Prioritization Of Patients Research Articles

Measuring the crowding of emergency departments: an assessment of the NEDOCS in Lombardy, Italy, and the development of a new objective indicator based on the waiting time for the first clinical assessment

BackgroundThere is no ubiquitous definition of Emergency Department (ED) crowding and several indicators have been proposed to measure it. The National ED Overcrowding Study (NEDOCS) score is among the most popular, even though it has been severely criticised. We used the waiting time for the physician’s initial assessment to evaluate the performance of the NEDOCS and proposed a new crowding indicator based on this objective measure.MethodsTo evaluate the NEDOCS, we used the 2022 data of all the Lombardy EDs and compared the distribution of waiting times across the five levels of the NEDOCS at ED arrival. To construct the new indicator, we estimated the centre-specific relationship between the total number of ED patients and the waiting time of those with minor or deferrable urgency. We defined seven classes of waiting times and calculated how many patients corresponded to an average waiting time in the classes. These centre-specific cutoffs were used to define the 7-level crowding indicator. The indicator was then compared to the NEDOCS score and validated on the first six months of 2023 data.ResultsPatients’ waiting time did not increase at the increase of the NEDOCS score, suggesting the absence of a relationship between this score and the effect of ED crowding on the ED capacity of evaluating new patients. The indicator we propose is easy to estimate in real-time and based on centre-specific cutoffs, which depend on the volume of yearly accesses. We observed minimal agreement between the proposed indicator and the NEDOCS in most EDs, both in the development and validation datasets.ConclusionsWe proposed to quantify ED crowding using the waiting time for physician’s initial assessment of patients with minor or deferrable urgency, which increases in crowding situations due to the prioritization of urgent patients. The centre-specific cutoffs avoid the problem of the heterogeneity of the volume of accesses and organization among EDs, while enabling a fair comparison between centres.

Public perceptions related to healthcare preparedness to anti-amyloid therapies for Alzheimer’s Disease in Japan

BackgroundThe approval of lecanemab, an anti-amyloid therapy for Alzheimer’s disease (AD), necessitates addressing healthcare preparedness for disease-modifying treatment (DMT) to ensure appropriate, safe, and sustainable drug administration. Understanding public perceptions on this matter is crucial. We aimed to assess discrepancies and similarities in the perceptions of Japanese trial-ready cohort study (‘J-TRC webstudy’) participants and clinical specialists in the fields of dementia treatment and radiology, concerning affairs related to challenges in DMT preparedness.MethodsThis was a cross-sectional prospective observational study conducted in November–December 2023. The J-TRC webstudy participants were invited to participate in an online survey using Google Forms, and clinical specialists were invited to complete a mail-based survey. Main questionnaire items had been designed to be common in both surveys, and their responses were analyzed for participant attributes, interests, attitudes, expectations, and concerns about DMTs without specifying lecanemab.ResultsResponses were obtained from n = 2,050 J-TRC webstudy participants and n = 1,518 clinical specialists. Compared to specialists, more J-TRC respondents perceived the eligible proportion for DMT as smaller (59.1% versus 30.7%), perceived the eligible severity for DMT as more limited (58.0% versus 24.5%), and perceived the efficacy of DMT as slightly more encouraging (29.3% versus 34.8%). In terms of treatment prioritization, both J-TRC respondents and specialist respondents exhibited similar levels of acceptance for prioritizing patients to treat: e.g., approximately two-thirds endorsed patient prioritization under hypothetical resource constraints or other reasons. A medical rationale emerged as the most compelling reason for acceptance of patient prioritization across the surveys. In contrast, the need to address vulnerable populations was the reason that led to the least acceptance of prioritization, followed by economic considerations.ConclusionsOur findings offer valuable insights into the discrepancies in knowledge and perception between patients and healthcare providers. This could enhance the delivery of patient information in clinical settings and inform the discussion surrounding patient prioritization strategies.

