1
|
Hope TMH, Neville D, Talozzi L, Foulon C, Forkel SJ, de Schotten MT, Price CJ. Testing the disconnectome symptom discoverer model on out-of-sample post-stroke language outcomes. Brain 2024; 147:e11-e13. [PMID: 37820032 PMCID: PMC10834246 DOI: 10.1093/brain/awad352] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/15/2023] [Accepted: 09/29/2023] [Indexed: 10/13/2023] Open
Affiliation(s)
- Thomas M H Hope
- Wellcome Centre for Human Neuroimaging, Department of Imaging Neuroscience, Institute of Neurology, University College London, London WC1N 3AR, UK
- Department of Psychological and Social Sciences, John Cabot University, 00162 Rome, Italy
| | - Douglas Neville
- Wellcome Centre for Human Neuroimaging, Department of Imaging Neuroscience, Institute of Neurology, University College London, London WC1N 3AR, UK
| | - Lia Talozzi
- Department of Neurology and Neurological Sciences, Stanford University School of Medicine, Stanford, CA 94304, USA
| | - Chris Foulon
- Brain Connectivity and Behaviour Laboratory, Sorbonne Universities, Paris 75006, France
- Queen Square Institute of Neurology, University College London, London WC1N 3BG, UK
| | - Stephanie J Forkel
- Brain Connectivity and Behaviour Laboratory, Sorbonne Universities, Paris 75006, France
- Queen Square Institute of Neurology, University College London, London WC1N 3BG, UK
- Donders Institute for Brain Cognition Behaviour, Radboud University, Nijmegen 6525, The Netherlands
- Centre for Neuroimaging Sciences, Department of Neuroimaging, Institute of Psychiatry, Psychology and Neuroscience, King’s College London, London SE5 8AF, UK
| | - Michel Thiebaut de Schotten
- Brain Connectivity and Behaviour Laboratory, Sorbonne Universities, Paris 75006, France
- Groupe d'Imagerie Neurofonctionnelle, Institut des Maladies Neurodégénératives-UMR 5293, CNRS, CEA, University of Bordeaux, Bordeaux, 33076, France
| | - Cathy J Price
- Wellcome Centre for Human Neuroimaging, Department of Imaging Neuroscience, Institute of Neurology, University College London, London WC1N 3AR, UK
| |
Collapse
|
2
|
Sperber C, Gallucci L, Mirman D, Arnold M, Umarova RM. Stroke lesion size - Still a useful biomarker for stroke severity and outcome in times of high-dimensional models. Neuroimage Clin 2023; 40:103511. [PMID: 37741168 PMCID: PMC10520672 DOI: 10.1016/j.nicl.2023.103511] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/09/2023] [Revised: 09/05/2023] [Accepted: 09/16/2023] [Indexed: 09/25/2023]
Abstract
BACKGROUND The volumetric size of a brain lesion is a frequently used stroke biomarker. It stands out among most imaging biomarkers for being a one-dimensional variable that is applicable in simple statistical models. In times of machine learning algorithms, the question arises of whether such a simple variable is still useful, or whether high-dimensional models on spatial lesion information are superior. METHODS We included 753 first-ever anterior circulation ischemic stroke patients (age 68.4±15.2 years; NIHSS at 24 h 4.4±5.1; modified Rankin Scale (mRS) at 3-months median[IQR] 1[0.75;3]) and traced lesions on diffusion-weighted MRI. In an out-of-sample model validation scheme, we predicted stroke severity as measured by NIHSS 24 h and functional stroke outcome as measured by mRS at 3 months either from spatial lesion features or lesion size. RESULTS For stroke severity, the best regression model based on lesion size performed significantly above chance (p < 0.0001) with R2 = 0.322, but models with spatial lesion features performed significantly better with R2 = 0.363 (t(752) = 2.889; p = 0.004). For stroke outcome, the best classification model based on lesion size again performed significantly above chance (p < 0.0001) with an accuracy of 62.8%, which was not different from the best model with spatial lesion features (62.6%, p = 0.80). With smaller training data sets of only 150 or 50 patients, the performance of high-dimensional models with spatial lesion features decreased up to the point of being equivalent or even inferior to models trained on lesion size. The combination of lesion size and spatial lesion features in one model did not improve predictions. CONCLUSIONS Lesion size is a decent biomarker for stroke outcome and severity that is slightly inferior to spatial lesion features but is particularly suited in studies with small samples. When low-dimensional models are desired, lesion size provides a viable proxy biomarker for spatial lesion features, whereas high-precision prediction models in personalised prognostic medicine should operate with high-dimensional spatial imaging features in large samples.
Collapse
Affiliation(s)
- Christoph Sperber
- Department of Neurology, Inselspital, University Hospital Bern, University of Bern, Bern, Switzerland.
| | - Laura Gallucci
- Department of Neurology, Inselspital, University Hospital Bern, University of Bern, Bern, Switzerland
| | - Daniel Mirman
- Department of Psychology, University of Edinburgh, Edinburgh, United Kingdom
| | - Marcel Arnold
- Department of Neurology, Inselspital, University Hospital Bern, University of Bern, Bern, Switzerland
| | - Roza M Umarova
- Department of Neurology, Inselspital, University Hospital Bern, University of Bern, Bern, Switzerland
| |
Collapse
|
3
|
Schevenels K, Michiels L, Lemmens R, De Smedt B, Zink I, Vandermosten M. The role of the hippocampus in statistical learning and language recovery in persons with post stroke aphasia. Neuroimage Clin 2022; 36:103243. [PMID: 36306718 PMCID: PMC9668653 DOI: 10.1016/j.nicl.2022.103243] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/29/2022] [Revised: 10/17/2022] [Accepted: 10/19/2022] [Indexed: 11/11/2022]
Abstract
Although several studies have aimed for accurate predictions of language recovery in post stroke aphasia, individual language outcomes remain hard to predict. Large-scale prediction models are built using data from patients mainly in the chronic phase after stroke, although it is clinically more relevant to consider data from the acute phase. Previous research has mainly focused on deficits, i.e., behavioral deficits or specific brain damage, rather than compensatory mechanisms, i.e., intact cognitive skills or undamaged brain regions. One such unexplored brain region that might support language (re)learning in aphasia is the hippocampus, a region that has commonly been associated with an individual's learning potential, including statistical learning. This refers to a set of mechanisms upon which we rely heavily in daily life to learn a range of regularities across cognitive domains. Against this background, thirty-three patients with aphasia (22 males and 11 females, M = 69.76 years, SD = 10.57 years) were followed for 1 year in the acute (1-2 weeks), subacute (3-6 months) and chronic phase (9-12 months) post stroke. We evaluated the unique predictive value of early structural hippocampal measures for short-term and long-term language outcomes (measured by the ANELT). In addition, we investigated whether statistical learning abilities were intact in patients with aphasia using three different tasks: an auditory-linguistic and visual task based on the computation of transitional probabilities and a visuomotor serial reaction time task. Finally, we examined the association of individuals' statistical learning potential with acute measures of hippocampal gray and white matter. Using Bayesian statistics, we found moderate evidence for the contribution of left hippocampal gray matter in the acute phase to the prediction of long-term language outcomes, over and above information on the lesion and the initial language deficit (measured by the ScreeLing). Non-linguistic statistical learning in patients with aphasia, measured in the subacute phase, was intact at the group level compared to 23 healthy older controls (8 males and 15 females, M = 74.09 years, SD = 6.76 years). Visuomotor statistical learning correlated with acute hippocampal gray and white matter. These findings reveal that particularly left hippocampal gray matter in the acute phase is a potential marker of language recovery after stroke, possibly through its statistical learning ability.
Collapse
Affiliation(s)
- Klara Schevenels
- Research Group Experimental Oto-Rhino-Laryngology, Department of Neurosciences, KU Leuven, Onderwijs en Navorsing 2 (O&N2), Herestraat 49 box 721, Leuven 3000, Belgium; Leuven Brain Institute, KU Leuven, Onderwijs en Navorsing 5 (O&N 5), Herestraat 49 box 1020, Leuven 3000, Belgium.
| | - Laura Michiels
- Department of Neurology, University Hospitals Leuven, Herestraat 49, Leuven 3000, Belgium; Research Group Experimental Neurology, Department of Neurosciences, KU Leuven, Herestraat 49 box 7003, Leuven 3000, Belgium; Laboratory of Neurobiology, VIB Center for Brain & Disease Research, Onderwijs en Navorsing 5 (O&N 5), Herestraat 49 box 602, Leuven 3000, Belgium; Leuven Brain Institute, KU Leuven, Onderwijs en Navorsing 5 (O&N 5), Herestraat 49 box 1020, Leuven 3000, Belgium.
| | - Robin Lemmens
- Department of Neurology, University Hospitals Leuven, Herestraat 49, Leuven 3000, Belgium; Research Group Experimental Neurology, Department of Neurosciences, KU Leuven, Herestraat 49 box 7003, Leuven 3000, Belgium; Laboratory of Neurobiology, VIB Center for Brain & Disease Research, Onderwijs en Navorsing 5 (O&N 5), Herestraat 49 box 602, Leuven 3000, Belgium; Leuven Brain Institute, KU Leuven, Onderwijs en Navorsing 5 (O&N 5), Herestraat 49 box 1020, Leuven 3000, Belgium.
