and humans
Ward, N. S. (2017) · Nature Reviews Neurology · doi:10.1038/nrneurol.2017.34 · Cited by 235
Precision medicine in stroke: towards personalized outcome predictions using artificial intelligence
Bonkhoff, A. K., & Grefkes, C. (2022) · Brain · doi:10.1093/brain/awab439 · Cited by 193
“SVMs are frequently used in multivariate lesion-symptom studies relying on neuroimaging data.(159) For example, a classification problem with two linearly”
InfluentialSelf-citationStructural neuroimaging as clinical predictor: A review of machine learning applications
Mateos-Pérez, J. M., Dadar, M., Lacalle-Aurioles, M., Iturria-Medina, Y., Zeighami, Y., & Evans, A. C. (2018) · NeuroImage: Clinical · doi:10.1016/j.nicl.2018.08.019 · Cited by 174
Pilgramm, S., de Haas, B., Helm, F., Zentgraf, K., Stark, R., Munzert, J., & Krüger, B. (2016) · Human Brain Mapping · doi:10.1002/hbm.23015 · Cited by 166
Shaping Early Reorganization of Neural Networks Promotes Motor Function after Stroke
Volz, L. J., Rehme, A., Michely, J., Nettekoven, C., Eickhoff, S. B., Fink, G. R., & Grefkes, C. (2016) · Cerebral Cortex · doi:10.1093/cercor/bhw034 · Cited by 170
“…probability maps of frontoparietal sensorimotor areas (Brodmann areas 6, 4 a/p, 3 a/b, 2, and 1) to focus inference on functional connectivity within the cortical sensorimotor network as provided by the SPM Anatomy Toolbox (Eickhoff et al. 2005; see Rehme et al. 2015 for further details).”
Self-citationBrain connectivity and neurological disorders after stroke
Baldassarre, A., Ramsey, L. E., Siegel, J. S., Shulman, G. L., & Corbetta, M. (2016) · Current Opinion in Neurology · doi:10.1097/wco.0000000000000396 · Cited by 141
Advanced Neurotechnologies for the Restoration of Motor Function
Micera, S., Caleo, M., Chisari, C., Hummel, F. C., & Pedrocchi, A. (2020) · Neuron · doi:10.1016/j.neuron.2020.01.039 · Cited by 171
Acute ischaemic stroke alters the brain’s preference for distinct dynamic connectivity states
Bonkhoff, A. K., Espinoza, F. A., Gazula, H., Vergara, V. M., Hensel, L., Michely, J., Paul, T., Rehme, A. K., Volz, L. J., Fink, G. R., et al. (2020) · Brain · doi:10.1093/brain/awaa101 · Cited by 137
“The third connectivity state did not differ in terms of dynamic connectivity specific measures, such as transitions, fraction and dwell times, but reflected many of the connectivity differences observed in the static analysis and previously described in the literature (Carter et al., 2010; Wang et al., 2010; Golestani…”
BackgroundMethodResultInfluentialSelf-citationMachine learning studies on major brain diseases: 5-year trends of 2014–2018
Sakai, K., & Yamada, K. (2018) · Japanese Journal of Radiology · doi:10.1007/s11604-018-0794-4 · Cited by 143
Yusuf, M., Atal, I., Li, J., Smith, P., Ravaud, P., Fergie, M., Callaghan, M., & Selfe, J. (2020) · BMJ Open · doi:10.1136/bmjopen-2019-034568 · Cited by 102
Lei, D., Pinaya, W. H. L., van Amelsvoort, T., Marcelis, M. C., Donohoe, G. J., Mothersill, D., Corvin, A. P., Gill, M., Vieira, S., Huang, X., et al. (2019) · Psychological Medicine · doi:10.1017/s0033291719001934 · Cited by 109
Mahajan, A., Vaidya, T. P., Gupta, A., Rane, S. U., & Gupta, S. (2019) · Cancer Research Statistics and Treatment · doi:10.4103/crst.crst_50_19 · Cited by 113
“used SVM in resting‐state functional magnetic resonance imaging (fMRI) data, by which endophenotypes of motor disability after stroke were identified and classified (endophenotype refers to an internal characteristic of a person which renders the individual more susceptible to a disorder).[12] Griffis et al.”