Patient Identification and Prioritization Tool: Utilizing the Electronic Medical Record to Optimize Clinical Nutrition Workflow

Patient Identification and Prioritization Tool: Utilizing the Electronic Medical Record to Optimize Clinical Nutrition Workflow

Cumulative incidence of vancomycin-resistant Enterococcus faecium detection by patient characteristics or possible exposures: prioritization of patients for active screening culture

The target population for active surveillance culture (ASC) of vancomycin-resistant Enterococcus species (VRE) by stool or rectal swabs has not been fully determined during VRE outbreaks in healthcare settings in non-VRE endemic situation. We evaluated cumulative incidences of VRE detection during a vancomycin-resistant Enterococcus faecium outbreak to determine reasonable target populations for ASC. Cases included inpatients whose first VRE-positive sample was obtained at Shizuoka General Hospital between February 2022 and January 2023, during which we conducted admission screening for possible high-risk patients, biweekly screening of all inpatients, admission and discharge screening in the high-care unit, and screening of contacts in each ward by using stool or rectal samples. We calculated cumulative incidences of VRE detection for those screened by patient characteristics or possible exposure. Among 60 cases identified, 55 (92%) were by ASC. Cumulative incidence was higher for contacts (6.4%, 15/234) than for those identified by other screening methods (0.5%, 40/8565). Among the patients identified through admission screening, those previously hospitalized in areas of reported VRE outbreaks had the highest cumulative incidence (6.6%, 5/78) followed by patients requiring toilet assistance (3.7%, 6/161). A bundle approach including ASC and prompt contact precautions by the hospital infection control team, local public health centre, and local and national infection control experts helped terminate the outbreak in seven months. Patients with contacts, prior hospitalization in areas with known VRE outbreaks, and who need toilet assistance appear to be high-risk populations for VRE detection and are candidates for ASC.

Can A Swallow Screen Score Be Used To Prioritise Dysphagia Assessments By A Speech And Language Therapist?

Abstract Background Dysphagia refers to any difficulty or discomfort associated with eating or swallowing. The prevalence is 10-50% in older persons and is associated with increased dependency and mortality. A non-validated Swallow Screen (SwSc) is used by a Community Specialist Team (CST) for older persons during Comprehensive Geriatric Assessment (CGA) to identify patients requiring Speech and Language Therapy (SLT) referral. The SwSc comprises 7 questions with “yes” or “no” answers. “Yes” answers score 1 point and “no” score 0. The SwSc score is the sum of these points. Higher scores indicate the presence of more symptoms of dysphagia. Patients with a SwSc score ≥1 are referred to an SLT. This study aimed to investigate if a higher SwSc score might indicate more severe dysphagia requiring more urgent assessment by an SLT. Methods This was a retrospective cohort study of patients ≥64 years referred to SLT by a CST from June 2023 to April 2024 inclusive. The SLT assessment included a Dysphagia Outcome Severity Scale (DOSS) score. The DOSS score ranges from 1-7, a lower score indicating a more severe dysphagia. Data was entered onto an Excel database and analysed. Biographical and CGA data was analysed using descriptive statistics. The SwSc and DOSS scores were ranked and compared using Spearman’s Rank Correlation Coefficient. Results Thirty-nine patients attended an SLT assessment. The mean age was 78, (SD=8.04). The mean Clinical Frailty Score 5 (SD=1.16) and mean modified Barthel Index score 16 (SD=3.75). There was a negative correlation between the SwSc and DOSS scores, r (37) = -.438, p=.005. Higher SwSc scores were associated with lower DOSS scores, indicating more severe dysphagia. Conclusion The SwSc can be easily administered by non-SLT clinicians. It may be used by an SLT to aid prioritisation of patients for assessment. Further research with a larger sample is required to establish its validity.

Clinical Translation and Implementation of a Bioartificial Pancreas Therapy: A Qualitative Study Exploring the Perspectives of People With Type 1 Diabetes.

The development of a hybrid beta-cell replacement approach, referred to as a personalized, transplantable bioartificial pancreas (BAP), holds promise to treat type 1 diabetes (T1D). This interview study aimed to explore patients' expectations, needs, concerns, and considerations when considering to undergo a BAP transplantation. Semistructured interviews were conducted with 24 participants diagnosed with T1D. Data collection stopped once data saturation was reached. Audio recordings of the interviews were transcribed verbatim. The interviews were independently analyzed by 2 researchers. A qualitative content analysis using an inductive approach was used. Three main themes emerged as follow: (1) hoped-for benefits, (2) concerns and decision-making considerations, and (3) procedural aspects. First, the participants expected benefits across medical, psychological, and social domains. Over these 3 domains, 9 subthemes were identified, including improved clinical outcomes, a cure for diabetes, more headspace, emotional relief, a shift in responsibility, protection of privacy, improved flexibility in daily life, less visible diseases, and improved relationships with others. Second, concerns and considerations about undergoing a BAP transplant comprised adverse events, the functionality of the BAP, the surgery procedure, the biological materials used, the transplant location, and the intrusiveness associated with follow-up care. Finally, procedural considerations included equitable access, patient prioritization, and trust and control. Incorporating insights from this study into the clinical development and implementation of the BAP is crucial to ensure alignment of the product and procedures with the needs and expectations of people with T1D.