| | - Bert De Smedt
- Parenting and Special Education Research Unit, Faculty of Psychology and Educational Sciences, KU leuven, Leopold Vanderkelenstraat 32 box 3765, Leuven 3000, Belgium; Leuven Brain Institute, KU Leuven, Onderwijs en Navorsing 5 (O&N 5), Herestraat 49 box 1020, Leuven 3000, Belgium.
| | - Inge Zink
- Research Group Experimental Oto-Rhino-Laryngology, Department of Neurosciences, KU Leuven, Onderwijs en Navorsing 2 (O&N2), Herestraat 49 box 721, Leuven 3000, Belgium; Leuven Brain Institute, KU Leuven, Onderwijs en Navorsing 5 (O&N 5), Herestraat 49 box 1020, Leuven 3000, Belgium.
| | - Maaike Vandermosten
- Research Group Experimental Oto-Rhino-Laryngology, Department of Neurosciences, KU Leuven, Onderwijs en Navorsing 2 (O&N2), Herestraat 49 box 721, Leuven 3000, Belgium; Leuven Brain Institute, KU Leuven, Onderwijs en Navorsing 5 (O&N 5), Herestraat 49 box 1020, Leuven 3000, Belgium.
| |
Collapse
|
4
|
Sperber C. The strange role of brain lesion size in cognitive neuropsychology. Cortex 2021; 146:216-226. [PMID: 34902680 DOI: 10.1016/j.cortex.2021.11.005] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/27/2021] [Revised: 07/11/2021] [Accepted: 11/03/2021] [Indexed: 11/18/2022]
Abstract
The size of brain lesions is a variable that is frequently considered in cognitive neuropsychology. In particular, lesion-deficit inference studies often control for lesion size, and the association of lesion size with post-stroke cognitive deficits and its predictive value are studied. In the present article, the role of lesion size in cognitive deficits and its computational or design-wise consideration is discussed and questioned. First, I argue that the commonly discussed role or effect of lesion size in cognitive deficits eludes us. A generally valid understanding of the causal relation of lesion size, lesion location, and cognitive deficits is unachievable. Second, founded on the theory of causal inference, I argue that lesion size control is no generally appropriate covariate control. Instead, it is identified as a procedure with only situational benefits, which is supported by empirical data. This theoretical background is used to suggest possible research practices in lesion-deficit inference, post-stroke outcome prediction, and behavioural studies. Last, control for lesion size is put into a bigger historical context - it is identified to relate to a long-known association problem in neuropsychology, which was previously discussed from the perspectives of a mislocalisation in lesion-deficit mapping and the symptom complex approach.
Collapse
Affiliation(s)
- Christoph Sperber
- Centre of Neurology, Hertie-Institute for Clinical Brain Research, University of Tübingen, Tübingen, Germany.
| |
Collapse
|
5
|
Hope TMH, Nardo D, Holland R, Ondobaka S, Akkad H, Price CJ, Leff AP, Crinion J. Lesion site and therapy time predict responses to a therapy for anomia after stroke: a prognostic model development study. Sci Rep 2021; 11:18572. [PMID: 34535718 PMCID: PMC8448867 DOI: 10.1038/s41598-021-97916-x] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/19/2021] [Accepted: 07/14/2021] [Indexed: 11/10/2022] Open
Abstract
Stroke is a leading cause of disability, and language impairments (aphasia) after stroke are both common and particularly feared. Most stroke survivors with aphasia exhibit anomia (difficulties with naming common objects), but while many therapeutic interventions for anomia have been proposed, treatment effects are typically much larger in some patients than others. Here, we asked whether that variation might be more systematic, and even predictable, than previously thought. 18 patients, each at least 6 months after left hemisphere stroke, engaged in a computerised treatment for their anomia over a 6-week period. Using only: (a) the patients' initial accuracy when naming (to-be) trained items; (b) the hours of therapy that they devoted to the therapy; and (c) whole-brain lesion location data, derived from structural MRI; we developed Partial Least Squares regression models to predict the patients' improvements on treated items, and tested them in cross-validation. Somewhat surprisingly, the best model included only lesion location data and the hours of therapy undertaken. In cross-validation, this model significantly out-performed the null model, in which the prediction for each patient was simply the mean treatment effect of the group. This model also made promisingly accurate predictions in absolute terms: the correlation between empirical and predicted treatment response was 0.62 (95% CI 0.27, 0.95). Our results indicate that individuals' variation in response to anomia treatment are, at least somewhat, systematic and predictable, from the interaction between where and how much lesion damage they have suffered, and the time they devoted to the therapy.
