1
|
King AJ, Angus DC, Cooper GF, Mowery DL, Seaman JB, Potter KM, Bukowski LA, Al-Khafaji A, Gunn SR, Kahn JM. A voice-based digital assistant for intelligent prompting of evidence-based practices during ICU rounds. J Biomed Inform 2023; 146:104483. [PMID: 37657712 PMCID: PMC10591951 DOI: 10.1016/j.jbi.2023.104483] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/24/2023] [Revised: 07/21/2023] [Accepted: 08/29/2023] [Indexed: 09/03/2023]
Abstract
OBJECTIVE To evaluate the technical feasibility and potential value of a digital assistant that prompts intensive care unit (ICU) rounding teams to use evidence-based practices based on analysis of their real-time discussions. METHODS We evaluated a novel voice-based digital assistant which audio records and processes the ICU care team's rounding discussions to determine which evidence-based practices are applicable to the patient but have yet to be addressed by the team. The system would then prompt the team to consider indicated but not yet delivered practices, thereby reducing cognitive burden compared to traditional rigid rounding checklists. In a retrospective analysis, we applied automatic transcription, natural language processing, and a rule-based expert system to generate personalized prompts for each patient in 106 audio-recorded ICU rounding discussions. To assess technical feasibility, we compared the system's prompts to those created by experienced critical care nurses who directly observed rounds. To assess potential value, we also compared the system's prompts to a hypothetical paper checklist containing all evidence-based practices. RESULTS The positive predictive value, negative predictive value, true positive rate, and true negative rate of the system's prompts were 0.45 ± 0.06, 0.83 ± 0.04, 0.68 ± 0.07, and 0.66 ± 0.04, respectively. If implemented in lieu of a paper checklist, the system would generate 56% fewer prompts per patient, with 50%±17% greater precision. CONCLUSION A voice-based digital assistant can reduce prompts per patient compared to traditional approaches for improving evidence uptake on ICU rounds. Additional work is needed to evaluate field performance and team acceptance.
Collapse
Affiliation(s)
- Andrew J King
- Department of Critical Care Medicine, University of Pittsburgh School of Medicine, Scaife Hall Suite 600, 3550 Terrace Street, Pittsburgh, PA 15261, USA.
| | - Derek C Angus
- Department of Critical Care Medicine, University of Pittsburgh School of Medicine, Scaife Hall Suite 600, 3550 Terrace Street, Pittsburgh, PA 15261, USA.
| | - Gregory F Cooper
- Department of Biomedical Informatics, University of Pittsburgh School of Medicine, Offices at Baum 4th Floor, 5607 Baum Blvd, Pittsburgh, PA 15206, USA.
| | - Danielle L Mowery
- Department of Biostatistics, Epidemiology, and Informatics, University of Pennsylvania School of Medicine, Blockley Hall 8th Floor, 423 Guardian Drive, Philadelphia, PA 19104, USA.
| | - Jennifer B Seaman
- Department of Acute & Tertiary Care, University of Pittsburgh School of Nursing, 336 Victoria Building, 3500 Victoria Street, Pittsburgh, PA 15261, USA.
| | - Kelly M Potter
- Department of Critical Care Medicine, University of Pittsburgh School of Medicine, Scaife Hall Suite 600, 3550 Terrace Street, Pittsburgh, PA 15261, USA.
| | - Leigh A Bukowski
- Department of Critical Care Medicine, University of Pittsburgh School of Medicine, Scaife Hall Suite 600, 3550 Terrace Street, Pittsburgh, PA 15261, USA.
| | - Ali Al-Khafaji
- Department of Critical Care Medicine, University of Pittsburgh School of Medicine, Scaife Hall Suite 600, 3550 Terrace Street, Pittsburgh, PA 15261, USA.
| | - Scott R Gunn
- Department of Critical Care Medicine, University of Pittsburgh School of Medicine, Scaife Hall Suite 600, 3550 Terrace Street, Pittsburgh, PA 15261, USA.
| | - Jeremy M Kahn
- Department of Critical Care Medicine, University of Pittsburgh School of Medicine, Scaife Hall Suite 600, 3550 Terrace Street, Pittsburgh, PA 15261, USA.
