CURATE.AI-assisted dose titration for anti-hypertensive personalized therapy: study protocol for a multi-arm, randomized, pilot feasibility trial using CURATE.AI (CURATE.AI ADAPT trial).

Aims: Artificial intelligence-driven small data platforms such as CURATE.AI hold potential for personalized hypertension care by assisting physicians in identifying personalized anti-hypertensive doses for titration. This trial aims to assess the feasibility of a larger randomized controlled trial (RCT), evaluating the efficacy of CURATE.AI-assisted dose titration intervention. We will also collect preliminary efficacy and safety data and explore stakeholder feedback in the early design process. Methods and results: In this open-label, randomized, pilot feasibility trial, we aim to recruit 45 participants with primary hypertension. Participants will be randomized in 1:1:1 ratio into control (no intervention), home blood pressure monitoring (active control; HBPM), or CURATE.AI arms (intervention; HBPM and CURATE.AI-assisted dose titration). The home treatments include 1 month of two-drug anti-hypertensive regimens. Primary endpoints assess the logistical (e.g. dose adherence) and scientific (e.g. percentage of participants for which CURATE.AI profiles can be generated) feasibility, and define the progression criteria for the RCT in a 'traffic light system'. Secondary endpoints assess preliminary efficacy [e.g. mean change in office blood pressures (BPs)] and safety (e.g. hospitalization events) associated with each treatment protocol. Participants with both baseline and post-treatment BP measurements will form the intent-to-treat analysis. Following their involvement with the CURATE.AI intervention, feedback from CURATE.AI participants and healthcare providers will be collected via exit survey and interviews. Conclusion: Findings from this study will inform about potential refinements of the current treatment protocols before proceeding with a larger RCT, or potential expansion to collect additional information. Positive results may suggest the potential efficacy of CURATE.AI to improve BP control. Trial registration number: NCT05376683.

Platform for the interdisciplinary study of cardiovascular, metabolic and neurovascular diseases (PICMAN) protocol.

Through extensive multisystem phenotyping, the central aim of Project PICMAN is to correlate metabolic flexibility to measures of cardiometabolic health, including myocardial diastolic dysfunction, coronary and cerebral atherosclerosis, body fat distribution and severity of non-alcoholic fatty liver disease. This cohort will form the basis of larger interventional trials targeting metabolic inflexibility in the prevention of cardiovascular disease. Participants aged 21-72 years with no prior manifest atherosclerotic cardiovascular disease (ASCVD) are being recruited from a preventive cardiology clinic and an existing cohort of non-alcoholic fatty liver disease (NAFLD) in an academic medical centre. A total of 120 patients will be recruited in the pilot phase of this study and followed up for 5 years. Those with 10-year ASCVD risk ≥ 5% as per the QRISK3 calculator are eligible. Those with established diabetes mellitus are excluded. Participants recruited undergo a detailed assessment of health behaviours and physical measurements. Participants also undergo a series of multimodality clinical phenotyping comprising cardiac tests, vascular assessments, metabolic tests, liver and neurovascular testing. Blood samples are also being collected and banked for plasma biomarkers, 'multi-omics analyses' and for generation of induced pluripotent stem cells (iPSC). Extensive evidence points to metabolic dysregulation as an early precursor of cardiovascular disease, particularly in Asia. We hypothesise that quantifiable metabolic inflexibility may be representative of an individual in his/her silent, but high-risk progression towards insulin resistance, diabetes and cardiovascular disease. The platform for interdisciplinary cardiovascular-metabolic-neurovascular diseases (PICMAN) is a pilot, prospective, multi-ethnic cohort study.

Illness severity assessment of older adults in critical illness using machine learning (ELDER-ICU): an international multicentre study with subgroup bias evaluation.

