Catherine Louise Thwaites

Catherine Louise Thwaites

Auto-generated profile, based on publicly available information

Catherine Louise Thwaites

Oxford University Clinical Research Unit, Ho Chi Minh City, Viet Nam

Research Focus & Metrics

Academic Career Length

24Years (2003-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 April 2019 in The Lancet
Verified
Journal Article
Closed access
LYLam Minh Yen
Lam Minh Yen
CTC Louise Thwaites
C Louise Thwaites

1 January 2015 in The Lancet
Verified
Journal Article
Closed access
CTC Louise Thwaites
C Louise Thwaites
NBNicholas J Beeching
Nicholas J Beeching
CNCharles Newton
Charles Newton

27 September 2024 in Nature Communications
Verified
Journal Article
Open access
PDF file
JYJenny Yang
Jenny Yang
NDNguyen Thanh Dung
Nguyen Thanh Dung
PTPham Ngoc Thach
Pham Ngoc Thach
NPNguyen Thanh Phong
Nguyen Thanh Phong
VPVu Dinh Phu
Vu Dinh Phu
DCDavid Clifton
David Clifton
The integration of artificial intelligence (AI) into healthcare systems within low-middle income countries (LMICs) has emerged as a central focus for various initiatives aiming to improve healthcare access and delivery quality. In contrast to high-income countries (HICs), which often possess the resources and infrastructure to adopt innovative healthcare technologies, LMICs confront resource limitations such as insufficient funding, outdated infrastructure, limited digital data, and a shortage of technical expertise. Consequently, many algorithms initially trained on data from non-LMIC settings are now being employed in LMIC contexts. However, the effectiveness of these systems in LMICs can be compromised when the unique local contexts and requirements are not adequately considered. In this study, we evaluate the feasibility of utilizing models developed in the United Kingdom (a HIC) within hospitals in Vietnam (a LMIC). Consequently, we present and discuss practical methodologies aimed at improving model performance, emphasizing the critical importance of tailoring solutions to the distinct healthcare systems found in LMICs. Our findings emphasize the necessity for collaborative initiatives and solutions that are sensitive to the local context in order to effectively tackle the healthcare challenges that are unique to these regions.

27 April 2020 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Open access
DKDani Kiyasseh
Dani Kiyasseh
GTGirmaw Abebe Tadesse
Girmaw Abebe Tadesse
LNLe Nguyen Thanh Nhan
Le Nguyen Thanh Nhan
LTLe Van Tan
Le Van Tan
LTLouise Thwaites
Louise Thwaites
DCDavid Clifton
David Clifton
The paucity of physiological time-series data collected from low-resource clinical settings limits the capabilities of modern machine learning algorithms in achieving high performance. Such performance is further hindered by class imbalance; datasets where a diagnosis is much more common than others. To overcome these two issues at low-cost while preserving privacy, data augmentation methods can be employed. In the time domain, the traditional method of time-warping could alter the underlying data distribution with detrimental consequences. This is prominent when dealing with physiological conditions that influence the frequency components of data. In this paper, we propose PlethAugment; three different conditional generative adversarial networks (CGANs) with an adapted diversity term for the generation of pathological photoplethysmogram (PPG) signals in order to boost medical classification performance. To evaluate and compare the GANs, we introduce a novel metric-agnostic method; the synthetic generalization curve. We validate this approach on two proprietary and two public datasets representing a diverse set of medical conditions. Compared to training on non-augmented class-balanced datasets, training on augmented datasets leads to an improvement of the AUROC by up to 29% when using cross validation. This illustrates the potential of the proposed CGANs to significantly improve classification performance.

18 January 2003 in BMJ
Verified
Journal Article
Open access
PDF file
CTC L Thwaites
C L Thwaites
JFJ J Farrar
J J Farrar
Footnotes Competing interests None declared.

1 March 2019 in International Journal of Infectious Diseases
Verified
Journal Article
Open access
MHMinh Tu Van Hoang
Minh Tu Van Hoang
TNTo Anh Nguyen
To Anh Nguyen
TTTan Thanh Tran
Tan Thanh Tran
TVThi Ty Hang Vu
Thi Ty Hang Vu
NLNguyen Truc Nhu Le
Nguyen Truc Nhu Le
HDH Rogier van Doorn
H Rogier van Doorn
Hand, foot and mouth disease (HFMD) has been associated with large outbreaks among young children in the Asia-Pacific Region since 1997, including cases of severe illness and death. Severe illness is often associated with enterovirus A71 (EV-A71). Vietnam experienced a large sustained outbreak of 200000 hospitalized cases and over 200 deaths in 2011-12, the large majority occurring in southern Vietnam. A prospective observational study was conducted in the outpatient clinics, infectious diseases wards, and paediatric intensive care units of the three main referral centres for the treatment of HFMD in southern Vietnam. Demographic data, basic laboratory parameters, and clinical data were recorded, and molecular diagnostic tests were performed. Between July 2013 and July 2015, a total of 1547 children were enrolled. Four serotypes of enterovirus A (EV-A71, Coxsackievirus (CV) A6, A10, and A16) were responsible for 1005 of 1327 diagnosed cases (75.7%). An unexpected dominance of EV-A71 was found among both inpatients and outpatients, as well as a strong association with severe illness. CV-A6 and CV-A10 emerged in Vietnam during the study period and replaced CV-A16. CV-A10 was associated with different clinical and laboratory characteristics. During admission, 119 children developed a more severe illness. It was found that children with a skin rash showed less progression of severity, but when a rash was present, a macular rash was significantly associated with an increased risk of progression. This study represents the most comprehensive descriptive HFMD study from Vietnam to date. Co-circulation and replacement of different serotypes has implications for vaccine development and implementation. These findings from a severely affected country add to our understanding of the presentation, progression, and aetiology of HFMD.