MethodFunctional connectivity drives stroke recovery: shifting the paradigm from correlation to causation
Cassidy, J. M., Mark, J. I., & Cramer, S. C. (2021) · Brain · doi:10.1093/brain/awab469 · Cited by 103
Artificial intelligence in stroke imaging: Current and future perspectives
Yedavalli, V. S., Tong, E., Martin, D., Yeom, K. W., & Forkert, N. D. (2020) · Clinical Imaging · doi:10.1016/j.clinimag.2020.09.005 · Cited by 110
Pool, E., Rehme, A. K., Eickhoff, S. B., Fink, G. R., & Grefkes, C. (2015) · NeuroImage · doi:10.1016/j.neuroimage.2015.01.034 · Cited by 97
“7 Mass-univariate SVM analysis To compare multivariate SVM classification with univariate classification, we also tested the classification accuracy of individual voxels within the motor network for the discrimination between right- and left-handers (Rehme et al., 2014).”
Self-citationTozlu, C., Edwards, D. J., Boes, A. D., Labar, D., Tsagaris, K. Z., Silverstein, J., Lane, H. P., Sabuncu, M. R., Liu, C. Y., & Kuceyeski, A. F. (2020) · Neurorehabilitation and neural repair · doi:10.1177/1545968320909796 · Cited by 94
“6 Rehme et al 52 used SVM to classify patients with respect to acute poststroke motor impairment based on the resting-state functional MRI; they reported a classification rate of > 80%.”
MethodThe structural connectome and motor recovery after stroke: predicting natural recovery
Koch, P., Park, C.-H., Girard, G., Beanato, E., Egger, P., Evangelista, G. G., Lee, J., Wessel, M. J., Morishita, T., Koch, G., et al. (2021) · Brain · doi:10.1093/brain/awab082 · Cited by 96
“MEP or CST structural integrity) and reached an accuracy between 70 and 86%.(13,15,16,37) However, these models have relevant limitations in correct phenotyping, especially for severely Table 1 Correlation coefficients for the proportional recovery rule”
BackgroundRehme, A. K., Volz, L. J., Feis, D., Eickhoff, S. B., Fink, G. R., & Grefkes, C. (2015) · Human Brain Mapping · doi:10.1002/hbm.22936 · Cited by 86
Self-citationAbnormal dynamic functional connectivity is linked to recovery after acute ischemic stroke
Bonkhoff, A. K., Schirmer, M. D., Bretzner, M., Etherton, M. R., Donahue, K., Tuozzo, C., Nardin, M., Giese, A., Wu, O., Calhoun, V. D., et al. (2021) · Human Brain Mapping · doi:10.1002/hbm.25366 · Cited by 85
“Motor impairments have previously been linked to decreases in functional connectivity between sensorimotor areas across hemispheres (Carter et al., 2010; Rehme et al., 2014).”
BackgroundInfluentialSelf-citationAI Applications in Adult Stroke Recovery and Rehabilitation: A Scoping Review Using AI
Senadheera, I., Hettiarachchi, P., Haslam, B. S., Nawaratne, R., Sheehan, J., Lockwood, K. J., Alahakoon, D., & Carey, L. M. (2024) · Sensors · doi:10.3390/s24206585 · Cited by 111
“Technological advancements, including AI, continue to be applied in stroke management to improve early detection, clinical outcome prediction and quick delivery of treatment by maximizing system efficiency from acute care [89,129,143].”
BackgroundMethodMeasuring functional connectivity in stroke: Approaches and considerations
Siegel, J. S., Shulman, G. L., & Corbetta, M. (2017) · Journal of Cerebral Blood Flow & Metabolism · doi:10.1177/0271678x17709198 · Cited by 74
Koch, P., & Hummel, F. C. (2017) · Current Opinion in Neurology · doi:10.1097/wco.0000000000000462 · Cited by 70
“References: 1: Rehme et al. 2015 [10&]; 2: Rehme et al. 2011 [12]; 3: Loubinoux et al. 2007 [11]; 4: Buma and van Kordelaar et al. 2016 [16], 5: Kononen et al. 2012 [48]; 6: Cunningham et al. 2015 [47]; 7: Cramer et al. 2007 [45]; 8: Ward et al. 2003 [116]; 9: Johansen-Berg et al. 2002 [113]; 10:…”
Neuroanatomy of post-stroke depression: the association between symptom clusters and lesion location
Krick, S., Koob, J. L., Latarnik, S., Volz, L. J., Fink, G. R., Grefkes, C., & Rehme, A. K. (2023) · Brain Communications · doi:10.1093/braincomms/fcad275 · Cited by 69
“51,52 In contrast, SVR allows the prediction of continuous variables based on the lesion status of multiple voxels.”
BackgroundSelf-citationLeveraging artificial intelligence in ischemic stroke imaging
Shafaat, O., Bernstock, J. D., Shafaat, A., Yedavalli, V. S., Elsayed, G., Gupta, S., Sotoudeh, E., Sair, H. I., Yousem, D. M., & Sotoudeh, H. (2021) · Journal of Neuroradiology · doi:10.1016/j.neurad.2021.05.001 · Cited by 57
Application of Artificial Intelligence in Modern Healthcare System
Datta, S., Barua, R., & Das, J. (2020) · IntechOpen eBooks · doi:10.5772/intechopen.90454 · Cited by 63
Noninvasive brain stimulation after stroke: it is time for large randomized controlled trials!
