CoChat

A computer vision system for deep learning-based detection of patient mobilization activities in the ICU

Open access

The DOI matches its Crossref record; 33 of the 33 references it cites were found in a registry or an index.

Abstract

Early and frequent patient mobilization substantially mitigates risk for post-intensive care syndrome and long-term functional impairment. We developed and tested computer vision algorithms to detect patient mobilization activities occurring in an adult ICU. Mobility activities were defined as moving the patient into and out of bed, and moving the patient into and out of a chair. A data set of privacy-safe-depth-video images was collected in the Intermountain LDS Hospital ICU, comprising 563 instances of mobility activities and 98,801 total frames of video data from seven wall-mounted depth sensors. In all, 67% of the mobility activity instances were used to train algorithms to detect mobility activity occurrence and duration, and the number of healthcare personnel involved in each activity. The remaining 33% of the mobility instances were used for algorithm evaluation. The algorithm for detecting mobility activities attained a mean specificity of 89.2% and sensitivity of 87.2% over the four activities; the algorithm for quantifying the number of personnel involved attained a mean accuracy of 68.8%.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41746-019-0087-z

Cites

33 of 33 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 1 Algorithm performance for detecting the occurrence of mobility activities. a Per-class specificity and sensitivity, evaluated at the frame-level. b Per-class receiver operating characteristic curves (ROC). These ROC curves demonstrate the trade-off between sensitivity (the true positive rate) and 1-specificity (the false-positive rate), as the detection thresholds are varied. The area under the ROC curve (AUC) is an aggregate measure of detection performance, and indicates the probability that the model will rank a positive example more highly than a negative example (a model whose predictions are 100% correct will have an AUC of 1.0)
Fig. 1 Algorithm performance for detecting the occurrence of mobility activities. a Per-class specificity and sensitivity, evaluated at the frame-level. b Per-class receiver operating characteristic curves (ROC). These ROC curves demonstrate the trade-off between sensitivity (the true positive rate) and 1-specificity (the false-positive rate), as the detection thresholds are varied. The area under the ROC curve (AUC) is an aggregate measure of detection performance, and indicates the probability that the model will rank a positive example more highly than a negative example (a model whose predictions are 100% correct will have an AUC of 1.0)CC BY · PubMed Central
Fig. 2 Algorithm performance for quantifying the number of healthcare personnel involved in mobility activities. A confusion matrix is shown for true number of healthcare personnel assisting with mobility activity instances (numbered 0–3), vs. the number of personnel detected by the algorithm. When a patient mobilizes alone, the number of detected healthcare personnel is reported as 0. When a patient mobilizes with one healthcare personnel assisting, this is reported as 1, etc. Values are normalized across each row (true number of personnel)
Fig. 2 Algorithm performance for quantifying the number of healthcare personnel involved in mobility activities. A confusion matrix is shown for true number of healthcare personnel assisting with mobility activity instances (numbered 0–3), vs. the number of personnel detected by the algorithm. When a patient mobilizes alone, the number of detected healthcare personnel is reported as 0. When a patient mobilizes with one healthcare personnel assisting, this is reported as 1, etc. Values are normalized across each row (true number of personnel)CC BY · PubMed Central
Fig. 3 Timelines of mobility activity occurrence and healthcare personnel involvement. Two timelines from condensed periods of time in patient rooms are shown. In each timeline, sampled depth image frames from the period are shown. Spatial bounding boxes of person detections are also overlaid (shown only in the center frame for ease of visualization). The temporal extents and number of healthcare personnel (abbreviated “pers.”) involved in each activity (taking into account that one person detected corresponds to the patient) are indicated on the timeline. Human-annotated ground truth is shown for comparison
Fig. 3 Timelines of mobility activity occurrence and healthcare personnel involvement. Two timelines from condensed periods of time in patient rooms are shown. In each timeline, sampled depth image frames from the period are shown. Spatial bounding boxes of person detections are also overlaid (shown only in the center frame for ease of visualization). The temporal extents and number of healthcare personnel (abbreviated “pers.”) involved in each activity (taking into account that one person detected corresponds to the patient) are indicated on the timeline. Human-annotated ground truth is shown for comparisonCC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 33 references

Cited by

See all 125

Metadata

Authors
Yeung, S., Rinaldo, F., Jopling, J., Liu, B., Mehra, R., Downing, N. L., Guo, M., Bianconi, G. M., Alahi, A., Lee, J., Campbell, B., Deru, K., Beninati, W., Fei-Fei, L., & Milstein, A.
Affiliations
  • Stanford University (US)
  • Stanford Medicine (US)
  • École Polytechnique Fédérale de Lausanne (CH)
  • Intermountain Healthcare (US)
Corresponding author
  • Yeung, Serena
  • Rinaldo, Francesca
Venue
npj Digital Medicine
Published
2019-03-01
Volume
2
Issue
1
Pages
11-11
ISSN
2398-6352 (ISSN-L)
OpenAlex
W2918817626
Cited by
125
References
33
Citations by year
2026: 13 · 2025: 15 · 2024: 13 · 2023: 15 · 2022: 15 · 2021: 26 · 2020: 24 · 2019: 4
FWCI
7.71
Type
journal article
Language
en
Open access
Licence
Locations
  • npj Digital Medicine (publishedVersion, cc-by)
  • Europe PMC (PubMed Central) (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
  • Infoscience (Ecole Polytechnique Fédérale de Lausanne) (submittedVersion, cc-by-nc-nd)
Funders
  • Intermountain Healthcare
  • Canada Excellence Research Chairs, Government of Canada
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Human Pose and Action Recognition
  • Health Sciences › Medicine › Critical Care and Intensive Care Medicine › Intensive Care Unit Cognitive Disorders
Keywords
patient mobilization, intensive care unit, computer vision, activity detection, depth video, bed mobility, post-intensive care syndrome, video surveillance

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: A computer vision system for deep learning-based detection of patient mobilization activities in the ICU. https://app.cochat.ai/papers/10.1038/s41746-019-0087-z
The paper
Yeung, S., Rinaldo, F., Jopling, J., Liu, B., Mehra, R., Downing, N. L., Guo, M., Bianconi, G. M., Alahi, A., Lee, J., Campbell, B., Deru, K., Beninati, W., Fei-Fei, L., & Milstein, A. (2019). A computer vision system for deep learning-based detection of patient mobilization activities in the ICU. npj Digital Medicine. https://doi.org/10.1038/s41746-019-0087-z

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.