BACKGROUND: Comorbidity, frailty, and decreased cognitive function lead to a higher risk of death in elderly patients (more than 65 years of age) during acute medical events. Early and accurate illness severity assessment can support appropriate decision making for clinicians caring for these patients. We aimed to develop ELDER-ICU, a machine learning model to assess the illness severity of older adults admitted to the intensive care unit (ICU) with cohort-specific calibration and evaluation for potential model bias. METHODS: In this retrospective, international multicentre study, the ELDER-ICU model was developed using data from 14 US hospitals, and validated in 171 hospitals from the USA and Netherlands. Data were extracted from the Medical Information Mart for Intensive Care database, electronic ICU Collaborative Research Database, and Amsterdam University Medical Centers Database. We used six categories of data as predictors, including demographics and comorbidities, physical frailty, laboratory tests, vital signs, treatments, and urine output. Patient data from the first day of ICU stay were used to predict in-hospital mortality. We used the eXtreme Gradient Boosting algorithm (XGBoost) to develop models and the SHapley Additive exPlanations method to explain model prediction. The trained model was calibrated before internal, external, and temporal validation. The final XGBoost model was compared against three other machine learning algorithms and five clinical scores. We performed subgroup analysis based on age, sex, and race. We assessed the discrimination and calibration of models using the area under receiver operating characteristic (AUROC) and standardised mortality ratio (SMR) with 95% CIs. FINDINGS: Using the development dataset (n=50 366) and predictive model building process, the XGBoost algorithm performed the best in all types of validations compared with other machine learning algorithms and clinical scores (internal validation with 5037 patients from 14 US hospitals, AUROC=0·866 [95% CI 0·851-0·880]; external validation in the US population with 20 541 patients from 169 hospitals, AUROC=0·838 [0·829-0·847]; external validation in European population with 2411 patients from one hospital, AUROC=0·833 [0·812-0·853]; temporal validation with 4311 patients from one hospital, AUROC=0·884 [0·869-0·897]). In the external validation set (US population), the median AUROCs of bias evaluations covering eight subgroups were above 0·81, and the overall SMR was 0·99 (0·96-1·03). The top ten risk predictors were the minimum Glasgow Coma Scale score, total urine output, average respiratory rate, mechanical ventilation use, best state of activity, Charlson Comorbidity Index score, geriatric nutritional risk index, code status, age, and maximum blood urea nitrogen. A simplified model containing only the top 20 features (ELDER-ICU-20) had similar predictive performance to the full model. INTERPRETATION: The ELDER-ICU model reliably predicts the risk of in-hospital mortality using routinely collected clinical features. The predictions could inform clinicians about patients who are at elevated risk of deterioration. Prospective validation of this model in clinical practice and a process for continuous performance monitoring and model recalibration are needed. FUNDING: National Institutes of Health, National Natural Science Foundation of China, National Special Health Science Program, Health Science and Technology Plan of Zhejiang Province, Fundamental Research Funds for the Central Universities, Drug Clinical Evaluate Research of Chinese Pharmaceutical Association, and National Key R&D Program of China.

Clinically Interpretable Machine Learning Models for Early Prediction of Mortality in Older Patients with Multiple Organ Dysfunction Syndrome: An International Multicenter Retrospective Study.

BACKGROUND: Multiple organ dysfunction syndrome (MODS) is associated with a high risk of mortality among older patients. Current severity scores are limited in their ability to assist clinicians with triage and management decisions. We aim to develop mortality prediction models for older patients with MODS admitted to the ICU. METHODS: The study analyzed older patients from 197 hospitals in the United States and 1 hospital in the Netherlands. The cohort was divided into the young-old (65-80 years) and old-old (≥80 years), which were separately used to develop and evaluate models including internal, external, and temporal validation. Demographic characteristics, comorbidities, vital signs, laboratory measurements, and treatments were used as predictors. We used the XGBoost algorithm to train models, and the SHapley Additive exPlanations (SHAP) method to interpret predictions. RESULTS: Thirty-four thousand four hundred and ninety-seven young-old (11.3% mortality) and 21 330 old-old (15.7% mortality) patients were analyzed. Discrimination AUROC of internal validation models in 9 046 U.S. patients was as follows: 0.87 and 0.82, respectively; discrimination of external validation models in 1 905 EUR patients was as follows: 0.86 and 0.85, respectively; and discrimination of temporal validation models in 8 690 U.S. patients: 0.85 and 0.78, respectively. These models outperformed standard clinical scores like Sequential Organ Failure Assessment and Acute Physiology Score III. The Glasgow Coma Scale, Charlson Comorbidity Index, and Code Status emerged as top predictors of mortality. CONCLUSIONS: Our models integrate data spanning physiologic and geriatric-relevant variables that outperform existing scores used in older adults with MODS, which represents a proof of concept of how machine learning can streamline data analysis for busy ICU clinicians to potentially optimize prognostication and decision making.

