The promise of digital healthcare technologies

Frontiers in Public Health, Journal Year: 2023, Volume and Issue: 11

Published: Sept. 26, 2023

Digital health technologies have been in use for many years a wide spectrum of healthcare scenarios. This narrative review outlines the current and future strategies significance digital modern applications. It covers state scientific field (delineating major strengths, limitations, applications) envisions impact relevant emerging key technologies. Furthermore, we attempt to provide recommendations innovative approaches that would accelerate benefit research, translation utilization

Language: Английский

---

Systematic review and meta-analysis of performance of wearable artificial intelligence in detecting and predicting depression

npj Digital Medicine, Journal Year: 2023, Volume and Issue: 6(1)

Published: May 5, 2023

Abstract Given the limitations of traditional approaches, wearable artificial intelligence (AI) is one technologies that have been exploited to detect or predict depression. The current review aimed at examining performance AI in detecting and predicting search sources this systematic were 8 electronic databases. Study selection, data extraction, risk bias assessment carried out by two reviewers independently. extracted results synthesized narratively statistically. Of 1314 citations retrieved from databases, 54 studies included review. pooled mean highest accuracy, sensitivity, specificity, root square error (RMSE) was 0.89, 0.87, 0.93, 4.55, respectively. lowest RMSE 0.70, 0.61, 0.73, 3.76, Subgroup analyses revealed there a statistically significant difference specificity between algorithms, sensitivity devices. Wearable promising tool for depression detection prediction although it its infancy not ready use clinical practice. Until further research improve performance, should be used conjunction with other methods diagnosing Further are needed examine based on combination device neuroimaging distinguish patients those diseases.

Language: Английский

---

Digital Biomarkers in Multiple Sclerosis

Brain Sciences, Journal Year: 2021, Volume and Issue: 11(11), P. 1519 - 1519

Published: Nov. 16, 2021

For incurable diseases, such as multiple sclerosis (MS), the prevention of progression and preservation quality life play a crucial role over entire therapy period. In MS, patients tend to become ill at younger age are so variable in terms their disease course that there is no standard therapy. Therefore, it necessary enable personalized possible respond promptly any changes, whether with noticeable symptoms or symptomless. Here, measurable parameters biological processes can be used, which provide good information regard prognostic diagnostic aspects, activity response therapy, so-called biomarkers Increasing digitalization availability easy-to-use devices technology also healthcare professionals use new class digital biomarkers-digital health technologies-to explain, influence and/or predict health-related outcomes. The from these stem quite broad, range wearables collect patients' during digitalized functional tests (e.g., Multiple Sclerosis Performance Test, dual-tasking performance speech) procedures optical coherence tomography) software-supported magnetic resonance imaging evaluation. These technologies offer timesaving way valuable data on regular basis long period time, not only once twice year routine visit clinic. they lead real-life acquisition, closer patient monitoring thus dataset useful for precision medicine. Despite great benefit increasing digitalization, now, path implementing widely unknown inconsistent. Challenges around validation, infrastructure, evidence generation, consistent collection analysis still persist. this narrative review, we explore existing future opportunities capture clinical care people may twin patient. To do this, searched published papers different systems context gathered perspectives under development already research approach.

Language: Английский

---

Wearable Artificial Intelligence for Anxiety and Depression: Scoping Review

Journal of Medical Internet Research, Journal Year: 2022, Volume and Issue: 25, P. e42672 - e42672

Published: Dec. 11, 2022

Anxiety and depression are the most common mental disorders worldwide. Owing to lack of psychiatrists around world, incorporation artificial intelligence (AI) into wearable devices (wearable AI) has been exploited provide health services.This review aimed explore features AI used for anxiety identify application areas open research issues.We searched 8 electronic databases (MEDLINE, PsycINFO, Embase, CINAHL, IEEE Xplore, ACM Digital Library, Scopus, Google Scholar) included studies that met inclusion criteria. Then, we checked cited screened were by studies. The study selection data extraction carried out 2 reviewers independently. extracted aggregated summarized using narrative synthesis.Of 1203 identified, 69 (5.74%) in this review. Approximately, two-thirds depression, whereas remaining it anxiety. frequent was diagnosing depression; however, none treatment purposes. Most targeted individuals aged between 18 65 years. device Actiwatch AW4 (Cambridge Neurotechnology Ltd). Wrist-worn type commonly category model development physical activity data, followed sleep heart rate data. frequently set from sources Depresjon. algorithm random forest, support vector machine.Wearable can offer great promise providing services related depression. Wearable be prescreening assessment Further reviews needed statistically synthesize studies' results performance effectiveness AI. Given its potential, technology companies should invest more

