Artificial Intelligence for Detection of Cardiovascular-Related Diseases from Wearable Devices: A Systematic Review and Meta-Analysis.
Ontology highlight
ABSTRACT: Purpose
Several artificial intelligence (AI) models for the detection and prediction of cardiovascular-related diseases, including arrhythmias, diabetes, and sleep apnea, have been reported. This systematic review and meta-analysis aimed to identify AI models developed for or applicable to wearable and mobile devices for diverse cardiovascular-related diseases.Materials and methods
The searched databases included Medline, Embase, and Cochrane Library. For AI models for atrial fibrillation (AF) detection, a meta-analysis of diagnostic accuracy was performed to summarize sensitivity and specificity.Results
A total of 102 studies were included in the qualitative review. There were AI models for the detection of arrythmia (n=62), followed by sleep apnea (n=11), peripheral vascular diseases (n=6), diabetes mellitus (n=5), hyper/hypotension (n=5), valvular heart disease (n=4), heart failure (n=3), myocardial infarction and cardiac arrest (n=2), and others (n=4). For quantitative analysis of 26 studies reporting AI models for AF detection, meta-analyzed sensitivity was 94.80% and specificity was 96.96%. Deep neural networks showed superior performance [meta-analyzed area under receiver operating characteristics curve (AUROC) of 0.981] compared to conventional machine learning algorithms (meta-analyzed AUROC of 0.961). However, AI models tested with proprietary dataset (meta-analyzed AUROC of 0.972) or data acquired from wearable devices (meta-analyzed AUROC of 0.977) showed inferior performance than those with public dataset (meta-analyzed AUROC of 0.986) or data from in-hospital devices (meta-analyzed AUROC of 0.983).Conclusion
This review found that AI models for diverse cardiovascular-related diseases are being developed, and that they are gradually developing into a form that is suitable for wearable and mobile devices.
SUBMITTER: Lee S
PROVIDER: S-EPMC8790582 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundArtificial intelligence (AI) has recently been applied to endoscopy and questionnaires for the evaluation of oesophageal diseases (ODs).AimWe performed a systematic review with meta-analysis to evaluate the performance of AI in the diagnosis of malignant and benign OD.MethodsWe searched MEDLINE, EMBASE, EMBASE Classic and the Cochrane Library. A bivariate random-effect model was used to calculate pooled diagnostic efficacy of AI models and endoscopists. The reference tests were histology for neoplasms and the clinical and instrumental diagnosis for gastro-oesophageal reflux disease (GERD). The pooled area under the summary receiver operating characteristic (AUROC), sensitivity, specificity, positive and negative likelihood ratio (PLR and NLR) and diagnostic odds ratio (DOR) were estimated.ResultsFor the diagnosis of Barrett's neoplasia, AI had AUROC of 0.90, sensitivity 0.89, specificity 0.86, PLR 6.50, NLR 0.13 and DOR 50.53. AI models' performance was comparable with that of endoscopists (P = 0.35). For the diagnosis of oesophageal squamous cell carcinoma, the AUROC, sensitivity, specificity, PLR, NLR and DOR were 0.97, 0.95, 0.92, 12.65, 0.05 and DOR 258.36, respectively. In this task, AI performed better than endoscopists although without statistically significant differences. In the detection of abnormal intrapapillary capillary loops, the performance of AI was: AUROC 0.98, sensitivity 0.94, specificity 0.94, PLR 14.75, NLR 0.07 and DOR 225.83. For the diagnosis of GERD based on questionnaires, the AUROC, sensitivity, specificity, PLR, NLR and DOR were 0.99, 0.97, 0.97, 38.26, 0.03 and 1159.6, respectively.ConclusionsAI demonstrated high performance in the clinical and endoscopic diagnosis of OD.
| S-EPMC9305819 | biostudies-literature
Project description:Artificial intelligence (AI) is a major branch of computer science that is fruitfully used for analyzing complex medical data and extracting meaningful relationships in datasets, for several clinical aims. Specifically, in the brain care domain, several innovative approaches have achieved remarkable results and open new perspectives in terms of diagnosis, planning, and outcome prediction. In this work, we present an overview of different artificial intelligent techniques used in the brain care domain, along with a review of important clinical applications. A systematic and careful literature search in major databases such as Pubmed, Scopus, and Web of Science was carried out using "artificial intelligence" and "brain" as main keywords. Further references were integrated by cross-referencing from key articles. 155 studies out of 2696 were identified, which actually made use of AI algorithms for different purposes (diagnosis, surgical treatment, intra-operative assistance, and postoperative assessment). Artificial neural networks have risen to prominent positions among the most widely used analytical tools. Classic machine learning approaches such as support vector machine and random forest are still widely used. Task-specific algorithms are designed for solving specific problems. Brain images are one of the most used data types. AI has the possibility to improve clinicians' decision-making ability in neuroscience applications. However, major issues still need to be addressed for a better practical use of AI in the brain. To this aim, it is important to both gather comprehensive data and build explainable AI algorithms.