| |
Collapse
|
2
|
Shi T, Chen B. Association between Ambient Illumination and Cognitive Impairment: A Population-Based Study of Older. Behav Neurol 2023; 2023:4131377. [PMID: 37077583 PMCID: PMC10110376 DOI: 10.1155/2023/4131377] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/22/2022] [Revised: 02/21/2023] [Accepted: 03/08/2023] [Indexed: 04/21/2023] Open
Abstract
It is well-established that light therapy can alleviate cognitive impairment, and ambient illumination (AI) can quantify the amount of exposure to light. However, the relationship between AI and cognitive impairment has been largely understudied. Objectives. We aimed to examine the cross-sectional associations between AI and impaired cognition using data from the National Health and Nutrition Examination Survey (NHANES) (2011-2013) database. Methods. The correlation between AI and cognitive impairment was analyzed using multivariate logistic regression models. Nonlinear correlations were explored using curve fitting. Results. Multivariate logistic regression yielded an OR of 0.872 (95% CI 0.699, 1.088) for the association between AI and cognitive impairment after adjusting for covariates. Smooth curve fitting showed that the correlation was nonlinear, with an inflection point at 1.22. Conclusions. These results suggested that the level of AI may be linked to cognitive impairment. We found a nonlinear relationship of AI with cognitive impairment.
Collapse
Affiliation(s)
- Tieyi Shi
- Heilongjiang University of Chinese Medicine, Harbin, China
| | - Baozhong Chen
- Heilongjiang University of Chinese Medicine, Harbin, China
| |
Collapse
|
3
|
Aznielle-Rodríguez T, Ontivero-Ortega M, Galán-García L, Sahli H, Valdés-Sosa M. Stable Sparse Classifiers predict cognitive impairment from gait patterns. Front Psychol 2022; 13:894576. [PMID: 36051195 PMCID: PMC9425080 DOI: 10.3389/fpsyg.2022.894576] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/12/2022] [Accepted: 07/06/2022] [Indexed: 11/13/2022] Open
Abstract
Background Although gait patterns disturbances are known to be related to cognitive decline, there is no consensus on the possibility of predicting one from the other. It is necessary to find the optimal gait features, experimental protocols, and computational algorithms to achieve this purpose. Purposes To assess the efficacy of the Stable Sparse Classifiers procedure (SSC) for discriminating young and healthy older adults (YA vs. HE), as well as healthy and cognitively impaired elderly groups (HE vs. MCI-E) from their gait patterns. To identify the walking tasks or combinations of tasks and specific spatio-temporal gait features (STGF) that allow the best prediction with SSC. Methods A sample of 125 participants (40 young- and 85 older-adults) was studied. They underwent assessment with five neuropsychological tests that explore different cognitive domains. A summarized cognitive index (MDCog), based on the Mahalanobis distance from normative data, was calculated. The sample was divided into three groups (young adults, healthy and cognitively impaired elderly adults) using k-means clustering of MDCog in addition to Age. The participants executed four walking tasks (normal, fast, easy- and hard-dual tasks) and their gait patterns, measured with a body-fixed Inertial Measurement Unit, were used to calculate 16 STGF and dual-task costs. SSC was then employed to predict which group the participants belonged to. The classification's performance was assessed using the area under the receiver operating curves (AUC) and the stable biomarkers were identified. Results The discrimination HE vs. MCI-E revealed that the combination of the easy dual-task and the fast walking task had the best prediction performance (AUC = 0.86, sensitivity: 90.1%, specificity: 96.9%, accuracy: 95.8%). The features related to gait variability and to the amplitude of vertical acceleration had the largest predictive power. SSC prediction accuracy was better than the accuracies obtained with linear discriminant analysis and support vector machine classifiers. Conclusions The study corroborated that the changes in gait patterns can be used to discriminate between young and healthy older adults and more importantly between healthy and cognitively impaired adults. A subset of gait tasks and STGF optimal for achieving this goal with SSC were identified, with the latter method superior to other classification techniques.
