Past, Present and Future of Research on Wearable Technologies for Healthcare: A Bibliometric Analysis Using Scopus

Sensors, Journal Year: 2022, Volume and Issue: 22(22), P. 8599 - 8599

Published: Nov. 8, 2022

Currently, wearable technology is present in different fields that aim to satisfy our needs daily life, including the improvement of health general, monitoring patient health, ensuring safety people workplace or supporting athlete training. The objective this bibliometric analysis examine and map scientific advances technologies healthcare, as well identify future challenges within field put forward some proposals address them. In order achieve objective, a search most recent related literature was carried out Scopus database. Our results show research can be divided into two periods: before 2013, it focused on design development sensors systems from an engineering perspective and, since has application well-being alignment with Sustainable Development Goals wherever feasible. reveal United States been country highest publication rates, 208 articles (34.7%). University California, Los Angeles, institution studies topic, 19 (3.1%). Sensors journal (Switzerland) platform subject, 51 (8.5%), one citation 1461. We keywords more specifically, pennant chart illustrate trends research, prioritizing area data collection through sensors, smart clothing other forms discrete physiological data.

Language: Английский

---

Autonomic Dysfunction during Acute SARS-CoV-2 Infection: A Systematic Review

Journal of Clinical Medicine, Journal Year: 2022, Volume and Issue: 11(13), P. 3883 - 3883

Published: July 4, 2022

Although autonomic dysfunction (AD) after the recovery from Coronavirus disease 2019 (COVID-19) has been thoroughly described, few data are available regarding involvement of nervous system (ANS) during acute phase SARS-CoV-2 infection. The primary aim this review was to summarize current knowledge AD occurring COVID-19. Secondarily, we aimed clarify prognostic value ANS and role parameters in predicting According PRISMA guidelines, performed a systematic across Scopus PubMed databases, resulting 1585 records. records check analysis included reports’ references allowed us include 22 articles. studies were widely heterogeneous for study population, dysautonomia assessment, COVID-19 severity. Heart rate variability tool most frequently chosen analyze parameters, followed by automated pupillometry. Most found COVID-19, often related worse outcome. Further needed evidence emerging suggests that complex imbalance is prominent feature leading poor prognosis.

Language: Английский

---

PCovNet: A presymptomatic COVID-19 detection framework using deep learning model using wearables data

Computers in Biology and Medicine, Journal Year: 2022, Volume and Issue: 147, P. 105682 - 105682

Published: June 7, 2022

Language: Английский

---

Wearable Artificial Intelligence for Detecting Anxiety: Systematic Review and Meta-Analysis

Journal of Medical Internet Research, Journal Year: 2023, Volume and Issue: 25, P. e48754 - e48754

Published: Nov. 8, 2023

Background Anxiety disorders rank among the most prevalent mental worldwide. symptoms are typically evaluated using self-assessment surveys or interview-based assessment methods conducted by clinicians, which can be subjective, time-consuming, and challenging to repeat. Therefore, there is an increasing demand for technologies capable of providing objective early detection anxiety. Wearable artificial intelligence (AI), combination AI technology wearable devices, has been widely used detect predict anxiety automatically, objectively, more efficiently. Objective This systematic review meta-analysis aims assess performance in detecting predicting Methods Relevant studies were retrieved searching 8 electronic databases backward forward reference list checking. In total, 2 reviewers independently carried out study selection, data extraction, risk-of-bias assessment. The included assessed risk bias a modified version Quality Assessment Diagnostic Accuracy Studies–Revised. Evidence was synthesized narrative (ie, text tables) statistical meta-analysis) approach as appropriate. Results Of 918 records identified, 21 (2.3%) this review. A results from 81% (17/21) revealed pooled mean accuracy 0.82 (95% CI 0.71-0.89). Meta-analyses 48% (10/21) showed sensitivity 0.79 0.57-0.91) specificity 0.92 0.68-0.98). Subgroup analyses demonstrated that not moderated algorithms, AI, devices used, status types, sources, standards, validation methods. Conclusions Although potential anxiety, it yet advanced enough clinical use. Until further evidence shows ideal should along with other assessments. device companies need develop promptly identify specific time points during day when levels high. Further research needed differentiate types compare different investigate impact neuroimaging on AI. Trial Registration PROSPERO CRD42023387560; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=387560

