LIVIVO - The Search Portal for Life Sciences

zur deutschen Oberfläche wechseln
Advanced search

Search results

Result 1 - 3 of total 3

Search options

  1. Article: Efficacy of Artificial Intelligence Software in the Automated Analysis of Left Ventricular Function in Echocardiography in Central Vietnam.

    Doan, Chi Thang / Tran, Khanh Hung / Luong, Viet Thang / Dang-Nguyen, Ngoc Hai / Ton-Nu, Victoria

    Acta informatica medica : AIM : journal of the Society for Medical Informatics of Bosnia & Herzegovina : casopis Drustva za medicinsku informatiku BiH

    2024  Volume 32, Issue 1, Page(s) 32–36

    Abstract: Background: In recent years, there has been a significant focus on the development of artificial intelligence (AI) applications in healthcare. However, current scientific evidence is still not convincing enough for the general public and the medical ... ...

    Abstract Background: In recent years, there has been a significant focus on the development of artificial intelligence (AI) applications in healthcare. However, current scientific evidence is still not convincing enough for the general public and the medical community to widely adopt AI in clinical practice.
    Objective: We conducted this study to investigate the correlation between left ventricular function indices assessed by AI and those evaluated by physicians.
    Methods: This cross-sectional descriptive study was conducted on 136 patients who attended and received treatment at Hue University of Medicine and Pharmacy Hospital from April 2022 to June 2023. Using QLAB version 15, Philips Healthcare.
    Results: The AI software accurately identified 98.5% of the echocardiographic cine-loops. However, there were about 1.5% of cine-loops that the software failed to recognize. The sensitivity of Ejection Fraction (EF) calculated by AI was 73.3%, specificity was 81.3%, and accuracy stood at 78.6%. A strong positive correlation was observed between EF measured by AI and that assessed by physicians, r = 0.701, p < 0.01. The sensitivity of Global Longitudinal Strain (GLS) calculated by AI was 42.1%, specificity was 84.8%, and accuracy was 67.6%. A moderate positive correlation was found between GLS measured by AI and physician's assessment, r = 0.460, p < 0.01.
    Conclusion: The use of AI software for evaluating left ventricular function through ejection fraction and global longitudinal strain is rapid and yields results comparable to cardiologists' echocardiographic assessments. The AI-powered software holds a promising and feasible future in clinical practice.
    Language English
    Publishing date 2024-03-21
    Publishing country Bosnia and Herzegovina
    Document type Journal Article
    ZDB-ID 2558601-4
    ISSN 1986-5988 ; 0353-8109
    ISSN (online) 1986-5988
    ISSN 0353-8109
    DOI 10.5455/aim.2024.32.32-36
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  2. Book ; Online: Manifold attack

    Tran, Khanh-Hung / Ngole-Mboula, Fred-Maurice / Starck, Jean-Luc

    2020  

    Abstract: Machine Learning in general and Deep Learning in particular has gained much interest in the recent decade and has shown significant performance improvements for many Computer Vision or Natural Language Processing tasks. In order to deal with databases ... ...

    Abstract Machine Learning in general and Deep Learning in particular has gained much interest in the recent decade and has shown significant performance improvements for many Computer Vision or Natural Language Processing tasks. In order to deal with databases which have just a small amount of training samples or to deal with models which have large amount of parameters, the regularization is indispensable. In this paper, we enforce the manifold preservation (manifold learning) from the original data into latent presentation by using "manifold attack". The later is inspired in a fashion of adversarial learning : finding virtual points that distort mostly the manifold preservation then using these points as supplementary samples to train the model. We show that our approach of regularization provides improvements for the accuracy rate and for the robustness to adversarial examples.
    Keywords Computer Science - Machine Learning ; Statistics - Machine Learning
    Publishing date 2020-09-13
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  3. Book ; Online: Semi-supervised dictionary learning with graph regularization and active points

    Tran, Khanh-Hung / Ngole-Mboula, Fred-Maurice / Starck, Jean-Luc / Prost, Vincent

    2020  

    Abstract: Supervised Dictionary Learning has gained much interest in the recent decade and has shown significant performance improvements in image classification. However, in general, supervised learning needs a large number of labelled samples per class to ... ...

    Abstract Supervised Dictionary Learning has gained much interest in the recent decade and has shown significant performance improvements in image classification. However, in general, supervised learning needs a large number of labelled samples per class to achieve an acceptable result. In order to deal with databases which have just a few labelled samples per class, semi-supervised learning, which also exploits unlabelled samples in training phase is used. Indeed, unlabelled samples can help to regularize the learning model, yielding an improvement of classification accuracy. In this paper, we propose a new semi-supervised dictionary learning method based on two pillars: on one hand, we enforce manifold structure preservation from the original data into sparse code space using Locally Linear Embedding, which can be considered a regularization of sparse code; on the other hand, we train a semi-supervised classifier in sparse code space. We show that our approach provides an improvement over state-of-the-art semi-supervised dictionary learning methods.
    Keywords Computer Science - Computer Vision and Pattern Recognition
    Subject code 006
    Publishing date 2020-09-13
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

To top