Dataset Information

Hilab system, a new point-of-care hematology analyzer supported by the Internet of Things and Artificial Intelligence.

ABSTRACT: The complete blood count (CBC) is one of the most requested tests by physicians. CBC tests, most realized in conventional hematological analyzers, are restricted to centralized laboratories due to frequent maintenance, large devices, and expensive costs required. On the other hand, most handheld CBC devices commercially available show high prices and are not liable to calibration or control procedures, which results in poor quality compared to standard hematology instruments. The Hilab system is a small-handed hematological platform that uses microscopy and chromatography techniques for blood cells and hematimetric parameters analysis through artificial intelligence, machine learning, and deep learning techniques. For clinical evaluation of the handheld CBC device, 450 blood samples were analyzed. The samples encompassed normal (82%) and pathological conditions (18%), such as thalassemias (2.2%), anemias (6.6%), and infections (9.2%). For all analytes, accuracy, precision, method comparison, and flagging capabilities of the Hilab System, were compared with the Sysmex XE-2100 (Sysmex, Japan) results. The sample source (venous and capillary) influences were also evaluated. Pearson correlation, Student t test, bias, and the Bland-Altman plot of each blood count analyte were calculated and shown. The significance level was set at p ≤ 0.05. For clinical evaluation, Hilab System and the Sysmex XE-2100 showed a strong correlation (r ≥ 0.9) for most evaluated parameters. In the precision study, analytes showed CV inside the limits established according to European Federation of Clinical Chemistry and Laboratory Medicine guidelines. The flagging capabilities of the Hilab system, compared to the manual microscopy technique, presented high sensibility, specificity, and accuracy. Venous and capillary samples (p > 0.05) do not differ statistically. Considering the need for point-of-care CBCs, the study indicated that the Hilab system provides fast, accurate, low cost, and robust analysis for reliable clinical use.

SUBMITTER: Gasparin AT

PROVIDER: S-EPMC9213419 | biostudies-literature | 2022 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Hilab system, a new point-of-care hematology analyzer supported by the Internet of Things and Artificial Intelligence.

Gasparin Aléxia Thamara AT Araujo Claudiane Isabel Franco CIF Schmitt Patricia P Cardoso Mônica Ribas MR Perussolo Maiara Carolina MC de Jesus Thainá Caroline Schuartz TCS Santiago Erika Bergamo EB Silva Ivan Lucas Reis ILR de Sousa Ricardo Gurgel RG Teng Flavia Zhu FZ Severo Evair Borges EB Ribeiro Victor Henrique Alves VHA Cardoso Milena Andreuzo MA Silva Fernanda D'Amico FD de Araujo Perazzoli Carolina Rodrigues CR de Holanda Farias João Samuel JS de Almeida Bernardo Montesanti Machado BMM Rogal Júnior Sergio Renato SR Figueredo Marcus Vinícius Mazega MVM

Scientific reports 20220621 1

The complete blood count (CBC) is one of the most requested tests by physicians. CBC tests, most realized in conventional hematological analyzers, are restricted to centralized laboratories due to frequent maintenance, large devices, and expensive costs required. On the other hand, most handheld CBC devices commercially available show high prices and are not liable to calibration or control procedures, which results in poor quality compared to standard hematology instruments. The Hilab system is ...[more]

