Effect of Cangrelor on Infarct Size in ST-Segment Elevation Myocardial Infarction Treated By Primary Percutaneous Coronary Intervention: A Randomized Controlled Trial (The PITRI Trial).

Background: The administration of intravenous cangrelor at reperfusion achieves faster onset of platelet P2Y12 inhibition than oral ticagrelor and has been shown to reduce myocardial infarct (MI) size in the pre-clinical setting. We hypothesized that the administration of cangrelor at reperfusion will reduce MI size and prevent microvascular obstruction (MVO) in patients with ST-segment elevation myocardial infarction (STEMI) undergoing primary percutaneous coronary intervention (PPCI). Methods: This was a Phase 2, multi-center, randomized, double-blind, placebo controlled clinical trial conducted between November 2017 to November 2021 in six cardiac centers in Singapore (NCT03102723). Patients were randomized to receive either cangrelor or placeboinitiated prior to the PPCI procedure on top of oral ticagrelor. The key exclusion criteria included: presenting <6 hours of symptom onset, prior MI and stroke or transient ischemic attack; on concomitant oral anticoagulants; and a contraindication for cardiovascular magnetic resonance (CMR). The primary efficacy endpoint was acute MI size by CMR within the first week expressed as percentage of the left ventricle mass ( %LVmass). MVO was identified as areas of dark core of hypoenhancement within areas of late gadolinium enhancement. The primary safety endpoint was Bleeding Academic Research Consortium (BARC)-defined major bleeding in the first 48 hours. Continuous variables were compared by Mann-Whitney U test [reported as median (1st quartile- 3rd quartile)] and categorical variables were compared by Fisher's exact test. A 2-sided P<0.05 was considered statistically significant. Results: Of 209 recruited patients, 164 patients (78% ) completed the acute CMR scan. There were no significant differences in acute MI size [placebo: 14.9 (7.3 - 22.6) %LVmass versus cangrelor: 16.3 (9.9 - 24.4)%LVmass, P=0.40] or the incidence [placebo: 48% versus cangrelor: 47%, P=0.99] and extent of MVO [placebo:1.63 (0.60 - 4.65)%LVmass versus cangrelor: 1.18 (0.53 - 3.37)%LVmass, P=0.46] between placebo and cangrelor despite a two-fold decrease in platelet reactivity with cangrelor. There were no BARC-defined major bleeding events in either group in the first 48 hours. Conclusions: Cangrelor administered at time of PPCI did not reduce acute MI size or prevent MVO in STEMI patients given oral ticagrelor despite a significant reduction of platelet reactivity during the PCI procedure.

Extracorporeal cardiopulmonary resuscitation versus conventional CPR in cardiac arrest: an updated meta-analysis and trial sequential analysis.

BACKGROUND: Extracorporeal cardiopulmonary resuscitation (ECPR) may reduce mortality and improve neurological outcomes in patients with cardiac arrest. We updated our existing meta-analysis and trial sequential analysis to further evaluate ECPR compared to conventional CPR (CCPR). METHODS: We searched three international databases from 1 January 2000 through 1 November 2023, for randomised controlled trials or propensity score matched studies (PSMs) comparing ECPR to CCPR in both out-of-hospital cardiac arrest (OHCA) and in-hospital cardiac arrest (IHCA). We conducted an updated random-effects meta-analysis, with the primary outcome being in-hospital mortality. Secondary outcomes included short- and long-term favourable neurological outcome and survival (30 days-1 year). We also conducted a trial sequential analysis to evaluate the required information size in the meta-analysis to detect a clinically relevant reduction in mortality. RESULTS: We included 13 studies with 14 pairwise comparisons (6336 ECPR and 7712 CCPR) in our updated meta-analysis. ECPR was associated with greater precision in reducing overall in-hospital mortality (OR 0.63, 95% CI 0.50-0.79, high certainty), to which the trial sequential analysis was concordant. The addition of recent studies revealed a newly significant decrease in mortality in OHCA (OR 0.62, 95% CI 0.45-0.84). Re-analysis of relevant secondary outcomes reaffirmed our initial findings of favourable short-term neurological outcomes and survival up to 30 days. Estimates for long-term neurological outcome and 90-day-1-year survival remained unchanged. CONCLUSIONS: We found that ECPR reduces in-hospital mortality, improves neurological outcome, and 30-day survival. We additionally found a newly significant benefit in OHCA, suggesting that ECPR may be considered in both IHCA and OHCA.

A machine-learning exploration of the exposome from preconception in early childhood atopic eczema, rhinitis and wheeze development.

