Machine Learning Approaches to Predict Functional Upper Extremity Use in Individuals with Stroke

Almubark, Ibrahim; Chang, Lin‐Ching; Holley, Rahsaan J.; Black, I.; Ji, Chen; Chan, Evan; Dromerick, Alexander W.; Lum, Peter S.

doi:10.1109/bigdata.2018.8622054

Cited by 5 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… 42 , 43 Recent work using supervised machine learning algorithms, have shown promising results in detecting arm use. 27 , 31 – 33 Although the performance of these machine learning approaches in patients are not as good as those in healthy subjects, they still perform better than activity counting or the gross movement score algorithms. Thus, these approaches are likely to gain traction in the coming years with an increasing focus on patient-specific models.…”

Section: Discussionmentioning

confidence: 99%

“… 28 – 30 Some accelerometry based data-driven approaches using machine learning algorithms to classify functional or non-functional movements yield higher classification accuracy but are restricted to specific tasks used in the laboratory setting. 31 – 33 Other methods to accurately measure arm use require multiple sensors which can lower patient compliance, or optical tracking which are impractical for the natural settings. Hence, there is a need for wearable devices with high sensitivity and specificity to detect functional and non-functional movements, along with good generalisability to estimate arm use in natural settings using minimum number of sensors.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Quantification of the relative arm use in patients with hemiparesis using inertial measurement units

David

ReethaJanetSureka

Gayathri

et al. 2021

Journal of Rehabilitation and Assistive Technologies Engineerin

View full text Add to dashboard Cite

Introduction Accelerometry-based activity counting for measuring arm use is prone to overestimation due to non-functional movements. In this paper, we used an inertial measurement unit (IMU)-based gross movement (GM) score to quantify arm use. Methods In this two-part study, we first characterized the GM by comparing it to annotated video recordings of 5 hemiparetic patients and 10 control subjects performing a set of activities. In the second part, we tracked the arm use of 5 patients and 5 controls using two wrist-worn IMUs for 7 and 3 days, respectively. The IMU data was used to develop quantitative measures (total and relative arm use) and a visualization method for arm use. Results From the characterization study, we found that GM detects functional activities with 50–60% accuracy and eliminates non-functional activities with >90% accuracy. Continuous monitoring of arm use showed that the arm use was biased towards the dominant limb and less paretic limb for controls and patients, respectively. Conclusions The gross movement score has good specificity but low sensitivity in identifying functional activity. The at-home study showed that it is feasible to use two IMU-watches to monitor relative arm use and provided design considerations for improving the assessment method. Clinical trial registry number: CTRI/2018/09/015648

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Quantification of the relative arm use in patients with hemiparesis using inertial measurement units

David

ReethaJanetSureka

Gayathri

et al. 2021

Journal of Rehabilitation and Assistive Technologies Engineerin

View full text Add to dashboard Cite

show abstract

“…For what concerns ML applications in post-stroke rehabilitation, research is still in a development phase, with extensively large numbers of studies evaluating longitudinal associations among features and discharge or longterm outcomes [8], and more limited studies dedicated to the development and validation of predictive models [9,10,11]. However, cross-validated ML models for prognosis of functional level on stroke cohorts are indeed generating a growing interest [12].…”

Section: Introductionmentioning

confidence: 99%

Cross-validation of predictive models for functional recovery after post-stroke rehabilitation

Campagnini

Liuzzi

Mannini

et al. 2022

J NeuroEngineering Rehabil

View full text Add to dashboard Cite

Background Rehabilitation treatments and services are essential for the recovery of post-stroke patients’ functions; however, the increasing number of available therapies and the lack of consensus among outcome measures compromises the possibility to determine an appropriate level of evidence. Machine learning techniques for prognostic applications offer accurate and interpretable predictions, supporting the clinical decision for personalised treatment. The aim of this study is to develop and cross-validate predictive models for the functional prognosis of patients, highlighting the contributions of each predictor. Methods A dataset of 278 post-stroke patients was used for the prediction of the class transition, obtained from the modified Barthel Index. Four classification algorithms were cross-validated and compared. On the best performing model on the validation set, an analysis of predictors contribution was conducted. Results The Random Forest obtained the best overall results on the accuracy (76.2%), balanced accuracy (74.3%), sensitivity (0.80), and specificity (0.68). The combination of all the classification results on the test set, by weighted voting, reached 80.2% accuracy. The predictors analysis applied on the Support Vector Machine, showed that a good trunk control and communication level, and the absence of bedsores retain the major contribution in the prediction of a good functional outcome. Conclusions Despite a more comprehensive assessment of the patients is needed, this work paves the way for the implementation of solutions for clinical decision support in the rehabilitation of post-stroke patients. Indeed, offering good prognostic accuracies for class transition and patient-wise view of the predictors contributions, it might help in a personalised optimisation of the patients’ rehabilitation path.

show abstract

“…Quantifying arm-use by without distinguishing between functional versus non-functional arm movements while assumptions on the mobility status of patients can lead to overestimation of arm-use [19][20][21] . Some data-driven approaches using supervised or unsupervised learning algorithms to classify functional or non-functional movements through accelerometry yield high classification accuracy, but are restricted to specific tasks that were used in the laboratory setting [22][23][24] . A simple, elegant and general algorithm to detect functional arm-use of an upper-limb was proposed by Leuenberger et al using a single IMU on the forearm 25 .…”

Section: Introductionmentioning

confidence: 99%

Quantification of the relative arm-use in patients with hemiparesis using inertial measurement units

David

ReethaJanetSureka

Gayathri

et al. 2020

Preprint

View full text Add to dashboard Cite

Background: The most popular method for measuring upper limb activity is based on accelerometry. However, this method is prone to overestimation and is agnostic to the functional utility of a movement. In this study, we used an inertial measurement unit(IMU)-based gross movement score to quantify arm-use in hemiparetic patients at home. Objectives: (i) Validate the gross movement score detected by wrist-worn IMUs against functional movements identified by human assessors. (ii) Test the feasibility of using wrist-worn IMUs to measure arm-use in patients' natural settings. Methods: To validate the gross movement score two independent assessors analyzed and annotated the video recordings of 5 hemiparetic patients and 10 healthy controls performing a set of activities while wearing IMUs. The second study tracked arm-use of 5 hemiparetic patients and 5 healthy controls using two wrist-worn IMUs for 7 days and 3 days, respectively. The IMU data obtained from this study was used to develop quantitative measures (total and relative arm-use (RAU)) and a visualization method for arm-use. Results: The gross movement score detects functional movement with 50-60% accuracy in hemiparetic patients, and is robust to non-functional movements. Healthy controls showed a slight bias towards the dominant arm (RAU: 40.52)°. Patients' RAU varied between 15-47° depending upon their impairment level and pre-stroke hand dominance. Conclusions: The gross movement score performs moderately well in detecting functional movements while rejecting non-functional movements. The patients' total arm-use is less than healthy controls, and their relative arm-use is skewed towards the less-impaired arm.

show abstract

Machine Learning Approaches to Predict Functional Upper Extremity Use in Individuals with Stroke

Cited by 5 publications

References 20 publications

Quantification of the relative arm use in patients with hemiparesis using inertial measurement units

Quantification of the relative arm use in patients with hemiparesis using inertial measurement units

Cross-validation of predictive models for functional recovery after post-stroke rehabilitation

Quantification of the relative arm-use in patients with hemiparesis using inertial measurement units

Contact Info

Product

Resources

About