Predicting Cognitive Recovery of Stroke Patients from the Structural MRI Connectome Using a Naïve Bayesian Tree Classifier

Rosalia Dacosta-Aguayo, Christian Stephan-Otto, Tibor Auer, Ic Clemente, Antoni Davalos, Nuria Bargallo, Maria Mataro, Manousos A. Klados

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Successful post-stroke prognosis and recovery strategies are heavily dependent on our understanding about how the damage to one specific region may impact to other remote regions, as well as the various functional networks involved in efficient cognitive function. In this study, 27 consecutive ischemic stroke patients were recruited. Stroke patients underwent two complete neuropsychological assessments between the first 72 hours after stroke arrival and three months later. They were further evaluated with a MRI protocol at 3 months. Patients were splitted into two groups according to their level of cognitive recovery. A data mining technique was then applied to the probabilistic tractography data in order to determine whether the structural connectivity features can efficiently classify good from poor recovery. We found that the connectivity probability between the left Superior Parietal Gyrus and the left Angular Gyrus can describe the cognitive classification (good versus poor recovery) after stroke. Both regions are involved in higher cognitive functioning and their dysfunction has been related to mild cognitive impairment and dementia. Our findings suggest that cognitive prognosis, in stroke patients, mainly depends on the connection of these two regions. An accurate model for the early prediction of stroke recovery as the one presented herein is fundamental to develop early personalized rehabilitation strategies.

LanguageEnglish
Title of host publicationProceedings - 2017 IEEE 30th International Symposium on Computer-Based Medical Systems, CBMS 2017
PublisherIEEE
Pages413-418
Number of pages6
Volume2017-June
ISBN (Electronic)9781538617106
DOIs
Publication statusPublished - 10 Nov 2017
Event30th IEEE International Symposium on Computer-Based Medical Systems, CBMS 2017 - Thessaloniki, Greece
Duration: 22 Jun 201724 Jun 2017

Publication series

NameProceedings IEEE International Symposium on Computer-Based Medical Systems
PublisherIEEE
ISSN (Print)2372-9198

Conference

Conference30th IEEE International Symposium on Computer-Based Medical Systems, CBMS 2017
CountryGreece
CityThessaloniki
Period22/06/1724/06/17

Fingerprint

Connectome
Magnetic resonance imaging
Classifiers
Stroke
Recovery
Patient rehabilitation
Data mining
Parietal Lobe
Data Mining
Cognition
Dementia
Rehabilitation

Keywords

  • cognitive recovery
  • Naïve Bayesian Tree
  • Stroke
  • structural connectome

Cite this

Dacosta-Aguayo, R., Stephan-Otto, C., Auer, T., Clemente, I., Davalos, A., Bargallo, N., ... Klados, M. A. (2017). Predicting Cognitive Recovery of Stroke Patients from the Structural MRI Connectome Using a Naïve Bayesian Tree Classifier. In Proceedings - 2017 IEEE 30th International Symposium on Computer-Based Medical Systems, CBMS 2017 (Vol. 2017-June, pp. 413-418). [8104229] (Proceedings IEEE International Symposium on Computer-Based Medical Systems). IEEE. https://doi.org/10.1109/CBMS.2017.106
Dacosta-Aguayo, Rosalia ; Stephan-Otto, Christian ; Auer, Tibor ; Clemente, Ic ; Davalos, Antoni ; Bargallo, Nuria ; Mataro, Maria ; Klados, Manousos A. / Predicting Cognitive Recovery of Stroke Patients from the Structural MRI Connectome Using a Naïve Bayesian Tree Classifier. Proceedings - 2017 IEEE 30th International Symposium on Computer-Based Medical Systems, CBMS 2017. Vol. 2017-June IEEE, 2017. pp. 413-418 (Proceedings IEEE International Symposium on Computer-Based Medical Systems).
@inproceedings{efc31a58559044d59a459b9b036211db,
title = "Predicting Cognitive Recovery of Stroke Patients from the Structural MRI Connectome Using a Na{\"i}ve Bayesian Tree Classifier",
abstract = "Successful post-stroke prognosis and recovery strategies are heavily dependent on our understanding about how the damage to one specific region may impact to other remote regions, as well as the various functional networks involved in efficient cognitive function. In this study, 27 consecutive ischemic stroke patients were recruited. Stroke patients underwent two complete neuropsychological assessments between the first 72 hours after stroke arrival and three months later. They were further evaluated with a MRI protocol at 3 months. Patients were splitted into two groups according to their level of cognitive recovery. A data mining technique was then applied to the probabilistic tractography data in order to determine whether the structural connectivity features can efficiently classify good from poor recovery. We found that the connectivity probability between the left Superior Parietal Gyrus and the left Angular Gyrus can describe the cognitive classification (good versus poor recovery) after stroke. Both regions are involved in higher cognitive functioning and their dysfunction has been related to mild cognitive impairment and dementia. Our findings suggest that cognitive prognosis, in stroke patients, mainly depends on the connection of these two regions. An accurate model for the early prediction of stroke recovery as the one presented herein is fundamental to develop early personalized rehabilitation strategies.",
keywords = "cognitive recovery, Na{\"i}ve Bayesian Tree, Stroke, structural connectome",
author = "Rosalia Dacosta-Aguayo and Christian Stephan-Otto and Tibor Auer and Ic Clemente and Antoni Davalos and Nuria Bargallo and Maria Mataro and Klados, {Manousos A.}",
year = "2017",
month = "11",
day = "10",
doi = "10.1109/CBMS.2017.106",
language = "English",
volume = "2017-June",
series = "Proceedings IEEE International Symposium on Computer-Based Medical Systems",
publisher = "IEEE",
pages = "413--418",
booktitle = "Proceedings - 2017 IEEE 30th International Symposium on Computer-Based Medical Systems, CBMS 2017",
address = "United States",