Grefkes, C., & Fink, G. R. (2016) · Current Opinion in Neurology · doi:10.1097/wco.0000000000000395 · Cited by 58
“All rights rese connectivity, whereas anatomical lesion location has a comparatively poor predictive value for behavioral deficits [15].”
BackgroundSelf-citationMohanty, R., Sinha, A. M., Remsik, A. B., Dodd, K. C., Young, B. M., Jacobson, T., McMillan, M., Thoma, J., Advani, H., Nair, V. A., et al. (2018) · Frontiers in Neuroscience · doi:10.3389/fnins.2018.00353 · Cited by 57
“…studies have underscored the utility of machine learning to not only differentiate among population groups (Dai et al., 2012; Meier et al., 2012; Rehme et al., 2014; Fergus et al., 2016; Khazaee et al., 2016; Ding et al., 2017) but also make predictions about behavioral outcomes using…”
BackgroundTscherpel, C., Hensel, L., Lemberg, K., Vollmer, M., Volz, L. J., Fink, G. R., & Grefkes, C. (2020) · Brain stimulation · doi:10.1016/j.brs.2020.01.016 · Cited by 56
“8 Besides, fMRI studies have equally shown that in patients suffering from motor stroke, 9 functional connectivity between ipsilesional M1 and contralesional parietal regions is 10 diminished in patients suffering from motor stroke [61,62], lending further support to the 11 notion of a relevant contribution of contral…”
Self-citationMRI radiomic features-based machine learning approach to classify ischemic stroke onset time
Zhang, Y., Liu, A.-F., Man, F., Zhang, Y.-Y., Li, C., Liu, Y.-E., Zhou, J. J., Zhang, A., Zhang, Y.-D., Lv, J., et al. (2021) · Journal of Neurology · doi:10.1007/s00415-021-10638-y · Cited by 45
Machine learning technique reveals intrinsic characteristics of schizophrenia: an alternative method
Li, J., Sun, Y., Huang, Y., Bezerianos, A., & Yu, R. (2018) · Brain Imaging and Behavior · doi:10.1007/s11682-018-9947-4 · Cited by 41
“Additionally, t-test and Fisher’s score can also be utilized for feature selection, which were applied to other differentiation tasks such as mental state classification and stroke identification (Li et al. 2016; Rehme et al. 2014).”
MethodDynamic connectivity predicts acute motor impairment and recovery post-stroke
Bonkhoff, A. K., Rehme, A. K., Hensel, L., Tscherpel, C., Volz, L. J., Espinoza, F. A., Gazula, H., Vergara, V. M., Fink, G. R., Calhoun, V. D., et al. (2021) · Brain Communications · doi:10.1093/braincomms/fcab227 · Cited by 49
“Images of patients with right-hemispheric lesions (n1⁄4 19) were flipped at the midsagittal plane.(8,17) As a consequence, no conclusions on hemispheric-specific effects can be drawn with respect to motor recovery.”
BackgroundSelf-citationBruyn, N. D., Meyer, S., Kessner, S. S., Essers, B., Cheng, B., Thomalla, G., Peeters, A. P., Sunaert, S. G., Duprez, T. P. J., Thijs, V., et al. (2018) · PLoS ONE · doi:10.1371/journal.pone.0205693 · Cited by 43
“A paper of Rehme et al [14] included increased intrahemispheric functional connectivity in their criteria for classification of upper limb function.”
BackgroundResultInfluentialConnectivity-Related Roles of Contralesional Brain Regions for Motor Performance Early after Stroke
Hensel, L., Tscherpel, C., Freytag, J., Ritter, S., Rehme, A. K., Volz, L. J., Eickhoff, S. B., Fink, G. R., & Grefkes, C. (2020) · Cerebral Cortex · doi:10.1093/cercor/bhaa270 · Cited by 39
Self-citationPredictive analytics and machine learning in stroke and neurovascular medicine
Saber, H., Somai, M. M., Rajah, G. B., Scalzo, F., & Liebeskind, D. S. (2019) · Neurological Research · doi:10.1080/01616412.2019.1609159 · Cited by 38
“Findings in both functional and structural MRI have been used as input features in machine learning models to predict motor and cognitive outcomes after stroke [47 – 51].”
MethodHordacre, B. G., Lotze, M., Jenkinson, M., Lazari, A., Barras, C. D., Boyd, L. A., & Hillier, S. (2021) · NeuroImage Clinical · doi:10.1016/j.nicl.2021.102558 · Cited by 37
“Several studies have reported decreased interhemispheric resting state connectivity between motor cortices is associated with reduced upper-limb behavior (Carter et al., 2010, 2011; Chen and Schlaug, 2013; Golestani et al., 2012; Park et al., 2011; Rehme et al., 2014; Urbin et al., 2014).”
Peng, C.-Y., Chen, Y., Cui, Y., Zhao, D.-L., Jiao, Y., Tang, T., Ju, S., & Teng, G. (2016) · PLoS ONE · doi:10.1371/journal.pone.0159574 · Cited by 35
“Neuroimaging is the technique most commonly used to assess cerebral diseases [11].”
MethodMRI Biomarkers for Hand-Motor Outcome Prediction and Therapy Monitoring following Stroke
Horn, U., Grothe, M., & Lotze, M. (2016) · Neural Plasticity · doi:10.1155/2016/9265621 · Cited by 35
“M1 and secondarymotor areas, particularly in the ipsilesional hemisphere [83].”
BackgroundPaul, T., Hensel, L., Rehme, A. K., Tscherpel, C., Eickhoff, S. B., Fink, G. R., Grefkes, C., & Volz, L. J. (2021) · Human Brain Mapping · doi:10.1002/hbm.25612 · Cited by 40
Self-citationzhong, J., Chen, D. Q., Nantes, J. C., Holmes, S. A., Hodaie, M., & Koski, L. M. (2016) · Brain Imaging and Behavior · doi:10.1007/s11682-016-9551-4 · Cited by 36
Moulton, E. J., Valabrègue, R., Lehéricy, S., Samson, Y., & Rosso, C. (2019) · NeuroImage Clinical · doi:10.1016/j.nicl.2019.101821 · Cited by 31
Somatosensory Deficits After Stroke: Insights From MRI Studies
Lv, Q., Zhang, J., Pan, Y., Liu, X., Miao, L., Peng, J., Song, L., Zou, Y., & Chen, X. (2022) · Frontiers in Neurology · doi:10.3389/fneur.2022.891283 · Cited by 32
Deep learning prediction of motor performance in stroke individuals using neuroimaging data
Karakış, R., Gürkahraman, K., Mitsis, G. D., & Boudrias, M. (2023) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2023.104357 · Cited by 30
Mohanty, R., Sinha, A. M., Remsik, A. B., Dodd, K. C., Young, B. M., Jacobson, T., McMillan, M., Thoma, J., Advani, H., Nair, V. A., et al. (2018) · Frontiers in Neuroscience · doi:10.3389/fnins.2018.00624 · Cited by 29
Ding, X., Yang, Y., Stein, E. A., & Ross, T. J. (2017) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2017.00362 · Cited by 29
“Resting-state data are widely investigated using machine learning approaches (Deshpande et al., 2010; Shen et al., 2010; Dai et al., 2012; Eloyan et al., 2012; Zeng et al., 2014; Iidaka, 2015; Liu et al., 2015; Rehme et al., 2015).”
MethodConnectivity-Based Predictions of Hand Motor Outcome for Patients at the Subacute Stage After Stroke
Lindow, J., Domín, M., Grothe, M., Horn, U., Eickhoff, S. B., & Lotze, M. (2016) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2016.00101 · Cited by 27
“Overall, stroke patients with motor impairment show decreased interhemispheric M1connectiviy and increased resting-state connectivity between ipsilesional M1 and secondary motor areas particularly in the ipsilesional hemisphere (Rehme et al., 2015).”
BackgroundResultSelf-citationApplication of Machine Learning Techniques in Healthcare
H, S. D., Sudha, V., & Jagadeesan, D. (2019) · Advances in computational intelligence and robotics book series · doi:10.4018/978-1-5225-9902-9.ch015 · Cited by 26
Selectively disrupted sensorimotor circuits in chronic stroke with hand dysfunction
Liu, F., Chen, C., Hong, W., Bai, Z., Wang, S., Lu, H., Lin, Q., Zhao, Z., & Tang, C. (2022) · CNS Neuroscience & Therapeutics · doi:10.1111/cns.13799 · Cited by 24
“These findings indicate that injury of the subcortical motor pathway results in specific disruption of sensorimotor circuits, which may inspire the development of neuroimaging biomarkers 40 and stimulation targets 41 in neurorehabilitation practice after chronic stroke.”
BackgroundDutta, D., Sen, S., Aruchamy, S., & Mandal, S. (2022) · Smart Health · doi:10.1016/j.smhl.2022.100264 · Cited by 31
Hensel, L., Grefkes, C., Tscherpel, C., Ringmaier, C., Kraus, D., Hamacher, S., Volz, L. J., & Fink, G. R. (2019) · BMJ Open · doi:10.1136/bmjopen-2019-034088 · Cited by 25
Self-citationSui, Y., Kan, C., Zhu, S., Zhang, T., Wang, J., Xu, S., Zhuang, R., Shen, Y., Wang, T., & Guo, C. (2022) · Frontiers in Neurology · doi:10.3389/fneur.2022.965856 · Cited by 26
Cerebral imaging of post-stroke plasticity and tissue repair
Loubinoux, I., Brihmat, N., Castel-Lacanal, E., & Marqué, P. (2017) · Revue Neurologique · doi:10.1016/j.neurol.2017.09.007 · Cited by 29
Constructing support vector machines with missing data
Stewart, T. G., Zeng, D., & Wu, M. C. (2018) · Wiley Interdisciplinary Reviews Computational Statistics · doi:10.1002/wics.1430 · Cited by 21
“SVMs have been used within a wide range of different applications, including gene expression analysis (Furey et al., 2000), functional magnetic resonance imaging analysis (Rehme et al., 2015), and other biomedical computer vision tasks.”
MethodIdentification of Early Vascular Dementia Patients With EEG Signal
Wang, C., Xu, J., Zhao, S., & Lou, W. (2019) · IEEE Access · doi:10.1109/access.2019.2918251 · Cited by 20
“6% with a sensitivity of 80% and a specificity of 85% in stroke [60], an accuracy of 93.”
BackgroundMethodVolz, L. J., Köcher, M., Lohmann, P., Shah, N. J., Fink, G. R., & Galldiks, N. (2018) · The Quarterly Journal of Nuclear Medicine and Molecular Imaging · doi:10.23736/s1824-4785.18.03101-1 · Cited by 17
Self-citationArtificial Intelligence in Diagnosis and Management of Ischemic Stroke
Gupta, M. (2019) · Biomedical Journal of Scientific & Technical Research · doi:10.26717/bjstr.2019.13.002398 · Cited by 16
Cortical propagation tracks functional recovery after stroke
Cecchini, G., Scaglione, A., Mascaro, A. L. A., Checcucci, C., Conti, E., Adam, I., Fanelli, D., Livi, R., Pavone, F. S., & Kreuz, T. (2021) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1008963 · Cited by 17
“Furthermore, these changes in resting state functional connectivity can be used to discriminate subjects with behavioral deficits [11, 12].”
BackgroundAllen, M. J., Pearn, K., Monks, T., Bray, B., Everson, R., Salmon, A., James, M. A., & Stein, K. (2019) · BMJ Open · doi:10.1136/bmjopen-2018-028296 · Cited by 13
Automated Assessment of Peristomal Skin Discoloration and Leakage Area Using Artificial Intelligence
Andersen, N. K., Trøjgaard, P., Herschend, N. O., & Størling, Z. M. (2020) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2020.00072 · Cited by 15
“, 2016), stroke and neuroimaging (Rehme et al., 2015; Kamnitsas et al., 2017), skin cancer (Esteva et al.”
BackgroundMethodYu, X., Jiaerken, Y., Xu, X., Jackson, A., Huang, P., Yang, L., Yuan, L., Lou, M., Jiang, Q., & Zhang, M. (2018) · European Radiology · doi:10.1007/s00330-018-5576-y · Cited by 14
Toward a hemorrhagic trauma severity score: fusing five physiological biomarkers
Bhat, A., Podstawczyk, D. A., Walther, B. K., Aggas, J. R., Machado-Aranda, D., Ward, K. R., & Guiseppi‐Elie, A. (2020) · Journal of Translational Medicine · doi:10.1186/s12967-020-02516-4 · Cited by 13
Predicting poststroke dyskinesia with resting-state functional connectivity in the motor network
Lin, S., Wang, D., Sang, H., Xiao, H., Yan, K., Wang, D., Zhang, Y., Yi, L., Shao, G., Shao, Z., et al. (2023) · Neurophotonics · doi:10.1117/1.nph.10.2.025001 · Cited by 13
“Rehme et al.(28) classified patients with hand motor deficits compared with controls and nonimpaired patients with an 82.”
BackgroundInfluentialFighting healthcare rocketing costs with value-based medicine: the case of stroke management
Esposti, F., & Banfi, G. (2020) · BMC Health Services Research · doi:10.1186/s12913-020-4925-0 · Cited by 14
A review of machine learning applications in heart health
Perrone, A. M., & Khoshgoftaar, T. M. (2025) · BioMedical Engineering OnLine · doi:10.1186/s12938-025-01430-4 · Cited by 14
“Rehme et al. [51] used MRI images using a model proven to be accurate for brain diseases to predict a patient’s motor ability, but the sample set only contained 60 images, and the size was not addressed in the experiment.”
Power Spectral Density Analysis of Long-Term Motor Recovery in Patients With Subacute Stroke
Min, Y.-S., Park, J. W., Jang, K. E., Lee, H. J., Lee, J., Lee, Y., Jung, T., & Chang, Y. (2018) · Neurorehabilitation and neural repair · doi:10.1177/1545968318818900 · Cited by 10
Friedrich, P., Patil, K. R., Mochalski, L. N., Li, X., Camilleri, J. A., Kröll, J., Wiersch, L., Eickhoff, S. B., & Weis, S. (2021) · Brain Structure and Function · doi:10.1007/s00429-021-02418-1 · Cited by 12
Self-citationCheng, F., Duan, Y., Jiang, H., Zeng, Y., Chen, X., Qin, L., Zhao, L., Yi, F., Tang, Y., & Liu, C. (2022) · BioMedical Engineering OnLine · doi:10.1186/s12938-022-01050-2 · Cited by 9
“, features with the classifiers, such as support vector machines (SVM), which has been proved widely to have the excellent generalization capability for new samples [19, 20].”
BackgroundDecoding with confidence: Statistical control on decoder maps
Chevalier, J.-A., Nguyen, T.-B., Salmon, J., Varoquaux, G. P., & Thirion, B. (2021) · NeuroImage · doi:10.1016/j.neuroimage.2021.117921 · Cited by 13
Cao, B., Guo, Y. Q., Guo, Y., Xie, Q., Chen, L., Huang, H., Yu, R., & Huang, R. (2021) · NeuroImage Clinical · doi:10.1016/j.nicl.2021.102797 · Cited by 10
Liu, F., Chen, C., Bai, Z., Hong, W., Wang, S., & Tang, C. (2022) · CNS Neuroscience & Therapeutics · doi:10.1111/cns.13946 · Cited by 12
Steiner, L., Homan, S., Everts, R., Federspiel, A., Kamal, S., Rodríguez, J. A. D., Kornfeld, S., Slavova, N., Wiest, R., Kaelin‐Lang, A., et al. (2021) · Scientific Reports · doi:10.1038/s41598-021-84671-2 · Cited by 10
Advancing brain network models to reconcile functional neuroimaging and clinical research
Kobeleva, X., Varoquaux, G. P., Dagher, A., Adhikari, M. H., Grefkes, C., & Gilson, M. (2022) · NeuroImage Clinical · doi:10.1016/j.nicl.2022.103262 · Cited by 9
“For instance, good motor recovery after a stroke can be classified according to primary motor cortex activity within the lesioned hemisphere measured using BOLD-fMRI on the first week after the stroke (Rehme et al., 2015).”
Self-citationScaling behaviours of deep learning and linear algorithms for the prediction of stroke severity
(2023) · doi:10.1093/braincomms/fcae007 · Cited by 8
“4 5-7 As such, there has thus been a quick adaptation of novel and powerful methods as soon as computational resources permitted their use.”
Brain Topological Reorganization Associated with Visual Neglect After Stroke
de Pasquale, F., Chiacchiaretta, P., Pavone, L., Sparano, A., Capotosto, P., Grillea, G., Committeri, G., & Baldassarre, A. (2023) · Brain Connectivity · doi:10.1089/brain.2020.0969 · Cited by 9
“…behavioral impairments in several domains (Siegel et al., 2016a) such as motor (Baldassarre et al., 2016a; Bauer et al., 2014; Carter et al., 2010; Rehme et al., 2015; Wang et al., 2010), visuo-spatial attention (Baldassarre et al., 2014, 2016a; Carter et al., 2010; He et al., 2007), language…”
BackgroundReduced Segregation of Brain Networks in Spatial Neglect After Stroke
Spadone, S., de Pasquale, F., Chiacchiaretta, P., Pavone, L., Capotosto, P., Pizzi, S. D., Digiovanni, A., Sensi, S. L., Committeri, G., & Baldassarre, A. (2022) · Brain Connectivity · doi:10.1089/brain.2021.0184 · Cited by 7
Basic Principles of rTMS in Motor Recovery After Stroke
Volz, L. J., & Grefkes, C. (2015) · Springer eBooks · doi:10.1007/978-3-319-25721-1_3 · Cited by 7
Self-citationHu, J., Du, J., Xu, Q., Yang, F., Zeng, F., Dai, X., Liu, X., Lu, G., & Zhang, Z. (2017) · Frontiers in Neurology · doi:10.3389/fneur.2017.00339 · Cited by 7
Salahuddin, T., Al-Maadeed, S. A., Petropoulos, I. N., Malik, R. A., Kamran, S., & Qidwai, U. A. (2019) · World Conference on Smart Trends in Systems, Security and Sustainability (WorldS4) · doi:10.1109/worlds4.2019.8904015 · Cited by 8
Neuroimaging and biological markers of different paretic hand outcomes after stroke
Wang, Z., Zheng, M., Yuan, B., Zhang, Y., Hong, W., Tang, C., & Wu, W. I. (2025) · Journal of NeuroEngineering and Rehabilitation · doi:10.1186/s12984-025-01682-0 · Cited by 7
“For example, two fMRI-based support vector machine (SVM) studies could accurately classify different hand deficits and predict functional recovery following stroke [19], particularly in patients with moderate impairment and high outcome variability [20].”
