Deep Eye-CU (DECU): Summarization of Patient Motion in the ICU

Torres, Carlos; Fried, Jeffrey; Rose, Kenneth; Manjunath, B. S.

doi:10.1007/978-3-319-48881-3_13

Cited by 4 publications

(6 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a study Deep Eye-CU (DECU) [33], proposed a pose and motion summarization model in ICU. DECU combines multimodal Hidden Markov Models, extracted frames from multiple sources, and features from multiview multimodal data to monitor the motion of a patient in ICU.…”

Section: Review Of Some Recent State-of-the-artsmentioning

confidence: 99%

Insights of Artificial Intelligence to Stop Spread of COVID-19

Sufian

Jat

Banerjee

2020

Studies in Big Data

View full text Add to dashboard Cite

, a pandemic that has pushed down human civilization in a severe threat. As viruses of COVID-19 like diseases are transferable from human to human, so it becomes very challenging to stop spreading these pandemics. These challenges are not only limited to the treatment of infected patients but also maintaining systematic social distancing to stop spreading the disease. However, maintaining social distancing is not entirely possible everywhere, like in hospitals, emergency sectors, etc. Some critical issues such as: carefully handling the Intensive Care Unite (ICU), patient care, hygienic practice, and systematic social distancing have become very necessary to slow down the spread of the new virus as appropriate vaccines or drugs are not yet available. In this time of crisis, Artificial Intelligence (AI) could assists in many more ways in addition to assisting diagnosis, drug or vaccine discovery. Therefore, this AI, especially algorithms of machine learning, deep learning, and computer vision along with edge computing and IoT technologies could be smart solutions for such challenges. This chapter brings such solutions through some insights of AI to assist to stop these COVID-19 like pandemics.

show abstract

Section: Review Of Some Recent State-of-the-artsmentioning

confidence: 99%

Insights of Artificial Intelligence to Stop Spread of COVID-19

Sufian

Jat

Banerjee

2020

Studies in Big Data

View full text Add to dashboard Cite

show abstract

“…The probability of duration \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} }{}$d_{u}$ \end{document} is given by: \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} }{}\begin{equation*} \Pr (d_{u}=l | y_{u} = i) = {\Pr }_{i}(l)\tag{8}\end{equation*} \end{document} Using segments and HSMMs we can model the state duration as a normal distribution \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} }{}${\Pr }_{i}(l) = {\mathcal {N}}_{l,i}(\mu,\sigma)$ \end{document} and the duration probability of the \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} }{}$i$ \end{document} -th state can be used to distinguish between slow, medium, and fast activities. We refer to [32] for details about HSMM parameter estimation and inference processes.…”

Section: Contextual Aspectsmentioning

confidence: 99%

“…Torres et al [31] introduce a coupled-constrained optimization technique that allows them to trust sensor sources for static pose classification. Torres et al [32] use a multimodal multiview system and combine it with time-series analysis to summarize patient motion. A pose detection and tracking system for rehabilitation is proposed in [20] .…”

Section: Introductionmentioning

confidence: 99%

Healthcare Event and Activity Logging

Torres

Fried

Manjunath

2018

IEEE J. Transl. Eng. Health Med.

Self Cite

View full text Add to dashboard Cite

The health of patients in the intensive care unit (ICU) can change frequently and inexplicably. Crucial events and activities responsible for these changes often go unnoticed. This paper introduces healthcare event and action logging (HEAL) which automatically and unobtrusively monitors and reports on events and activities that occur in a medical ICU room. HEAL uses a multimodal distributed camera network to monitor and identify ICU activities and estimate sanitation-event qualifiers. At the core is a novel approach to infer person roles based on semantic interactions, a critical requirement in many healthcare settings where individuals’ identities must not be identified. The proposed approach for activity representation identifies contextual aspects basis and estimates aspect weights for proper action representation and reconstruction. The flexibility of the proposed algorithms enables the identification of people roles by associating them with inferred interactions and detected activities. A fully working prototype system is developed, tested in a mock ICU room and then deployed in two ICU rooms at a community hospital, thus offering unique capabilities for data gathering and analytics. The proposed method achieves a role identification accuracy of 84% and a backtracking role identification of 79% for obscured roles using interaction and appearance features on real ICU data. Detailed experimental results are provided in the context of four event-sanitation qualifiers: clean, transmission, contamination, and unclean.

show abstract

“…Previous Work. In [37] we introduced the time-series representation of sleep-pose patterns using HHMs and deep features to represent sleep poses. Although this improves the static pose classification, the methods are limited by lack of flexibility in modeling state duration and the inability to identify key poses across multiple modalities and views.…”

Section: Introductionmentioning

confidence: 99%

“…MASH addresses these limitations by introducing a flexible framework to model state duration using time segments and HMM-modified inference. In addition, MASH introduces a keyframe algorithm to identify discriminant and informative frames (i.e., pseudo-poses), which replaces the conventional K-means method used in [37], and improves the overall summarization performance.…”

Section: Introductionmentioning

confidence: 99%

A Multiview Multimodal System for Monitoring Patient Sleep

Torres

Fried

Rose

et al. 2018

IEEE Trans. Multimedia

Self Cite

View full text Add to dashboard Cite

Clinical observations indicate that during critical care at the hospitals, a patient's sleep positioning and motion have a significant effect on recovery rate. Unfortunately, there is no formal medical protocol to record, quantify, and analyze motion of patients. There are very few clinical studies that use manual analysis of sleep poses and motion recordings to support medical benefits of patient positioning and motion monitoring. Manual processes do not scale, are prone to human errors, and put strain on an already taxed healthcare workforce. This study introduces Multimodal, Multiview Motion Analysis and Summarization for healthcare (MASH). MASH is an autonomous system, which addresses these issues by monitoring healthcare environments and enabling the recording and analysis of patient sleep-pose patterns. MASH uses three RGB-D cameras to monitor patients in a medical Intensive Care Unit (ICU) room. The proposed algorithms estimate pose direction at different temporal resolutions and use keyframes to efficiently represent pose transition dynamics. MASH combines deep features computed from the data with a modified version of Hidden Markov Model (HMM) to flexibly model pose duration and summarize patient motion. The performance is evaluated in ideal (BC: Bright and Clear/occlusion-free) and natural (DO: Dark and Occluded) scenarios at two motion resolutions and in two environments: a mock-up and a medical ICU. The usage of deep features is evaluated and their performance compared with engineered features. Experimental results using deep features in DO scenes increases performance from 86.7% to 93.6%, while matching the classification performance of engineered features in BC scenes. The performance of MASH is compared with HMM and C3D. The overall overtime tracing and summarization error rate across all methods increased when transitioning from the mock-up to the the medical ICU data. The proposed keyframe estimation helps achieve a 78% transition classification accuracy.

show abstract

Deep Eye-CU (DECU): Summarization of Patient Motion in the ICU

Cited by 4 publications

References 20 publications

Insights of Artificial Intelligence to Stop Spread of COVID-19

Insights of Artificial Intelligence to Stop Spread of COVID-19

Healthcare Event and Activity Logging

A Multiview Multimodal System for Monitoring Patient Sleep

Contact Info

Product

Resources

About