BACKGROUND: Most previous research on the environmental epidemiology of childhood atopic eczema, rhinitis and wheeze is limited in the scope of risk factors studied. Our study adopted a machine learning approach to explore the role of the exposome starting already in the preconception phase. METHODS: We performed a combined analysis of two multi-ethnic Asian birth cohorts, the Growing Up in Singapore Towards healthy Outcomes (GUSTO) and the Singapore PREconception Study of long Term maternal and child Outcomes (S-PRESTO) cohorts. Interviewer-administered questionnaires were used to collect information on demography, lifestyle and childhood atopic eczema, rhinitis and wheeze development. Data training was performed using XGBoost, genetic algorithm and logistic regression models, and the top variables with the highest importance were identified. Additive explanation values were identified and inputted into a final multiple logistic regression model. Generalised structural equation modelling with maternal and child blood micronutrients, metabolites and cytokines was performed to explain possible mechanisms. RESULTS: The final study population included 1151 mother-child pairs. Our findings suggest that these childhood diseases are likely programmed in utero by the preconception and pregnancy exposomes through inflammatory pathways. We identified preconception alcohol consumption and maternal depressive symptoms during pregnancy as key modifiable maternal environmental exposures that increased eczema and rhinitis risk. Our mechanistic model suggested that higher maternal blood neopterin and child blood dimethylglycine protected against early childhood wheeze. After birth, early infection was a key driver of atopic eczema and rhinitis development. CONCLUSION: Preconception and antenatal exposomes can programme atopic eczema, rhinitis and wheeze development in utero. Reducing maternal alcohol consumption during preconception and supporting maternal mental health during pregnancy may prevent atopic eczema and rhinitis by promoting an optimal antenatal environment. Our findings suggest a need to include preconception environmental exposures in future research to counter the earliest precursors of disease development in children.

Using heart rate variability to develop a predictive model for post-operative cardiovascular complications following major abdominal surgery: A pilot study.

BACKGROUND: Heart Rate Variability (HRV) is a dynamic reflection of heart rhythm regulation by various physiological inputs. HRV deviations have been found to correlate with clinical outcomes in patients under physiological stresses. Perioperative cardiovascular complications occur in up to 5% of adult patients undergoing abdominal surgery and are associated with significantly increased mortality. This pilot study aimed to develop a predictive model for post-operative cardiovascular complications using HRV parameters for early risk stratification and aid post-operative clinical decision-making. METHODS: Adult patients admitted to High Dependency Units after elective major abdominal surgery were recruited. The primary composite outcome was defined as cardiovascular complications within 7 days post-operatively. ECG monitoring for HRV parameters was conducted at three time points (pre-operative, immediately post-operative, and post-operative day 1) and analyzed based on outcome group and time interactions. Candidate HRV predictors were included in a multivariable logistic regression analysis incorporating a stepwise selection algorithm. RESULTS: 89 patients were included in the analysis, with 8 experiencing cardiovascular complications. Three HRV parameters, when measured immediately post-operatively and composited with patient age, provided the basis for a predictive model with AUC of 0.980 (95% CI: 0.953, 1.00). The negative predictive value was 1.00 at a statistically optimal predicted probability cut-off point of 0.16. CONCLUSION: Our model holds potential for accelerating clinical decision-making and aiding in patient triaging post-operatively, using easily acquired HRV parameters. Risk stratification with our model may enable safe early step-down care in patients assessed to have a low risk profile of post-operative cardiovascular complications.

Association between Conversion to Shockable Rhythms and Survival with Favorable Neurological Outcomes for Out-of-Hospital Cardiac Arrests.

