Child wasting and concurrent stunting in low- and middle-income countries.

Sustainable Development Goal 2.2-to end malnutrition by 2030-includes the elimination of child wasting, defined as a weight-for-length z-score that is more than two standard deviations below the median of the World Health Organization standards for child growth1. Prevailing methods to measure wasting rely on cross-sectional surveys that cannot measure onset, recovery and persistence-key features that inform preventive interventions and estimates of disease burden. Here we analyse 21 longitudinal cohorts and show that wasting is a highly dynamic process of onset and recovery, with incidence peaking between birth and 3 months. Many more children experience an episode of wasting at some point during their first 24 months than prevalent cases at a single point in time suggest. For example, at the age of 24 months, 5.6% of children were wasted, but by the same age (24 months), 29.2% of children had experienced at least one wasting episode and 10.0% had experienced two or more episodes. Children who were wasted before the age of 6 months had a faster recovery and shorter episodes than did children who were wasted at older ages; however, early wasting increased the risk of later growth faltering, including concurrent wasting and stunting (low length-for-age z-score), and thus increased the risk of mortality. In diverse populations with high seasonal rainfall, the population average weight-for-length z-score varied substantially (more than 0.5 z in some cohorts), with the lowest mean z-scores occurring during the rainiest months; this indicates that seasonally targeted interventions could be considered. Our results show the importance of establishing interventions to prevent wasting from birth to the age of 6 months, probably through improved maternal nutrition, to complement current programmes that focus on children aged 6-59 months.

Early-childhood linear growth faltering in low- and middle-income countries.

Globally, 149 million children under 5 years of age are estimated to be stunted (length more than 2 standard deviations below international growth standards)1,2. Stunting, a form of linear growth faltering, increases the risk of illness, impaired cognitive development and mortality. Global stunting estimates rely on cross-sectional surveys, which cannot provide direct information about the timing of onset or persistence of growth faltering-a key consideration for defining critical windows to deliver preventive interventions. Here we completed a pooled analysis of longitudinal studies in low- and middle-income countries (n = 32 cohorts, 52,640 children, ages 0-24 months), allowing us to identify the typical age of onset of linear growth faltering and to investigate recurrent faltering in early life. The highest incidence of stunting onset occurred from birth to the age of 3 months, with substantially higher stunting at birth in South Asia. From 0 to 15 months, stunting reversal was rare; children who reversed their stunting status frequently relapsed, and relapse rates were substantially higher among children born stunted. Early onset and low reversal rates suggest that improving children's linear growth will require life course interventions for women of childbearing age and a greater emphasis on interventions for children under 6 months of age.

Causes and consequences of child growth faltering in low-resource settings.

Growth faltering in children (low length for age or low weight for length) during the first 1,000 days of life (from conception to 2 years of age) influences short-term and long-term health and survival1,2. Interventions such as nutritional supplementation during pregnancy and the postnatal period could help prevent growth faltering, but programmatic action has been insufficient to eliminate the high burden of stunting and wasting in low- and middle-income countries. Identification of age windows and population subgroups on which to focus will benefit future preventive efforts. Here we use a population intervention effects analysis of 33 longitudinal cohorts (83,671 children, 662,763 measurements) and 30 separate exposures to show that improving maternal anthropometry and child condition at birth accounted for population increases in length-for-age z-scores of up to 0.40 and weight-for-length z-scores of up to 0.15 by 24 months of age. Boys had consistently higher risk of all forms of growth faltering than girls. Early postnatal growth faltering predisposed children to subsequent and persistent growth faltering. Children with multiple growth deficits exhibited higher mortality rates from birth to 2 years of age than children without growth deficits (hazard ratios 1.9 to 8.7). The importance of prenatal causes and severe consequences for children who experienced early growth faltering support a focus on pre-conception and pregnancy as a key opportunity for new preventive interventions.

Predicting Self-Reported Social Risk in Medically Complex Adults Using Electronic Health Data.