PMID: 35729182

Similar Datasets

Project description:IntroductionThe increasing availability of healthcare data and rapid development of big data analytic methods has opened new avenues for use of Artificial Intelligence (AI)- and Machine Learning (ML)-based technology in medical practice. However, applications at the point of care are still scarce.ObjectiveReview and discuss case studies to understand current capabilities for applying AI/ML in the healthcare setting, and regulatory requirements in the US, Europe and China.MethodsA targeted narrative literature review of AI/ML based digital tools was performed. Scientific publications (identified in PubMed) and grey literature (identified on the websites of regulatory agencies) were reviewed and analyzed.ResultsFrom the regulatory perspective, AI/ML-based solutions can be considered medical devices (i.e., Software as Medical Device, SaMD). A case series of SaMD is presented. First, tools for monitoring and remote management of chronic diseases are presented. Second, imaging applications for diagnostic support are discussed. Finally, clinical decision support tools to facilitate the choice of treatment and precision dosing are reviewed. While tested and validated algorithms for precision dosing exist, their implementation at the point of care is limited, and their regulatory and commercialization pathway is not clear. Regulatory requirements depend on the level of risk associated with the use of the device in medical practice, and can be classified into administrative (manufacturing and quality control), software-related (design, specification, hazard analysis, architecture, traceability, software risk analysis, cybersecurity, etc.), clinical evidence (including patient perspectives in some cases), non-clinical evidence (dosing validation and biocompatibility/toxicology) and other, such as e.g. benefit-to-risk determination, risk assessment and mitigation. There generally is an alignment between the US and Europe. China additionally requires that the clinical evidence is applicable to the Chinese population and recommends that a third-party central laboratory evaluates the clinical trial results.ConclusionsThe number of promising AI/ML-based technologies is increasing, but few have been implemented widely at the point of care. The need for external validation, implementation logistics, and data exchange and privacy remain the main obstacles.

Project description:BackgroundAnemia is one of the most impactful nutrient deficiencies in the world and disproportionately affects children in low-resource settings. Point-of-care devices (PoCDs) measuring blood hemoglobin (Hb) are widely used in such settings to screen for anemia due to their low cost, speed, and convenience. Here we present the first iteration of Aptus, a new PoCD which measures Hb and hematocrit (HCT).AimTo evaluate the accuracy of Aptus and HemoCue® Hb 301 against an automated hematology analyzer (Medonic®) in Gambian children aged 6-35 months and the Aptus' usage in the field.MethodsAptus, HemoCue® and Medonic® were compared using venous blood (n = 180), and Aptus and HemoCue® additionally using capillary blood (n = 506). Agreement was estimated using Bland-Altman analysis and Lin's concordance. Usage was assessed by error occurrence and user experience.ResultsMean Hb values in venous blood did not significantly differ between Aptus and HemoCue® (10.44±1.05 vs 10.56±0.93g/dl, p>0.05), but both measured higher Hb concentrations than Medonic® (9.75±0.99g/dl, p<0.0001). Lin's coefficient between Aptus and Medonic® was rc = 0.548, between HemoCue® and Medonic® rc = 0.636. Mean bias between the PoCDs venous measurements was -0.11g/dl with limits of agreement (LoA) -1.63 and 1.40g/dl. The bias was larger for the comparisons between the Medonic® and both Aptus (0.69g/dl, LoA 0.92 and 2.31g/dl) and HemoCue® (0.81g/dl, LoA 0.17 and 1.78g/dl). ROC curves showed an AUC of 0.933 in HemoCue® and 0.799 in Aptus. Capillary Hb was higher with Aptus than HemoCue® (10.33±1.11g/dl vs 10.01±1.07g/dl, p<0.0001). Mean bias was 0.32g/dl with LoA of -1.91 and 2.54g/dl. Aptus' usage proved intuitive, yet time-to-results and cuvettes could be improved.ConclusionBoth PoCDs showed a relatively limited bias but large LoA. Aptus and HemoCue® showed similar accuracy, while both overestimated Hb levels. Aptus showed promise, with its operation unimpaired by field conditions as well as being able to show HCT values.