Collapse
Affiliation(s)
- Tania Aznielle-Rodríguez
- Department of Electronics, Cuban Center for Neuroscience, Havana, Cuba
- Electronics and Informatics Department, Vrije Universiteit Brussels, Brussels, Belgium
| | - Marlis Ontivero-Ortega
- Department of Neuroinformatics, Cuban Center for Neuroscience, Havana, Cuba
- Department of Data Analysis, Faculty of Psychological and Educational Sciences, Ghent University, Ghent, Belgium
| | | | - Hichem Sahli
- Electronics and Informatics Department, Vrije Universiteit Brussels, Brussels, Belgium
- Interuniversity Microelectronics Centre, Heverlee, Belgium
| | - Mitchell Valdés-Sosa
- Department of Cognitive Neuroscience, Cuban Center for Neuroscience, Havana, Cuba
- *Correspondence: Mitchell Valdés-Sosa
| |
Collapse
|
4
|
Dasgupta P, Hughes JA, Daley M, Sejdić E. Is Human Walking a Network Medicine Problem? An Analysis Using Symbolic Regression Models with Genetic Programming. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2021; 206:106104. [PMID: 33951562 PMCID: PMC8205964 DOI: 10.1016/j.cmpb.2021.106104] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/28/2020] [Accepted: 04/05/2021] [Indexed: 06/12/2023]
Abstract
BACKGROUND AND OBJECTIVE Human walking is typically assessed using a sensor placed on the lower back or the hip. Such analyses often ignore that the arms, legs, and body trunk movements all have significant roles during walking; in other words, these body nodes with accelerometers form a body sensor network (BSN). BSN refers to a network of wearable sensors or devices on the human body that collects physiological signals. Our study proposes that human locomotion could be considered as a network of well-connected nodes. METHODS While hypothesizing that accelerometer data can model this BSN, we collected accelerometer signals from six body areas from ten healthy participants performing a cognitive task. Machine learning based on genetic programming was used to produce a collection of non-linear symbolic models of human locomotion. RESULTS With implications in precision medicine, our primary finding was that our BSN models fit the data from the lower back's accelerometer and describe subject-specific data the best compared to all other models. Across subjects, models were less effective due to the diversity of human sizes. CONCLUSIONS A BSN relationship between all six body nodes has been shown to describe the subject-specific data, which indicates that the network-medicine relationship between these nodes is essential in adequately describing human walking. Our gait analyses can be used for several clinical applications such as medical diagnostics as well as creating a baseline for healthy walking with and without a cognitive load.
Collapse
Affiliation(s)
- Pritika Dasgupta
- Department of Biomedical Informatics, School of Medicine, University of Pittsburgh, Pittsburgh, PA, 15261, USA.
| | - James Alexander Hughes
- Department of Computer Science, St. Francis Xavier University, Antigonish, Nova Scotia, B2G 2W5, Canada
| | - Mark Daley
- Department of Computer Science, Middlesex College, University of Western Ontario, London, Ontario, N6A 3K7, Canada
| | - Ervin Sejdić
- Department of Biomedical Informatics, School of Medicine, University of Pittsburgh, Pittsburgh, PA, 15261, USA; Department of Electrical and Computer Engineering, Swanson School of Engineering, University of Pittsburgh, Pittsburgh, PA, 15261, USA; Department of Bioengineering, Swanson School of Engineering, University of Pittsburgh, Pittsburgh, PA, 15261, USA
| |
Collapse
|
5
|
Dasgupta P, VanSwearingen J, Godfrey A, Redfern M, Montero-Odasso M, Sejdic E. Acceleration Gait Measures as Proxies for Motor Skill of Walking: A Narrative Review. IEEE Trans Neural Syst Rehabil Eng 2021; 29:249-261. [PMID: 33315570 PMCID: PMC7995554 DOI: 10.1109/tnsre.2020.3044260] [Citation(s) in RCA: 14] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/23/2023]
Abstract
In adults 65 years or older, falls or other neuromotor dysfunctions are often framed as walking-related declines in motor skill; the frequent occurrence of such decline in walking-related motor skill motivates the need for an improved understanding of the motor skill of walking. Simple gait measurements, such as speed, do not provide adequate information about the quality of the body motion's translation during walking. Gait measures from accelerometers can enrich measurements of walking and motor performance. This review article will categorize the aspects of the motor skill of walking and review how trunk-acceleration gait measures during walking can be mapped to motor skill aspects, satisfying a clinical need to understand how well accelerometer measures assess gait. We will clarify how to leverage more complicated acceleration measures to make accurate motor skill decline predictions, thus furthering fall research in older adults.
