Mixture of hidden Markov models for accelerometer data

Chaumaray, Marie Du Roy de; Marbac, Matthieu; Navarro, Fabien

doi:10.1214/20-aoas1375

Cited by 5 publications

(2 citation statements)

References 72 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of wearable technologies and sensor data for medical problems is gaining increasing interest from the statistical community, see for example Huang et al (2019), de Chaumaray et al (2020), Qian et al (2020). The difficulty in monitoring performances due to the presence of disturbing factors, such as environmental conditions or other withinactivity sources of variability, is widely accepted; see, for example Schneider et al (2018).…”

Section: Introductionmentioning

confidence: 99%

Doubly-online changepoint detection for monitoring health status during sports activities

Stival¹,

Bernardi²,

Δελλαπόρτας³

2022

Preprint

View full text Add to dashboard Cite

We provide an online framework for analyzing data recorded by smart watches during running activities. In particular, we focus on identifying variations in the behavior of one or more measurements caused by changes in physical condition, such as physical discomfort, periods of prolonged de-training, or even the malfunction of measuring devices. Our framework considers data as a sequence of running activities represented by multivariate time series of physical and biometric data. We combine classical changepoint detection models with an unknown number of components with Gaussian state space models to detect distributional changes between a sequence of activities. The model considers multiple sources of dependence due to the sequential nature of subsequent activities, the autocorrelation structure within each activity, and the contemporaneous dependence between different variables. We provide an online Expectation-Maximization (EM) algorithm involving a sequential Monte Carlo (SMC) approximation of changepoint predicted probabilities. As a byproduct of our model assumptions, our proposed approach processes sequences of multivariate time series in a doubly-online framework. While classical changepoint models detect changes between subsequent activities, the state space framework coupled with the online EM algorithm provides the additional benefit of estimating the real-time probability that a current activity is a changepoint.

show abstract

Section: Introductionmentioning

confidence: 99%

Doubly-online changepoint detection for monitoring health status during sports activities

Stival¹,

Bernardi²,

Δελλαπόρτας³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Instead, we propose the use of hierarchical HMMs for disease progression modeling, particularly mixture of HMMs (mHMMs) and their variants that can explicitly model group-level similarities of patients. We are motivated by the applications of mHMMs in other domains where they have been shown to outperform HMMs such as modeling activity levels in accelerometer data (de Chaumaray et al, 2020), modeling clickstreams of web surfers (Ypma & Heskes, 2008) and modeling human mobility using geo-tagged social media data (Zhang et al, 2016). We summarize our contributions and the organization of the paper below:…”

Section: Introductionmentioning

confidence: 99%

Mixture of Input-Output Hidden Markov Models for Heterogeneous Disease Progression Modeling

Ceritli¹,

Creagh²,

Clifton³

2022

Preprint

View full text Add to dashboard Cite

A particular challenge for disease progression modeling is the heterogeneity of a disease and its manifestations in the patients. Existing approaches often assume the presence of a single disease progression characteristics which is unlikely for neurodegenerative disorders such as Parkinson' disease. In this paper, we propose a hierarchical time-series model that can discover multiple disease progression dynamics. The proposed model is an extension of an input-output hidden Markov model that takes into account the clinical assessments of patients' health status and prescribed medications. We illustrate the benefits of our model using a synthetically generated dataset and a real-world longitudinal dataset for Parkinson's disease.

show abstract

Mixture of Input-Output Hidden Markov Models for Heterogeneous Disease Progression Modeling

Ceritli

Creagh

Clifton

2022

2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI)

View full text Add to dashboard Cite

Mixture of hidden Markov models for accelerometer data

Cited by 5 publications

References 72 publications

Doubly-online changepoint detection for monitoring health status during sports activities

Doubly-online changepoint detection for monitoring health status during sports activities

Mixture of Input-Output Hidden Markov Models for Heterogeneous Disease Progression Modeling

Mixture of Input-Output Hidden Markov Models for Heterogeneous Disease Progression Modeling

Contact Info

Product

Resources

About