skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


  • NSF Public Access
  • Search Results
  • A machine learning approach to identifying important features for achieving step thresholds in individuals with chronic stroke
Title: A machine learning approach to identifying important features for achieving step thresholds in individuals with chronic stroke
BackgroundWhile many factors are associated with stepping activity after stroke, there is significant variability across studies. One potential reason to explain this variability is that there are certain characteristics that arenecessaryto achieve greater stepping activity that differ from others thatmayneed to be targeted to improve stepping activity. ObjectiveUsing two step thresholds (2500 steps/day, corresponding to home vs. community ambulation and 5500 steps/day, corresponding to achieving physical activity guidelines through walking), we applied 3 different algorithms to determine which predictors are most important to achieve these thresholds. MethodsWe analyzed data from 268 participants with stroke that included 25 demographic, performance-based and self-report variables. Step 1 of our analysis involved dimensionality reduction using lasso regularization. Step 2 applied drop column feature importance to compute the mean importance of each variable. We then assessed which predictors were important to all 3 mathematically unique algorithms. ResultsThe number of relevant predictors was reduced from 25 to 7 for home vs. community and from 25 to 16 for aerobic thresholds. Drop column feature importance revealed that 6 Minute Walk Test and speed modulation were the only variables found to be important to all 3 algorithms (primary characteristics)for each respective threshold. Other variables related to readiness to change activity behavior and physical health, among others, were found to be important to one or two algorithms (ancillary characteristics). ConclusionsAddressing physical capacity isnecessary but not sufficientto achieve important step thresholds, asancillary characteristics, such as readiness to change activity behavior and physical health may also need to be targeted. This delineation may explain heterogeneity across studies examining predictors of stepping activity in stroke.  more » « less
Award ID(s):
1951474 1934650
PAR ID:
10558567
Author(s) / Creator(s):
; ; ; ;
Editor(s):
Lee, YunJu
Publisher / Repository:
Public Library of Science
Date Published:
Journal Name:
PLOS ONE
Volume:
17
Issue:
6
ISSN:
1932-6203
Page Range / eLocation ID:
e0270105
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ; ; (, American Journal of Human Biology)
    Abstract ObjectivesThe immune system of milk (ISOM) creates a mother–infant immune axis that plays an important role in protecting infants against infectious disease (ID). Tradeoffs in the immune system suggest the potential for both protection and harm, so we conceive of two dimensions via which the ISOM impacts infants: promotion of protective activity and control of activity directed at benign targets. High variability in ISOM activity across mother–infant dyads suggests investment the ISOM may have evolved to be sensitive to maternal and/or infant characteristics. We assessed predictors of appropriate and misdirected proinflammatory ISOM activity in an environment of high ID risk, testing predictions drawn from life history theory and other evolutionary perspectives. MethodsWe characterized milk in vitro interleukin‐6 (IL‐6) responses toSalmonella enterica(a target of protective immune activity;N = 96) andEscherichia coli(a benign target;N = 85) among mother–infant dyads in rural Kilimanjaro, Tanzania. We used ordered logistic regression and mixture models to evaluate maternal and infant characteristics as predictors of IL‐6 responses. ResultsIn all models, IL‐6 responses toS.entericaincreased with maternal age and decreased with gravidity. In mixture models, IL‐6 responses toE.colideclined with maternal age and increased with gravidity. No other considered variables were consistently associated with IL‐6 responses. ConclusionsThe ISOM's capacities for appropriate proinflammatory activity and control of misdirected proinflammatory activity increases with maternal age and decreases with gravidity. These findings are consistent with the hypothesis that the mother–infant immune axis has evolved to respond to maternal life history characteristics. 
    more » « less
  2. ; ; ; (, JMIR Biomedical Engineering)
    BackgroundStroke therapy is essential to reduce impairments and improve motor movements by engaging autogenous neuroplasticity. Traditionally, stroke rehabilitation occurs in inpatient and outpatient rehabilitation facilities. However, recent literature increasingly explores moving the recovery process into the home and integrating technology-based interventions. This study advances this goal by promoting in-home, autonomous recovery for patients who experienced a stroke through robotics-assisted rehabilitation and classifying stroke residual severity using machine learning methods. ObjectiveOur main objective is to use kinematics data collected during in-home, self-guided therapy sessions to develop supervised machine learning methods, to address a clinician’s autonomous classification of stroke residual severity–labeled data toward improving in-home, robotics-assisted stroke rehabilitation. MethodsIn total, 33 patients who experienced a stroke participated in in-home therapy sessions using Motus Nova robotics rehabilitation technology to capture upper and lower body motion. During each therapy session, the Motus Hand and Motus Foot devices collected movement data, assistance data, and activity-specific data. We then synthesized, processed, and summarized these data. Next, the therapy session data were paired with clinician-informed, discrete stroke residual severity labels: “no range of motion (ROM),” “low ROM,” and “high ROM.” Afterward, an 80%:20% split was performed to divide the dataset into a training set and a holdout test set. We used 4 machine learning algorithms to classify stroke residual severity: light gradient boosting (LGB), extra trees classifier, deep feed-forward neural network, and classical logistic regression. We selected models based on 10-fold cross-validation and measured their performance on a holdout test dataset using F1-score to identify which model maximizes stroke residual severity classification accuracy. ResultsWe demonstrated that the LGB method provides the most reliable autonomous detection of stroke severity. The trained model is a consensus model that consists of 139 decision trees with up to 115 leaves each. This LGB model boasts a 96.70% F1-score compared to logistic regression (55.82%), extra trees classifier (94.81%), and deep feed-forward neural network (70.11%). ConclusionsWe showed how objectively measured rehabilitation training paired with machine learning methods can be used to identify the residual stroke severity class, with efforts to enhance in-home self-guided, individualized stroke rehabilitation. The model we trained relies only on session summary statistics, meaning it can potentially be integrated into similar settings for real-time classification, such as outpatient rehabilitation facilities. 
    more » « less
  3. ; ; ; ; ; ; ; ; (, American Journal of Physical Medicine & Rehabilitation)
    ObjectiveThis quasi-experimental study examined the effect of repetitive finger stimulation on brain activation in eight stroke and seven control subjects, measured by quantitative electroencephalogram. MethodsWe applied 5 mins of 2-Hz repetitive bilateral index finger transcutaneous electrical nerve stimulation and compared differences pre– and post–transcutaneous electrical nerve stimulation using quantitative electroencephalogram metrics delta/alpha ratio and delta-theta/alpha-beta ratio. ResultsBetween-group differences before and after stimulation were significantly different in the delta/alpha ratio (z= −2.88,P= 0.0040) and the delta-theta/alpha-beta ratio variables (z= −3.90 withP< 0.0001). Significant decrease in the delta/alpha ratio and delta-theta/alpha-beta ratio variables after the transcutaneous electrical nerve stimulation was detected only in the stroke group (delta/alpha ratio diff = 3.87,P= 0.0211) (delta-theta/alpha-beta ratio diff = 1.19,P= 0.0074). ConclusionsThe decrease in quantitative electroencephalogram metrics in the stroke group may indicate improved brain activity after transcutaneous electrical nerve stimulation. This finding may pave the way for a future novel therapy based on transcutaneous electrical nerve stimulation and quantitative electroencephalogram measures to improve brain recovery after stroke. 