Developing and Validating Multi-Modal Models for Mortality Prediction in COVID-19 Patients: a Multi-center Retrospective Study.

The unprecedented global crisis brought about by the COVID-19 pandemic has sparked numerous efforts to create predictive models for the detection and prognostication of SARS-CoV-2 infections with the goal of helping health systems allocate resources. Machine learning models, in particular, hold promise for their ability to leverage patient clinical information and medical images for prediction. However, most of the published COVID-19 prediction models thus far have little clinical utility due to methodological flaws and lack of appropriate validation. In this paper, we describe our methodology to develop and validate multi-modal models for COVID-19 mortality prediction using multi-center patient data. The models for COVID-19 mortality prediction were developed using retrospective data from Madrid, Spain (N = 2547) and were externally validated in patient cohorts from a community hospital in New Jersey, USA (N = 242) and an academic center in Seoul, Republic of Korea (N = 336). The models we developed performed differently across various clinical settings, underscoring the need for a guided strategy when employing machine learning for clinical decision-making. We demonstrated that using features from both the structured electronic health records and chest X-ray imaging data resulted in better 30-day mortality prediction performance across all three datasets (areas under the receiver operating characteristic curves: 0.85 (95% confidence interval: 0.83-0.87), 0.76 (0.70-0.82), and 0.95 (0.92-0.98)). We discuss the rationale for the decisions made at every step in developing the models and have made our code available to the research community. We employed the best machine learning practices for clinical model development. Our goal is to create a toolkit that would assist investigators and organizations in building multi-modal models for prediction, classification, and/or optimization.

Delirium prediction in the ICU: designing a screening tool for preventive interventions.

Introduction: Delirium occurrence is common and preventive strategies are resource intensive. Screening tools can prioritize patients at risk. Using machine learning, we can capture time and treatment effects that pose a challenge to delirium prediction. We aim to develop a delirium prediction model that can be used as a screening tool. Methods: From the eICU Collaborative Research Database (eICU-CRD) and the Medical Information Mart for Intensive Care version III (MIMIC-III) database, patients with one or more Confusion Assessment Method-Intensive Care Unit (CAM-ICU) values and intensive care unit (ICU) length of stay greater than 24 h were included in our study. We validated our model using 21 quantitative clinical parameters and assessed performance across a range of observation and prediction windows, using different thresholds and applied interpretation techniques. We evaluate our models based on stratified repeated cross-validation using 3 algorithms, namely Logistic Regression, Random Forest, and Bidirectional Long Short-Term Memory (BiLSTM). BiLSTM represents an evolution from recurrent neural network-based Long Short-Term Memory, and with a backward input, preserves information from both past and future. Model performance is measured using Area Under Receiver Operating Characteristic, Area Under Precision Recall Curve, Recall, Precision (Positive Predictive Value), and Negative Predictive Value metrics. Results: We evaluated our results on 16 546 patients (47% female) and 6294 patients (44% female) from eICU-CRD and MIMIC-III databases, respectively. Performance was best in BiLSTM models where, precision and recall changed from 37.52% (95% confidence interval [CI], 36.00%-39.05%) to 17.45 (95% CI, 15.83%-19.08%) and 86.1% (95% CI, 82.49%-89.71%) to 75.58% (95% CI, 68.33%-82.83%), respectively as prediction window increased from 12 to 96 h. After optimizing for higher recall, precision and recall changed from 26.96% (95% CI, 24.99%-28.94%) to 11.34% (95% CI, 10.71%-11.98%) and 93.73% (95% CI, 93.1%-94.37%) to 92.57% (95% CI, 88.19%-96.95%), respectively. Comparable results were obtained in the MIMIC-III cohort. Conclusions: Our model performed comparably to contemporary models using fewer variables. Using techniques like sliding windows, modification of threshold to augment recall and feature ranking for interpretability, we addressed shortcomings of current models.