Collapse
|
6
|
Suffoletto B, Dasgupta P, Uymatiao R, Huber J, Flickinger K, Sejdic E. A Preliminary Study Using Smartphone Accelerometers to Sense Gait Impairments Due to Alcohol Intoxication. J Stud Alcohol Drugs 2020; 81:505-510. [PMID: 32800088 PMCID: PMC7437548 DOI: 10.15288/jsad.2020.81.505] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/21/2019] [Accepted: 03/25/2020] [Indexed: 02/08/2024] Open
Abstract
OBJECTIVE Sensing the effects of alcohol consumption in real time could offer numerous opportunities to reduce related harms. This study sought to explore accuracy of gait-related features measured by smartphone accelerometer sensors on detecting alcohol intoxication (breath alcohol concentration [BrAC] > .08%). METHOD In a controlled laboratory study, participants (N = 17; 12 male) were asked to walk 10 steps in a straight line, turn, and walk 10 steps back before drinking and each hour, for up to 7 hours after drinking a weight-based dose of alcohol to reach a BrAC of .20%. Smartphones were placed on the lumbar region and 3-axis accelerometer data was recorded at a rate of 100 Hz. Accelerometer data were segmented into task segments (i.e., walk forward, walk backward). Features were generated for each overlapping 1-second windows, and the data set was split into training and testing data sets. Logistic regression models were used to estimate accuracy for classifying BrAC ≤ .08% from BrAC > .08% for each subject. RESULTS Across participants, BrAC > .08% was predicted with a mean accuracy of 92.5% using logistic regression, an improvement from a naive model accuracy of 88.2% (mean sensitivity = .89; specificity = .92; positive predictive value = .77; and negative predictive value = .97). The two most informative accelerometer features were mean signal amplitude and variance of the signal in the x-axis (i.e., gait sway). CONCLUSIONS We found preliminary evidence supporting use of gait-related features measured by smartphone accelerometer sensors to detect alcohol intoxication. Future research should determine whether these findings replicate in situ.
Collapse
Affiliation(s)
- Brian Suffoletto
- Department of Emergency Medicine, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania
| | - Pritika Dasgupta
- Department of Biomedical Informatics, School of Medicine, University of Pittsburgh, Pittsburgh, Pennsylvania
| | - Ray Uymatiao
- Department of Emergency Medicine, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania
| | - James Huber
- Department of Emergency Medicine, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania
| | - Kate Flickinger
- Department of Emergency Medicine, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania
| | - Ervin Sejdic
- Department of Electrical and Computer Engineering, Swanson School of Engineering, University of Pittsburgh, Pittsburgh, Pennsylvania
| |
Collapse
|
7
|
Dierick F, Buisseret F, Renson M, Luta AM. Digital natives and dual task: Handling it but not immune against cognitive-locomotor interferences. PLoS One 2020; 15:e0232328. [PMID: 32428037 PMCID: PMC7236988 DOI: 10.1371/journal.pone.0232328] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/07/2019] [Accepted: 04/13/2020] [Indexed: 11/19/2022] Open
Abstract
Digital natives developed in an electronic dual tasking world. This paper addresses two questions. Do digital natives respond differently under a cognitive load realized during a locomotor task in a dual-tasking paradigm and how does this address the concept of safety? We investigate the interplay between cognitive (talking and solving Raven’s matrices) and locomotor (walking on a treadmill) tasks in a sample of 17 graduate level participants. The costs of dual-tasking on gait were assessed by studying changes in stride interval time and its variability at long-range. A safety index was designed and computed from total relative change between the variability indices in the single walking and dual-task conditions. As expected, results indicate high Raven’s scores with gait changes found between the dual task conditions compared to the single walking task. Greater changes are observed in the talking condition compared to solving Raven’s matrices, resulting in high safety index values observed in 5 participants. We conclude that, although digital natives are efficient in performing the dual tasks when they are not emotional-based, modification of gait are observable. Due to the variation within participants and the observation of high safety index values in several of them, individuals that responded poorly to low cognitive loads should be encouraged to not perform dual task when executing a primate task of safety to themselves or others.
Collapse
Affiliation(s)
- Frédéric Dierick
- CeREF, Mons, Belgium
- Centre National de Rééducation Fonctionnelle et de Réadaptation – Rehazenter, Laboratoire d’Analyse du Mouvement et de la Posture (LAMP), Luxembourg, Grand-Duché de Luxembourg
- * E-mail:
| | - Fabien Buisseret
- CeREF, Mons, Belgium
- Laboratoire Forme et Fonctionnement Humain, HELHa, Montignies-sur-Sambre, Belgium
- Service de Physique Nucléaire et Subnucléaire, Université de Mons, UMONS Research Institute for Complex Systems, Mons, Belgium
| | - Mathieu Renson
- Laboratoire Forme et Fonctionnement Humain, HELHa, Montignies-sur-Sambre, Belgium
| | - Adèle Mae Luta
- Eleda International Ltd, Ormond Beach, Florida, United States of America
| |
Collapse
|