Language: Английский

---

Smart Consumer Wearables as Digital Diagnostic Tools: A Review

Diagnostics, Journal Year: 2022, Volume and Issue: 12(9), P. 2110 - 2110

Published: Aug. 31, 2022

The increasing usage of smart wearable devices has made an impact not only on the lifestyle users, but also biological research and personalized healthcare services. These devices, which carry different types sensors, have emerged as digital diagnostic tools. Data from such enabled prediction detection various physiological well psychological conditions diseases. In this review, we focused applications wrist-worn wearables to detect multiple diseases cardiovascular diseases, neurological disorders, fatty liver metabolic including diabetes, sleep quality, illnesses. fruitful requires fast insightful data analysis, is feasible through machine learning. discussed machine-learning outcomes for analyses. Finally, current challenges with data, future perspectives tools domains.

Language: Английский

---

Association of Demographic and Socioeconomic Indicators With the Use of Wearable Devices Among Children

JAMA Network Open, Journal Year: 2023, Volume and Issue: 6(3), P. e235681 - e235681

Published: March 30, 2023

Importance The use of consumer-grade wearable devices for collecting data biomedical research may be associated with social determinants health (SDoHs) linked to people’s understanding and willingness join remain engaged in remote studies. Objective To examine whether demographic socioeconomic indicators are a device study adherence collection children. Design, Setting, Participants This cohort used usage collected from 10 414 participants (aged 11-13 years) at the year-2 follow-up (2018-2020) ongoing Adolescent Brain Cognitive Development (ABCD) Study, performed 21 sites across United States. Data were analyzed November 2021 July 2022. Main Outcomes Measures 2 primary outcomes (1) participant retention substudy (2) total wear time during 21-day observation period. Associations between end points sociodemographic economic examined. Results mean (SD) age was 12.00 (0.72) years, 5444 (52.3%) male participants. Overall, 1424 (13.7%) Black; 2048 (19.7%), Hispanic; 5615 (53.9%) White. Substantial differences observed that participated shared (wearable [WDC]; 7424 [71.3%]) compared those who did not participate or share (no [NWDC]; 2900 [28.7%]). Black children significantly underrepresented (−59%) WDC (847 [11.4%]) NWDC (577 [19.3%]; P < .001). In contrast, White overrepresented (+132%) (4301 [57.9%]) vs (1314 [43.9%]; Children low-income households (<$24 999) (638 [8.6%]) (492 [16.5%]; retained substantially shorter duration (16 days; 95% CI, 14-17 days) (21 21-21 .001) substudy. addition, notably different (β = −43.00 hours; −55.11 −30.88 Conclusions Relevance this study, large-scale showed considerable terms enrollment daily time. While provide an opportunity real-time, high-frequency contextual monitoring individuals’ health, future studies should account address representational bias SDoH factors.

Language: Английский

---

Exploring the Psychological and Physiological Insights Through Digital Phenotyping by Analyzing the Discrepancies Between Subjective Insomnia Severity and Activity-Based Objective Sleep Measures: Observational Cohort Study

JMIR Mental Health, Journal Year: 2025, Volume and Issue: 12, P. e67478 - e67478

Published: Jan. 27, 2025

Background Insomnia is a prevalent sleep disorder affecting millions worldwide, with significant impacts on daily functioning and quality of life. While traditionally assessed through subjective measures such as the Severity Index (ISI), advent wearable technology has enabled continuous, objective monitoring in natural environments. However, relationship between insomnia severity parameters remains unclear. Objective This study aims to (1) explore severity, measured by ISI scores, activity-based obtained devices; (2) determine whether perceptions align sleep; (3) identify key psychological physiological factors contributing complaints. Methods A total 250 participants, including both individuals without aged 19-70 years, were recruited from March 2023 November 2023. Participants grouped based scores: no insomnia, mild, moderate, severe insomnia. Data collection involved assessments self-reported questionnaires measurements using devices (Fitbit Inspire 3) that monitored parameters, physical activity, heart rate. The participants also used smartphone app for ecological momentary assessment, recording alcohol consumption, caffeine intake, exercise, stress. Statistical analyses compare groups measures. Results indicated differences general structure (eg, time, rapid eye movement light time) among (mild, severe) classified scores (all P>.05). Interestingly, group had longer awake times lower compared groups. Among groups, observed regarding P>.05), suggesting similar patterns regardless severity. There stress levels, dysfunctional beliefs about sleep, symptoms restless leg syndrome P≤.001), higher associated these factors. Contrary expectations, intake (P=.42) consumption (P=.07) Conclusions findings demonstrate discrepancy beyond duration may contribute Psychological factors, stress, beliefs, legs syndrome, appear play roles perception These results highlight importance considering evaluation treatment suggest potential avenues personalized strategies address aspects disturbances. Trial Registration Clinical Research Information Service KCT0009175; https://cris.nih.go.kr/cris/search/detailSearch.do?seq=26133

