Learning meaningful latent space representations for patient risk stratification: Model development and validation for dengue and other acute febrile illness.

Background: Increased data availability has prompted the creation of clinical decision support systems. These systems utilise clinical information to enhance health care provision, both to predict the likelihood of specific clinical outcomes or evaluate the risk of further complications. However, their adoption remains low due to concerns regarding the quality of recommendations, and a lack of clarity on how results are best obtained and presented. Methods: We used autoencoders capable of reducing the dimensionality of complex datasets in order to produce a 2D representation denoted as latent space to support understanding of complex clinical data. In this output, meaningful representations of individual patient profiles are spatially mapped in an unsupervised manner according to their input clinical parameters. This technique was then applied to a large real-world clinical dataset of over 12,000 patients with an illness compatible with dengue infection in Ho Chi Minh City, Vietnam between 1999 and 2021. Dengue is a systemic viral disease which exerts significant health and economic burden worldwide, and up to 5% of hospitalised patients develop life-threatening complications. Results: The latent space produced by the selected autoencoder aligns with established clinical characteristics exhibited by patients with dengue infection, as well as features of disease progression. Similar clinical phenotypes are represented close to each other in the latent space and clustered according to outcomes broadly described by the World Health Organisation dengue guidelines. Balancing distance metrics and density metrics produced results covering most of the latent space, and improved visualisation whilst preserving utility, with similar patients grouped closer together. In this case, this balance is achieved by using the sigmoid activation function and one hidden layer with three neurons, in addition to the latent dimension layer, which produces the output (Pearson, 0.840; Spearman, 0.830; Procrustes, 0.301; GMM 0.321). Conclusion: This study demonstrates that when adequately configured, autoencoders can produce two-dimensional representations of a complex dataset that conserve the distance relationship between points. The output visualisation groups patients with clinically relevant features closely together and inherently supports user interpretability. Work is underway to incorporate these findings into an electronic clinical decision support system to guide individual patient management.

Metformin as adjunctive therapy for dengue in overweight and obese patients: a protocol for an open-label clinical trial (MeDO).

Background:  Dengue is a disease of major global importance. While most symptomatic infections are mild, a small proportion of patients progress to severe disease with risk of hypovolaemic shock, organ dysfunction and death.  In the absence of effective antiviral or disease modifying drugs, clinical management is solely reliant on supportive measures. Obesity is a growing problem among young people in Vietnam and is increasingly recognised as an important risk factor for severe dengue, likely due to alterations in host immune and inflammatory pathways. Metformin, a widely used anti-hyperglycaemic agent with excellent safety profile, has demonstrated potential as a dengue therapeutic in vitro and in a retrospective observational study of adult dengue patients with type 2 diabetes.  This study aims to assess the safety and tolerability of metformin treatment in overweight and obese dengue patients, and investigate its effects on several clinical, immunological and virological markers of disease severity. Methods: This open label trial of 120 obese/overweight dengue patients will be performed in two phases, with a metformin dose escalation if no safety concerns arise in phase one. The primary endpoint is identification of clinical and laboratory adverse events.  Sixty overweight and obese dengue patients aged 10-30 years will be enrolled at the Hospital for Tropical Diseases in Ho Chi Minh City, Vietnam. Participants will complete a 5-day course of metformin therapy and be compared to a non-treated group of 60 age-matched overweight and obese dengue patients. Discussion:  Previously observed antiviral and immunomodulatory effects of metformin make it a promising dengue therapeutic candidate in appropriately selected patients. This study will assess the safety and tolerability of adjunctive metformin in the management of overweight and obese young dengue patients, as well as its effects on markers of viral replication, endothelial dysfunction and host immune responses.  Trial registration: ClinicalTrials.gov: NCT04377451 (May 6 th 2020).

Expert voices and equal partnerships: establishing Controlled Human Infection Models (CHIMs) in Vietnam.

The number of controlled human infection models (CHIMs) conducted worldwide has increased considerably in recent years, although few have been conducted in low and middle-income countries (LMICs), where infectious diseases have the greatest burden. Recently Oxford University Clinical Research Unit (OUCRU) in Ho Chi Minh City (HCMC) started developing CHIM research proposals motivated by the need to develop a clearer and more grounded understanding of the issues surrounding the conduct of CHIMs in LMICs. To explore initial perceptions and barriers to conducting CHIMs in Vietnam, OUCRU researchers conducted a set of key stakeholder interviews early in 2018 and held a CHIM workshop in HCMC in March 2018. This paper summarizes the discussions from the workshop and outlines a way forward for conducting CHIMs in Vietnam.

Methods to discriminate primary from secondary dengue during acute symptomatic infection.

BACKGROUND: Dengue virus infection results in a broad spectrum of clinical outcomes, ranging from asymptomatic infection through to severe dengue. Although prior infection with another viral serotype, i.e. secondary dengue, is known to be an important factor influencing disease severity, current methods to determine primary versus secondary immune status during the acute illness do not consider the rapidly evolving immune response, and their accuracy has rarely been evaluated against an independent gold standard. METHODS: Two hundred and ninety-three confirmed dengue patients were classified as experiencing primary, secondary or indeterminate infections using plaque reduction neutralisation tests performed 6 months after resolution of the acute illness. We developed and validated regression models to differentiate primary from secondary dengue on multiple acute illness days, using Panbio Indirect IgG and in-house capture IgG and IgM ELISA measurements performed on over 1000 serial samples obtained during acute illness. RESULTS: Cut-offs derived for the various parameters demonstrated progressive change (positively or negatively) by day of illness. Using these time varying cut-offs it was possible to determine whether an infection was primary or secondary on single specimens, with acceptable performance. The model using Panbio Indirect IgG responses and including an interaction with illness day showed the best performance throughout, although with some decline in performance later in infection. Models based on in-house capture IgG levels, and the IgM/IgG ratio, also performed well, though conversely performance improved later in infection. CONCLUSIONS: For all assays, the best fitting models estimated a different cut-off value for different days of illness, confirming how rapidly the immune response changes during acute dengue. The optimal choice of assay will vary depending on circumstance. Although the Panbio Indirect IgG model performs best early on, the IgM/IgG capture ratio may be preferred later in the illness course.

Hemostatic changes in Vietnamese children with mild dengue correlate with the severity of vascular leakage rather than bleeding.

The mechanisms underlying the bleeding manifestations and coagulopathy associated with dengue remain unclear, in part because of the focus of much previous work on severe disease without an appropriate comparison group. We describe detailed clinical and laboratory profiles for a large group of children with dengue of all severities, and a group with similar non-dengue febrile illnesses, all followed prospectively from early presentation through to recovery. Among the dengue-infected patients but not the controls, thrombocytopenia, increased partial thromboplastin times and reduced fibrinogen concentrations were apparent from an early stage, and these abnormalities correlated strongly with the severity and timing of vascular leakage but not bleeding. There was little evidence of procoagulant activation. The findings do not support a primary diagnosis of disseminated intravascular coagulation to explain the intrinsic coagulopathy. An alternative biologically plausible hypothesis is discussed.