Prediction of blood lactate values in critically ill patients: a retrospective multi-center cohort study.

Elevations in initially obtained serum lactate levels are strong predictors of mortality in critically ill patients. Identifying patients whose serum lactate levels are more likely to increase can alert physicians to intensify care and guide them in the frequency of tending the blood test. We investigate whether machine learning models can predict subsequent serum lactate changes. We investigated serum lactate change prediction using the MIMIC-III and eICU-CRD datasets in internal as well as external validation of the eICU cohort on the MIMIC-III cohort. Three subgroups were defined based on the initial lactate levels: (i) normal group (< 2 mmol/L), (ii) mild group (2-4 mmol/L), and (iii) severe group (> 4 mmol/L). Outcomes were defined based on increase or decrease of serum lactate levels between the groups. We also performed sensitivity analysis by defining the outcome as lactate change of > 10% and furthermore investigated the influence of the time interval between subsequent lactate measurements on predictive performance. The LSTM models were able to predict deterioration of serum lactate values of MIMIC-III patients with an AUC of 0.77 (95% CI 0.762-0.771) for the normal group, 0.77 (95% CI 0.768-0.772) for the mild group, and 0.85 (95% CI 0.840-0.851) for the severe group, with only a slightly lower performance in the external validation. The LSTM demonstrated good discrimination of patients who had deterioration in serum lactate levels. Clinical studies are needed to evaluate whether utilization of a clinical decision support tool based on these results could positively impact decision-making and patient outcomes.

Prediction of in-hospital mortality of Clostriodiodes difficile infection using critical care database: a big data-driven, machine learning approach.

RESEARCH OBJECTIVES: Clostriodiodes difficile infection (CDI) is a major cause of healthcare-associated diarrhoea with high mortality. There is a lack of validated predictors for severe outcomes in CDI. The aim of this study is to derive and validate a clinical prediction tool for CDI in-hospital mortality using a large critical care database. METHODOLOGY: The demographics, clinical parameters, laboratory results and mortality of CDI were extracted from the Medical Information Mart for Intensive Care-III (MIMIC-III) database. We subsequently trained three machine learning models: logistic regression (LR), random forest (RF) and gradient boosting machine (GBM) to predict in-hospital mortality. The individual performances of the models were compared against current severity scores (Clostridiodes difficile Associated Risk of Death Score (CARDS) and ATLAS (Age, Treatment with systemic antibiotics, leukocyte count, Albumin and Serum creatinine as a measure of renal function) by calculating area under receiver operating curve (AUROC). We identified factors associated with higher mortality risk in each model. SUMMARY OF RESULTS: From 61 532 intensive care unit stays in the MIMIC-III database, there were 1315 CDI cases. The mortality rate for CDI in the study cohort was 18.33%. AUROC was 0.69 (95% CI, 0.60 to 0.76) for LR, 0.71 (95% CI, 0.62 to 0.77) for RF and 0.72 (95% CI, 0.64 to 0.78) for GBM, while previously AUROC was 0.57 (95% CI, 0.51 to 0.65) for CARDS and 0.63 (95% CI, 0.54 to 0.70) for ATLAS. Albumin, lactate and bicarbonate were significant mortality factors for all the models. Free calcium, potassium, white blood cell, urea, platelet and mean blood pressure were present in at least two of the three models. CONCLUSION: Our machine learning derived CDI in-hospital mortality prediction model identified pertinent factors that can assist critical care clinicians in identifying patients at high risk of dying from CDI.

Varying association of laboratory values with reference ranges and outcomes in critically ill patients: an analysis of data from five databases in four countries across Asia, Europe and North America.

