Bayesian classification of falls risk

Martinez, Matthew; De Leon, Phillip L.; Keeley, David

doi:10.1016/j.gaitpost.2018.09.028

Title: Bayesian classification of falls risk

Full Record
Other Related Research

Abstract

Background. Prior research in falls risk prediction often relies on qualitative and/or clinical methods. There are two challenges with these methods. First, qualitative methods typically use falls history to determine falls risk. Second, clinical methods do not quantify the uncertainty in the classification decision. In this paper, we propose using Bayesian classification to predict falls risk using vectors of gait variables shown to contribute to falls risk. Research Questions: (1) Using a vector of risk ratios for specific gait variables shown to contribute to falls risk, how can older adults be classified as low or high falls risk? and (2) how can the uncertainty in the classifier decision be quantified when using a vector of gait variables? Methods. Using a pressure sensitive walkway, biomechanical measurements of gait were collected from 854 adults over the age of 65. In our method, we first determine low and high falls risk labels for vectors of risk ratios using the k-means algorithm. Next, the posterior probability of low or high falls risk class membership is obtained from a two component Gaussian mixture model (GMM) of gait vectors, which enables risk assessment directly from the underlying biomechanics. We classify the gait vectors using a thresholdmore »« less

Authors:

Martinez, Matthew ^[1]; De Leon, Phillip L. ^[2]; Keeley, David ^[3]

Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); New Mexico State Univ., Las Cruces, NM (United States). Klipsch School of Electrical and Computer Engineering
New Mexico State Univ., Las Cruces, NM (United States). Klipsch School of Electrical and Computer Engineering
New Mexico State Univ., Las Cruces, NM (United States). Dept. of Kinesiology and Dance

Publication Date:: Mon Oct 01 00:00:00 EDT 2018

Research Org.:: Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)

Sponsoring Org.:: USDOE

OSTI Identifier:: 1483982

Report Number(s):: SAND-2018-11631J
Journal ID: ISSN 0966-6362; 670075

Grant/Contract Number:: AC04-94AL85000

Resource Type:: Accepted Manuscript

Journal Name:: Gait & Posture

Additional Journal Information:: Journal Volume: 67; Journal Issue: C; Journal ID: ISSN 0966-6362

Country of Publication:: United States

Language:: English

Subject:: 97 MATHEMATICS AND COMPUTING; 59 BASIC BIOLOGICAL SCIENCES

Citation Formats


                    Martinez, Matthew, De Leon, Phillip L., and Keeley, David. Bayesian classification of falls risk.  United States: N. p., 2018. 
Web.  doi:10.1016/j.gaitpost.2018.09.028.

Copy to clipboard


                    Martinez, Matthew, De Leon, Phillip L., & Keeley, David. Bayesian classification of falls risk.  United States.  https://doi.org/10.1016/j.gaitpost.2018.09.028

Copy to clipboard


                    Martinez, Matthew, De Leon, Phillip L., and Keeley, David. Mon .  
"Bayesian classification of falls risk".  United States.  https://doi.org/10.1016/j.gaitpost.2018.09.028.  https://www.osti.gov/servlets/purl/1483982.

Copy to clipboard


                    
@article{osti_1483982,

  title        = {Bayesian classification of falls risk},

  author       = {Martinez, Matthew and De Leon, Phillip L. and Keeley, David},

  abstractNote = {Background. Prior research in falls risk prediction often relies on qualitative and/or clinical methods. There are two challenges with these methods. First, qualitative methods typically use falls history to determine falls risk. Second, clinical methods do not quantify the uncertainty in the classification decision. In this paper, we propose using Bayesian classification to predict falls risk using vectors of gait variables shown to contribute to falls risk. Research Questions: (1) Using a vector of risk ratios for specific gait variables shown to contribute to falls risk, how can older adults be classified as low or high falls risk? and (2) how can the uncertainty in the classifier decision be quantified when using a vector of gait variables? Methods. Using a pressure sensitive walkway, biomechanical measurements of gait were collected from 854 adults over the age of 65. In our method, we first determine low and high falls risk labels for vectors of risk ratios using the k-means algorithm. Next, the posterior probability of low or high falls risk class membership is obtained from a two component Gaussian mixture model (GMM) of gait vectors, which enables risk assessment directly from the underlying biomechanics. We classify the gait vectors using a threshold based on Youden's J statistic. Results. Through a Monte Carlo simulation and an analysis of the receiver operating characteristic (ROC), we demonstrate that our Bayesian classifier, when compared to the k-means falls risk labels, achieves an accuracy greater than 96% at predicting low or high falls risk. Significance. Our analysis indicates that our approach based on a Bayesian framework and an individual's underlying biomechanics can predict falls risk while quantifying uncertainty in the classification decision.},

  doi          = {10.1016/j.gaitpost.2018.09.028},

  journal      = {Gait & Posture},

  number       = C,

  volume       = 67,

  place        = {United States},

  year         = {Mon Oct 01 00:00:00 EDT 2018},

  month        = {Mon Oct 01 00:00:00 EDT 2018}

}

Copy to clipboard

Journal Article:

Free Publicly Available Full Text

Accepted Manuscript (DOE)

Publisher's Version of Record

https://doi.org/10.1016/j.gaitpost.2018.09.028

Other availability

Search WorldCat to find libraries that may hold this journal

Citation Metrics:

Cited by: 4 works

Citation information provided by
Web of Science

Save / Share:

Export Metadata

Save to My Library

Similar Records in DOE PAGES and OSTI.GOV collections:

Falls Risk Classification of Older Adults Using Deep Neural Networks and Transfer Learning

Journal Article Martinez, Matthew Thomas ; De Leon, Phillip - IEEE Journal of Biomedical and Health Informatics

Prior research in falls risk classification using inertial sensors has relied on the use of engineered features, which has concluded in a feature space containing hundreds of features that are likely redundant and possibly irrelevant. In this paper, we propose using fully convolutional neural networks (FCNNs) to classify older adults at low or high risk of falling using inertial sensor data collected from a smartphone. Due to the limited nature of older adult inertial gait data sets, we first pre-train the FCNN models using a publicly available data set for pedestrian activity recognition. Then via transfer learning, we train themore »« less
Cited by 9
https://doi.org/10.1109/JBHI.2019.2906499

Full Text Available
A Bayesian nonrigid registration method to enhance intraoperative target definition in image-guided prostate procedures through uncertainty characterization

Journal Article Pursley, Jennifer ; Risholm, Petter ; Fedorov, Andriy ; ... - Medical Physics

Purpose: This study introduces a probabilistic nonrigid registration method for use in image-guided prostate brachytherapy. Intraoperative imaging for prostate procedures, usually transrectal ultrasound (TRUS), is typically inferior to diagnostic-quality imaging of the pelvis such as endorectal magnetic resonance imaging (MRI). MR images contain superior detail of the prostate boundaries and provide substructure features not otherwise visible. Previous efforts to register diagnostic prostate images with the intraoperative coordinate system have been deterministic and did not offer a measure of the registration uncertainty. The authors developed a Bayesian registration method to estimate the posterior distribution on deformations and provide a case-specific measuremore »« less
https://doi.org/10.1118/1.4760992
Bayesian State-Space Modeling Framework for Understanding and Predicting Golden Eagle Movements Using Telemetry Data

Conference Sandhu, Rimple ; Tripp, Charles ; Brandes, David ; ...

Predicting raptor movements through a wind power plant under given atmospheric and topographical conditions is a crucial first step in the overall goal of quantifying the risk of turbine-related collisions and mortalities. Extracting behavioral traits of golden eagles (Aquila chrysaetos) from telemetry data requires the fusion of noisy and sparse movement data (location, heading, velocity) with a stochastic mathematical representation of the eagles' decision-making processes. In this study, we framed this problem in a Bayesian state-space framework where both observations and decision-making are assumed to be stochastic processes connected through hidden states (mode of flight, intent), and the unknown modelmore »« less
Full Text Available
Robust importance sampling for error estimation in the context of optimal Bayesian transfer learning

Journal Article Maddouri, Omar ; Qian, Xiaoning ; Alexander, Francis J. ; ... - Patterns

Classification has been a major task for building intelligent systems because it enables decision-making under uncertainty. Classifier design aims at building models from training data for representing feature-label distributions-either explicitly or implicitly. In many scientific or clinical settings, training data are typically limited, which impedes the design and evaluation of accurate classifiers. Although transfer learning can improve the learning in target domains by incorporating data from relevant source domains, it has received little attention for performance assessment, notably in error estimation. Here, we investigate knowledge transferability in the context of classification error estimation within a Bayesian paradigm. We introduce amore »« less
https://doi.org/10.1016/j.patter.2021.100428
Synergy and other ineffective mixture risk definitions.

Journal Article Hertzberg, R ; MacDonell, M ; Environmental Assessment - Sci. Total Environ.

A substantial effort has been spent over the past few decades to label toxicologic interaction outcomes as synergistic, antagonistic, or additive. Although useful in influencing the emotions of the public and the press, these labels have contributed fairly little to our understanding of joint toxic action. Part of the difficulty is that their underlying toxicological concepts are only defined for two chemical mixtures, while most environmental and occupational exposures are to mixtures of many more chemicals. Furthermore, the mathematical characterizations of synergism and antagonism are inextricably linked to the prevailing definition of 'no interaction,' instead of some intrinsic toxicological property.more »« less
https://doi.org/10.1016/S0048-9697(01)01113-5

Similar Records