Language: Английский

---

Basic principles of artificial intelligence in dermatology explained using melanoma

JDDG Journal der Deutschen Dermatologischen Gesellschaft, Journal Year: 2024, Volume and Issue: 22(3), P. 339 - 347

Published: Feb. 15, 2024

Summary The use of artificial intelligence (AI) continues to establish itself in the most diverse areas medicine at an increasingly fast pace. Nevertheless, many healthcare professionals lack basic technical understanding how this technology works, which severely limits its application clinical settings and research. Thus, we would like discuss functioning classification AI using melanoma as example review build behind AI. For purpose, elaborate illustrations are used that quickly reveal involved. Previous reviews tend focus on potential applications AI, thereby missing opportunity develop a deeper subject matter is so important for application. Malignant has become significant burden systems. If discovered early, better prognosis can be expected, why skin cancer screening popular supported by health insurance. number experts remains finite, reducing their availability leading longer waiting times. Therefore, innovative ideas need implemented provide necessary care. machine learning offers ability recognize melanomas from images level comparable experienced dermatologists under optimized conditions.

Language: Английский

---

The Impact of SARS-CoV-2 Infection on Heart Rate Variability: A Systematic Review of Observational Studies with Control Groups

International Journal of Environmental Research and Public Health, Journal Year: 2023, Volume and Issue: 20(2), P. 909 - 909

Published: Jan. 4, 2023

Autonomic nervous system (ANS) dysfunction can arise after severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection and heart rate variability (HRV) tests assess its integrity. This review investigated the relationship between impact of SARS-CoV-2 on HRV parameters. Comprehensive searches were conducted in four electronic databases. Observational studies with a control group reporting direct parameters July 2022 included. A total 17 observational included this review. The square root mean squared differences successive NN intervals (RMSSD) was most frequently investigated. Some found that decreases RMSSD high frequency (HF) power associated or poor prognosis COVID-19. Also, increases normalized unit HF related to death critically ill COVID-19 patients. findings showed infection, severity COVID-19, are likely be reflected some HRV-related However, considerable heterogeneity highlighted. methodological quality not optimal. suggest rigorous accurate measurements highly needed topic.

Language: Английский

---

Paving the Roadmap for XAI and IML in Healthcare: Data-Driven Discoveries and the FIXAIH Framework

Published: Jan. 1, 2025

Integrating Explainable Artificial Intelligence (XAI) and Interpretable Machine Learning (IML) in healthcare enhances trust transparency, crucial for outcomes that directly affect patient care. In this paper, we design a machine learning-based analysis tool to systematically analyze dataset of 5,083 academic articles, focusing on how XAI IML can be effectively integrated into healthcare. Our identifies categorizes 13 key parameters across three macro-parameters: Research Methods, Health Disorders, Disease Prevention. This categorization, informed by focused review over 200 helped clarify specific applications challenges associated with settings. These illustrate the profound impact advancing healthcare, from improving diagnostic accuracy treatment efficacy predicting preventing health risks. Methods enhance analytic capabilities clinical decision-making, Disorders apply managing diseases such as cancer chronic conditions, Prevention uses predictive analytics improve preventive strategies. Based these findings, propose FIXAIH framework, designed operationalize insights actionable guidelines interpretability, explainability, accountability AI systems By offering structured comprehensive guidelines, framework ensures tools are not only technically proficient but also ethically sound easily understandable professionals. paper aims bridge technical-proficiency gap promote practical application technologies, fostering more reliable user-centric approach medical field.

