Prediction Tools for Stroke Rehabilitation

Stinear, Cathy M.; Smith, Marie-Claire; Byblow, Winston D.

doi:10.1161/strokeaha.119.025696

Cited by 129 publications

(120 citation statements)

References 76 publications

Supporting

Mentioning

113

Contrasting

Unclassified

Order By: Relevance

“…The prediction of outcome is critically important when planning appropriate rehabilitation for stroke patients. [1][2][3] Magnetic resonance imaging, transcranial magnetic stimulation, magnetoencephalography, and other modalities have been used for rehabilitation planning. 4) A recent systematic review suggested that magnetic resonance diffusion tensor imaging (DTI) is potentially one of the most useful techniques to predict poststroke motor recovery.…”

Section: Introductionmentioning

confidence: 99%

Outcome in Stroke Patients Is Associated with Age and Fractional Anisotropy in the Cerebral Peduncles: A Multivariate Regression Study

Koyama

Uchiyama

Domen

2020

PRM

View full text Add to dashboard Cite

Diffusion tensor fractional anisotropy (FA) in the corticospinal tracts has been used to assess the long-term outcome in stroke patients. Patient age and the type of stroke may also affect outcomes. In this study, we investigated the associations of age, type of stroke, and FA in the ipsilesional and contralesional cerebral peduncles with stroke outcomes. Methods: This study involved 80 patients with stroke (40 hemorrhagic, 40 ischemic) that we had investigated previously. Diffusion tensor FA images were obtained between 14 and 21 days post-stroke. FA values in the ipsilesional and contralesional cerebral peduncles were extracted and their ratio (rFA) was calculated. Outcome was assessed using the Brunnstrom stage, the motor component of the Functional Independence Measure (FIM-motor) at discharge, and the length of stay until discharge from rehabilitation. Using forward stepwise multivariate regression, we assessed the associations of rFA, contralesional FA, age, and type of stroke with outcome measures. Results: rFA and contralesional FA were included in the final model for the Brunnstrom stage in the upper limbs. There was a strong association between hemorrhagic stroke and poorer lower extremity function. rFA, contralesional FA, and age were included in the final model for FIM-motor and length of stay. The effect of rFA on all outcome measures was stronger than that of contralesional FA. The effect of age on FIM-motor was as strong as that of rFA. Conclusions: Neural damage in the corticospinal tracts (indicated by rFA) had the strongest effect on outcome measures, whereas the level of disability (measured by FIM-motor) was associated with a broader range of factors, including age.

show abstract

Section: Introductionmentioning

confidence: 99%

Outcome in Stroke Patients Is Associated with Age and Fractional Anisotropy in the Cerebral Peduncles: A Multivariate Regression Study

Koyama

Uchiyama

Domen

2020

PRM

View full text Add to dashboard Cite

show abstract

“…There is very compelling evidence that physiological variables explain individual differences in recovery, 19 but this is a very different question from claiming that recovery is "proportional". Thus, rather than concluding that individuals with lower cortico-spinal tract integrity are more likely to be "non-fitters", we think a more appropriate conclusion is that individuals with lower cortico-spinal tract integrity are likely to show minimal recovery.…”

Section: Discussionmentioning

confidence: 99%

“…13,14 Indeed, a number of researchers have started making strides in this direction, using longitudinal methods to explore trajectories of stroke recovery. 15,16 Understanding which factors explain, or better yet predict [17][18][19] stroke trajectories is a very important area of research. These research questions are, however, quite orthogonal to the proportional recovery rule.…”