| S-EPMC7556883 | biostudies-literature
Project description:BackgroundThe gold standard for the diagnosis of liver fibrosis and nonalcoholic fatty liver disease (NAFLD) is liver biopsy. Various noninvasive modalities, e.g., ultrasonography, elastography and clinical predictive scores, have been used as alternatives to liver biopsy, with limited performance. Recently, artificial intelligence (AI) models have been developed and integrated into noninvasive diagnostic tools to improve their performance.MethodsWe systematically searched for studies on AI-assisted diagnosis of liver fibrosis and NAFLD on MEDLINE, Scopus, Web of Science and Google Scholar. The pooled sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and diagnostic odds ratio (DOR) with their 95% confidence intervals (95% CIs) were calculated using a random effects model. A summary receiver operating characteristic curve and the area under the curve was generated to determine the diagnostic accuracy of the AI-assisted system. Subgroup analyses by diagnostic modalities, population and AI classifiers were performed.ResultsWe included 19 studies reporting the performances of AI-assisted ultrasonography, elastrography, computed tomography, magnetic resonance imaging and clinical parameters for the diagnosis of liver fibrosis and steatosis. For the diagnosis of liver fibrosis, the pooled sensitivity, specificity, PPV, NPV and DOR were 0.78 (0.71-0.85), 0.89 (0.81-0.94), 0.72 (0.58-0.83), 0.92 (0.88-0.94) and 31.58 (11.84-84.25), respectively, for cirrhosis; 0.86 (0.80-0.90), 0.87 (0.80-0.92), 0.85 (0.75-0.91), 0.88 (0.82-0.92) and 37.79 (16.01-89.19), respectively; for advanced fibrosis; and 0.86 (0.78-0.92), 0.81 (0.77-0.84), 0.88 (0.80-0.93), 0.77 (0.58-0.89) and 26.79 (14.47-49.62), respectively, for significant fibrosis. Subgroup analyses showed significant differences in performance for the diagnosis of fibrosis among different modalities. The pooled sensitivity, specificity, PPV, NPV and DOR were 0.97 (0.76-1.00), 0.91 (0.78-0.97), 0.95 (0.87-0.98), 0.93 (0.80-0.98) and 191.52 (38.82-944.81), respectively, for the diagnosis of liver steatosis.ConclusionsAI-assisted systems have promising potential for the diagnosis of liver fibrosis and NAFLD. Validations of their performances are warranted before implementing these AI-assisted systems in clinical practice.Trial registrationThe protocol was registered with PROSPERO (CRD42020183295).
| S-EPMC7788739 | biostudies-literature
Project description:Background: This systematic review summarizes the current evidence about the effectiveness of wearable assistive technologies for upper limbs support during activities of daily living for individuals with neuromuscular diseases. Methods: Fourteen studies have been included in the meta-analysis, involving 184 participants. All included studies compared patients ability to perform functional tasks with and without assistive devices. Results: An overall effect size of 1.06 (95% CI = 0.76-1.36, p < 0.00001) was obtained, demonstrating that upper limbs assistive devices significantly improve the performance in activities of daily living in people with neuromuscular diseases. A significant interaction between studies evaluating functional improvement with externally-assessed outcome measures or self-perceived outcome measures has been detected. In particular, the effect size of the sub-group considering self-perceived scales was 1.38 (95% CI = 1.08-1.68), while the effect size of the other group was 0.77 (95% CI = 0.41-1.11), meaning that patients' perceived functional gain is often higher than the functional gain detectable through clinical scales. Conclusion: Overall, the quality of the evidence ranged from low to moderate, due to low number of studies and participants, limitations in the selection of participants and in the blindness of outcome assessors, and risk of publication bias. Significance: A large magnitude effect and a clear dose-response gradient were found, therefore, a strong recommendation, in favor of the use of assistive devices could be suggested.
| S-EPMC6992540 | biostudies-literature
Project description:Abstract Aims High blood pressure (BP) is the commonest modifiable cardiovascular risk factor, yet its monitoring remains problematic. Wearable cuffless BP devices offer potential solutions; however, little is known about their validity and utility. We aimed to systematically review the validity, features and clinical use of wearable cuffless BP devices. Methods and results We searched MEDLINE, Embase, IEEE Xplore and the Cochrane Database till December 2019 for studies that reported validating cuffless BP devices. We extracted information about study characteristics, device features, validation processes, and clinical applications. Devices were classified according to their functions and features. We defined devices with a mean systolic BP (SBP) and diastolic BP (DBP) biases of <5 mmHg as valid as a consensus. Our definition of validity did not include assessment of device measurement precision, which is assessed by standard deviation of the mean difference—a critical component of ISO protocol validation criteria. Study quality was assessed using the Quality Assessment of Diagnostic Accuracy Studies version 2 tool. A random-effects model meta-analysis was performed to summarise the mean biases for SBP and DBP across studies. Of the 430 studies identified, 16 studies (15 devices, 974 participants) were selected. The majority of devices (81.3%) used photoplethysmography to estimate BP against a reference device; other technologies included tonometry, auscultation and electrocardiogram. In addition to BP and heart rate, some devices also measured night-time BP (n = 5), sleep monitoring (n = 3), oxygen saturation (n = 3), temperature (n = 2) and electrocardiogram (n = 3). Eight devices showed mean biases of <5 mmHg for SBP and DBP compared with a reference device and three devices were commercially available. The meta-analysis showed no statistically significant differences between the wearable and reference devices for SBP (pooled mean difference = 3.42 mmHg, 95% CI: −2.17, 9.01, I2 95.4%) and DBP (pooled mean = 1.16 mmHg, 95% CI: −1.26, 3.58, I2 87.1%). Conclusion Several cuffless BP devices are currently available using different technologies, offering the potential for continuous BP monitoring. The variation in standards and validation protocols limited the comparability of findings across studies and the identification of the most accurate device. Challenges such as validation using standard protocols and in real-life settings must be overcome before they can be recommended for uptake into clinical practice. Graphical Abstract Graphical abstract Wearable BP device system.
| S-EPMC9708022 | biostudies-literature
Project description:BackgroundWearables and artificial intelligence (AI)-powered digital health platforms that utilize machine learning algorithms can autonomously measure a senior's change in activity and behavior and may be useful tools for proactive interventions that target modifiable risk factors.ObjectiveThe goal of this study was to analyze how a wearable device and AI-powered digital health platform could provide improved health outcomes for older adults in assisted living communities.MethodsData from 490 residents from six assisted living communities were analyzed retrospectively over 24 months. The intervention group (+CP) consisted of 3 communities that utilized CarePredict (n=256), and the control group (-CP) consisted of 3 communities (n=234) that did not utilize CarePredict. The following outcomes were measured and compared to baseline: hospitalization rate, fall rate, length of stay (LOS), and staff response time.ResultsThe residents of the +CP and -CP communities exhibit no statistical difference in age (P=.64), sex (P=.63), and staff service hours per resident (P=.94). The data show that the +CP communities exhibited a 39% lower hospitalization rate (P=.02), a 69% lower fall rate (P=.01), and a 67% greater length of stay (P=.03) than the -CP communities. The staff alert acknowledgment and reach resident times also improved in the +CP communities by 37% (P=.02) and 40% (P=.02), respectively.ConclusionsThe AI-powered digital health platform provides the community staff with actionable information regarding each resident's activities and behavior, which can be used to identify older adults that are at an increased risk for a health decline. Staff can use this data to intervene much earlier, protecting seniors from conditions that left untreated could result in hospitalization. In summary, the use of wearables and AI-powered digital health platform can contribute to improved health outcomes for seniors in assisted living communities. The accuracy of the system will be further validated in a larger trial.
| S-EPMC7516685 | biostudies-literature
Project description:An artificial muscle actuator resolves practical engineering problems in compact wearable devices, which are limited to conventional actuators such as electromagnetic actuators. Abstracting the fundamental advantages of an artificial muscle actuator provides a small-scale, high-power actuating system with a sensing capability for developing varifocal augmented reality glasses and naturally fit haptic gloves. Here, we design a shape memory alloy-based lightweight and high-power artificial muscle actuator, the so-called compliant amplified shape memory alloy actuator. Despite its light weight (0.22 g), the actuator has a high power density of 1.7 kW/kg, an actuation strain of 300% under 80 g of external payload. We show how the actuator enables image depth control and an immersive tactile response in the form of augmented reality glasses and two-way communication haptic gloves whose thin form factor and high power density can hardly be achieved by conventional actuators.
