Predicting Deterioration from Wearable Sensor Data in People with Mild COVID-19 DOI Creative Commons
Jin-Yeong Kang, Ye Seul Bae, Eui Kyu Chie

et al.

Sensors, Journal Year: 2023, Volume and Issue: 23(23), P. 9597 - 9597

Published: Dec. 4, 2023

Coronavirus has caused many casualties and is still spreading. Some people experience rapid deterioration that mild at first. The aim of this study to develop a prediction model for COVID-19 patients during the isolation period. We collected vital signs from wearable devices clinical questionnaires. derivation cohort consisted diagnosed with between September December 2021, external validation March June 2022. To model, total 50 participants wore device an average 77 h. evaluate 181 infected 65 designed machine learning-based models predict in COVID-19. 10 min advance, showed area under receiver characteristic curve (AUC) 0.99, 8 h AUC 0.84. found certain variables are important vary depending on point time predict. Efficient monitoring possible by utilizing data sensors symptom self-reports.

Language: Английский

The GenAI is out of the bottle: generative artificial intelligence from a business model innovation perspective DOI Creative Commons
Dominik K. Kanbach, Louisa Heiduk,

Georg Blueher

et al.

Review of Managerial Science, Journal Year: 2023, Volume and Issue: 18(4), P. 1189 - 1220

Published: Sept. 13, 2023

Abstract The introduction of ChatGPT in November 2022 by OpenAI has stimulated substantial discourse on the implementation artificial intelligence (AI) various domains such as academia, business, and society at large. Although AI been utilized numerous areas for several years, emergence generative (GAI) applications ChatGPT, Jasper, or DALL-E are considered a breakthrough acceleration technology due to their ease use, intuitive interface, performance. With GAI, it is possible create variety content texts, images, audio, code, even videos. This creates implications businesses requiring deeper examination, including an influence business model innovation (BMI). Therefore, this study provides BMI perspective GAI with two primary contributions: (1) development six comprehensive propositions outlining impact businesses, (2) discussion three industry examples, specifically software engineering, healthcare, financial services. employs qualitative analysis using scoping review methodology, drawing from wide-ranging sample 513 data points. These include academic publications, company reports, public information press releases, news articles, interviews, podcasts. thus contributes growing management research concerning AI's potential offers practical insights into how utilize develop new improve existing models.

Language: Английский

Citations

158

Self-supervised learning for human activity recognition using 700,000 person-days of wearable data DOI Creative Commons
Hang Yuan, Shing Chan, Andrew P. Creagh

et al.

npj Digital Medicine, Journal Year: 2024, Volume and Issue: 7(1)

Published: April 12, 2024

Language: Английский

Citations

39

Evolution of nanostructured skin patches towards multifunctional wearable platforms for biomedical applications DOI
Daniel Rybak, Yu‐Chia Su, Yang Li

et al.

Nanoscale, Journal Year: 2023, Volume and Issue: 15(18), P. 8044 - 8083

Published: Jan. 1, 2023

Skin patches (SPs) have rapidly advanced to rehabilitation, health monitoring, self-powered and integrated systems. Accordingly, design of nanomaterials, flexible substrates, hydrogels nanofibers can facilitate the therapeutic application SPs.

Language: Английский

Citations

36

Does deidentification of data from wearable devices give us a false sense of security? A systematic review DOI Creative Commons
Lucy Chikwetu, Miao Yu,

Melat K. Woldetensae

et al.

The Lancet Digital Health, Journal Year: 2023, Volume and Issue: 5(4), P. e239 - e247

Published: Feb. 15, 2023

Language: Английский

Citations

35

Real-World Accuracy of Wearable Activity Trackers for Detecting Medical Conditions: Systematic Review and Meta-Analysis DOI Creative Commons
Ben Singh, Sébastien Chastin, Aaron Miatke

et al.

JMIR mhealth and uhealth, Journal Year: 2024, Volume and Issue: 12, P. e56972 - e56972

Published: Aug. 30, 2024

Wearable activity trackers, including fitness bands and smartwatches, offer the potential for disease detection by monitoring physiological parameters. However, their accuracy as specific diagnostic tools remains uncertain.

Language: Английский

Citations

10

Artificial intelligence‐driven change redefining radiology through interdisciplinary innovation DOI Creative Commons
Runqiu Huang, Xiaolin Meng, Xiaoxuan Zhang

et al.

Deleted Journal, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 6, 2025

Abstract Artificial intelligence (AI) is rapidly advancing, yet its applications in radiology remain relatively nascent. From a spatiotemporal perspective, this review examines the forces driving AI development and integration with medicine radiology, particular focus on advancements addressing major diseases that significantly threaten human health. Temporally, advent of foundational model architectures, combined underlying drivers development, accelerating progress interventions their practical applications. Spatially, discussion explores potential evolving methodologies to strengthen interdisciplinary within medicine, emphasizing four critical points imaging process, as well application disease management, including emergence commercial products. Additionally, current utilization deep learning reviewed, future through multimodal foundation models Generative Pre‐trained Transformer are anticipated.

Language: Английский

Citations

2

Self-Repairing and Energy-Harvesting Triboelectric Sensor for Tracking Limb Motion and Identifying Breathing Patterns DOI
Jagan Singh Meena, Tran Duc Khanh, Seung‐Boo Jung

et al.