BACKGROUND: Social barriers to health care, such as food insecurity, financial distress, and housing instability, may impede effective clinical management for individuals with chronic illness. Systematic strategies are needed to more efficiently identify at-risk individuals who may benefit from proactive outreach by health care systems for screening and referral to available social resources. OBJECTIVE: To create a predictive model to identify a higher likelihood of food insecurity, financial distress, and/or housing instability among adults with multiple chronic medical conditions. RESEARCH DESIGN AND SUBJECTS: We developed and validated a predictive model in adults with 2 or more chronic conditions who were receiving care within Kaiser Permanente Northern California (KPNC) between January 2017 and February 2020. The model was developed to predict the likelihood of a "yes" response to any of 3 validated self-reported survey questions related to current concerns about food insecurity, financial distress, and/or housing instability. External model validation was conducted in a separate cohort of adult non-Medicaid KPNC members aged 35-85 who completed a survey administered to a random sample of health plan members between April and June 2021 (n = 2820). MEASURES: We examined the performance of multiple model iterations by comparing areas under the receiver operating characteristic curves (AUCs). We also assessed algorithmic bias related to race/ethnicity and calculated model performance at defined risk thresholds for screening implementation. RESULTS: Patients in the primary modeling cohort (n = 11,999) had a mean age of 53.8 (±19.3) years, 64.7% were women, and 63.9% were of non-White race/ethnicity. The final, simplified model with 30 predictors (including utilization, diagnosis, behavior, insurance, neighborhood, and pharmacy-based variables) had an AUC of 0.68. The model remained robust within different race/ethnic strata. CONCLUSIONS: Our results demonstrated that a predictive model developed using information gleaned from the medical record and from public census tract data can be used to identify patients who may benefit from proactive social needs assessment. Depending on the prevalence of social needs in the target population, different risk output thresholds could be set to optimize positive predictive value for successful outreach. This predictive model-based strategy provides a pathway for prioritizing more intensive social risk outreach and screening efforts to the patients who may be in greatest need.

Human Immunodeficiency Virus Status, Tenofovir Exposure, and the Risk of Poor Coronavirus Disease 19 Outcomes: Real-World Analysis From 6 United States Cohorts Before Vaccine Rollout.

BACKGROUND: People with human immunodeficiency virus (HIV) (PWH) may be at increased risk for severe coronavirus disease 2019 (COVID-19) outcomes. We examined HIV status and COVID-19 severity, and whether tenofovir, used by PWH for HIV treatment and people without HIV (PWoH) for HIV prevention, was associated with protection. METHODS: Within 6 cohorts of PWH and PWoH in the United States, we compared the 90-day risk of any hospitalization, COVID-19 hospitalization, and mechanical ventilation or death by HIV status and by prior exposure to tenofovir, among those with severe acute respiratory syndrome coronavirus 2 infection between 1 March and 30 November 2020. Adjusted risk ratios (aRRs) were estimated by targeted maximum likelihood estimation, with adjustment for demographics, cohort, smoking, body mass index, Charlson comorbidity index, calendar period of first infection, and CD4 cell counts and HIV RNA levels (in PWH only). RESULTS: Among PWH (n = 1785), 15% were hospitalized for COVID-19 and 5% received mechanical ventilation or died, compared with 6% and 2%, respectively, for PWoH (n = 189 351). Outcome prevalence was lower for PWH and PWoH with prior tenofovir use. In adjusted analyses, PWH were at increased risk compared with PWoH for any hospitalization (aRR, 1.31 [95% confidence interval, 1.20-1.44]), COVID-19 hospitalizations (1.29 [1.15-1.45]), and mechanical ventilation or death (1.51 [1.19-1.92]). Prior tenofovir use was associated with reduced hospitalizations among PWH (aRR, 0.85 [95% confidence interval, .73-.99]) and PWoH (0.71 [.62-.81]). CONCLUSIONS: Before COVID-19 vaccine availability, PWH were at greater risk for severe outcomes than PWoH. Tenofovir was associated with a significant reduction in clinical events for both PWH and PWoH.

Exploiting nonsystematic covariate monitoring to broaden the scope of evidence about the causal effects of adaptive treatment strategies.

In studies based on electronic health records (EHR), the frequency of covariate monitoring can vary by covariate type, across patients, and over time, which can limit the generalizability of inferences about the effects of adaptive treatment strategies. In addition, monitoring is a health intervention in itself with costs and benefits, and stakeholders may be interested in the effect of monitoring when adopting adaptive treatment strategies. This paper demonstrates how to exploit nonsystematic covariate monitoring in EHR-based studies to both improve the generalizability of causal inferences and to evaluate the health impact of monitoring when evaluating adaptive treatment strategies. Using a real world, EHR-based, comparative effectiveness research (CER) study of patients with type II diabetes mellitus, we illustrate how the evaluation of joint dynamic treatment and static monitoring interventions can improve CER evidence and describe two alternate estimation approaches based on inverse probability weighting (IPW). First, we demonstrate the poor performance of the standard estimator of the effects of joint treatment-monitoring interventions, due to a large decrease in data support and concerns over finite-sample bias from near-violations of the positivity assumption (PA) for the monitoring process. Second, we detail an alternate IPW estimator using a no direct effect assumption. We demonstrate that this estimator can improve efficiency but at the potential cost of increase in bias from violations of the PA for the treatment process.