Ma, Y., Zhang, P., Tang, Y., Pan, C., Li, G., Liu, N., Hu, Y., & Tang, Z. (2020) · Brain Hemorrhages · doi:10.1016/j.hest.2020.01.006 · Cited by 7
Ghaderi, S., Mohammadi, M., Sayehmiri, F., Mohammadi, S., Tavasol, A., Rezaei, M., & Ghalyanchi‐Langeroudi, A. (2024) · Journal of Magnetic Resonance Imaging · doi:10.1002/jmri.29364 · Cited by 8
Prediction of stroke severity: systematic evaluation of lesion representations
Bonkhoff, A. K., Cohen, A. L., Drew, W., Ferguson, M. A., Hussain, A., Lin, C., Schaper, F. L. W. V. J., Bourached, A., Giese, A., de Oliveira, L. C., et al. (2024) · Annals of Clinical and Translational Neurology · doi:10.1002/acn3.52215 · Cited by 8
Sun, Z., Cao, Z., Ge, L., Li, Y., Huang, H., Li, M., & Qiu, S. (2025) · Meta-Radiology · doi:10.1016/j.metrad.2025.100136 · Cited by 8
A Classification Model Based on an Adaptive Neuro-fuzzy Inference System for Disease Prediction
Mohanty, R., Solanki, S. S., Mallick, P. K., & Pani, S. K. (2020) · Studies in computational intelligence · doi:10.1007/978-981-15-5495-7_7 · Cited by 8
Behavioral and neuroanatomical correlates of facial emotion processing in post-stroke depression
Koob, J. L., Gorski, M., Krick, S., Mustin, M., Fink, G. R., Grefkes, C., & Rehme, A. K. (2024) · NeuroImage Clinical · doi:10.1016/j.nicl.2024.103586 · Cited by 6
“Support vector regression (SVR) is a particular case of support vector machines, which are employed to solve binary classification problems, e.g., whether a disease is either present or absent (Rehme et al., 2015a; Rehme et al., 2015b).”
BackgroundSelf-citationSun, J., Wang, D., Chen, S., Pang, R., Liu, H., Wang, J., Zhang, Y., Wang, C., & Yang, A. (2021) · Medicine in Novel Technology and Devices · doi:10.1016/j.medntd.2021.100083 · Cited by 4
Potential Use of Artificial Intelligence in a Healthcare System
Agrawal, O. D., & Madhavi, J. S. (2022) · The Chinese Journal of Artificial Intelligence · doi:10.2174/2666782701666220805105655 · Cited by 5
Neuroimaging and kinematic biomarkers of post-stroke upper limb motor impairment
Chen, J. L., Lam, T. K., Baniña, M. C., Piscitelli, D., & Levin, M. F. (2025) · NeuroImage Clinical · doi:10.1016/j.nicl.2025.103854 · Cited by 4
“Studies using these methodologies have reported that ipsilesional premotor and primary motor connectivity explained ~27 % of variance in motor performance (Paul et al., 2021) and is related to post-stroke motor impairment (Rehme et al., 2015).”
Dynamic topological changes of the motor network after stroke
Baldassarre, A., Guidotti, R., Pizzella, V., Bassi, M. S., Pavone, L., Committeri, G., Sensi, S. L., Ilmoniemi, R. J., Ziemann, U., Romani, G. L., et al. (2025) · NeuroImage Clinical · doi:10.1016/j.nicl.2025.103907 · Cited by 4
“The first pattern, i.e., RvCS-LCS, is strongly consistent with several lines of evidence indicating that motor impairment is associated with a disruption of the inter-hemispheric functional connectivity within the motor network (Carter et al., 2010; Rehme et al., 2015; Baldassarre et al., 2016a).”
