Related references
Note: Only part of the references are listed.
Review
Medical Informatics
Raphael Henshaw Ekpo et al.
Summary: Machine learning is an automated modeling method in data analysis that allows for the discovery of insights from large datasets without explicit programming. This study aims to explore machine learning strategies to address the weaknesses of existing asthma prediction models in children and summarize the current models. The results reveal that the existing models have limitations in decision support, clinical impact, and predictive accuracy. ANN and SVM algorithms perform best in the prediction of pediatric asthma.
HEALTH AND TECHNOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Rotem Haba et al.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Review
Respiratory System
Shiqiu Xiong et al.
Summary: This systematic review and meta-analysis aimed to evaluate the prediction performance of machine learning-based models for predicting asthma exacerbations. The study found that machine learning has great potential in predicting asthma exacerbations, but there is heterogeneity in the methodology of these models.
BMC PULMONARY MEDICINE
(2023)
Editorial Material
Economics
Ahmad Z. Al Meslamani
JOURNAL OF MEDICAL ECONOMICS
(2023)
Review
Social Issues
Ahmed Zahlan et al.
Summary: Artificial intelligence (AI) innovation in healthcare is a significant area of research. A systematic literature review of 378 published studies on AI innovation in healthcare was conducted to identify research directions focusing on the most crucial AI-based healthcare applications, challenges associated with AI integration in healthcare, and student adoption of AI in healthcare curricula. An exploratory study of over 2700 AI-enabled healthcare startups worldwide was also conducted. The gaps identified and future research directions proposed in this study will contribute to the development of legislation that promotes the adoption of AI in healthcare.
TECHNOLOGY IN SOCIETY
(2023)
Review
Business
Omar Ali et al.
Summary: The use of AI systems is leading to rapid changes in the administrative and medical processes of healthcare organizations, particularly in the field of early detection and diagnosis. Studies have shown that AI can improve the quality of healthcare services and enhance human life in various ways. This study provides a systematic review of academic articles on the application of AI in the healthcare sector, presenting a classification framework based on four dimensions: AI-enabled healthcare benefits, challenges, methodologies, and functionalities.
JOURNAL OF INNOVATION & KNOWLEDGE
(2023)
Article
Medicine, General & Internal
Jesus Gomez Rossi et al.
Article
Respiratory System
Susanne J. van de Hei et al.
Summary: This study aims to investigate the effectiveness of a smart inhaler asthma self-management programme on medication adherence and clinical outcomes in adults with uncontrolled asthma, to evaluate its acceptability. The research will be carried out with an open-label cluster randomised controlled trial of 12 months to study the impact of smart inhaler programmes on medication adherence and asthma control.
BMJ OPEN RESPIRATORY RESEARCH
(2022)
Article
Allergy
Jesus Lopez-Tiro et al.
Summary: The economic impact and treatment outcomes of severe asthma in Mexico have not been assessed. A study of 60 patients found that the cost per patient and the number of exacerbations were higher in the uncontrolled severe asthma (UCSA) group compared to the controlled severe asthma (CSA) group, with a positive association between cost and exacerbations.
WORLD ALLERGY ORGANIZATION JOURNAL
(2022)
Article
Cell Biology
Anuradha Ray et al.
Summary: There is an unprecedented opportunity to accurately diagnose and manage asthma by using machine learning to integrate high-dimensional molecular data with clinical characteristics. Asthma is a complex and heterogeneous disease that cannot be solely explained by an abnormal T2 immune response. Integrating multi-omics asthma datasets and clinical data is necessary to understand asthma heterogeneity.
CELL REPORTS MEDICINE
(2022)
Article
Critical Care Medicine
Joe G. Zein et al.
Summary: Machine learning models built with outpatient data accurately predicted asthma exacerbations and severity, enhancing the quality of outpatient care and preventing adverse outcomes.
Article
Health Care Sciences & Services
Nicole M. Thomasian et al.
Summary: This article discusses the issue of bias in healthcare artificial intelligence, emphasizing the need for consensus at the policy level to regulate algorithmic bias and ensure their ethical integration into the health system.
JOURNAL OF PUBLIC HEALTH POLICY
(2021)
Article
Medicine, General & Internal
Andrew S. Tseng et al.
Summary: The study evaluated the cost-effectiveness of an artificial intelligence electrocardiogram algorithm for universal screening at age 65, finding it cost-effective in various clinical scenarios but sensitive to test performance, disease characteristics, and testing costs. Further research on disease progression and treatment, as well as external validation of the AI-ECG, is recommended to improve cost-effectiveness modeling.
MAYO CLINIC PROCEEDINGS
(2021)
Review
Respiratory System
Konstantinos P. Exarchos et al.
EUROPEAN RESPIRATORY JOURNAL
(2020)
Article
Oncology
Gang Yu et al.
ANNALS OF TRANSLATIONAL MEDICINE
(2020)
Article
Public, Environmental & Occupational Health
Eduardo Costa et al.
REVISTA DE SAUDE PUBLICA
(2018)
Article
Respiratory System
Tursynbek Nurmagambetov et al.
ANNALS OF THE AMERICAN THORACIC SOCIETY
(2018)