    more » « less
  4. ; ; ; ; ; ; ; ; ; (, JAMA)
    ImportanceSince 2013, the American College of Cardiology (ACC) and American Heart Association (AHA) have recommended the pooled cohort equations (PCEs) for estimating the 10-year risk of atherosclerotic cardiovascular disease (ASCVD). An AHA scientific advisory group recently developed the Predicting Risk of cardiovascular disease EVENTs (PREVENT) equations, which incorporated kidney measures, removed race as an input, and improved calibration in contemporary populations. PREVENT is known to produce ASCVD risk predictions that are lower than those produced by the PCEs, but the potential clinical implications have not been quantified. ObjectiveTo estimate the number of US adults who would experience changes in risk categorization, treatment eligibility, or clinical outcomes when applying PREVENT equations to existing ACC and AHA guidelines. Design, Setting, and ParticipantsNationally representative cross-sectional sample of 7765 US adults aged 30 to 79 years who participated in the National Health and Nutrition Examination Surveys of 2011 to March 2020, which had response rates ranging from 47% to 70%. Main Outcomes and MeasuresDifferences in predicted 10-year ASCVD risk, ACC and AHA risk categorization, eligibility for statin or antihypertensive therapy, and projected occurrences of myocardial infarction or stroke. ResultsIn a nationally representative sample of 7765 US adults aged 30 to 79 years (median age, 53 years; 51.3% women), it was estimated that using PREVENT equations would reclassify approximately half of US adults to lower ACC and AHA risk categories (53.0% [95% CI, 51.2%-54.8%]) and very few US adults to higher risk categories (0.41% [95% CI, 0.25%-0.62%]). The number of US adults receiving or recommended for preventive treatment would decrease by an estimated 14.3 million (95% CI, 12.6 million-15.9 million) for statin therapy and 2.62 million (95% CI, 2.02 million-3.21 million) for antihypertensive therapy. The study estimated that, over 10 years, these decreases in treatment eligibility could result in 107 000 additional occurrences of myocardial infarction or stroke. Eligibility changes would affect twice as many men as women and a greater proportion of Black adults than White adults. Conclusion and RelevanceBy assigning lower ASCVD risk predictions, application of the PREVENT equations to existing treatment thresholds could reduce eligibility for statin and antihypertensive therapy among 15.8 million US adults. 
    more » « less
  5. ; ; ; ; ; (, Infectious Diseases of Poverty)
    Abstract BackgroundNeglected tropical diseases affect the most vulnerable populations and cause chronic and debilitating disorders. Socioeconomic vulnerability is a well-known and important determinant of neglected tropical diseases. For example, poverty and sanitation could influence parasite transmission. Nevertheless, the quantitative impact of socioeconomic conditions on disease transmission risk remains poorly explored. MethodsThis study investigated the role of socioeconomic variables in the predictive capacity of risk models of neglected tropical zoonoses using a decade of epidemiological data (2007–2018) from Brazil. Vector-borne diseases investigated in this study included dengue, malaria, Chagas disease, leishmaniasis, and Brazilian spotted fever, while directly-transmitted zoonotic diseases included schistosomiasis, leptospirosis, and hantaviruses. Environmental and socioeconomic predictors were combined with infectious disease data to build environmental and socioenvironmental sets of ecological niche models and their performances were compared. ResultsSocioeconomic variables were found to be as important as environmental variables in influencing the estimated likelihood of disease transmission across large spatial scales. The combination of socioeconomic and environmental variables improved overall model accuracy (or predictive power) by 10% on average (P < 0.01), reaching a maximum of 18% in the case of dengue fever. Gross domestic product was the most important socioeconomic variable (37% relative variable importance, all individual models exhibitedP < 0.00), showing a decreasing relationship with disease indicating poverty as a major factor for disease transmission. Loss of natural vegetation cover between 2008 and 2018 was the most important environmental variable (42% relative variable importance,P < 0.05) among environmental models, exhibiting a decreasing relationship with disease probability, showing that these diseases are especially prevalent in areas where natural ecosystem destruction is on its initial stages and lower when ecosystem destruction is on more advanced stages. ConclusionsDestruction of natural ecosystems coupled with low income explain macro-scale neglected tropical and zoonotic disease probability in Brazil. Addition of socioeconomic variables improves transmission risk forecasts on tandem with environmental variables. Our results highlight that to efficiently address neglected tropical diseases, public health strategies must target both reduction of poverty and cessation of destruction of natural forests and savannas. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email