BACKGROUND: Despite wide usage across all areas of medicine, it is uncertain how useful standard reference ranges of laboratory values are for critically ill patients. OBJECTIVES: The aim of this study is to assess the distributions of standard laboratory measurements in more than 330 selected intensive care units (ICUs) across the USA, Amsterdam, Beijing and Tarragona; compare differences and similarities across different geographical locations and evaluate how they may be associated with differences in length of stay (LOS) and mortality in the ICU. METHODS: A multi-centre, retrospective, cross-sectional study of data from five databases for adult patients first admitted to an ICU between 2001 and 2019 was conducted. The included databases contained patient-level data regarding demographics, interventions, clinical outcomes and laboratory results. Kernel density estimation functions were applied to the distributions of laboratory tests, and the overlapping coefficient and Cohen standardised mean difference were used to quantify differences in these distributions. RESULTS: The 259 382 patients studied across five databases in four countries showed a high degree of heterogeneity with regard to demographics, case mix, interventions and outcomes. A high level of divergence in the studied laboratory results (creatinine, haemoglobin, lactate, sodium) from the locally used reference ranges was observed, even when stratified by outcome. CONCLUSION: Standardised reference ranges have limited relevance to ICU patients across a range of geographies. The development of context-specific reference ranges, especially as it relates to clinical outcomes like LOS and mortality, may be more useful to clinicians.

A Weakly-Supervised Named Entity Recognition Machine Learning Approach for Emergency Medical Services Clinical Audit.

Clinical performance audits are routinely performed in Emergency Medical Services (EMS) to ensure adherence to treatment protocols, to identify individual areas of weakness for remediation, and to discover systemic deficiencies to guide the development of the training syllabus. At present, these audits are performed by manual chart review, which is time-consuming and laborious. In this paper, we report a weakly-supervised machine learning approach to train a named entity recognition model that can be used for automatic EMS clinical audits. The dataset used in this study contained 58,898 unlabeled ambulance incidents encountered by the Singapore Civil Defence Force from 1st April 2019 to 30th June 2019. With only 5% labeled data, we successfully trained three different models to perform the NER task, achieving F1 scores of around 0.981 under entity type matching evaluation and around 0.976 under strict evaluation. The BiLSTM-CRF model was 1~2 orders of magnitude lighter and faster than our BERT-based models. Our proposed proof-of-concept approach may improve the efficiency of clinical audits and can also help with EMS database research. Further external validation of this approach is needed.

Factors influencing protective behaviours during haze episodes in Singapore: A population-based study.

INTRODUCTION: Haze is a recurrent problem in Southeast Asia. Exposure to haze is linked to ophthalmic, respiratory and cardiovascular diseases, and mortality. In this study, we investigated the role of demographic factors, knowledge and perceived risk in influencing protective behaviours during the 2013 haze in Singapore. METHODS: We evaluated 696 adults in a cross-sectional study. Participants were sampled via a 2-stage simple random sampling without replacement from a large residential district in Singapore in 2015. The questionnaire measured the participant's knowledge, perceived risk and behaviours during the Southeast Asian haze crisis in 2013. Reliability and validity of the questionnaire were assessed using comparative fit index (≥0.96) and root mean square error of approximation (≤0.05). We performed structural equation modelling to examine the relationship between the hypothesised factors and protective behaviours. RESULTS: More than 95% of the individuals engaged in at least 1 form of protective behaviour. Knowledge was strongly associated with protective behaviours via direct effect (ß=0.45, 95% CI 0.19-0.69, P<0.001) and indirect effect through perceived risk (ß=0.18, 95% CI 0.07-0.31, P=0.002). Perceived risk was associated with protective behaviours (ß=0.28, 95% CI:0.11-0.44, P=0.002). A lower household income and ethnic minority were associated with protective behaviours. A lower education level and smokers were associated with lower knowledge of haze. A higher education and ethnic minority were associated with a lower perceived risk. Wearing of N95 masks was associated with other haze-related protective behaviours (ß=0.24, 95% CI 0.08-0.37, P=0.001). CONCLUSION: Knowledge was associated with protective behaviours, suggesting the importance of public education. Efforts should target those of lower education level and smokers. The wearing of N95 masks correlates with uptake of other protective behaviours.