ACS Applied Materials & Interfaces, Journal Year: 2023, Volume and Issue: 15(24), P. 29486 - 29498

Published: June 9, 2023

The increasing prevalence of health problems stemming from sedentary lifestyles and evolving workplace cultures has placed a substantial burden on healthcare systems. Consequently, remote wearable monitoring systems have emerged as essential tools to track individuals' well-being. Self-powered triboelectric nanogenerators (TENGs) exhibited significant potential for use emerging detection devices capable recognizing body movements breathing patterns. However, several challenges remain be addressed in order fulfill the requirements self-healing ability, air permeability, energy harvesting, suitable sensing materials. These materials must possess high flexibility, lightweight, excellent charging effects both electropositive electronegative layers. In this work, we investigated self-healable electrospun polybutadiene-based urethane (PBU) positive layer titanium carbide (Ti3C2Tx) MXene negative fabrication an energy-harvesting TENG device. PBU consists maleimide furfuryl components well hydrogen bonds that trigger Diels–Alder reaction, contributing its properties. Moreover, incorporates multitude carbonyl amine groups, which create dipole moments stiff flexible segments polymer. This characteristic positively influences qualities by facilitating electron transfer between contacting materials, ultimately resulting output performance. We employed device applications monitor human motion pattern recognition. soft fibrous-structured generates stable open-circuit voltage up 30 V short-circuit current 4 μA at operation frequency 4.0 Hz, demonstrating remarkable cyclic stability. A feature our is allows restoration functionality performance after sustaining damage. been achieved through utilization fibers, can repaired via simple vapor solvent method. innovative approach enables maintain optimal continue functioning effectively even multiple uses. After integration with rectifier, charge various capacitors power 120 LEDs. self-powered active sensor, attaching it purposes. Additionally, demonstrates capability recognize patterns real time, offering valuable insights into individual's respiratory health.

Language: Английский

Citations

22

Septic shock in the immunocompromised cancer patient: a narrative review DOI Creative Commons
Joseph L. Nates, Frédéric Pène,

Michaël Darmon

et al.

Critical Care, Journal Year: 2024, Volume and Issue: 28(1)

Published: Aug. 30, 2024

Immunosuppressed patients, particularly those with cancer, represent a momentous and increasing portion of the population, especially as cancer incidence rises population growth aging. These patients are at heightened risk developing severe infections, including sepsis septic shock, due to multiple immunologic defects such neutropenia, lymphopenia, T B-cell impairment. The diverse complex nature these profiles, compounded by concomitant use immunosuppressive therapies (e.g., corticosteroids, cytotoxic drugs, immunotherapy), superimposed breakage natural protective barriers mucosal damage, chronic indwelling catheters, alterations anatomical structures), increases various infections. other conditions that mimic pose substantial diagnostic therapeutic challenges. Factors elevate progression shock in include advanced age, pre-existing comorbidities, frailty, type severity immunosuppression, hypoalbuminemia, hypophosphatemia, Gram-negative bacteremia, timing responses initial treatment. management vulnerable or varies biased clinical practices may result delayed access intensive care worse outcomes. While is typically associated poor outcomes malignancies, survival has significantly improved over time. Therefore, understanding addressing unique needs through new paradigm, which includes integration innovative technologies into our healthcare system wireless technologies, medical informatics, precision medicine), targeted strategies, robust practices, early identification diagnosis, coupled prompt admission high-level facilities promote multidisciplinary approach, crucial for improving their prognosis overall rates.

Language: Английский

Citations

8

Application of wearables for remote monitoring of oncology patients: A scoping review DOI Creative Commons
K. Closs, Marlo Verket, Dirk Müller‐Wieland

et al.

Digital Health, Journal Year: 2024, Volume and Issue: 10

Published: Jan. 1, 2024

Objective This review aims to systematically map and categorize the current state of wearable applications among oncology patients identify determinants impeding clinical implementation. Methods A Medline, Embase clinicaltrials.gov search identified journal articles, conference abstracts, letters, reports, dissertations registered studies on use wearables in with malignancies published up 10 November 2021. Results Of 2509 records identified, 112 met eligibility criteria. these, 9.8% (11/112) were RCTs 47.3% (53/112) publications observational. Wearables investigated pre-treatment (2.7%; 3/112), during treatment (34.8%; 39/112), post-treatment (17.9%; 20/112), survivors (27.7%; 31/112) non-specified or multiple phases (17.0%; 19/112). Medical-grade applied 22.3% (25/112) publications. Primary objectives ranged from technical feasibility (8.0%; 9/112), user (42.9%; 48/112) correlational analysis (40.2%; 45/112) outcome change (8.9%; 10/112). Outcome was mostly regarding physical activity improvement (80.0%; 8/10). Most (39.3%; 24/61) featured cancer types, breast as most prevalent specific type (22.3% publications, 16.4% studies). Conclusions using are focused assessing consumer-grade wearables, whereas rates efficacy low. Substantial improvements clinically relevant endpoints by such morbidity mortality yet be demonstrated.

Language: Английский

Citations

5

Emerging technologies for COVID (ET-CoV) detection and diagnosis: Recent advancements, applications, challenges, and future perspectives DOI Open Access
Amir Rehman, Huanlai Xing, Muhammad Adnan Khan

et al.

Biomedical Signal Processing and Control, Journal Year: 2023, Volume and Issue: 83, P. 104642 - 104642

Published: Feb. 11, 2023

Language: Английский

Citations

10