}

Dacosta-Aguayo, R, Stephan-Otto, C, Auer, T, Clemente, I, Davalos, A, Bargallo, N, Mataro, M & Klados, MA 2017, Predicting Cognitive Recovery of Stroke Patients from the Structural MRI Connectome Using a Naïve Bayesian Tree Classifier. in Proceedings - 2017 IEEE 30th International Symposium on Computer-Based Medical Systems, CBMS 2017. vol. 2017-June, 8104229, Proceedings IEEE International Symposium on Computer-Based Medical Systems, IEEE, pp. 413-418, 30th IEEE International Symposium on Computer-Based Medical Systems, CBMS 2017, Thessaloniki, Greece, 22/06/17. https://doi.org/10.1109/CBMS.2017.106

Predicting Cognitive Recovery of Stroke Patients from the Structural MRI Connectome Using a Naïve Bayesian Tree Classifier. / Dacosta-Aguayo, Rosalia; Stephan-Otto, Christian; Auer, Tibor; Clemente, Ic; Davalos, Antoni; Bargallo, Nuria; Mataro, Maria; Klados, Manousos A.

Proceedings - 2017 IEEE 30th International Symposium on Computer-Based Medical Systems, CBMS 2017. Vol. 2017-June IEEE, 2017. p. 413-418 8104229 (Proceedings IEEE International Symposium on Computer-Based Medical Systems).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Predicting Cognitive Recovery of Stroke Patients from the Structural MRI Connectome Using a Naïve Bayesian Tree Classifier

AU - Dacosta-Aguayo, Rosalia

AU - Stephan-Otto, Christian

AU - Auer, Tibor

AU - Clemente, Ic

AU - Davalos, Antoni

AU - Bargallo, Nuria

AU - Mataro, Maria

AU - Klados, Manousos A.

PY - 2017/11/10

Y1 - 2017/11/10

N2 - Successful post-stroke prognosis and recovery strategies are heavily dependent on our understanding about how the damage to one specific region may impact to other remote regions, as well as the various functional networks involved in efficient cognitive function. In this study, 27 consecutive ischemic stroke patients were recruited. Stroke patients underwent two complete neuropsychological assessments between the first 72 hours after stroke arrival and three months later. They were further evaluated with a MRI protocol at 3 months. Patients were splitted into two groups according to their level of cognitive recovery. A data mining technique was then applied to the probabilistic tractography data in order to determine whether the structural connectivity features can efficiently classify good from poor recovery. We found that the connectivity probability between the left Superior Parietal Gyrus and the left Angular Gyrus can describe the cognitive classification (good versus poor recovery) after stroke. Both regions are involved in higher cognitive functioning and their dysfunction has been related to mild cognitive impairment and dementia. Our findings suggest that cognitive prognosis, in stroke patients, mainly depends on the connection of these two regions. An accurate model for the early prediction of stroke recovery as the one presented herein is fundamental to develop early personalized rehabilitation strategies.

AB - Successful post-stroke prognosis and recovery strategies are heavily dependent on our understanding about how the damage to one specific region may impact to other remote regions, as well as the various functional networks involved in efficient cognitive function. In this study, 27 consecutive ischemic stroke patients were recruited. Stroke patients underwent two complete neuropsychological assessments between the first 72 hours after stroke arrival and three months later. They were further evaluated with a MRI protocol at 3 months. Patients were splitted into two groups according to their level of cognitive recovery. A data mining technique was then applied to the probabilistic tractography data in order to determine whether the structural connectivity features can efficiently classify good from poor recovery. We found that the connectivity probability between the left Superior Parietal Gyrus and the left Angular Gyrus can describe the cognitive classification (good versus poor recovery) after stroke. Both regions are involved in higher cognitive functioning and their dysfunction has been related to mild cognitive impairment and dementia. Our findings suggest that cognitive prognosis, in stroke patients, mainly depends on the connection of these two regions. An accurate model for the early prediction of stroke recovery as the one presented herein is fundamental to develop early personalized rehabilitation strategies.

KW - cognitive recovery

KW - Naïve Bayesian Tree

KW - Stroke

KW - structural connectome

UR - http://www.scopus.com/inward/record.url?scp=85040375770&partnerID=8YFLogxK

U2 - 10.1109/CBMS.2017.106

DO - 10.1109/CBMS.2017.106

M3 - Conference contribution

VL - 2017-June

T3 - Proceedings IEEE International Symposium on Computer-Based Medical Systems

SP - 413

EP - 418

BT - Proceedings - 2017 IEEE 30th International Symposium on Computer-Based Medical Systems, CBMS 2017

PB - IEEE

ER -

Dacosta-Aguayo R, Stephan-Otto C, Auer T, Clemente I, Davalos A, Bargallo N et al. Predicting Cognitive Recovery of Stroke Patients from the Structural MRI Connectome Using a Naïve Bayesian Tree Classifier. In Proceedings - 2017 IEEE 30th International Symposium on Computer-Based Medical Systems, CBMS 2017. Vol. 2017-June. IEEE. 2017. p. 413-418. 8104229. (Proceedings IEEE International Symposium on Computer-Based Medical Systems). https://doi.org/10.1109/CBMS.2017.106