Use of Machine Learning to Develop a Risk-Stratification Tool for Emergency Department Patients With Acute Heart Failure.

STUDY OBJECTIVE: We use variables from a recently derived acute heart failure risk-stratification rule (STRATIFY) as a basis to develop and optimize risk prediction using additional patient clinical data from electronic health records and machine-learning models. METHODS: Using a retrospective cohort design, we identified all emergency department (ED) visits for acute heart failure between January 1, 2017, and December 31, 2018, among adult health plan members of a large system with 21 EDs. The primary outcome was any 30-day serious adverse event, including death, cardiopulmonary resuscitation, balloon-pump insertion, intubation, new dialysis, myocardial infarction, or coronary revascularization. Starting with the 13 variables from the STRATIFY rule (base model), we tested whether predictive accuracy in a different population could be enhanced with additional electronic health record-based variables or machine-learning approaches (compared with logistic regression). We calculated our derived model area under the curve (AUC), calculated test characteristics, and assessed admission rates across risk categories. RESULTS: Among 26,189 total ED encounters, mean patient age was 74 years, 51.7% were women, and 60.7% were white. The overall 30-day serious adverse event rate was 18.8%. The base model had an AUC of 0.76 (95% confidence interval 0.74 to 0.77). Incorporating additional variables led to improved accuracy with logistic regression (AUC 0.80; 95% confidence interval 0.79 to 0.82) and machine learning (AUC 0.85; 95% confidence interval 0.83 to 0.86). We found that 11.1%, 25.7%, and 48.9% of the study population had predicted serious adverse event risk of less than or equal to 3%, less than or equal to 5%, and less than or equal to 10%, respectively, and 28% of those with less than or equal to 3% risk were admitted. CONCLUSION: Use of a machine-learning model with additional variables improved 30-day risk prediction compared with conventional approaches.

Associations between spousal caregiving and health among older adults in Mexico: A targeted estimation approach.

OBJECTIVE: To evaluate associations between spousal caregiving and mental and physical health among older adults in Mexico. METHODS: Data come from the Mexican Health & Aging Study, a national population-based study of adults ≥50 years and their spouses (2001-2015). We compared outcomes for spousal caregivers to outcomes for those whose spouses had difficulty with at least one basic or instrumental activity of daily living (I/ADL) but were not providing care; the control group conventionally includes all married respondents regardless of spouse's need for care. We used targeted maximum likelihood estimation to evaluate the associations with past-week depressive symptoms, lower-body functional limitations, and chronic health conditions. RESULTS: At baseline, 846 women and 629 men had a spouse with ≥1 I/ADL. Of these, 60.9% of women and 52.6% of men were spousal caregivers. Spousal caregiving was associated with more past-week depressive symptoms for men (Marginal Risk Difference (RD): 0.27, 95% confidence internal [CI]: 0.03, 0.51) and women (RD: 0.15, 95% CI: 0.07, 0.23). We could not draw conclusions about associations with lower-body functional limitations and chronic health conditions. On average, all respondents whose spouses had caregiving needs had poorer health than the overall sample. CONCLUSION: We found evidence of an association between spousal caregiving and mental health among older Mexican adults with spouses who had need for care. However, our findings suggest that older adults who are both currently providing or at risk of providing spousal care may need targeted programs and policies to support health and long-term care needs.

US Migration Status of Adult Children and Cognitive Decline Among Older Parents Who Remain in Mexico.