Language: Английский

---

Wearable Devices to Diagnose and Monitor the Progression of COVID-19 Through Heart Rate Variability Measurement: Systematic Review and Meta-Analysis

Journal of Medical Internet Research, Journal Year: 2023, Volume and Issue: 25, P. e47112 - e47112

Published: Oct. 11, 2023

Background Recent studies have linked low heart rate variability (HRV) with COVID-19, indicating that this parameter can be a marker of the onset disease and its severity predictor mortality in infected people. Given large number wearable devices capture physiological signals human body easily noninvasively, several used equipment to measure HRV individuals related these measures COVID-19. Objective The objective study was assess utility measurements obtained from as predictive indicators well worsening symptoms affected individuals. Methods A systematic review conducted searching following databases up end January 2023: Embase, PubMed, Web Science, Scopus, IEEE Xplore. Studies had include (1) patients COVID-19 (2) involving use devices. We also meta-analysis reduce possible biases increase statistical power primary research. Results main finding association between symptoms. In some cases, it predict before positive clinical test. reported reduction parameters is associated Individuals presented SD normal-to-normal interbeat intervals root mean square successive differences compared healthy decrease 3.25 ms (95% CI −5.34 −1.16 ms), 1.24 −3.71 1.23 ms). Conclusions Wearable changes HRV, such smartwatches, rings, bracelets, provide information allows for identification during presymptomatic period through an indirect noninvasive self-diagnosis.

Language: Английский

---

A tree-based explainable AI model for early detection of Covid-19 using physiological data

BMC Medical Informatics and Decision Making, Journal Year: 2024, Volume and Issue: 24(1)

Published: June 24, 2024

Abstract With the outbreak of COVID-19 in 2020, countries worldwide faced significant concerns and challenges. Various studies have emerged utilizing Artificial Intelligence (AI) Data Science techniques for disease detection. Although cases declined, there are still deaths around world. Therefore, early detection before onset symptoms has become crucial reducing its extensive impact. Fortunately, wearable devices such as smartwatches proven to be valuable sources physiological data, including Heart Rate (HR) sleep quality, enabling inflammatory diseases. In this study, we utilize an already-existing dataset that includes individual step counts heart rate data predict probability infection symptoms. We train three main model architectures: Gradient Boosting classifier (GB), CatBoost trees, TabNet analyze compare their respective performances. also add interpretability layer our best-performing model, which clarifies prediction results allows a detailed assessment effectiveness. Moreover, created private by gathering from Fitbit guarantee reliability avoid bias. The identical set models was then applied using same pre-trained models, were documented. Using tree-based method, outperformed previous with accuracy 85% on publicly available dataset. Furthermore, produced 81% when You will find source code link: https://github.com/OpenUAE-LAB/Covid-19-detection-using-Wearable-data.git .

Language: Английский

---

The Relationship between Nursing Students’ Smart Devices Addiction and Their Perception of Artificial Intelligence

Healthcare, Journal Year: 2022, Volume and Issue: 11(1), P. 110 - 110

Published: Dec. 30, 2022

Background: The concept of addiction in relation to cellphone and smartphone use is not new, with several researchers already having explored this phenomenon. Artificial intelligence has become important the rapid development technology field recent years. It a very positive impact on our day-to-day life. Aim: To investigate relationship between nursing students’ smart devices their perceptions artificial intelligence. Methods: A cross-sectional design was applied. data were collected from 697 students over three months at College Nursing, Princess Nourah bint Abdulrahman University. Results: correlation test shows significant device respondents (p-value < 0.05). In addition, majority students, 72.7% (507), are moderately addicted smartphones, 21.8% (152) highly addicted, only 5.5% (38) have low addiction. Meanwhile, 83.6% (583) them high levels perception rest, 16.4% (114), moderate level. Conclusions: varies significantly according level utilization.

Language: Английский

---