Project description:BACKGROUND:Artificial intelligence (AI) and the Internet of Intelligent Things (IIoT) are promising technologies to prevent the concerningly rapid spread of coronavirus disease (COVID-19) and to maximize safety during the pandemic. With the exponential increase in the number of COVID-19 patients, it is highly possible that physicians and health care workers will not be able to treat all cases. Thus, computer scientists can contribute to the fight against COVID-19 by introducing more intelligent solutions to achieve rapid control of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the virus that causes the disease. OBJECTIVE:The objectives of this review were to analyze the current literature, discuss the applicability of reported ideas for using AI to prevent and control COVID-19, and build a comprehensive view of how current systems may be useful in particular areas. This may be of great help to many health care administrators, computer scientists, and policy makers worldwide. METHODS:We conducted an electronic search of articles in the MEDLINE, Google Scholar, Embase, and Web of Knowledge databases to formulate a comprehensive review that summarizes different categories of the most recently reported AI-based approaches to prevent and control the spread of COVID-19. RESULTS:Our search identified the 10 most recent AI approaches that were suggested to provide the best solutions for maximizing safety and preventing the spread of COVID-19. These approaches included detection of suspected cases, large-scale screening, monitoring, interactions with experimental therapies, pneumonia screening, use of the IIoT for data and information gathering and integration, resource allocation, predictions, modeling and simulation, and robotics for medical quarantine. CONCLUSIONS:We found few or almost no studies regarding the use of AI to examine COVID-19 interactions with experimental therapies, the use of AI for resource allocation to COVID-19 patients, or the use of AI and the IIoT for COVID-19 data and information gathering/integration. Moreover, the adoption of other approaches, including use of AI for COVID-19 prediction, use of AI for COVID-19 modeling and simulation, and use of AI robotics for medical quarantine, should be further emphasized by researchers because these important approaches lack sufficient numbers of studies. Therefore, we recommend that computer scientists focus on these approaches, which are still not being adequately addressed.

Project description:BackgroundPoint-of-care ultrasonography (POCUS) enables access to cardiac imaging directly at the bedside but is limited by brief acquisition, variation in acquisition quality, and lack of advanced protocols.ObjectiveTo develop and validate deep learning models for detecting underdiagnosed cardiomyopathies on cardiac POCUS, leveraging a novel acquisition quality-adapted modeling strategy.MethodsTo develop the models, we identified transthoracic echocardiograms (TTEs) of patients across five hospitals in a large U.S. health system with transthyretin amyloid cardiomyopathy (ATTR-CM, confirmed by Tc99m-pyrophosphate imaging), hypertrophic cardiomyopathy (HCM, confirmed by cardiac magnetic resonance), and controls enriched for the presence of severe AS. In a sample of 290,245 TTE videos, we used novel augmentation approaches and a customized loss function to weigh image and view quality to train a multi-label, view agnostic video-based convolutional neural network (CNN) to discriminate the presence of ATTR-CM, HCM, and/or AS. Models were tested across 3,758 real-world POCUS videos from 1,879 studies in 1,330 independent emergency department (ED) patients from 2011 through 2023.ResultsOur multi-label, view-agnostic classifier demonstrated state-of-the-art performance in discriminating ATTR-CM (AUROC 0.98 [95%CI: 0.96-0.99]) and HCM (AUROC 0.95 [95% CI: 0.94-0.96]) on standard TTE studies. Automated metrics of anatomical view correctness confirmed significantly lower quality in POCUS vs TTE videos (median view classifier confidence of 0.63 [IQR: 0.44-0.88] vs 0.93 [IQR: 0.69-1.00], p<0.001). When deployed to POCUS videos, our algorithm effectively discriminated ATTR-CM and HCM with AUROC of up to 0.94 (parasternal long-axis (PLAX)), and 0.85 (apical 4 chamber), corresponding to positive diagnostic odds ratios of 46.7 and 25.5, respectively. In total, 18/35 (51.4%) of ATTR-CM and 32/57 (41.1%) of HCM patients in the POCUS cohort had an AI-positive screen in the year before their eventual confirmatory imaging.ConclusionsWe define and validate an AI framework that enables scalable, opportunistic screening of under-diagnosed cardiomyopathies using POCUS.

Dataset Information

Hilab system, a new point-of-care hematology analyzer supported by the Internet of Things and Artificial Intelligence.

Publications

Hilab system, a new point-of-care hematology analyzer supported by the Internet of Things and Artificial Intelligence.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets