MétaCan
Menu
← Back to cohort
Record W4223520050 · doi:10.21203/rs.3.rs-1514146/v1

The Use of Machine Learning and Deep Learning Techniques to Assess Proprioceptive Impairments of the Upper Limb after Stroke

2022· preprint· en· W4223520050 on OpenAlexaff
Md. Delowar Hossain, Stephen H. Scott, Tyler Cluff, Sean P. Dukelow

Bibliographic record

VenueResearch Square · 2022
Typepreprint
Languageen
FieldMedicine
TopicStroke Rehabilitation and Recovery
Canadian institutionsQueen's UniversityUniversity of Calgary
Fundersnot available
KeywordsArtificial intelligenceRandom forestMachine learningDeep learningComputer scienceSupport vector machineStroke (engine)Task (project management)Physical medicine and rehabilitationConvolutional neural networkArtificial neural networkLogistic regressionMedicineEngineering

Abstract

fetched live from OpenAlex

Abstract Background Proprioception is commonly impaired after stroke. Robotic tools precisely measure multiple attributes of position sense and create large datasets. Previously, we quantified individual performance based on single measured robotic parameters and an overall task score in an arm position matching (APM) task. In the present manuscript, we used machine learning and deep learning techniques to classify whether individuals had a stroke or not based on their robotic APM task performance. Methods Participants performed an APM task in the Kinarm exoskeleton robot that produced 12 parameters to quantify multiple attributes of position sense. We first quantified impairment in individual parameters and overall task score by determining if participants with stroke fell outside of the 95% cut-off score of control (normative) values. Then, we applied five machine learning algorithms: Logistic Regression, Decision Tree, Random Forest, Random Forest with Hyperparameters Tuning, and Support Vector Machine; and a deep learning algorithm: Deep Neural Network, to classify individual participants as to whether or not they had a stroke based only on robotic assessment results using a 10-fold cross-validation approach. Results We recruited 429 participants with neuroimaging confirmed stroke (< 35 days post-stroke) and 465 healthy controls. Depending on the APM parameter, we observed that 10.9–48.4% of stroke participants were impaired. Using the overall task score, 44% were impaired. The mean performance metrics of machine learning and deep learning models were: accuracy 82.4%, precision 85.6%, recall 76.5%, and F1 score 80.6%. All machine learning and deep learning models displayed similar classification accuracy; however, the Random Forest model had the highest numerical accuracy (83%). Our models showed high sensitivity and specificity (AUC = 0.89) in classifying individual participants based on their performance in the APM task. We also found that variability was the most important feature of classifying performance in the APM task. Conclusion Our machine learning and deep learning models displayed similar classification accuracy. Each model classified more participants correctly as stroke or control than classification of impairment based on individual parameters or overall task score using a cut-off score. Machine learning and deep learning techniques may provide opportunities to better understand proprioceptive impairments after stroke.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.007
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.002
Threshold uncertainty score0.013

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0020.007
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0000.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0010.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.062
GPT teacher head0.402
Teacher spread0.340 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations1
Published2022
Admission routes1
Has abstractyes

Explore more

Same venueResearch Square→Same topicStroke Rehabilitation and Recovery→French-language works237,207→