Advancing Kidney Transplantation: A Machine Learning Approach to Enhance Donor-Recipient Matching.

(1) Background: Globally, the kidney donor shortage has made the allocation process critical for patients awaiting a kidney transplant. Adopting Machine Learning (ML) models for donor-recipient matching can potentially improve kidney allocation processes when compared with traditional points-based systems. (2) Methods: This study developed an ML-based approach for donor-recipient matching. A comprehensive evaluation was conducted using ten widely used classifiers (logistic regression, decision tree, random forest, support vector machine, gradient boosting, boost, CatBoost, LightGBM, naive Bayes, and neural networks) across three experimental scenarios to ensure a robust approach. The first scenario used the original dataset, the second used a merged version of the dataset, and the last scenario used a hierarchical architecture model. Additionally, a custom ranking algorithm was designed to identify the most suitable recipients. Finally, the ML-based donor-recipient matching model was integrated into a web-based platform called Nephron. (3) Results: The gradient boost model was the top performer, achieving a remarkable and consistent accuracy rate of 98% across the three experimental scenarios. Furthermore, the custom ranking algorithm outperformed the conventional cosine and Jaccard similarity methods in identifying the most suitable recipients. Importantly, the platform not only facilitated efficient patient selection and prioritisation for kidney allocation but can be flexibly adapted for other solid organ allocation systems built on similar criteria. (4) Conclusions: This study proposes an ML-based approach to optimize donor-recipient matching within the kidney allocation process. Successful implementation of this methodology demonstrates significant potential to enhance both efficiency and fairness in kidney transplantation.

Multimodal fusion learning for long QT syndrome pathogenic genotypes in a racially diverse population

Congenital long QT syndrome (LQTS) diagnosis is complicated by limited genetic testing at scale, low prevalence, and normal QT corrected interval in patients with high-risk genotypes. We developed a deep learning approach combining electrocardiogram (ECG) waveform and electronic health record data to assess whether patients had pathogenic variants causing LQTS. We defined patients with high-risk genotypes as having ≥1 pathogenic variant in one of the LQTS-susceptibility genes. We trained the model using data from United Kingdom Biobank (UKBB) and then fine-tuned in a racially/ethnically diverse cohort using Mount Sinai BioMe Biobank. Following group-stratified 5-fold splitting, the fine-tuned model achieved area under the precision-recall curve of 0.29 (95% confidence interval [CI] 0.28–0.29) and area under the receiver operating curve of 0.83 (0.82–0.83) on independent testing data from BioMe. Multimodal fusion learning has promise to identify individuals with pathogenic genetic mutations to enable patient prioritization for further work up.

Strategies for adapting under pressure: an interview study in intensive care units

BackgroundHealthcare systems are operating under substantial pressures. Clinicians and managers are constantly having to make adaptations, which are typically improvised, highly variable and not coordinated across teams. This study aimed...

Prioritising patients for publicly funded bariatric surgery in Queensland, Australia.

This study reports the development and pilot application of the Bariatric Surgery Assessment and Prioritisation Tool (BAPT) for use in a public health system. The BAPT was designed as a patient prioritisation instrument to assess patients with excessive weight and type 2 diabetes suitable for bariatric surgery. We assessed whether the instrument successfully identified those who gained the greatest benefits including weight loss, diabetes remission, reduction in comorbidities, and health-related quality of life (HR-QoL). The BAPT instrument was applied to score 292 patients referred for bariatric surgery in Queensland between 2017 and 2020 based on their, body mass index, diabetes status, surgical risk (e.g. pulmonary embolism) and comorbidities (e.g. non-alcoholic steatohepatitis). These data were collected at referral and at 12-months post-surgery for 130 patients and stratified by BAPT scores. Outcomes included clinical and HR-QoL. Patients' BAPT scores ranged from 12 to 78 (possible range 2-98). Those with higher scores tended to be younger (p < 0.001), have higher BMI (p < 0.001) or require insulin to manage diabetes (p < 0.01). All patients lost similar percentages of body weight (20-25%, p = 0.73) but higher-scoring patients were more likely to discontinue oral diabetes medications (p < 0.001) and the improvement in glycated haemoglobin was four times greater in patients scoring 70-79 points compared to those scoring 20-29 (p < 0.05). Those who scored ≥ 50 on the BAPT were substantially more likely to obtain diabetes remission (57% vs 31%). BAPT scores of 40 and above tended to have greater improvement in HR-QoL. The BAPT prioritised younger patients with higher BMIs who realised greater improvements in their diabetes after bariatric surgery. Higher-scoring BAPT patients should be prioritised for bariatric surgery as they have a greater likelihood of attaining diabetes remission.