Low- and middle-income countries (LMICs) are experiencing rapid aging, a growing dementia burden, and relatively high rates of out-migration among working-age adults. Family member migration status may be a unique societal determinant of cognitive aging in LMIC settings. We aimed to evaluate the association between adult child US migration status and change in cognitive performance scores using data from the Mexican Health and Aging Study, a population-based, national-level cohort study of Mexico adults aged ≥50 years at baseline (2001), with 2-, 12-, and 14-year follow-up waves (2003, 2012, and 2015). Cognitive performance assessments were completed by 5,972 and 4,939 respondents at 11 years and 14 years of follow-up, respectively. For women, having an adult child in the United States was associated with steeper decline in verbal memory scores (e.g., for 9-year change in immediate verbal recall z score, marginal risk difference (RD) = -0.09 (95% confidence interval (CI): -0.16, -0.03); for delayed verbal recall z score, RD = -0.10 (95% CI: -0.17, -0.03)) and overall cognitive performance (for overall cognitive performance z score, RD = -0.04, 95% CI: -0.07, -0.00). There were mostly null associations for men. To our knowledge, this is the first study to have evaluated the association between family member migration status and cognitive decline; future work should be extended to other LMICs facing population aging.

Having an Adult Child in the United States, Physical Functioning, and Unmet Needs for Care Among Older Mexican Adults.

BACKGROUND: Migration of adult children may impact the health of aging parents who remain in low- and middle-income countries. Prior studies have uncovered mixed associations between adult child migration status and physical functioning of older parents; none to our knowledge has examined the impact on unmet caregiving needs. METHODS: Data come from a population-based study of Mexican adults ≥50 years. We used longitudinal targeted maximum likelihood estimation to estimate associations between having an adult child US migrant and lower-body functional limitations, and both needs and unmet needs for assistance with basic or instrumental activities of daily living (ADLs/IADLs) for 11,806 respondents surveyed over an 11-year period. RESULTS: For women, having an adult child US migrant at baseline and 2-year follow-up was associated with fewer lower-body functional limitations [marginal risk difference (RD) = -0.14, 95% confidence interval (CI) = -0.26, -0.01] and ADLs/IADLs (RD = -0.08, 95% CI = -0.16, -0.001) at 2-year follow-up. Having an adult child US migrant at all waves was associated with a higher prevalence of functional limitations at 11-year follow-up (RD = 0.04, 95% CI = 0.01, 0.06). Having an adult child US migrant was associated with a higher prevalence of unmet needs for assistance at 2 (RD = 0.13, 95% CI = 0.04, 0.21) and 11-year follow-up for women (RD = 0.07, 95% CI = -0.02, 0.15) and 11-year follow-up for men (RD = 0.08, 95% CI = 0.00, 0.16). CONCLUSION: Having an adult child US migrant had mixed associations with physical functioning, but substantial adverse associations with unmet caregiving needs for a cohort of older adults in Mexico.

Comparing predictive abilities of longitudinal child growth models.

The Bill and Melinda Gates Foundation's Healthy Birth, Growth and Development knowledge integration project aims to improve the overall health and well-being of children across the world. The project aims to integrate information from multiple child growth studies to allow health professionals and policy makers to make informed decisions about interventions in lower and middle income countries. To achieve this goal, we must first understand the conditions that impact on the growth and development of children, and this requires sensible models for characterising different growth patterns. The contribution of this paper is to provide a quantitative comparison of the predictive abilities of various statistical growth modelling techniques based on a novel leave-one-out validation approach. The majority of existing studies have used raw growth data for modelling, but we show that fitting models to standardised data provide more accurate estimation and prediction. Our work is illustrated with an example from a study into child development in a middle income country in South America.

Targeted learning with daily EHR data.

Electronic health records (EHR) data provide a cost- and time-effective opportunity to conduct cohort studies of the effects of multiple time-point interventions in the diverse patient population found in real-world clinical settings. Because the computational cost of analyzing EHR data at daily (or more granular) scale can be quite high, a pragmatic approach has been to partition the follow-up into coarser intervals of pre-specified length (eg, quarterly or monthly intervals). The feasibility and practical impact of analyzing EHR data at a granular scale has not been previously evaluated. We start filling these gaps by leveraging large-scale EHR data from a diabetes study to develop a scalable targeted learning approach that allows analyses with small intervals. We then study the practical effects of selecting different coarsening intervals on inferences by reanalyzing data from the same large-scale pool of patients. Specifically, we map daily EHR data into four analytic datasets using 90-, 30-, 15-, and 5-day intervals. We apply a semiparametric and doubly robust estimation approach, the longitudinal Targeted Minimum Loss-Based Estimation (TMLE), to estimate the causal effects of four dynamic treatment rules with each dataset, and compare the resulting inferences. To overcome the computational challenges presented by the size of these data, we propose a novel TMLE implementation, the "long-format TMLE," and rely on the latest advances in scalable data-adaptive machine-learning software, xgboost and h2o, for estimation of the TMLE nuisance parameters.