Section: Figure 1 Data Adapted Frommentioning

confidence: 99%

Statistical considerations for drawing conclusions about recovery

Lohse

Hawe²,

Dukelow³

et al. 2019

Preprint

View full text Add to dashboard Cite

Background. Numerous studies have found large statistical relationships between the amount of recovery and initial impairments in people with stroke. When change scores are regressed onto initial impairments, the resulting slope is approximately ≈ 0.7 for a variety of outcomes. These findings have led to the 70% "proportional recovery rule" and the argument that proportional recovery represents a biological phenomenon. Previous studies of proportional recovery are confounded by statistical limitations that come from regressing change scores onto initial impairments in bounded scales.Objective. Our goal is to show that data claimed as evidence for proportional recovery are generally consistent with random patterns of recovery, once statistical limitations are taken into account.Methods. Using a pooled dataset of N = 373 Fugl-Meyer Assessment (FMA) upper extremity scores extracted from published literature, we ran simulations to illustrate three main arguments:(1) Mathematical coupling renders the traditional null-hypothesis significance test irrelevant in proportional recovery studies; (2) Proportional recovery is one of many alternative hypotheses;(3) Current evidence claimed in favor of proportional recovery is consistent with uniform random recovery. Results.Our simulations show that if all data were included (no exclusion of "non-fitters") regressing change scores onto initial impairments in a bounded scale would lead to a slope of ≈ 0.5. Similarly, cluster analysis will spuriously identify groups of fitters and non-fitters, leading to a slope for the fitters of ≈ 0.7, when the underlying recovery is random. Conclusions.These results cast doubt on the validity of "proportional recovery" as a population level-statistic and a biological phenomenon.

show abstract

“…One of the active ingredients to ensure successful neurorehabilitation is a careful adaptation of the therapy regimen to the characteristics and deficits of an individual (i.e., personalized therapy) [5,8,6]. For this purpose, predicting whether a patient is susceptible to positively respond to a specific neurorehabilitation intervention is of primary interest to researchers and clinicians, as it can help to set more realistic therapy goals, optimize therapy time, and reduce costs related to unsuccessful interventions [9,10,11,12]. In addition, it promises to define homogenous and responsive groups for large-scale and resource-intensive clinical trials.…”

Section: Introductionmentioning

confidence: 99%

“…Predicting therapy outcomes at an individual level promises to provide clinically-relevant information [9,10,11,12], but requires appropriate modeling and evaluation strategies that go beyond the commonly applied linear correlation analyses. More advanced approaches are necessary to account for potentially non-linear relationships and the high behavioral inter-subject variability commonly observed in neurological disorders.…”

Section: Introductionmentioning

confidence: 99%

Personalized prediction of rehabilitation outcomes in multiple sclerosis: a proof-of-concept using clinical data, digital health metrics, and machine learning

Kanzler

Lamers

Feys

et al. 2020

Preprint

View full text Add to dashboard Cite

Background.A personalized prediction of upper limb neurorehabilitation outcomes in persons with multiple sclerosis (pwMS) promises to optimize the allocation of therapy and to stratify individuals for resource-demanding clinical trials. Previous research identified predictors on a population level through linear models and clinical data, including conventional assessments describing sensorimotor impairments. The objective of this work was to explore the feasibility of providing an individualized and more accurate prediction of rehabilitation outcomes in pwMS by leveraging non-linear machine learning models, clinical data, and digital health metrics characterizing sensorimotor impairments. Methods.Clinical data and digital health metrics were recorded from eleven pwMS undergoing neurorehabilitation. Machine learning models were trained on data recorded pre-intervention. The dependent variables indicated whether a considerable improvement on the activity level was observed across the intervention or not (binary classification), as defined by the Action Research Arm Test (ARAT), Box and Block Test (BBT), or Nine Hole Peg Test (NHPT). Results.In a cross-validation, considerable improvements in ARAT or BBT could be accurately predicted (94% balanced accuracy) by only relying on patient master data. Considerable improvements in NHPT could be accurately predicted (89% balanced accuracy), but required knowledge about sensorimotor impairments. Assessing these with digital health metrics instead of conventional scales allowed increasing the balanced accuracy by +17% . Non-linear machine-learning models improved the predictive accuracy for the NHPT by +25% compared to linear models. Conclusions.This work demonstrates the feasibility of a personalized prediction of upper limb neurorehabilitation outcomes in pwMS using multi-modal data collected before neurorehabilitation and machine learning. Information from digital health metrics about sensorimotor impairment was necessary to predict changes in dexterous hand control, thereby underlining their potential to provide a more sensitive and fine-grained assessment than conventional scales. Non-linear models outperformed ones, suggesting that the commonly assumed linearity of neurorehabilitation is oversimplified.clinicaltrials.gov registration number: NCT02688231 2

show abstract

Prediction Tools for Stroke Rehabilitation

Cited by 129 publications

References 76 publications

Outcome in Stroke Patients Is Associated with Age and Fractional Anisotropy in the Cerebral Peduncles: A Multivariate Regression Study

Outcome in Stroke Patients Is Associated with Age and Fractional Anisotropy in the Cerebral Peduncles: A Multivariate Regression Study

Statistical considerations for drawing conclusions about recovery

Personalized prediction of rehabilitation outcomes in multiple sclerosis: a proof-of-concept using clinical data, digital health metrics, and machine learning

Contact Info

Product

Resources

About