ORCID Profile
0000-0002-5888-5660
Current Organisations
The Chinese University of Hong Kong
,
University of Brighton
,
Kwong Wah Hospital
,
Indianna University
,
Hospital Authority
,
Griffiths Univeristy
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Publisher: Elsevier BV
Date: 12-2013
DOI: 10.1016/J.CTIM.2013.09.008
Abstract: To evaluate the sustaining effects of Tai chi Qigong in improving the physiological health for COPD patients at sixth month. A randomized controlled trial. Subjects were in three randomly assigned groups: Tai chi Qigong group, exercise group, and control group. The 206 subjects were recruited from five general outpatient clinics. Tai chi Qigong group completed a 3-month Tai chi Qigong program. Exercise group practiced breathing and walking as an exercise. Control group received usual care. Primary outcomes included six-minute walking distance and lung functions. Secondary outcomes were dyspnea and fatigue levels, number of exacerbations and hospital admissions. Tai chi Qigong group showed a steady improvement in exercise capacity (P<.001) from baseline to the sixth month. The mean walking distance increased from 298 to 349 meters (+17%). No significant changes were noted in the other two groups. Tai chi Qigong group also showed improvement in lung functions (P<.001). Mean forced expiratory volume in 1s increased from .89 to .99l (+11%). No significant change was noted in the exercise group. Deterioration was found in the control group, with mean volume decreased from .89 to .84l (-5.67%). Significant decreased in the number of exacerbations was observed in the Tai chi Qigong group. No changes in dyspnea and fatigue levels were noted among the three groups. Tai chi Qigong has sustaining effects in improving the physiological health and is a useful and appropriate exercise for COPD patients.
Publisher: Oxford University Press (OUP)
Date: 02-2023
Abstract: This paper discusses the rapidly evolving healthcare risk landscape and considers how emerging trends—such as advancement of medical technology, cyber security, pandemic risks, increasing prevalence of noncommunicable health conditions, and the shift towards patient autonomy—are shaping the nature of liabilities faced by doctors and healthcare professionals. Then it discusses practical ways to mitigate clinical risks and resolve the medico-legal claims or inquiries that arise while addressing the role that indemnity providers should play.
Publisher: JMIR Publications Inc.
Date: 17-05-2023
Abstract: nabling a health system to learn from its historical and emerging data is a primary focus of medical AI research. Though digital pathology (DP) hasn’t gained similar popularity as clinical radiology and hospitalization research, its semistructured data drove natural language processing (NLP) to reveal codable insights from textual data. However, obtaining high-quality annotated s les as yet depended on predefined templates or human annotators, which became a bottleneck of automation. We noticed the prolonged undermining of morphology electronic health records (EHR) and its potential to supply high-quality labels and be the stepping stone towards automatic AI and a self-learning system. o develop an annotation-free NLP pipeline with proper human control for auto-deriving precise codes that had been annotated by a health system’s pathologists, text preprocessing, constructing machine learning classifiers to annotate text with clinically precise codes, and enabling system-wide application of the designed NLP pipeline to investigate historical data and enhance health information, promotion, and communication. sing colorectal dysplasia as an ex le, we developed the NLP pipeline with EHR of a population who attended baseline colorectal procedures in Hong Kong’s public health system between 2000 and 2018 when aged 50-75 years. The high-quality morphology codes were precisely-graded dysplasia, where high-grade dysplasia served as the positive label. After identifying precisely-coded, ambiguously-coded, and unlabeled cases from the EHR, we standardized the textual data before feeding them into a bidirectional long short-term memory neural network classification model. Our experimental design examined factors including two kinds of the unit of text analysis (report-/episode-based), the active learning with text curation, and the minimum s le size required for training an accurate classifier. Model performance was measured in testing and validation sets by the area under the receiver operating curve (AUC). ore than 35% of eligible text reports mentioned dysplasia. Precisely-graded dysplasia yielded a low prevalence in morphology codes. Still, the NLP pipeline identified more than 10,000 cases of high-grade dysplasia, which supplied a sufficient amount of positive cases for proving the efficacy of the proposed NLP pipeline. All testing AUCs of report-based active learning with text curation exceeded 0.88. A 200 s le size or more could secure 0.95 testing AUCs with active learning of text curation. Holding other factors the same, validation AUCs were worse than testing AUCs, indicating ambiguously-labeled cases were likely of the complex original text. e demonstrated the feasibility, novel performances, and applications in automating annotation-free NLP pipelines at a system level. Our interdisciplinary pipeline can be a formal standard approach for a health system to realize self-learning from semistructured pathology EHR, with an orientation of precision public health and better person-centric care.
Location: United Kingdom of Great Britain and Northern Ireland
Location: No location found
Location: United Kingdom of Great Britain and Northern Ireland
Location: United Kingdom of Great Britain and Northern Ireland
Location: United Kingdom of Great Britain and Northern Ireland
Location: Australia
Location: United Kingdom of Great Britain and Northern Ireland
Location: United Kingdom of Great Britain and Northern Ireland
No related grants have been discovered for Albert Lee.