• Home
  • Search
  • Fall risk classification for people with lower extremity amputations using random forests and smartphone sensor features from a 6-minute walk test
  • Cite Icon24
  • https://doi.org/10.1371/journal.pone.0247574Copy DOI Icon

Fall risk classification for people with lower extremity amputations using random forests and smartphone sensor features from a 6-minute walk test

  • Apr 26, 2021
  • PLoS ONE
  • Kyle J F Daines +4 more
Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Fall-risk classification is a challenging but necessary task to enable the recommendation of preventative programs for individuals identified at risk for falling. Existing research has primarily focused on older adults, with no predictive fall-risk models for lower limb amputees, despite their greater likelihood of fall-risk than older adults. In this study, 89 amputees with varying degrees of lower limb amputation were asked if they had fallen in the past 6 months. Those who reported at least one fall were considered a fall risk. Each participant performed a 6 minute walk test (6MWT) with an Android smartphone placed in a holder located on the back of the pelvis. A fall-risk classification method was developed using data from sensors within the smartphone. The Ottawa Hospital Rehabilitation Center Walk Test app captured accelerometer and gyroscope data during the 6MWT. From this data, foot strikes were identified, and 248 features were extracted from the collection of steps. Steps were segmented into turn and straight walking, and four different data sets were created: turn steps, straightaway steps, straightaway and turn steps, and all steps. From these, three feature selection techniques (correlation-based feature selection, relief F, and extra trees classifier ensemble) were used to eliminate redundant or ineffective features. Each feature subset was tested with a random forest classifier and optimized for the best number of trees. The best model used turn data, with three features selected by Correlation-based feature selection (CFS), and used 500 trees in a random forest classifier. The resulting metrics were 81.3% accuracy, 57.2% sensitivity, 94.9% specificity, a Matthews correlation coefficient of 0.587, and an F1 score of 0.83. Since the outcomes are comparable to metrics achieved by existing clinical tests, the classifier may be viable for use in clinical practice.

Loading PDF

Similar Papers
  • Research Article
  • Citations15

Feature Selection Techniques on Thyroid, Hepatitis, and Breast Cancer Datasets

  • Mar 31, 2013
  • International Journal on Data Mining and Intelligent Information Technology Applications
  • Mohammad Ashraf - +2
  • Book Chapter

Field Exercise Testing: 6-Minute Walk and Shuttle Walk Tests

  • Jan 01, 2018
  • Annemarie L Lee +3
  • Research Article

Enhanced IoT Security Using Machine Learning Technology

  • Jan 01, 2025
  • International Journal of Advanced Computer Science and Applications
  • Rawan Yousef Bukhowah +2
  • PDF
  • Research Article
  • Citations9

Analysis of Multiobjective Algorithms for the Classification of Multi-Label Video Datasets

  • Jan 01, 2020
  • IEEE Access
  • Gizem Nur Karagoz +3
  • Research Article
  • Citations2

Effective hybrid feature subset selection for multilevel datasets using decision tree classifiers

  • Jan 01, 2023
  • International Journal of Advanced Intelligence Paradigms
  • S Dinakaran +1
  • Research Article

Evaluating the two-minute walk test as a time-efficient alternative to the six-minute walk test in Nigerian older adults: Insights from an exploratory mediation and moderation analysis

  • Mar 01, 2026
  • Archives of Gerontology and Geriatrics Plus
  • Michael E Kalu +7
  • Conference Article
  • Citations8

Identification of Nominal Attributes for Intelligent Classification of Chronic Kidney Disease using Optimization Algorithm

  • Jul 01, 2020
  • Jerlin Rubini Lambert +2
  • Book Chapter
  • Citations1

Analysis of Ensemble Classifiers with Feature Selection for an Effective Intrusion Detection Model

  • Aug 28, 2020
  • Atreya Dyaram +3
  • Research Article
  • Citations1

Improving with Hybrid Feature Selection in Software Defect Prediction

  • Apr 23, 2024
  • Jurnal Online Informatika
  • Muhammad Yoga Adha Pratama +4
  • Conference Article
  • Citations12

Gene selection stability's dependence on dataset difficulty

  • Aug 01, 2013
  • David J Dittman +3
  • Research Article
  • Citations30

Deep belief network-based approach for detecting Alzheimer's disease using the multi-omics data

  • Jan 01, 2023
  • Computational and Structural Biotechnology Journal
  • Nivedhitha Mahendran +1
  • Research Article
  • Citations19

Translation of a Motor Learning Walking Rehabilitation Program Into a Group-Based Exercise Program for Community-Dwelling Older Adults

  • Oct 19, 2015
  • PM&R
  • Jennifer S Brach +5
  • Conference Article
  • Citations3

Dimensionality reduction for high dimensional data

  • Oct 27, 2014
  • Aditya Kumar +2
  • Book Chapter
  • Citations5

Machine Learning-Based Depression Detection

  • Oct 14, 2022
  • Saikat Biswas +4
  • Research Article

Comparison between 6 Min Walk Test and Incremental Shuttle Walk Test in Middle Aged Women with Type 2 Diabetes: A Pilot Study

  • Sep 20, 2025
  • International Journal of Physiotherapy and Research
  • Vishnu K Nair +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.