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.

Early diagnostic indicators of dengue versus other febrile illnesses in Asia and Latin America (IDAMS study): a multicentre, prospective, observational study.

BACKGROUND: Improvements in the early diagnosis of dengue are urgently needed, especially in resource-limited settings where the distinction between dengue and other febrile illnesses is crucial for patient management. METHODS: In this prospective, observational study (IDAMS), we included patients aged 5 years and older with undifferentiated fever at presentation from 26 outpatient facilities in eight countries (Bangladesh, Brazil, Cambodia, El Salvador, Indonesia, Malaysia, Venezuela, and Viet Nam). We used multivariable logistic regression to investigate the association between clinical symptoms and laboratory tests with dengue versus other febrile illnesses between day 2 and day 5 after onset of fever (ie, illness days). We built a set of candidate regression models including clinical and laboratory variables to reflect the need of a comprehensive versus parsimonious approach. We assessed performance of these models via standard measures of diagnostic values. FINDINGS: Between Oct 18, 2011, and Aug 4, 2016, we recruited 7428 patients, of whom 2694 (36%) were diagnosed with laboratory-confirmed dengue and 2495 (34%) with (non-dengue) other febrile illnesses and met inclusion criteria, and were included in the analysis. 2703 (52%) of 5189 included patients were younger than 15 years, 2486 (48%) were aged 15 years or older, 2179 (42%) were female and 3010 (58%) were male. Platelet count, white blood cell count, and the change in these variables from the previous day of illness had a strong association with dengue. Cough and rhinitis had strong associations with other febrile illnesses, whereas bleeding, anorexia, and skin flush were generally associated with dengue. Model performance increased between day 2 and 5 of illness. The comprehensive model (18 clinical and laboratory predictors) had sensitivities of 0·80 to 0·87 and specificities of 0·80 to 0·91, whereas the parsimonious model (eight clinical and laboratory predictors) had sensitivities of 0·80 to 0·88 and specificities of 0·81 to 0·89. A model that includes laboratory markers that are easy to measure (eg, platelet count or white blood cell count) outperformed the models based on clinical variables only. INTERPRETATION: Our results confirm the important role of platelet and white blood cell counts in diagnosing dengue, and the importance of serial measurements over subsequent days. We successfully quantified the performance of clinical and laboratory markers covering the early period of dengue. Resulting algorithms performed better than published schemes for distinction of dengue from other febrile illnesses, and take into account the dynamic changes over time. Our results provide crucial information needed for the update of guidelines, including the Integrated Management of Childhood Illness handbook. FUNDING: EU's Seventh Framework Programme. TRANSLATIONS: For the Bangla, Bahasa Indonesia, Portuguese, Khmer, Spanish and Vietnamese translations of the abstract see Supplementary Materials section.

Clinical prognostic models for severe dengue: a systematic review protocol.

Background: Dengue is a common mosquito-borne, with high morbidity rates recorded in the annual. Dengue contributes to a major disease burden in many tropical countries. This demonstrates the urgent need in developing effective approaches to identify severe cases early. For this purpose, many multivariable prognostic models using multiple prognostic variables were developed to predict the risk of progression to severe outcomes. The aim of the planned systematic review is to identify and describe the existing clinical multivariable prognostic models for severe dengue as well as examine the possibility of combining them. These findings will suggest directions for further research of this field. Methods: This protocol has followed the guidelines of the Preferred Reporting Items for Systematic Reviews and Meta - Analyses Protocol (PRISMA-P). We will conduct a comprehensive search of Pubmed, Embase, and Web of Science. Eligibility criteria include being published in peer-review journals, focusing on human subjects and developing the multivariable prognostic model for severe dengue, without any restriction on language, location and period of publication, and study design. The reference list will be captured and removed from duplications. We will use the Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies (CHARMS) checklist to extract data and Prediction study risk of bias assessment tool (PROBAST) to assess the study quality. Discussion: This systematic review will describe the existing prediction models, summarize the current status of prognostic research on dengue, and report the possibility to combine the models to optimize the power of each paradigm. PROSPERO registration: CRD42018102907.

Factors associated with a low prevalence of exclusive breastfeeding during hospital stay in urban and semi-rural areas of southern Vietnam.

BACKGROUND: There is a paucity of data regarding risk factors associated with suboptimal breastfeeding practices in urbanized areas of low-middle income countries (LMICs). METHODS: Through a large prospective birth cohort, which enrolled 6706 infants in Vietnam between 2009 and 2013, we investigated the practice of exclusive breastfeeding during hospital stay in urban and semi-rural populations and aimed to identify factors associated with suboptimal breastfeeding practices. Univariate and multivariable logistic regression were performed to determine factors associated with not exclusive breastfeeding during hospital stay. RESULTS: Of 6076 mothers, 33% (2187) breastfed their infant exclusively before hospital discharge; 9% (364/4248) in urban and 74% (1823/2458) in semi-rural areas. Exclusive breastfeeding up to 4 months was recorded in 15% (959/6210) of participants; this declined to < 1% (56/6093) at 6 months. Delivery by Caesarean section (Odds Ratio [OR] 0.07; 95% Confidence Interval [CI] 0.04, 0.11 and OR 0.05; 95% CI 0.03, 0.08) and neonatal complications (OR 0.2; 95% CI 0.07, 0.47 and OR 0.25; 95% CI 0.14, 0.46) were common and highly significant risk factors associated with a lack of exclusive breastfeeding during hospital stay in urban and semi-rural settings, respectively. CONCLUSIONS: To our knowledge, this is the first large-scale investigation aimed at identifying factors associated with exclusive breastfeeding during hospital stay in Vietnam. Breastfeeding promotion strategies should prioritize common risk factors in hospital, such as Caesarean section and neonatal complications, and other location specific factors associated with socioeconomics.

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.

Corticosteroids for dengue - why don't they work?

BACKGROUND: Dysregulated immune responses may contribute to the clinical complications that occur in some patients with dengue. FINDINGS: In Vietnamese pediatric dengue cases randomized to early prednisolone therapy, 81 gene-transcripts (0.2% of the 47,231 evaluated) were differentially abundant in whole-blood between high-dose (2 mg/kg) prednisolone and placebo-treated patients two days after commencing therapy. Prominent among the 81 transcripts were those associated with T and NK cell cytolytic functions. Additionally, prednisolone therapy was not associated with changes in plasma cytokine levels. CONCLUSION: The inability of prednisolone treatment to markedly attenuate the host immune response is instructive for planning future therapeutic strategies for dengue.