Use of Technology to Aid Clinical Audit in an Asian Emergency Medical Services Department.

Although clinical audit is generally accepted to be an essential part of quality review and continuous quality improvement, there are limited reports on and several barriers to the implementation of effective clinical audit in an emergency medicine services (EMS) organization. The barriers include the significant amount of time, resources, and effort often required to conduct the audit. In this paper, we present a technology-enabled clinical audit tool, termed Medical Service Transformation and Innovation Compass (MYSTIC), which has transformed the way the clinical audit is performed in our EMS department. MYSTIC is a Python program we developed in-house, that extracts data from data fields found in routine ambulance case records maintained by our paramedics, and automatically assigns "pass" or "fail" flags based on pre-defined audit criteria. Compared to previous manual auditing, implementation of the MYSTIC computerized audit system increased the coverage of cases undergoing audit from 10% to 100% of all EMS-attended cases, and we were able to promptly identify and address some deficits in training and knowledge amongst our paramedics.

Predicting mortality, thrombus recurrence and persistence in patients with post-acute myocardial infarction left ventricular thrombus.

Left ventricular thrombus (LVT) is a common complication of acute myocardial infarction and is associated with morbidity from embolic complications. Predicting which patients will develop death or persistent LVT despite anticoagulation may help clinicians identify high-risk patients. We developed a random forest (RF) model that predicts death or persistent LVT and evaluated its performance. This was a single-center retrospective cohort study in an academic tertiary center. We included 244 patients with LVT in our study. Patients who did not receive anticoagulation (n = 8) or had unknown (n = 31) outcomes were excluded. The primary outcome was a composite outcome of death, recurrent LVT and persistent LVT. We selected a total of 31 predictors collected at the point of LVT diagnosis based on clinical relevance. We compared conventional regularized logistic regression with the RF algorithm. There were 156 patients who had resolution of LVT and 88 patients who experienced the composite outcome. The RF model achieved better performance and had an AUROC of 0.700 (95% CI 0.553-0.863) on a validation dataset. The most important predictors for the composite outcome were receiving a revascularization procedure, lower visual ejection fraction (EF), higher creatinine, global wall motion abnormality, higher prothrombin time, higher body mass index, higher activated partial thromboplastin time, older age, lower lymphocyte count and higher neutrophil count. The RF model accurately identified patients with post-AMI LVT who developed the composite outcome. Further studies are needed to validate its use in clinical practice.

Predicting Clinical Outcomes in Acute Ischemic Stroke Patients Undergoing Endovascular Thrombectomy with Machine Learning : A Systematic Review and Meta-analysis.

PURPOSE: Conventional predictive models are based on a combination of clinical and neuroimaging parameters using traditional statistical approaches. Emerging studies have shown that the machine learning (ML) prediction models with multiple pretreatment clinical variables have the potential to accurately prognosticate the outcomes in acute ischemic stroke (AIS) patients undergoing thrombectomy, and hence identify patients suitable for thrombectomy. This article summarizes the published studies on ML models in large vessel occlusion AIS patients undergoing thrombectomy. METHODS: We searched electronic databases including PubMed from 1 January 2000 up to 14 October 2019 for studies that evaluated ML algorithms for the prediction of outcomes in stroke patients undergoing thrombectomy. We then used random-effects bivariate meta-analysis models to summarize the studies. RESULTS: We retained a total of five studies that evaluated ML (4 support vector machine, 1 decision tree model) with a combined cohort of 802 patients. The prevalence of good functional outcome defined by 90-day mRS of 0-2 when available. Random effects model demonstrated that the AUC was 0.846 (95% confidence interval, CI 0.686-0.902). A pooled diagnostic odds ratio of 12.6 was computed. The pooled sensitivity and specificity were 0.795 (95% CI 0.651-0.889) and 0.780 (95% CI 0.634-0.879), respectively. CONCLUSION: ML may be useful as an adjunct to clinical assessment to predict functional outcomes in AIS patients undergoing thrombectomy, and hence identify suitable patients for treatment. Further studies validating ML models in large multicenter cohorts are necessary to explore this further.

Blood pressure trend in hospitalized adult dengue patients.

BACKGROUND: Monitoring of blood pressure is an important part of management of dengue illness. Large scale studies of temporal trend of blood pressure in adult dengue are lacking. In this study, we examined the differences in time trend of systolic (SBP) and diastolic blood pressure (DBP) in patients with and without severe dengue (SD), dengue hemorrhagic fever (DHF) and pre-existing hypertension, and elderly versus non-elderly patients. METHODS: We studied a retrospective cohort from 2005 to 2008 of 6,070 hospitalized adult dengue patients confirmed by polymerase chain reaction or clinical criteria plus positive dengue serology. Dengue severity was defined according to World Health Organization 1997 and 2009 guidelines. We used Bayesian hierarchical Markov models to compare the daily mean SBP and DBP between different subgroups. Analysis was conducted by day of defervescence (denoted as day 0), and day of illness onset (denoted as day 1) respectively. RESULTS: SBP decreased to a nadir during the critical phase before defervescence and was significantly lower for patients with SD or DHF, compared with patients without SD or DHF. DBP increased marginally more for patients with SD or DHF in the critical phase before defervescence. By day of defervescence, comparison of patients with and without SD showed significant difference in SBP from day -6 to day +6, except days +1, +3 and +5, and similarly in DBP except days 0, and +4 to +6. Comparison of patients with and without DHF showed significant difference in SBP from day -6 to day -1, but for DBP, significant difference was noted from day -6 to day +6, except day -2 to day 0. By day of illness, SBP differed significantly between patients with and without SD from illness days 1 to 10, and DBP from illness days 7 to 12. Between patients with and without DHF, SBP differed significantly on illness days 1, 2, 4 to 7, while DBP from days 7 to 12. On analysis by days of defervescence or by days of illness, elderly patients and those with hypertension showed consistently higher SBP and DBP throughout their hospitalization, as compared with their younger and non-hypertensive counterparts. CONCLUSION: In SD or DHF, SBP decreased to a nadir around the day of defervescence, and recovered to a level exceeding that in febrile phase by days 2 or 3 post-defervescence. Elderly patients and patients with pre-existing hypertension maintained higher SBP and DBP throughout the duration of dengue infection.

Urban Intelligence for Pandemic Response: Viewpoint.

Previous epidemic management research proves the importance of city-level information, but also highlights limited expertise in urban data applications during a pandemic outbreak. In this paper, we provide an overview of city-level information, in combination with analytical and operational capacity, that define urban intelligence for supporting response to disease outbreaks. We present five components (movement, facilities, people, information, and engagement) that have been previously investigated but remain siloed to successfully orchestrate an integrated pandemic response. Reflecting on the coronavirus disease (COVID-19) outbreak that was first identified in Wuhan, China, we discuss the opportunities, technical challenges, and foreseeable controversies for deploying urban intelligence during a pandemic. Finally, we emphasize the urgency of building urban intelligence through cross-disciplinary research and collaborative practice on a global scale.

Alcohol Use Disorder and Heavy Episodic Drinking in Rural Communities in Cambodia: Risk Factors and Community-Perceived Strategies.

Alcohol misuse is increasing in Southeast Asia. We investigated the extent of and risk factors for alcohol use disorder (AUD) and heavy episodic drinking (HED) in a rural community in Cambodia. We also attempted to explore the communities' perception of alcohol misuse and elicited potential community-based strategies to address the alcohol problem. A mixed-methods study design was used, combining a cross-sectional questionnaire survey with qualitative interviews (focus group discussions and key informant interviews). AUD and HED were measured using the AUDs Identification Test Alcohol Consumption questionnaire. The prevalence of AUD and HED was high: 25% and 31%, respectively. Male sex, younger age, and increasing income were significant risk factors. The communities were well aware of the harmful effects of alcohol, expressed the importance of implementing community-based measures, and proposed various community-led solutions. Evidence-based strategies that are culturally appropriate, accepted, and driven by communities are urgently needed.