BACKGROUND: The initial cardiac rhythm in out-of-hospital cardiac arrest (OHCA) portends different prognoses and affects treatment decisions. Initial shockable rhythms are associated with good survival and neurological outcomes but there is conflicting evidence for those who initially present with non-shockable rhythms. The aim of this study is to evaluate if OHCA with conversion from non-shockable (i.e., asystole and pulseless electrical activity) rhythms to shockable rhythms compared to OHCA remaining in non-shockable rhythms is associated with better survival and neurological outcomes. METHOD: OHCA cases from the Pan-Asian Resuscitation Outcomes Study registry in 13 countries between January 2009 and February 2018 were retrospectively analyzed. Cases with missing initial rhythms, age <18 years, presumed non-medical cause of arrest, and not conveyed by emergency medical services were excluded. Multivariable logistic regression analysis was performed to evaluate the relationship between initial and subsequent shockable rhythm, survival to discharge, and survival with favorable neurological outcomes (cerebral performance category 1 or 2). RESULTS: Of the 116,387 cases included. 11,153 (9.6%) had initial shockable rhythms and 9,765 (8.4%) subsequently converted to shockable rhythms. Japan had the lowest proportion of OHCA patients with initial shockable rhythms (7.3%). For OHCA with initial shockable rhythm, the adjusted odds ratios (aOR) for survival and good neurological outcomes were 8.11 (95% confidence interval [CI] 7.62-8.63) and 15.4 (95%CI 14.1-16.8) respectively. For OHCA that converted from initial non-shockable to shockable rhythms, the aORs for survival and good neurological outcomes were 1.23 (95%CI 1.10-1.37) and 1.61 (95%CI 1.35-1.91) respectively. The aORs for survival and good neurological outcomes were 1.48 (95%CI 1.22-1.79) and 1.92 (95%CI 1.3 - 2.84) respectively for initial asystole, while the aOR for survival in initial pulseless electrical activity patients was 0.83 (95%CI 0.71-0.98). Prehospital adrenaline administration had the highest aOR (2.05, 95%CI 1.93-2.18) for conversion to shockable rhythm. CONCLUSION: In this ambidirectional cohort study, conversion from non-shockable to shockable rhythm was associated with improved survival and neurologic outcomes compared to rhythms that continued to be non-shockable. Continued advanced resuscitation may be beneficial for OHCA with subsequent conversion to shockable rhythms.

Assertive community treatment for high-utilizing alcohol misuse patients: a before-and-after cohort study protocol.

BACKGROUND: The challenge posed by Alcohol-Related Frequent Attenders (ARFAs) in Emergency Departments (EDs) is growing in Singapore, marked by limited engagement with conventional addiction treatment pathways. Recognizing this gap, this study aims to explore the potential benefits of Assertive Community Treatment (ACT) - an innovative, community-centered, harm-reduction strategy-in mitigating the frequency of ED visits, curbing Emergency Medical Services (EMS) calls, and uplifting health outcomes across a quartet of Singaporean healthcare institutions. METHODS: Employing a prospective before-and-after cohort design, this investigation targeted ARFAs aged 21 years and above, fluent in English or Mandarin. Eligibility was determined by a history of at least five ED visits in the preceding year, with no fewer than two due to alcohol-related issues. The study contrasted health outcomes of patients integrated into the ACT care model versus their experiences under the exclusive provision of standard emergency care across Hospitals A, B, C and D. Following participants for half a year post-initial assessment, the evaluation metrics encompassed socio-demographic factors, ED, and EMS engagement frequencies, along with validated health assessment tools, namely Christo Inventory for Substance-misuse Services (CISS) scores, University of California, Los Angeles (UCLA) Loneliness scores, and Centre for Epidemiologic Studies Depression Scale Revised (CESD-R-10) scores. DISCUSSION: Confronted with intricate socio-economic and medical challenges, the ARFA cohort often grapples with heightened vulnerabilities in relation to alcohol misuse. Pioneering the exploration of ACT's efficacy with ARFAs in a Singaporean context, our research is anchored in a patient-centered approach, designed to comprehensively address these multifaceted clinical profiles. While challenges, like potential high attrition rates and sporadic data collection, are anticipated, the model's prospective contribution towards enhancing patient well-being and driving healthcare efficiencies in Singapore is substantial. Our findings have the potential to reshape healthcare strategies and policy recommendations. TRIAL REGISTRATION: ClinicalTrials.gov, NCT04447079. Initiated on 25 June 2020.

Implementation of Prediction Models in the Emergency Department from an Implementation Science Perspective-Determinants, Outcomes, and Real-World Impact: A Scoping Review.

STUDY OBJECTIVE: Prediction models offer a promising form of clinical decision support in the complex and fast-paced environment of the emergency department (ED). Despite significant advancements in model development and validation, implementation of such models in routine clinical practice remains elusive. This scoping review aims to survey the current state of prediction model implementation in the ED and to provide insights on contributing factors and outcomes from an implementation science perspective. METHODS: We searched 4 databases from their inception to May 20, 2022: MEDLINE (through PubMed), Embase, Scopus, and CINAHL. Articles that reported implementation outcomes and/or contextual determinants under the Reach, Effectiveness, Adoption, Implementation Maintenance (RE-AIM)/Practical, Robust, Implementation, and Sustainability Model (PRISM) framework were included. Characteristics of studies, models, and results of the RE-AIM/PRISM domains were summarized narratively. RESULTS: Thirty-six reports on 31 implementations were included. The most common prediction models implemented were early warning scores. The most common implementation strategies used were training stakeholders, infrastructural changes, and using evaluative or iterative strategies. Only one report examined ED patients' perspectives, whereas the rest were focused on the experience of health care workers or organizational stakeholders. Key determinants of successful implementation include strong stakeholder engagement, codevelopment of workflows and implementation strategies, education, and usability. CONCLUSION: Examining ED prediction models from an implementation science perspective can provide valuable insights and help guide future implementations.

Comparing outcomes of out-of-hospital cardiac arrest patients with initial shockable rhythm in Singapore and Osaka using population-based databases.

BACKGROUND: Previous research indicated outcomes among refractory out-of-hospital cardiac arrest (OHCA) patients with initial shockable rhythm were different in Singapore and Osaka, Japan, possibly due to the differences in access to extracorporeal cardiopulmonary resuscitation. However, this previous study had a risk of selection bias. To address this concern, this study aimed to evaluate the outcomes between Singapore and Osaka for OHCA patients with initial shockable rhythm using only population-based databases. METHODS: This was a secondary analysis of two OHCA population-based databases in Osaka and Singapore, including adult OHCA patients with initial shockable rhythm. A machine-learning-based prediction model was derived from the Osaka data (n = 3088) and applied to the PAROS-SG data (n = 2905). We calculated the observed-expected ratio (OE ratio) for good neurological outcomes observed in Singapore and the expected derived from the data in Osaka by dividing subgroups with or without prehospital ROSC. RESULTS: The one-month good neurological outcomes in Osaka and Singapore among patients with prehospital ROSC were 70% (791/1,125) and 57% (440/773), and among patients without prehospital ROSC were 10% (196/1963) and 2.8% (60/2,132). After adjusting patient characteristics, the outcome in Singapore was slightly better than expected from Osaka in patients with ROSC (OE ratio, 1.067 [95%CI 1.012 to 1.125]), conversely, it was worse than expected in patients without prehospital ROSC (OE ratio, 0.238 [95%CI 0.173 to 0.294]). CONCLUSION: This study showed the outcomes of OHCA patients without prehospital ROSC in Singapore were worse than expected derived from Osaka data even using population-based databases. (249/250 words).

Outcome assessment for out-of-hospital cardiac arrest patients in Singapore and Japan with initial shockable rhythm.

BACKGROUND: Singapore and Osaka in Japan have comparable population sizes and prehospital management; however, the frequency of ECPR differs greatly for out-of-hospital cardiac arrest (OHCA) patients with initial shockable rhythm. Given this disparity, we hypothesized that the outcomes among the OHCA patients with initial shockable rhythm in Singapore were different from those in Osaka. The aim of this study was to evaluate the outcomes of OHCA patients with initial shockable rhythm in Singapore compared to the expected outcomes derived from Osaka data using machine learning-based prediction models. METHODS: This was a secondary analysis of two OHCA databases: the Singapore PAROS database (SG-PAROS) and the Osaka-CRITICAL database from Osaka, Japan. This study included adult (18-74 years) OHCA patients with initial shockable rhythm. A machine learning-based prediction model was derived and validated using data from the Osaka-CRITICAL database (derivation data 2012-2017, validation data 2018-2019), and applied to the SG-PAROS database (2010-2016 data), to predict the risk-adjusted probability of favorable neurological outcomes. The observed and expected outcomes were compared using the observed-expected ratio (OE ratio) with 95% confidence intervals (CI). RESULTS: From the SG-PAROS database, 1,789 patients were included in the analysis. For OHCA patients who achieved return of spontaneous circulation (ROSC) on hospital arrival, the observed favorable neurological outcome was at the same level as expected (OE ratio: 0.905 [95%CI: 0.784-1.036]). On the other hand, for those who had continued cardiac arrest on hospital arrival, the outcomes were lower than expected (shockable rhythm on hospital arrival, OE ratio: 0.369 [95%CI: 0.258-0.499], and nonshockable rhythm, OE ratio: 0.137 [95%CI: 0.065-0.235]). CONCLUSION: This observational study found that the outcomes for patients with initial shockable rhythm but who did not obtain ROSC on hospital arrival in Singapore were lower than expected from Osaka. We hypothesize this is mainly due to differences in the use of ECPR.

In-hospital extracorporeal cardiopulmonary resuscitation for patients with out-of-hospital cardiac arrest: an analysis by time-dependent propensity score matching using a nationwide database in Japan.

BACKGROUND: Extracorporeal cardiopulmonary resuscitation (ECPR) has been proposed as a rescue therapy for patients with refractory cardiac arrest. This study aimed to evaluate the association between ECPR and clinical outcomes among patients with out-of-hospital cardiac arrest (OHCA) using risk-set matching with a time-dependent propensity score. METHODS: This was a secondary analysis of the JAAM-OHCA registry data, a nationwide multicenter prospective study of patients with OHCA, from June 2014 and December 2019, that included adults (≥ 18 years) with OHCA. Initial cardiac rhythm was classified as shockable and non-shockable. Patients who received ECPR were sequentially matched with the control, within the same time (minutes) based on time-dependent propensity scores calculated from potential confounders. The odds ratios with 95% confidence intervals (CI) for 30-day survival and 30-day favorable neurological outcomes were estimated for ECPR cases using a conditional logistic model. RESULTS: Of 57,754 patients in the JAAM-OHCA registry, we selected 1826 patients with an initial shockable rhythm (treated with ECPR, n = 913 and control, n = 913) and a cohort of 740 patients with an initial non-shockable rhythm (treated with ECPR, n = 370 and control, n = 370). In these matched cohorts, the odds ratio for 30-day survival in the ECPR group was 1.76 [95%CI 1.38-2.25] for shockable rhythm and 5.37 [95%CI 2.53-11.43] for non-shockable rhythm, compared to controls. For favorable neurological outcomes, the odds ratio in the ECPR group was 1.11 [95%CI 0.82-1.49] for shockable rhythm and 4.25 [95%CI 1.43-12.63] for non-shockable rhythm, compared to controls. CONCLUSION: ECPR was associated with increased 30-day survival in patients with OHCA with initial shockable and even non-shockable rhythms. Further research is warranted to investigate the reproducibility of the results and who is the best candidate for ECPR.

FedScore: A privacy-preserving framework for federated scoring system development.

OBJECTIVE: We propose FedScore, a privacy-preserving federated learning framework for scoring system generation across multiple sites to facilitate cross-institutional collaborations. MATERIALS AND METHODS: The FedScore framework includes five modules: federated variable ranking, federated variable transformation, federated score derivation, federated model selection and federated model evaluation. To illustrate usage and assess FedScore's performance, we built a hypothetical global scoring system for mortality prediction within 30 days after a visit to an emergency department using 10 simulated sites divided from a tertiary hospital in Singapore. We employed a pre-existing score generator to construct 10 local scoring systems independently at each site and we also developed a scoring system using centralized data for comparison. RESULTS: We compared the acquired FedScore model's performance with that of other scoring models using the receiver operating characteristic (ROC) analysis. The FedScore model achieved an average area under the curve (AUC) value of 0.763 across all sites, with a standard deviation (SD) of 0.020. We also calculated the average AUC values and SDs for each local model, and the FedScore model showed promising accuracy and stability with a high average AUC value which was closest to the one of the pooled model and SD which was lower than that of most local models. CONCLUSION: This study demonstrates that FedScore is a privacy-preserving scoring system generator with potentially good generalizability.

The Effect of Building-Level Socioeconomic Status on Bystander Cardiopulmonary Resuscitation: A Retrospective Cohort Study.

OBJECTIVE: Understanding the social determinants of bystander cardiopulmonary resuscitation (CPR) receipt can inform the design of public health interventions to increase bystander CPR. The association of socioeconomic status with bystander CPR is generally poorly understood. We evaluated the relationship between socioeconomic status and bystander CPR in cases of out-of-hospital cardiac arrest (OHCA). METHODS: This was a retrospective cohort study based on the Singapore cohort of the Pan-Asian Resuscitation Outcomes Study registry between 2010 and 2018. We categorized patients into low, medium, and high Singapore Housing Index (SHI) levels-a building-level index of socioeconomic status. The primary outcome was receipt of bystander CPR. The secondary outcomes were prehospital return of spontaneous circulation and survival to discharge. RESULTS: A total of 12,730 OHCA cases were included, the median age was 71 years, and 58.9% were male. The bystander CPR rate was 56.7%. Compared to patients in the low SHI category, those in the medium and high SHI categories were more likely to receive bystander CPR (medium SHI: adjusted odds ratio [aOR] 1.48, 95% CI 1.30-1.69; high SHI: aOR 1.93, 95% CI 1.67-2.24). High SHI patients had higher survival compared to low SHI patients on unadjusted analysis (OR 1.79, 95% CI 1.08-2.96), but not adjusted analysis (adjusted for age, sex, race, witness status, arrest time, past medical history of cancer, and first arrest rhythm). When comparing high with low SHI, females had larger increases in bystander CPR rates than males. CONCLUSIONS: Lower building-level socioeconomic status was independently associated with lower rate of bystander CPR, and females were more susceptible to the effect of low socioeconomic status on lower rate of bystander CPR.

Characteristics and Outcomes of Traumatic Cardiac Arrests in the Pan-Asian Resuscitation Outcomes Study.

OBJECTIVE: Little is known about survival outcomes after traumatic cardiac arrest in Asia, or the association of Utstein factors with survival after traumatic cardiac arrests. This study aimed to describe the epidemiology and outcomes of traumatic cardiac arrests in Asia, and analyze Utstein factors associated with survival. METHODS: Traumatic cardiac arrest patients from 13 countries in the Pan-Asian Resuscitation Outcomes Study registry from 2009 to 2018 were analyzed. Multilevel logistic regression was performed to identify factors associated with the primary outcomes of survival to hospital discharge and favorable neurological outcome (Cerebral Performance Category (CPC) 1-2), and the secondary outcome of return of spontaneous circulation (ROSC). RESULTS: There were 207,455 out-of-hospital cardiac arrest cases, of which 13,631 (6.6%) were trauma patients aged 18 years and above with resuscitation attempted and who had survival outcomes reported. The median age was 57 years (interquartile range 39-73), 23.0% received bystander cardiopulmonary resuscitation (CPR), 1750 (12.8%) had ROSC, 461 (3.4%) survived to discharge, and 131 (1.0%) had CPC 1-2. Factors associated with higher rates of survival to discharge and favorable neurological outcome were arrests witnessed by emergency medical services or private ambulances (survival to discharge adjusted odds ratio (aOR) = 2.95, 95% confidence interval (CI) = 1.99-4.38; CPC 1-2 aOR = 2.57, 95% CI = 1.25-5.27), bystander CPR (survival to discharge aOR = 2.16; 95% CI 1.71-2.72; CPC 1-2 aOR = 4.98, 95% CI = 3.27-7.57), and initial shockable rhythm (survival to discharge aOR = 12.00; 95% CI = 6.80-21.17; CPC 1-2 aOR = 33.28, 95% CI = 11.39-97.23) or initial pulseless electrical activity (survival to discharge aOR = 3.98; 95% CI = 2.99-5.30; CPC 1-2 aOR = 5.67, 95% CI = 3.05-10.53) relative to asystole. CONCLUSIONS: In traumatic cardiac arrest, early aggressive resuscitation may not be futile and bystander CPR may improve outcomes.

Development of a real-world database for asthma and COPD: The SingHealth-Duke-NUS-GSK COPD and Asthma Real-World Evidence (SDG-CARE) collaboration.

PURPOSE: The SingHealth-Duke-GlaxoSmithKline COPD and Asthma Real-world Evidence (SDG-CARE) collaboration was formed to accelerate the use of Singaporean real-world evidence in research and clinical care. A centerpiece of the collaboration was to develop a near real-time database from clinical and operational data sources to inform healthcare decision making and research studies on asthma and chronic obstructive pulmonary disease (COPD). METHODS: Our multidisciplinary team, including clinicians, epidemiologists, data scientists, medical informaticians and IT engineers, adopted the hybrid waterfall-agile project management methodology to develop the SingHealth COPD and Asthma Data Mart (SCDM). The SCDM was developed within the organizational data warehouse. It pulls and maps data from various information systems using extract, transform and load (ETL) pipelines. Robust user testing and data verification was also performed to ensure that the business requirements were met and that the ETL pipelines were valid. RESULTS: The SCDM includes 199 data elements relevant to asthma and COPD. Data verification was performed and found the SCDM to be reliable. As of December 31, 2019, the SCDM contained 36,407 unique patients with asthma and COPD across the spectrum from primary to tertiary care in our healthcare system. The database updates weekly to add new data of existing patients and to include new patients who fulfil the inclusion criteria. CONCLUSIONS: The SCDM was systematically developed and tested to support the use RWD for clinical and health services research in asthma and COPD. This can serve as a platform to provide research and operational insights to improve the care delivered to our patients.

Cardiac arrest centres: what, who, when, and where?

PURPOSE OF REVIEW: Cardiac arrest centres (CACs) may play a key role in providing postresuscitation care, thereby improving outcomes in out-of-hospital cardiac arrest (OHCA). There is no consensus on CAC definitions or the optimal CAC transport strategy despite advances in research. This review provides an updated overview of CACs, highlighting evidence gaps and future research directions. RECENT FINDINGS: CAC definitions vary worldwide but often feature 24/7 percutaneous coronary intervention capability, targeted temperature management, neuroprognostication, intensive care, education, and research within a centralized, high-volume hospital. Significant evidence exists for benefits of CACs related to regionalization. A recent meta-analysis demonstrated clearly improved survival with favourable neurological outcome and survival among patients transported to CACs with conclusions robust to sensitivity analyses. However, scarce data exists regarding 'who', 'when', and 'where' for CAC transport strategies. Evidence for OHCA patients without ST elevation postresuscitation to be transported to CACs remains unclear. Preliminary evidence demonstrated greater benefit from CACs among patients with shockable rhythms. Randomized controlled trials should evaluate specific strategies, such as bypassing nearest hospitals and interhospital transfer. SUMMARY: Real-world study designs evaluating CAC transport strategies are needed. OHCA patients with underlying culprit lesions, such as those with ST-elevation myocardial infarction (STEMI) or initial shockable rhythms, will likely benefit the most from CACs.

AutoScore-Ordinal: an interpretable machine learning framework for generating scoring models for ordinal outcomes.

BACKGROUND: Risk prediction models are useful tools in clinical decision-making which help with risk stratification and resource allocations and may lead to a better health care for patients. AutoScore is a machine learning-based automatic clinical score generator for binary outcomes. This study aims to expand the AutoScore framework to provide a tool for interpretable risk prediction for ordinal outcomes. METHODS: The AutoScore-Ordinal framework is generated using the same 6 modules of the original AutoScore algorithm including variable ranking, variable transformation, score derivation (from proportional odds models), model selection, score fine-tuning, and model evaluation. To illustrate the AutoScore-Ordinal performance, the method was conducted on electronic health records data from the emergency department at Singapore General Hospital over 2008 to 2017. The model was trained on 70% of the data, validated on 10% and tested on the remaining 20%. RESULTS: This study included 445,989 inpatient cases, where the distribution of the ordinal outcome was 80.7% alive without 30-day readmission, 12.5% alive with 30-day readmission, and 6.8% died inpatient or by day 30 post discharge. Two point-based risk prediction models were developed using two sets of 8 predictor variables identified by the flexible variable selection procedure. The two models indicated reasonably good performance measured by mean area under the receiver operating characteristic curve (0.758 and 0.793) and generalized c-index (0.737 and 0.760), which were comparable to alternative models. CONCLUSION: AutoScore-Ordinal provides an automated and easy-to-use framework for development and validation of risk prediction models for ordinal outcomes, which can systematically identify potential predictors from high-dimensional data.

AutoScore-Survival: Developing interpretable machine learning-based time-to-event scores with right-censored survival data.

BACKGROUND: Scoring systems are highly interpretable and widely used to evaluate time-to-event outcomes in healthcare research. However, existing time-to-event scores are predominantly created ad-hoc using a few manually selected variables based on clinician's knowledge, suggesting an unmet need for a robust and efficient generic score-generating method. METHODS: AutoScore was previously developed as an interpretable machine learning score generator, integrating both machine learning and point-based scores in the strong discriminability and accessibility. We have further extended it to the time-to-event outcomes and developed AutoScore-Survival, for generating time-to-event scores with right-censored survival data. Random survival forest provided an efficient solution for selecting variables, and Cox regression was used for score weighting. We implemented our proposed method as an R package. We illustrated our method in a study of 90-day survival prediction for patients in intensive care units and compared its performance with other survival models, the random survival forest, and two traditional clinical scores. RESULTS: The AutoScore-Survival-derived scoring system was more parsimonious than survival models built using traditional variable selection methods (e.g., penalized likelihood approach and stepwise variable selection), and its performance was comparable to survival models using the same set of variables. Although AutoScore-Survival achieved a comparable integrated area under the curve of 0.782 (95% CI: 0.767-0.794), the integer-valued time-to-event scores generated are favorable in clinical applications because they are easier to compute and interpret. CONCLUSIONS: Our proposed AutoScore-Survival provides a robust and easy-to-use machine learning-based clinical score generator to studies of time-to-event outcomes. It gives a systematic guideline to facilitate the future development of time-to-event scores for clinical applications.

Deep learning for temporal data representation in electronic health records: A systematic review of challenges and methodologies.

OBJECTIVE: Temporal electronic health records (EHRs) contain a wealth of information for secondary uses, such as clinical events prediction and chronic disease management. However, challenges exist for temporal data representation. We therefore sought to identify these challenges and evaluate novel methodologies for addressing them through a systematic examination of deep learning solutions. METHODS: We searched five databases (PubMed, Embase, the Institute of Electrical and Electronics Engineers [IEEE] Xplore Digital Library, the Association for Computing Machinery [ACM] Digital Library, and Web of Science) complemented with hand-searching in several prestigious computer science conference proceedings. We sought articles that reported deep learning methodologies on temporal data representation in structured EHR data from January 1, 2010, to August 30, 2020. We summarized and analyzed the selected articles from three perspectives: nature of time series, methodology, and model implementation. RESULTS: We included 98 articles related to temporal data representation using deep learning. Four major challenges were identified, including data irregularity, heterogeneity, sparsity, and model opacity. We then studied how deep learning techniques were applied to address these challenges. Finally, we discuss some open challenges arising from deep learning. CONCLUSION: Temporal EHR data present several major challenges for clinical prediction modeling and data utilization. To some extent, current deep learning solutions can address these challenges. Future studies may consider designing comprehensive and integrated solutions. Moreover, researchers should incorporate clinical domain knowledge into study designs and enhance model interpretability to facilitate clinical implementation.

AutoScore-Imbalance: An interpretable machine learning tool for development of clinical scores with rare events data.

BACKGROUND: Medical decision-making impacts both individual and public health. Clinical scores are commonly used among various decision-making models to determine the degree of disease deterioration at the bedside. AutoScore was proposed as a useful clinical score generator based on machine learning and a generalized linear model. However, its current framework still leaves room for improvement when addressing unbalanced data of rare events. METHODS: Using machine intelligence approaches, we developed AutoScore-Imbalance, which comprises three components: training dataset optimization, sample weight optimization, and adjusted AutoScore. Baseline techniques for performance comparison included the original AutoScore, full logistic regression, stepwise logistic regression, least absolute shrinkage and selection operator (LASSO), full random forest, and random forest with a reduced number of variables. These models were evaluated based on their area under the curve (AUC) in the receiver operating characteristic analysis and balanced accuracy (i.e., mean value of sensitivity and specificity). By utilizing a publicly accessible dataset from Beth Israel Deaconess Medical Center, we assessed the proposed model and baseline approaches to predict inpatient mortality. RESULTS: AutoScore-Imbalance outperformed baselines in terms of AUC and balanced accuracy. The nine-variable AutoScore-Imbalance sub-model achieved the highest AUC of 0.786 (0.732-0.839), while the eleven-variable original AutoScore obtained an AUC of 0.723 (0.663-0.783), and the logistic regression with 21 variables obtained an AUC of 0.743 (0.685-0.801). The AutoScore-Imbalance sub-model (using a down-sampling algorithm) yielded an AUC of 0.771 (0.718-0.823) with only five variables, demonstrating a good balance between performance and variable sparsity. Furthermore, AutoScore-Imbalance obtained the highest balanced accuracy of 0.757 (0.702-0.805), compared to 0.698 (0.643-0.753) by the original AutoScore and the maximum of 0.720 (0.664-0.769) by other baseline models. CONCLUSIONS: We have developed an interpretable tool to handle clinical data imbalance, presented its structure, and demonstrated its superiority over baselines. The AutoScore-Imbalance tool can be applied to highly unbalanced datasets to gain further insight into rare medical events and facilitate real-world clinical decision-making.

Protocol for a multi-site randomized controlled trial of a stepped-care intervention for emergency department patients with panic-related anxiety.

BACKGROUND: Approximately 40% of Emergency Department (ED) patients with chest pain meet diagnostic criteria for panic-related anxiety, but only 1-2% are correctly diagnosed and appropriately managed in the ED. A stepped-care model, which focuses on providing evidence-based interventions in a resource-efficient manner, is the state-of-the art for treating panic disorder patients in medical settings such as primary care. Stepped-care has yet to be tested in the ED setting, which is the first point of contact with the healthcare system for most patients with panic symptoms. METHODS: This multi-site randomized controlled trial (RCT) aims to evaluate the clinical, patient-centred, and economic effectiveness of a stepped-care intervention in a sample of 212 patients with panic-related anxiety presenting to the ED of Singapore's largest public healthcare group. Participants will be randomly assigned to either: 1) an enhanced care arm consisting of a stepped-care intervention for panic-related anxiety; or 2) a control arm consisting of screening for panic attacks and panic disorder. Screening will be followed by baseline assessments and blocked randomization in a 1:1 ratio. Masked follow-up assessments will be conducted at 1, 3, 6, and 12 months. Clinical outcomes will be panic symptom severity and rates of panic disorder. Patient-centred outcomes will be health-related quality of life, daily functioning, psychiatric comorbidity, and health services utilization. Economic effectiveness outcomes will be the incremental cost-effectiveness ratio of the stepped-care intervention relative to screening alone. DISCUSSION: This trial will examine the impact of early intervention for patients with panic-related anxiety in the ED setting. The results will be used to propose a clinically-meaningful and cost-effective model of care for ED patients with panic-related anxiety. TRIAL REGISTRATION: ClinicalTrials.gov NCT03632356. Retrospectively registered 15 August 2018.