Mediation of Neighborhood Effects on Adolescent Substance Use by the School and Peer Environments.

BACKGROUND: Evidence suggests that aspects of the neighborhood environment may influence risk of problematic drug use among adolescents. Our objective was to examine mediating roles of aspects of the school and peer environments on the effect of receiving a Section 8 housing voucher and using it to move out of public housing on adolescent substance use outcomes. METHODS: We used data from the Moving to Opportunity (MTO) experiment that randomized receipt of a Section 8 housing voucher. Hypothesized mediators included school climate, safety, peer drug use, and participation in an after-school sport or club. We applied a doubly robust, semiparametric estimator to longitudinal MTO data to estimate stochastic direct and indirect effects of randomization on cigarette use, marijuana use, and problematic drug use. Stochastic direct and indirect effects differ from natural direct and indirect effects in that they do not require assuming no posttreatment confounder of the mediator-outcome relationship. Such an assumption would be at odds with any causal model that reflects an intervention affecting a mediator and outcome through adherence to treatment assignment. RESULTS: Having friends who use drugs and involvement in after-school sports or clubs partially mediated the effect of housing voucher receipt on adolescent substance use (e.g., stochastic indirect effect 0.45% [95% confidence interval: 0.12%, 0.79%] for having friends who use drugs and 0.04% [95% confidence interval: -0.02%, 0.10%] for involvement in after-school sports or clubs mediating the relationship between housing voucher receipt and marijuana use among boys). However, these mediating effects were small, contributing only fractions of a percent to the effect of voucher receipt on probability of substance use. No school environment variables were mediators. CONCLUSIONS: Measured school- and peer-environment variables played little role in mediating the effect of housing voucher receipt on subsequent adolescent substance use.

Estimating outcomes and cost effectiveness using a single-arm clinical trial: ofatumumab for double-refractory chronic lymphocytic leukemia.

BACKGROUND: Ofatumumab (Arzerra®, Novartis) is a treatment for chronic lymphocytic leukemia refractory to fludarabine and alemtuzumab [double refractory (DR-CLL)]. Ofatumumab was licensed on the basis of an uncontrolled Phase II study, Hx-CD20-406, in which patients receiving ofatumumab survived for a median of 13.9 months. However, the lack of an internal control arm presents an obstacle for the estimation of comparative effectiveness. METHODS: The objective of the study was to present a method to estimate the cost effectiveness of ofatumumab in the treatment of DR-CLL. As no suitable historical control was available for modelling, the outcomes from non-responders to ofatumumab were used to model the effect of best supportive care (BSC). This was done via a Cox regression to control for differences in baseline characteristics between groups. This analysis was included in a partitioned survival model built in Microsoft® Excel with utilities and costs taken from published sources, with costs and quality-adjusted life years (QALYs) were discounted at a rate of 3.5% per annum. RESULTS: Using the outcomes seen in non-responders, ofatumumab is expected to add approximately 0.62 life years (1.50 vs. 0.88). Using published utility values this translates to an additional 0.30 QALYs (0.77 vs. 0.47). At the list price, ofatumumab had a cost per QALY of £130,563, and a cost per life year of £63,542. The model was sensitive to changes in assumptions regarding overall survival estimates and utility values. CONCLUSIONS: This study demonstrates the potential of using data for non-responders to model outcomes for BSC in cost-effectiveness evaluations based on single-arm trials. Further research is needed on the estimation of comparative effectiveness using uncontrolled clinical studies.

simcausal R Package: Conducting Transparent and Reproducible Simulation Studies of Causal Effect Estimation with Complex Longitudinal Data.

The simcausal R package is a tool for specification and simulation of complex longitudinal data structures that are based on non-parametric structural equation models. The package aims to provide a flexible tool for simplifying the conduct of transparent and reproducible simulation studies, with a particular emphasis on the types of data and interventions frequently encountered in real-world causal inference problems, such as, observational data with time-dependent confounding, selection bias, and random monitoring processes. The package interface allows for concise expression of complex functional dependencies between a large number of nodes, where each node may represent a measurement at a specific time point. The package allows for specification and simulation of counterfactual data under various user-specified interventions (e.g., static, dynamic, deterministic, or stochastic). In particular, the interventions may represent exposures to treatment regimens, the occurrence or non-occurrence of right-censoring events, or of clinical monitoring events. Finally, the package enables the computation of a selected set of user-specified features of the distribution of the counterfactual data that represent common causal quantities of interest, such as, treatment-specific means, the average treatment effects and coefficients from working marginal structural models. The applicability of simcausal is demonstrated by replicating the results of two published simulation studies.

Causal Inference for Social Network Data.

We describe semiparametric estimation and inference for causal effects using observational data from a single social network. Our asymptotic results are the first to allow for dependence of each observation on a growing number of other units as sample size increases. In addition, while previous methods have implicitly permitted only one of two possible sources of dependence among social network observations, we allow for both dependence due to transmission of information across network ties and for dependence due to latent similarities among nodes sharing ties. We propose new causal effects that are specifically of interest in social network settings, such as interventions on network ties and network structure. We use our methods to reanalyze an influential and controversial study that estimated causal peer effects of obesity using social network data from the Framingham Heart Study; after accounting for network structure we find no evidence for causal peer effects.

Technical evaluation of methods for identifying chemotherapy-induced febrile neutropenia in healthcare claims databases.

BACKGROUND: Healthcare claims databases have been used in several studies to characterize the risk and burden of chemotherapy-induced febrile neutropenia (FN) and effectiveness of colony-stimulating factors against FN. The accuracy of methods previously used to identify FN in such databases has not been formally evaluated. METHODS: Data comprised linked electronic medical records from Geisinger Health System and healthcare claims data from Geisinger Health Plan. Subjects were classified into subgroups based on whether or not they were hospitalized for FN per the presumptive "gold standard" (ANC <1.0×10(9)/L, and body temperature ≥38.3°C or receipt of antibiotics) and claims-based definition (diagnosis codes for neutropenia, fever, and/or infection). Accuracy was evaluated principally based on positive predictive value (PPV) and sensitivity. RESULTS: Among 357 study subjects, 82 (23%) met the gold standard for hospitalized FN. For the claims-based definition including diagnosis codes for neutropenia plus fever in any position (n=28), PPV was 100% and sensitivity was 34% (95% CI: 24-45). For the definition including neutropenia in the primary position (n=54), PPV was 87% (78-95) and sensitivity was 57% (46-68). For the definition including neutropenia in any position (n=71), PPV was 77% (68-87) and sensitivity was 67% (56-77). CONCLUSIONS: Patients hospitalized for chemotherapy-induced FN can be identified in healthcare claims databases--with an acceptable level of mis-classification--using diagnosis codes for neutropenia, or neutropenia plus fever.

Automated analysis of unstructured clinical assessments improves emergency department triage performance: A retrospective deep learning analysis.

Objectives: Efficient and accurate emergency department (ED) triage is critical to prioritize the sickest patients and manage department flow. We explored the use of electronic health record data and advanced predictive analytics to improve triage performance. Methods: Using a data set of over 5 million ED encounters of patients 18 years and older across 21 EDs from 2016 to 2020, we derived triage models using deep learning to predict 2 outcomes: hospitalization (primary outcome) and fast-track eligibility (exploratory outcome), defined as ED discharge with <2 resource types used (eg, laboratory or imaging studies) and no critical events (eg, resuscitative medications use or intensive care unit [ICU] admission). We report area under the receiver operator characteristic curve (AUC) and 95% confidence intervals (CI) for models using (1) triage variables alone (demographics and vital signs), (2) triage nurse clinical assessment alone (unstructured notes), and (3) triage variables plus clinical assessment for each prediction target. Results: We found 12.7% of patients were hospitalized (n = 673,659) and 37.0% were fast-track eligible (n = 1,966,615). The AUC was lowest for models using triage variables alone: AUC 0.77 (95% CI 0.77-0.78) and 0.70 (95% CI 0.70-0.71) for hospitalization and fast-track eligibility, respectively, and highest for models incorporating clinical assessment with triage variables for both hospitalization and fast-track eligibility: AUC 0.87 (95% CI 0.87-0.87) for both prediction targets. Conclusion: Our findings highlight the potential to use advanced predictive analytics to accurately predict key ED triage outcomes. Predictive accuracy was optimized when clinical assessments were added to models using simple structured variables alone.