Promoting medication safety for older adults upon hospital discharge: Guiding principles for a medication discharge plan.

Older adults are at risk of adverse drug events during transition of care from hospital to community, thus optimal communication about medications at discharge is essential. Standardization of medication discharge plan (MDP) is lacking. This study aimed to (1) create a standardized MDP for older adults using consensus-based principles, (2) create a short-version MDP and (3) generate a practical guide. Modified Delphi was used to establish consensus on guiding principles for the MDP. Additionally, participants were asked about guiding principles deemed most essential, patient prioritization, the format and mode of transmission of the MDP. Twenty-six guiding principles reached consensus, with 17 prioritized for a short-version MDP. The practical guide includes explanations of the guiding principles, criteria for patient selection and recommendations on the format and mode of transmission. The results of this study will assist implementation of MDPs when older adults are discharged from hospital.

Efficacy and safety of a digital check-in and triage kiosk in emergency departments: a systematic review protocol

IntroductionIncreasing demand for healthcare services worldwide has led to unprecedented challenges in managing patient flow and delivering timely care in emergency care settings. Overcrowding, prolonged waiting times, reduced patient satisfaction...

Optimising the use of colonoscopy to improve risk stratification for colorectal cancer in symptomatic patients: A decision-curve analysis.

Pressured healthcare resources make risk stratification and patient prioritisation fundamental issues for the investigation of colorectal cancer (CRC) in symptomatic patients. The present study uses machine learning algorithms and decision strategies to improve the appropriate use of colonoscopy. All symptomatic patients in a single health board (2018-2021) proceeding to colonoscopy to investigate for CRC were included. Machine learning algorithms (NeuralNetwork, randomForest, Logistic regression, Naïve-Bayes and Adaboost) were used to risk-stratify patients for CRC using demographics, symptoms, quantitative faecal immunochemical test (qFIT) and haematological tests. Decision curve analyses were performed to determine the optimal decision strategies. 3776 patients were included (median age, 65; M:F,0.9:1.0) and CRC was identified in 217 patients (5.7%). qFIT > 400 μg Hb/g was the most important variable (%IncMSE = 78.5). RandomForrest had the highest area under curve (0.91) and accuracy (0.80) for CRC. When utilising decision curve analysis (DCA), 30%, 46% and 54% of colonoscopies were saved at accepted CRC probabilities of 1%, 2% and 3%, respectively. RandomForrest modelling had superior net clinical benefit compared to default colonoscopy strategies. MLA-derived decision strategies that account for patient and referrer risk preference reduce colonoscopy demand and carry net clinical benefit compared to default colonoscopy strategies.

Incorporating machine learning and optimization techniques for assigning patients to operating rooms by considering fairness policies

Operating rooms (ORs) are key to a hospital's profitability, and increasing their benefits helps decrease surgical costs, minimize patient waiting times, and boost the number of patients admitted for surgery. This study presents a mixed-integer linear programming (MILP) model to address the issue of treating inpatients in operating rooms waiting for admission to the referral department. Moreover, it proposes a practical algorithm that minimizes overtime costs in operating rooms and increases patient satisfaction. Our model uses an integrated machine learning - tabu search (ML-TS) method. The proposed model uses differential ML and heuristic rules to achieve enhanced performance and scalability in solving complex optimization problems. A fairness policy is implemented, combined with an optimization method, to guide patient prioritization. This approach considers factors like urgency, waiting times, or specific patient needs and helps determine the order in which patients are scheduled for surgery. The outcomes imply that patient adaptability has led to savings ranging from 50% to 65% per surgery. Additionally, the Machine Learning-Tabu Search (ML-TS) algorithm has increased performance by about 35%. These algorithms also let the OR manager define the size of the uncertainty set and regulate overtime costs while accommodating surgeons' preferences as managerial implications insight. It adeptly navigates the solution space, identifies feasible solutions, and accelerates convergence.

At-admission prediction of mortality and pulmonary embolism in an international cohort of hospitalised patients with COVID-19 using statistical and machine learning methods

By September 2022, more than 600 million cases of SARS-CoV-2 infection have been reported globally, resulting in over 6.5 million deaths. COVID-19 mortality risk estimators are often, however, developed with small unrepresentative samples and with methodological limitations. It is highly important to develop predictive tools for pulmonary embolism (PE) in COVID-19 patients as one of the most severe preventable complications of COVID-19. Early recognition can help provide life-saving targeted anti-coagulation therapy right at admission. Using a dataset of more than 800,000 COVID-19 patients from an international cohort, we propose a cost-sensitive gradient-boosted machine learning model that predicts occurrence of PE and death at admission. Logistic regression, Cox proportional hazards models, and Shapley values were used to identify key predictors for PE and death. Our prediction model had a test AUROC of 75.9% and 74.2%, and sensitivities of 67.5% and 72.7% for PE and all-cause mortality respectively on a highly diverse and held-out test set. The PE prediction model was also evaluated on patients in UK and Spain separately with test results of 74.5% AUROC, 63.5% sensitivity and 78.9% AUROC, 95.7% sensitivity. Age, sex, region of admission, comorbidities (chronic cardiac and pulmonary disease, dementia, diabetes, hypertension, cancer, obesity, smoking), and symptoms (any, confusion, chest pain, fatigue, headache, fever, muscle or joint pain, shortness of breath) were the most important clinical predictors at admission. Age, overall presence of symptoms, shortness of breath, and hypertension were found to be key predictors for PE using our extreme gradient boosted model. This analysis based on the, until now, largest global dataset for this set of problems can inform hospital prioritisation policy and guide long term clinical research and decision-making for COVID-19 patients globally. Our machine learning model developed from an international cohort can serve to better regulate hospital risk prioritisation of at-risk patients.

Significant increase of emergency hernia operation during COVID.

During the COVID-19 pandemic, elective surgeries including hernia repairs, were postponed, or cancelled completely. However, it has been stated previously that the volume of surgical emergency hernia repairs did not drop during this period. Due to the disruption in elective surgeries, waiting lists have increased rapidly, causing a suspected treatment delay. To gain improved insight in preoperative patient prioritization, the aim of this multicenter study was to track volumes of hernia surgery before, during and after the pandemic to investigate for a shift from elective towards emergency hernia surgery. A retrospective study using hernia databases from four regional hospitals to account for altered referral patterns (elective versus emergent), capturing patients' admissions and surgery times for both groin and ventral hernia repair was conducted. Study period was predefined from March 2019 to March 2023. Data are presented as descriptive statistics. During the historic period, 106 of 2267 hernia surgeries (4.7%) performed were defined as emergency repairs. During the pandemic, 3864 elective surgeries were executed, of which 213(5.5%) emergencies. During the current period, the portion of emergencies dropped to 4.9% (110 emergency hernia repairs); (p = 0.039). A non-significant increase in emergent incisional hernia repair during the pandemic period was found chronologically 9.9%, 11.8% and 11.6% emergent repairs(p = 0.75). There were no statistically significant differences across the hernia types in elective versus urgent rate. During the historic period, 106 of 2267 hernia surgeries (4.7%) performed were defined as emergency repairs. During the pandemic, 3864 elective surgeries were executed, of which 213(5.5%) emergencies. During the current period, the portion of emergencies dropped to 4.9% (110 emergency hernia repairs); (p = 0.039). A non-significant increase in emergent incisional hernia repair during the pandemic period was found chronologically 9.9%, 11.8% and 11.6% emergent repairs(p = 0.75). There were no statistically significant differences across the hernia types in elective versus urgent rate. Regionwide data showed a 15% decline in hernia repairs during the pandemic compared to historical levels, with an 0.8% increase in emergent repairs. Surgery rates are still convalescent after the pandemic, with a persistent proportion of emergent surgeries. These numbers emphasize the challenges in selecting patient whose hernia repair should not be postponed.

Cost-effectiveness of preoperative pharmaceutical care consultations: a 5-year analysis

ObjectivesPreoperative medication errors can be prevented by screening patients through a preoperative pharmaceutical care consultation. The aim of this study was to analyse the cost-effectiveness of implementing such a consultation...

Admission prioritization of heart failure patients with multiple comorbidities.

The primary objective of this study was to enhance the operational efficiency of the current healthcare system by proposing a quicker and more effective approach for healthcare providers to deliver services to individuals facing acute heart failure (HF) and concurrent medical conditions. The aim was to support healthcare staff in providing urgent services more efficiently by developing an automated decision-support Patient Prioritization (PP) Tool that utilizes a tailored machine learning (ML) model to prioritize HF patients with chronic heart conditions and concurrent comorbidities during Urgent Care Unit admission. The study applies key ML models to the PhysioNet dataset, encompassing hospital admissions and mortality records of heart failure patients at Zigong Fourth People's Hospital in Sichuan, China, between 2016 and 2019. In addition, the model outcomes for the PhysioNet dataset are compared with the Healthcare Cost and Utilization Project (HCUP) Maryland (MD) State Inpatient Data (SID) for 2014, a secondary dataset containing heart failure patients, to assess the generalizability of results across diverse healthcare settings and patient demographics. The ML models in this project demonstrate efficiencies surpassing 97.8% and specificities exceeding 95% in identifying HF patients at a higher risk and ranking them based on their mortality risk level. Utilizing this machine learning for the PP approach underscores risk assessment, supporting healthcare professionals in managing HF patients more effectively and allocating resources to those in immediate need, whether in hospital or telehealth settings.

Optimizing Telehealth: Leveraging Key Performance Indicators for Enhanced TeleHealth and Digital Healthcare Outcomes (Telemechron Study).

Over the past decade, the use of telehealth has garnered increasing attention. The focus on quality aspects has seen significant growth in tandem with the telehealth expansion. Having useful indicators in this area is becoming increasingly strategic for fully integrating the technology into the health domain. These indicators can help monitor and evaluate the quality of telehealth services, guiding improvements and ensuring that these digital solutions meet the necessary standards for effective healthcare delivery. The purpose of this study is to analyze Key performance indicators (KPIs) in telehealth within institutional websites and the scientific dissemination world by means of a narrative review. A narrative review was proposed with these two specific points of view based on a standardized checklist and a quality control procedure for including scientific papers in the analysis. Results from scientific studies emphasize KPIs such as patient outcomes, operational efficiency, technical reliability, and cost-effectiveness. These include measures like improvements in condition management, patient satisfaction, consultation numbers, waiting times, and cost savings. Institutional documents from entities like the WHO also show diverse perspectives, focusing on equitable access, clinical excellence, patient prioritization, response times, and patient and staff satisfaction. The findings suggest that adopting a comprehensive set of KPIs and continuously monitoring and evaluating telehealth services can enhance their effectiveness, efficiency, and equity, ultimately improving healthcare outcomes and accessibility.

External validation of a paediatric Smart triage model for use in resource limited facilities.

Models for digital triage of sick children at emergency departments of hospitals in resource poor settings have been developed. However, prior to their adoption, external validation should be performed to ensure their generalizability. We externally validated a previously published nine-predictor paediatric triage model (Smart Triage) developed in Uganda using data from two hospitals in Kenya. Both discrimination and calibration were assessed, and recalibration was performed by optimizing the intercept for classifying patients into emergency, priority, or non-urgent categories based on low-risk and high-risk thresholds. A total of 2539 patients were eligible at Hospital 1 and 2464 at Hospital 2, and 5003 for both hospitals combined; admission rates were 8.9%, 4.5%, and 6.8%, respectively. The model showed good discrimination, with area under the receiver-operator curve (AUC) of 0.826, 0.784 and 0.821, respectively. The pre-calibrated model at a low-risk threshold of 8% achieved a sensitivity of 93% (95% confidence interval, (CI):89%-96%), 81% (CI:74%-88%), and 89% (CI:85%-92%), respectively, and at a high-risk threshold of 40%, the model achieved a specificity of 86% (CI:84%-87%), 96% (CI:95%-97%), and 91% (CI:90%-92%), respectively. Recalibration improved the graphical fit, but new risk thresholds were required to optimize sensitivity and specificity.The Smart Triage model showed good discrimination on external validation but required recalibration to improve the graphical fit of the calibration plot. There was no change in the order of prioritization of patients following recalibration in the respective triage categories. Recalibration required new site-specific risk thresholds that may not be needed if prioritization based on rank is all that is required. The Smart Triage model shows promise for wider application for use in triage for sick children in different settings.