Stroke clinical outcome prediction
A patient’s re-integration to his/her community after an acute ischemic stroke injury employs neuroplasticity of the brain to recover the clinical deficit resulting from post-stroke injury. Neuroimaging research posits that there is a direct relationship between the structural integrity (location and volume of the lesions) of the brain regions and the severity of clinical deficit. Another factor that dramatically impacts patient recovery is effective and appropriate treatment delivery.
Machine learning tools allow to investigate the relationships between the clinical presentation of stroke, patient medical history and lifestyle, treatment decision, and the long-term functional outcome of stroke patients. In this context, predictive models of clinical outcome can help estimate patient recovery and act as decision-support systems to adapt precision-medicine practices for stroke treatment and rehabilitation. We are currently exploring statistical learning, machine learning, and deep learning approaches to quantify population-specific structure-function relationships of the brain.
Publications
Nils D. Forkert, Tobias Verleger, Bastian Cheng, Götz Thomalla, Claus C. Hilgetag, Jens Fiehler: Multiclass support vector machine-based lesion mapping predicts functional outcome in ischemic stroke patients. PLOS ONE, 10(6), e0129569, 2015. DOI: 10.1371/journal.pone.0129569
Bastian Cheng, Nils D. Forkert, Melissa Zavaglia, Claus C. Hilgetag, Amir Golsari, Susanne Siemonsen, Jens Fiehler, Salva Pedraza, Josep Puig, Tae-Hee Cho, Josef Alawneh, Jean-Claude Baron, Leif Østergaard, Christian Gerloff, Götz Thomalla: Influence of stroke infarct location on functional outcome measured by the modified Rankin Scale. Stroke, 45(6),1695-1702, 2014. DOI: 10.1161/STROKEAHA.114.005152
Melissa Zavaglia, Nils D. Forkert, Bastian Cheng, Christian Gerloff, Götz Thomalla, Claus C. Hilgetag: Mapping causal functional contributions derived from the clinical assessment of brain damage after stroke. NeuroImage: Clinical, 9, 83-94, 2015. DOI: 10.1016/j.nicl.2015.07.009
Deepthi Rajashekar, Matthias Wilms, Kent G. Hecker, Michael D. Hill, Sean Dukelow, Jens Fiehler, and Nils D. Forkert: The Impact of Covariates in Voxel-Wise Lesion-Symptom Mapping. Frontiers of Neurology. 11:854, 2020. DOI: 10.3389/fneur.2020.00854
Deepthi Rajashekar, Pauline Mouches, Jens Fiehler, Bijoy K Menon, Mayank Goyal, Andrew M Demchuk, Michael D Hill, Sean P Dukelow, and Nils D Forkert: Structural integrity of white matter tracts as a predictor of acute ischemic stroke outcome. International Journal of Stroke 1747493020915251, 2020. DOI: 10.1177/1747493020915251
Deepthi Rajashekar, Ravinder Singh, Bijoy Menon, Nils D. Forkert: Eloquence of white matter tracts in acute ischemic stroke patients. International Stroke Conference 2019, Honolulu, USA, 2019.
Team members
-
Deepthi Rajashekar
-
Matthias Wilms
-
Emma Stanley