Language: Английский

---

Machine Learning Models to Identify Individuals With Imminent Suicide Risk Using a Wearable Device: A Pilot Study

Psychiatry Investigation, Journal Year: 2025, Volume and Issue: 22(2), P. 156 - 166

Published: Feb. 18, 2025

Objective We aimed to determine whether individuals at immediate risk of suicide could be identified using data from a commercially available wearable device.Methods Thirty-nine participants experiencing acute depressive episodes and 20 age- sex-matched healthy controls wore device (Galaxy Watch Active2) for two months. collected on activities, sleep, physiological metrics like heart rate variability the device. Participants rated their mood spontaneously twice daily Likert scale displayed Mood ratings by clinicians were performed weeks 0, 2, 4, 8. The was assessed Hamilton Depression Rating Scale’s item score (HAMD-3). developed predictive models machine learning: single-level model that processed all simultaneously identify those (HAMD-3 scores ≥1) multilevel model. compared predictions imminent both models.Results Both single-step multi-step effectively predicted risk. outperformed in predicting with area under curve 0.89 0.88. In model, HAMD total most significant, whereas diagnosis key predictors.Conclusion Wearable devices are promising tool identifying suicide. Future research more refined temporal resolution is recommended.

Language: Английский

---

Uptrend in global managed honey bee colonies and production based on a six-decade viewpoint, 1961–2017

Scientific Reports, Journal Year: 2022, Volume and Issue: 12(1)

Published: Dec. 9, 2022

We conducted a retrospective study to examine the long-term trends for global honey bee population and its two main products: beeswax. Our analysis was based on data collected by Food Agriculture Organization of United Nations from 1961 2017. During this period, there were increases in number managed colonies (85.0%), production (181.0%) beeswax (116.0%). The amount produced per colony increased 45.0%, signifying improvements efficiency producing honey. Concurrently, human grew 144.0%. Whilst absolute globally, capita declined 19.9% 13.6 1000 10.9 Beeswax had similar trend as reduced 8.5% 8.2 7.5 kg population. In contrast, 42.9% at level. growth outpaced that colonies. Continuation raises possibility having shortfall pollinators meet increasing consumer demand pollinated crops. To mitigate these challenges locally driven solutions will be key influencing factors differed geographically.

Language: Английский

---

Digital phenotype of mood disorders: A conceptual and critical review

Frontiers in Psychiatry, Journal Year: 2022, Volume and Issue: 13

Published: July 26, 2022

Mood disorders are commonly diagnosed and staged using clinical features that rely merely on subjective data. The concept of digital phenotyping is based the idea collecting real-time markers human behavior allows us to determine signature a pathology. This strategy assumes behaviors quantifiable from data extracted analyzed through sensors, wearable devices, or smartphones. That could bring shift in diagnosis mood disorders, introducing for first time additional examinations psychiatric routine care.The main objective this review was propose conceptual critical literature regarding theoretical technical principles phenotypes applied disorders.We conducted by updating previous article querying PubMed database between February 2017 November 2021 titles with relevant keywords phenotyping, artificial intelligence.Out 884 articles included evaluation, 45 were taken into account classified source (multimodal, actigraphy, ECG, smartphone use, voice analysis, body temperature). For depressive episodes, finding decrease terms functional biological parameters [decrease activities walking, number calls SMS messages, temperature heart rate variability (HRV)], while manic phase produces reverse phenomenon (increase activities, HRV).The various studies presented support potential interest computerize characteristics disorders.

Language: Английский

---