| S-EPMC9293895 | biostudies-literature
Project description:BackgroundOlder adults may use wearable devices for various reasons, ranging from monitoring clinically relevant health metrics or detecting falls to monitoring physical activity. Little is known about how this population engages with wearable devices, and no qualitative synthesis exists to describe their shared experiences with long-term use.ObjectiveThis study aims to synthesize qualitative studies of user experience after a multi-day trial with a wearable device to understand user experience and the factors that contribute to the acceptance and use of wearable devices.MethodsWe conducted a systematic search in CINAHL, APA PsycINFO, PubMed, and Embase (2015-2020; English) with fixed search terms relating to older adults and wearable devices. A meta-synthesis methodology was used. We extracted themes from primary studies, identified key concepts, and applied reciprocal and refutational translation techniques; findings were synthesized into third-order interpretations, and finally, a "line-of-argument" was developed. Our overall goal was theory development, higher-level abstraction, and generalizability for making this group of qualitative findings more accessible.ResultsIn total, we reviewed 20 papers; 2 evaluated fall detection devices, 1 tested an ankle-worn step counter, and the remaining 17 tested activity trackers. The duration of wearing ranged from 3 days to 24 months. The views of 349 participants (age: range 51-94 years) were synthesized. Four key concepts were identified and outlined: motivation for device use, user characteristics (openness to engage and functional ability), integration into daily life, and device features. Motivation for device use is intrinsic and extrinsic, encompassing many aspects of the user experience, and appears to be as, if not more, important than the actual device features. To overcome usability barriers, an older adult must be motivated by the useful purpose of the device. A device that serves its intended purpose adds value to the user's life. The user's needs and the support structure around the device-aspects that are often overlooked-seem to play a crucial role in long-term adoption. Our "line-of-argument" model describes how motivation, ease of use, and device purpose determine whether a device is perceived to add value to the user's life, which subsequently predicts whether the device will be integrated into the user's life.ConclusionsThe added value of a wearable device is the resulting balance of motivators (or lack thereof), device features (and their accuracy), ease of use, device purpose, and user experience. The added value contributes to the successful integration of the device into the daily life of the user. Useful device features alone do not lead to continued use. A support structure should be placed around the user to foster motivation, encourage peer engagement, and adapt to the user's preferences.
| S-EPMC8212622 | biostudies-literature
Project description:The aim was to systematically synthesize the current research and influence of artificial intelligence (AI) models on temporomandibular joint (TMJ) osteoarthritis (OA) diagnosis using cone-beam computed tomography (CBCT) or panoramic radiography. Seven databases (PubMed, Embase, Scopus, Web of Science, LILACS, ProQuest, and SpringerLink) were searched for TMJ OA and AI articles. We used QUADAS-2 to assess the risk of bias, while with MI-CLAIM we checked the minimum information about clinical artificial intelligence modeling. Two hundred and three records were identified, out of which seven were included, amounting to 10,077 TMJ images. Three studies focused on the diagnosis of TMJ OA using panoramic radiography with various transfer learning models (ResNet model) on which the meta-analysis was performed. The pooled sensitivity was 0.76 (95% CI 0.35–0.95) and the specificity was 0.79 (95% CI 0.75–0.83). The other studies investigated the 3D shape of the condyle and disease classification observed on CBCT images, as well as the numerous radiomics features that can be combined with clinical and proteomic data to investigate the most effective models and promising features for the diagnosis of TMJ OA. The accuracy of the methods was nearly equivalent; it was higher when the indeterminate diagnosis was excluded or when fine-tuning was used.
| S-EPMC9918072 | biostudies-literature
Project description:BackgroundMetastasis commonly occur in the bone tissue. Artificial intelligence (AI) has become increasingly prevalent in the medical sector as support in decision-making, diagnosis, and treatment processes. The objective of this systematic review was to assess the reliability of AI systems in clinical, radiological, and pathological aspects of bone metastases.MethodsWe included studies that evaluated the use of AI applications in patients affected by bone metastases. Two reviewers performed a digital search on 31 December 2023 on PubMed, Scopus, and Cochrane library and extracted authors, AI method, interest area, main modalities used, and main objectives from the included studies.ResultsWe included 59 studies that analyzed the contribution of computational intelligence in diagnosing or forecasting outcomes in patients with bone metastasis. Six studies were specific for spine metastasis. The study involved nuclear medicine (44.1%), clinical research (28.8%), radiology (20.4%), or molecular biology (6.8%). When a primary tumor was reported, prostate cancer was the most common, followed by lung, breast, and kidney.ConclusionsAppropriately trained AI models may be very useful in merging information to achieve an overall improved diagnostic accuracy and treatment for metastasis in the bone. Nevertheless, there are still concerns with the use of AI systems in medical settings. Ethical considerations and legal issues must be addressed to facilitate the safe and regulated adoption of AI technologies. The limitations of the study comprise a stronger emphasis on early detection rather than tumor management and prognosis as well as a high heterogeneity for type of tumor, AI technology and radiological techniques, pathology, or laboratory samples involved.
| S-EPMC11311270 | biostudies-literature