Dataset Information

Measuring Patient Mobility in the ICU Using a Novel Noninvasive Sensor.

ABSTRACT: OBJECTIVES:To develop and validate a noninvasive mobility sensor to automatically and continuously detect and measure patient mobility in the ICU. DESIGN:Prospective, observational study. SETTING:Surgical ICU at an academic hospital. PATIENTS:Three hundred sixty-two hours of sensor color and depth image data were recorded and curated into 109 segments, each containing 1,000 images, from eight patients. INTERVENTIONS:None. MEASUREMENTS AND MAIN RESULTS:Three Microsoft Kinect sensors (Microsoft, Beijing, China) were deployed in one ICU room to collect continuous patient mobility data. We developed software that automatically analyzes the sensor data to measure mobility and assign the highest level within a time period. To characterize the highest mobility level, a validated 11-point mobility scale was collapsed into four categories: nothing in bed, in-bed activity, out-of-bed activity, and walking. Of the 109 sensor segments, the noninvasive mobility sensor was developed using 26 of these from three ICU patients and validated on 83 remaining segments from five different patients. Three physicians annotated each segment for the highest mobility level. The weighted Kappa (?) statistic for agreement between automated noninvasive mobility sensor output versus manual physician annotation was 0.86 (95% CI, 0.72-1.00). Disagreement primarily occurred in the "nothing in bed" versus "in-bed activity" categories because "the sensor assessed movement continuously," which was significantly more sensitive to motion than physician annotations using a discrete manual scale. CONCLUSIONS:Noninvasive mobility sensor is a novel and feasible method for automating evaluation of ICU patient mobility.

SUBMITTER: Ma AJ

PROVIDER: S-EPMC5697716 | biostudies-literature | 2017 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Measuring Patient Mobility in the ICU Using a Novel Noninvasive Sensor.

Ma Andy J AJ Rawat Nishi N Reiter Austin A Shrock Christine C Zhan Andong A Stone Alex A Rabiee Anahita A Griffin Stephanie S Needham Dale M DM Saria Suchi S

Critical care medicine 20170401 4

<h4>Objectives</h4>To develop and validate a noninvasive mobility sensor to automatically and continuously detect and measure patient mobility in the ICU.<h4>Design</h4>Prospective, observational study.<h4>Setting</h4>Surgical ICU at an academic hospital.<h4>Patients</h4>Three hundred sixty-two hours of sensor color and depth image data were recorded and curated into 109 segments, each containing 1,000 images, from eight patients.<h4>Interventions</h4>None.<h4>Measurements and main results</h4>T ...[more]

PMID: 28291092

Similar Datasets

Project description:PurposeEarly mobilization in the intensive care unit (ICU) can improve patient outcomes but has perceived barriers to implementation. As part of an ongoing structured quality improvement project to increase mobilization of medical ICU patients by nurses and clinical technicians, we adapted the existing, validated Patient Mobilization Attitudes & Beliefs Survey (PMABS) for the ICU setting and evaluated its performance characteristics and results.Materials and methodsThe 26-item PMABS adapted for the ICU (PMABS-ICU) was administered as an online survey to 163 nurses, clinical technicians, respiratory therapists, attending and fellow physicians, nurse practitioners, and physician assistants in one medical ICU. We evaluated the overall and subscale (knowledge, attitude, and behavior) scores and compared these scores by respondent characteristics (clinical role and years of work experience).ResultsThe survey response rate was 96% (155/163). The survey demonstrated acceptable discriminant validity and acceptable internal consistency for the overall scale (Cronbach α: 0.82, 95% confidence interval: 0.76-0.85), with weaker internal consistency for all subscales (Cronbach α: 0.62-0.69). Across all respondent groups, the overall barrier score (range: 1-100) was relatively low, with attending physicians perceiving the lowest barriers (median [interquartile range]: 30 [28-34]) and nurses perceiving the highest (37 [31-40]). Within the first 10 years of work experience, greater experience was associated with a lower overall barrier score (-0.8 for each additional year; P = 0.02).ConclusionsIn our medical ICU, across 6 different clinical roles, there were relatively low perceived barriers to patient mobility, with greater work experience over the first 10 years being associated with lower perceived barriers. As part of a structured quality improvement project, the PMABS-ICU may be valuable in assisting to identify specific perceived barriers for consideration in designing mobility interventions for the ICU setting.

Project description:BACKGROUND:Mobility is a key outcome in older patients with cognitive impairment. The de Morton Mobility Index (DEMMI) is an established measure of older people's mobility that is promising for use in older patients with cognitive impairment. The aim of this study was to examine the DEMMI's psychometric properties in older patients with dementia, delirium or other cognitive impairment. METHODS:This cross-sectional study was performed in a geriatric hospital and includes older acute medical patients with cognitive impairment indicated by a Mini Mental State Examination (MMSE) score ≤ 24 points. A Rasch analysis was performed to check the DEMMI's unidimensionality. Construct validity was assessed by testing 13 hypotheses about expected correlations between the DEMMI and outcome measures of similar or related constructs, and about expected differences of DEMMI scores between groups differing in mobility related characteristics. Administration times were recorded. RESULTS:A sample of 153 patients with mild (MMSE 19-24 points; 63%) and moderate (MMSE: 10-18 points; 37%) cognitive impairment was included (age range: 65-99 years; mean MMSE: 19 ± 4, range: 8-24 points; diagnosis of dementia and delirium: 40% and 18%, respectively). Rasch analysis indicated unidimensionality with an overall fit to the model (P = 0.107). Internal consistency reliability was excellent (Cronbach's alpha = 0.92). Eleven out of 13 (85%) hypotheses on construct validity were confirmed. The DEMMI showed good feasibility, and no adverse events occurred. The mean administration time of 5 min (range: 1-10) was not influenced by the level of cognitive impairment. In contrast to some other comparator instruments, no floor or ceiling effects were evident for the DEMMI. CONCLUSIONS:Results indicate sufficient psychometric properties of the DEMMI in older patients with cognitive impairment. TRIAL REGISTRATION:German Clinical Trials Register ( DRKS00005591 ). Registered February 2, 2015.

Project description:BackgroundLanguage in nonmedical data sets is known to transmit human-like biases when used in natural language processing (NLP) algorithms that can reinforce disparities. It is unclear if NLP algorithms of medical notes could lead to similar transmissions of biases.Research questionCan we identify implicit bias in clinical notes, and are biases stable across time and geography?Study design and methodsTo determine whether different racial and ethnic descriptors are similar contextually to stigmatizing language in ICU notes and whether these relationships are stable across time and geography, we identified notes on critically ill adults admitted to the University of California, San Francisco (UCSF), from 2012 through 2022 and to Beth Israel Deaconess Hospital (BIDMC) from 2001 through 2012. Because word meaning is derived largely from context, we trained unsupervised word-embedding algorithms to measure the similarity (cosine similarity) quantitatively of the context between a racial or ethnic descriptor (eg, African-American) and a stigmatizing target word (eg, nonco-operative) or group of words (violence, passivity, noncompliance, nonadherence).ResultsIn UCSF notes, Black descriptors were less likely to be similar contextually to violent words compared with White descriptors. Contrastingly, in BIDMC notes, Black descriptors were more likely to be similar contextually to violent words compared with White descriptors. The UCSF data set also showed that Black descriptors were more similar contextually to passivity and noncompliance words compared with Latinx descriptors.InterpretationImplicit bias is identifiable in ICU notes. Racial and ethnic group descriptors carry different contextual relationships to stigmatizing words, depending on when and where notes were written. Because NLP models seem able to transmit implicit bias from training data, use of NLP algorithms in clinical prediction could reinforce disparities. Active debiasing strategies may be necessary to achieve algorithmic fairness when using language models in clinical research.

Dataset Information

Measuring Patient Mobility in the ICU Using a Novel Noninvasive Sensor.

Publications

Measuring Patient Mobility in the ICU Using a Novel Noninvasive Sensor.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets