Digital wearable insole-based identification of knee arthropathies and gait signatures using machine learning
- Regeneron, United States
Abstract
Gait is impaired in musculoskeletal conditions, such as knee arthropathy. Gait analysis is used in clinical practice to inform diagnosis and to monitor disease progression or intervention response. However, clinical gait analysis relies on subjective visual observation of walking, as objective gait analysis has not been possible within clinical settings due to the expensive equipment, large-scale facilities, and highly trained staff required. Relatively low-cost wearable digital insoles may offer a solution to these challenges. In this work, we demonstrate how a digital insole measuring osteoarthritis-specific gait signatures yields similar results to the clinical gait-lab standard. To achieve this, we constructed a machine learning model, trained on force plate data collected in participants with knee arthropathy and controls. This model was highly predictive of force plate data from a validation set (area under the receiver operating characteristics curve [auROC] = 0.86; area under the precision-recall curve [auPR] = 0.90) and of a separate, independent digital insole dataset containing control and knee osteoarthritis subjects (auROC = 0.83; auPR = 0.86). After showing that digital insole derived gait characteristics are comparable to traditional gait measurements, we next showed that a single stride of raw sensor time series data could be accurately assigned to each subject, highlighting that individuals using digital insoles can be identified by their gait characteristics. This work provides a framework for a promising alternative to traditional clinical gait analysis methods, adds to the growing body of knowledge regarding wearable technology analytical pipelines, and supports clinical development of at-home gait assessments, with the potential to improve the ease, frequency, and depth of patient monitoring.
Data availability
Anonymized data and computer code to reproduce all figures will be made available as supplementary files to this manuscript. All relevant demographic and clinical information, all vGRF, derived gait characteristics, and raw sensor time series data, will be provided, in addition to R and Python scripts used to perform the analysis. Additionally, this information will be uploaded to a Regeneron GitHub account here: https://github.com/regeneron-mpds. This data will be made fully available prior to final publication of this manuscript. The GaitRec dataset is available online here: https://www.nature.com/articles/s41597-020-0481-z
Article and author information
Author details
Matthew F Wipperman
Funding
Regeneron Pharmaceuticals (N/A)
- Matthew F Wipperman
- Allen Z Lin
- Kaitlyn M Gayvert
- Benjamin Lahner
- Selin Somersan-Karakaya
- Xuefang Wu
- Joseph Im
- Minji Lee
- Bharatkumar Koyani
- Ian Setliff
- Malika Thakur
- Daoyu Duan
- Aurora Breazna
- Fang Wang
- Wei Keat Lim
- Gabor Halasz
- Jacek Urbanek
- Yamini Patel
- Gurinder S Atwal
- Jennifer D Hamilton
- Oren Levy
- Andreja Avbersek
- Rinol Alaj
- Sara C Hamon
- Olivier Harari
The funders had no role in study design, data collection and interpretation, or the decision to submit the work for publication.
Reviewing Editor
- Hristo Dimitrov, University of Cambridge, United Kingdom
Ethics
Human subjects: For the pilot study, participants were recruited internally within the Regeneron facility located in Tarrytown, NY, USA, and were provided written informed consent prior to participation. The study was considered exempt research under the Common Rule (45 CFR Sec 46.104). The R5069-OA-1849 study protocol received Institutional Review Board and ethics committee approvals from Moldova Medicines and Medical Device Agency and National Ethics Committee for Moldova, and the Western Institutional Review Board.
Version history
- Preprint posted: October 7, 2022 (view preprint)
- Received: January 12, 2023
- Accepted: April 26, 2024
- Accepted Manuscript published: April 30, 2024 (version 1)
- Version of Record published: June 5, 2024 (version 2)
Copyright
© 2024, Wipperman et al.
This article is distributed under the terms of the Creative Commons Attribution License permitting unrestricted use and redistribution provided that the original author and source are credited.
Metrics
-
- 637
- views
-
- 106
- downloads
-
- 0
- citations
Views, downloads and citations are aggregated across all versions of this paper published by eLife.