Clinical applications of deep learning in neurology and its enhancements with future directions
Olaniyan, O. T., Adetunji, C. O., Adeyomoye, O., Dare, A., Adeniyi, M. J., & Enoch, A. (2022) · Elsevier eBooks · doi:10.1016/b978-0-323-90277-9.00026-2 · Cited by 4
Machine Learning Approaches and Neuroimaging in Cognitive Functions of the Human Brain: A Review
Aram, S., Kornev, D., Sadeghian, R., Sardari, S. E., Venu, S. K., Dashtestani, H., & Gandjbakhche, A. (2020) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-51041-1_4 · Cited by 3
Normative connectome-based analysis of sensorimotor deficits in acute subcortical stroke
Weigel, K., Klingner, C. M., Brodoehl, S., Wagner, F., Schwab, M., Güllmar, D., Mayer, T. E., Güttler, F. V., Teichgräber, U. K.-M., & Gaser, C. (2024) · Frontiers in Neuroscience · doi:10.3389/fnins.2024.1400944 · Cited by 3
“To optimize prediction models, integrating these features into machine learning approaches is crucial, as the quality of input features heavily influences model performance (Rehme et al., 2015; Mouridsen et al., 2020; Jayakumar et al., 2022).”
MethodKarnadipa, T., Chong, B., Shim, V., Fernandez, J., Lin, D. J., Stinear, C. M., & Wang, A. (2025) · NeuroImage · doi:10.1016/j.neuroimage.2025.121376 · Cited by 2
Pahwa, B., Tayal, A., & Garg, K. (2024) · World Neurosurgery · doi:10.1016/j.wneu.2024.01.059 · Cited by 2
Machine Learning for Interpretation of Brain Images: A Detailed Analysis through survey
Bagavathi, C. (2021) · International Conference on Computing, Communication, and Intelligent Systems (ICCCIS) · doi:10.1109/icccis51004.2021.9397238 · Cited by 2
“SVM on MRI have produced an accuracy of 87.6% [29].”
BackgroundInfluentialFunktionserholung nach Schlaganfall und die therapeutische Rolle der nicht-invasiven Hirnstimulation
Tscherpel, C., & Grefkes, C. (2020) · Klinische Neurophysiologie · doi:10.1055/a-1272-9435 · Cited by 2
“Zwar wurden bereits erste Versuche unternommen, mittels multivariater maschineller Lernverfahren das motorische Defizit oder motorische Outcome in Patienten auf der Grundlage von fMRT-Daten zu prädizieren [124, 125].”
Self-citation
Metadata
- Authors
- Rehme, A. K., Volz, L. J., Feis, D.-L., Bomilcar-Focke, I., Liebig, T., Eickhoff, S. B., Fink, G. R., & Grefkes, C.
- Affiliations
- Forschungszentrum Jülich (DE)
- Max Planck Society (DE)
- Max Planck Institute for Metabolism Research (DE)
- University of Cologne (DE)
- Corresponding author
- Rehme, A. K.
- Venue
- Cerebral Cortex
- Publisher
- Oxford University Press (OUP)
- Published
- 2014-05-16
- Volume
- 25
- Issue
- 9
- Pages
- 3046-3056
- ISSN
- 1047-3211 (ISSN-L)
- 1460-2199
- OpenAlex
- W2120701355
- Cited by
- 117
- References
- 70
- Citations by year
- 2026: 3 · 2025: 10 · 2024: 6 · 2023: 6 · 2022: 14 · 2021: 19 · 2020: 16 · 2019: 13 · 2018: 11 · 2017: 7 · 2016: 8 · 2015: 4
- FWCI
- 3.53
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Cerebral Cortex (publishedVersion)
- PubMed (publishedVersion)
- Kölner Universitäts PublikationsServer (Universität zu Köln) (publishedVersion)
- MPG.PuRe (Max Planck Society) (submittedVersion)
- Topics
- Life Sciences › Neuroscience › Cognitive Neuroscience › Functional Brain Connectivity Studies
- Health Sciences › Medicine › Rehabilitation › Stroke Rehabilitation and Recovery
- Life Sciences › Neuroscience › Neurology › Transcranial Magnetic Stimulation Studies
- Keywords
- acute stroke, motor impairment, resting-state fMRI, support vector machine, multivariate decoding, interhemispheric connectivity, primary motor cortex, premotor cortex, lesion localization, endophenotypes
- MeSH terms
- Machine Learning, Aged, Aged, 80 and over, Brain, Brain Mapping, Disability Evaluation, Female, Humans, Image Processing, Computer-Assisted, Male, Middle Aged, Movement Disorders, Neural Pathways, Rest, Severity of Illness Index, Stroke, Neuroimaging
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.