Collapse
Affiliation(s)
- Thomas M H Hope
- Institute of Cognitive Neuroscience, University College London, 17-19 Queen Square, London, WC1N 3AR, UK.
- Wellcome Centre for Human Neuroimaging, University College London, London, UK.
| | - Davide Nardo
- Institute of Cognitive Neuroscience, University College London, 17-19 Queen Square, London, WC1N 3AR, UK
- MRC Cognition and Brain Sciences Unit, Cambridge University, London, UK
| | - Rachel Holland
- Division of Language and Communication Science, City University of London, London, UK
| | - Sasha Ondobaka
- Institute of Cognitive Neuroscience, University College London, 17-19 Queen Square, London, WC1N 3AR, UK
| | - Haya Akkad
- Institute of Cognitive Neuroscience, University College London, 17-19 Queen Square, London, WC1N 3AR, UK
| | - Cathy J Price
- Wellcome Centre for Human Neuroimaging, University College London, London, UK
| | - Alexander P Leff
- Institute of Cognitive Neuroscience, University College London, 17-19 Queen Square, London, WC1N 3AR, UK
- UCL Queen Square Institute of Neurology, London, UK
| | - Jenny Crinion
- Institute of Cognitive Neuroscience, University College London, 17-19 Queen Square, London, WC1N 3AR, UK
| |
Collapse
|
6
|
Kasties V, Karnath H, Sperber C. Strategies for feature extraction from structural brain imaging in lesion-deficit modelling. Hum Brain Mapp 2021; 42:5409-5422. [PMID: 34415093 PMCID: PMC8519857 DOI: 10.1002/hbm.25629] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/28/2021] [Revised: 06/30/2021] [Accepted: 08/07/2021] [Indexed: 12/25/2022] Open
Abstract
High‐dimensional modelling of post‐stroke deficits from structural brain imaging is highly relevant to basic cognitive neuroscience and bears the potential to be translationally used to guide individual rehabilitation measures. One strategy to optimise model performance is well‐informed feature selection and representation. However, different feature representation strategies were so far used, and it is not known what strategy is best for modelling purposes. The present study compared the three common main strategies: voxel‐wise representation, lesion‐anatomical componential feature reduction and region‐wise atlas‐based feature representation. We used multivariate, machine‐learning‐based lesion‐deficit models to predict post‐stroke deficits based on structural lesion data. Support vector regression was tuned by nested cross‐validation techniques and tested on held‐out validation data to estimate model performance. While we consistently found the numerically best models for lower‐dimensional, featurised data and almost always for principal components extracted from lesion maps, our results indicate only minor, non‐significant differences between different feature representation styles. Hence, our findings demonstrate the general suitability of all three commonly applied feature representations in lesion‐deficit modelling. Likewise, model performance between qualitatively different popular brain atlases was not significantly different. Our findings also highlight potential minor benefits in individual fine‐tuning of feature representations and the challenge posed by the high, multifaceted complexity of lesion data, where lesion‐anatomical and functional criteria might suggest opposing solutions to feature reduction.
Collapse
Affiliation(s)
- Vanessa Kasties
- Centre of Neurology, Division of NeuropsychologyHertie‐Institute for Clinical Brain Research, University of TübingenTübingenGermany
| | - Hans‐Otto Karnath
- Centre of Neurology, Division of NeuropsychologyHertie‐Institute for Clinical Brain Research, University of TübingenTübingenGermany
| | - Christoph Sperber
- Centre of Neurology, Division of NeuropsychologyHertie‐Institute for Clinical Brain Research, University of TübingenTübingenGermany
| |
Collapse
|
7
|
Rethinking causality and data complexity in brain lesion-behaviour inference and its implications for lesion-behaviour modelling. Cortex 2020; 126:49-62. [DOI: 10.1016/j.cortex.2020.01.004] [Citation(s) in RCA: 33] [Impact Index Per Article: 8.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/10/2019] [Revised: 11/30/2019] [Accepted: 01/10/2020] [Indexed: 01/04/2023]
|
8
|
Sperber C, Karnath HO. Inhibition between human brain areas or methodological artefact? Brain 2020; 143:e38. [PMID: 32413900 DOI: 10.1093/brain/awaa092] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/14/2022] Open
Affiliation(s)
- Christoph Sperber
- Center of Neurology, Division of Neuropsychology, Hertie-Institute for Clinical Brain Research, University of Tübingen, Tübingen, Germany
| | - Hans-Otto Karnath
- Center of Neurology, Division of Neuropsychology, Hertie-Institute for Clinical Brain Research, University of Tübingen, Tübingen, Germany
| |
Collapse
|