Download links
A two-part list of links to download the article, or parts of the article, in various formats.
Downloads (link to download the article as PDF)
Open citations (links to open the citations from this article in various online reference manager services)
Cite this article (links to download the citations from this article in formats compatible with various reference manager tools)
Digital wearable insole-based identification of knee arthropathies and gait signatures using machine learning
eLife 13:e86132.
https://doi.org/10.7554/eLife.86132
Further reading
-
- Medicine
There is clear evidence that the sympathetic nervous system (SNS) mediates bone metabolism. Histological studies show abundant SNS innervation of the periosteum and bone marrow-these nerves consist of noradrenergic fibers that immunostain for tyrosine hydroxylase, dopamine beta hydroxylase, or neuropeptide Y. Nonetheless, the brain sites that send efferent SNS outflow to bone have not yet been characterized. Using pseudorabies (PRV) viral transneuronal tracing, we report, for the first time, the identification of central SNS outflow sites that innervate bone. We find that the central SNS outflow to bone originates from 87 brain nuclei, sub-nuclei and regions of six brain divisions, namely the midbrain and pons, hypothalamus, hindbrain medulla, forebrain, cerebral cortex, and thalamus. We also find that certain sites, such as the raphe magnus (RMg) of the medulla and periaqueductal gray (PAG) of the midbrain, display greater degrees of PRV152 infection, suggesting that there is considerable site-specific variation in the levels of central SNS outflow to bone. This comprehensive compendium illustrating the central coding and control of SNS efferent signals to bone should allow for a greater understanding of the neural regulation of bone metabolism, and importantly and of clinical relevance, mechanisms for central bone pain.
-
- Computational and Systems Biology
- Medicine
Background:
Preterm birth is the leading cause of neonatal morbidity and mortality worldwide. Most cases of preterm birth occur spontaneously and result from preterm labor with intact (spontaneous preterm labor [sPTL]) or ruptured (preterm prelabor rupture of membranes [PPROM]) membranes. The prediction of spontaneous preterm birth (sPTB) remains underpowered due to its syndromic nature and the dearth of independent analyses of the vaginal host immune response. Thus, we conducted the largest longitudinal investigation targeting vaginal immune mediators, referred to herein as the immunoproteome, in a population at high risk for sPTB.
Methods:
Vaginal swabs were collected across gestation from pregnant women who ultimately underwent term birth, sPTL, or PPROM. Cytokines, chemokines, growth factors, and antimicrobial peptides in the samples were quantified via specific and sensitive immunoassays. Predictive models were constructed from immune mediator concentrations.
Results:
Throughout uncomplicated gestation, the vaginal immunoproteome harbors a cytokine network with a homeostatic profile. Yet, the vaginal immunoproteome is skewed toward a pro-inflammatory state in pregnant women who ultimately experience sPTL and PPROM. Such an inflammatory profile includes increased monocyte chemoattractants, cytokines indicative of macrophage and T-cell activation, and reduced antimicrobial proteins/peptides. The vaginal immunoproteome has improved predictive value over maternal characteristics alone for identifying women at risk for early (<34 weeks) sPTB.
Conclusions:
The vaginal immunoproteome undergoes homeostatic changes throughout gestation and deviations from this shift are associated with sPTB. Furthermore, the vaginal immunoproteome can be leveraged as a potential biomarker for early sPTB, a subset of sPTB associated with extremely adverse neonatal outcomes.
Funding:
This research was conducted by the Perinatology Research Branch, Division of Obstetrics and Maternal-Fetal Medicine, Division of Intramural Research, Eunice Kennedy Shriver National Institute of Child Health and Human Development, National Institutes of Health, U.S. Department of Health and Human Services (NICHD/NIH/DHHS) under contract HHSN275201300006C. ALT, KRT, and NGL were supported by the Wayne State University Perinatal Initiative in Maternal, Perinatal and Child Health.
