Hospital performance evaluation indicators: a scoping review.

BACKGROUND: Hospitals are the biggest consumers of health system budgets and hence measuring hospital performance by quantitative or qualitative accessible and reliable indicators is crucial. This review aimed to categorize and present a set of indicators for evaluating overall hospital performance. METHODS: We conducted a literature search across three databases, i.e., PubMed, Scopus, and Web of Science, using possible keyword combinations. We included studies that explored hospital performance evaluation indicators from different dimensions. RESULTS: We included 91 English language studies published in the past 10 years. In total, 1161 indicators were extracted from the included studies. We classified the extracted indicators into 3 categories, 14 subcategories, 21 performance dimensions, and 110 main indicators. Finally, we presented a comprehensive set of indicators with regard to different performance dimensions and classified them based on what they indicate in the production process, i.e., input, process, output, outcome and impact. CONCLUSION: The findings provide a comprehensive set of indicators at different levels that can be used for hospital performance evaluation. Future studies can be conducted to validate and apply these indicators in different contexts. It seems that, depending on the specific conditions of each country, an appropriate set of indicators can be selected from this comprehensive list of indicators for use in the performance evaluation of hospitals in different settings.

An Agile Systems Modeling Framework for Bed Resource Planning During COVID-19 Pandemic in Singapore.

Background: The COVID-19 pandemic has had a major impact on health systems globally. The sufficiency of hospitals' bed resource is a cornerstone for access to care which can significantly impact the public health outcomes. Objective: We describe the development of a dynamic simulation framework to support agile resource planning during the COVID-19 pandemic in Singapore. Materials and Methods: The study data were derived from the Singapore General Hospital and public domain sources over the period from 1 January 2020 till 31 May 2020 covering the period when the initial outbreak and surge of COVID-19 cases in Singapore happened. The simulation models and its variants take into consideration the dynamic evolution of the pandemic and the rapidly evolving policies and processes in Singapore. Results: The models were calibrated against historical data for the Singapore COVID-19 situation. Several variants of the resource planning model were rapidly developed to adapt to the fast-changing COVID-19 situation in Singapore. Conclusion: The agility in adaptable models and robust collaborative management structure enabled the quick deployment of human and capital resources to sustain the high level of health services delivery during the COVID-19 surge.

Machine learning-based demand forecasting in cancer palliative care home hospitalization.

OBJECTIVE: To develop an effective Management Information System (MIS) that is empowered by predictive models that can forecast the demand of end-stage cancer home hospitalized patients in individual and population levels, and help palliative care service systems operate smoothly where the demand is highly fluctuating, resources are limited, expensive, and hardly adjustable in a short time, and the backlog and shortage costs are high. METHOD: Inspired by real problems faced by a palliative care center providing various medical, nursing, psychological, and social services in a home-based setting, two Long Short-Term Memory (LSTM) based deep learning models are proposed for demand forecasting at both individual and population levels. The individual-level model can predict the type and time of the next service required for a specific patient with a given demographic and health profile, and the population-level model helps with the prediction of next week's demand for various services in a center supporting a specific patient population. Predicted demand informs on optimal resource and operations plan through a well designed MIS. RESULTS: Experiments were conducted on a dataset consisting of more than 4000 cancer patients with a Palliative Performance Scale (PPS) of 40 and below discharged from hospital to home under a national palliative care center's home hospitalization service in Iran from September 2012 to July 2019. The models outperformed conventional time-series forecasting methods where applicable. Results indicate that the proposed models were capable of forecasting patients' demand with astonishing performances both individually and on larger scales. CONCLUSION: Intelligent demand forecasting can help palliative care home hospitalization systems to overcome the challenge of progressive demand growth when a considerable portion of patients are approaching death, followed by a sudden drop in demand when those patients pass away. It helps to improve resource utilization and quality of care concurrently.

Maximum expected survival rate model for public access defibrillator placement.

AIM: Mathematical optimization of automated external defibrillator (AED) placement has demonstrated potential to improve survival of out-of-hospital cardiac arrest (OHCA). Existing models mostly aim to improve accessibility based on coverage radius and do not account for detailed impact of delayed defibrillation on survival. We aimed to predict OHCA survival based on time to defibrillation and developed an AED placement model to directly maximize the expected survival rate. METHODS: We stratified OHCAs occurring in Singapore (2010-2017) based on time to defibrillation and developed a regression model to predict the Utstein survival rate. We then developed a novel AED placement model, the maximum expected survival rate (MESR) model. We compared the performance of MESR with a maximum coverage model developed for Canada that was shown to be generalizable to other settings (Denmark). The survival gain of MESR was assessed through 10-fold cross-validation for placement of 20 to 1000 new AEDs in Singapore. Statistical analysis was performed using χ2 and McNemar's tests. RESULTS: During the study period, 15,345 OHCAs occurred. The power-law approximation with R2 of 91.33% performed best among investigated models. It predicted a survival of 54.9% with defibrillation within the first two minutes after collapse that was reduced by more than 60% without defibrillation within the first 4 minutes. MESR outperformed the maximum coverage model with P-value < 0.05 (<0.0001 in 22 of 30 experiments). CONCLUSION: We developed a novel AED placement model based on the impact of time to defibrillation on OHCA outcomes. Mathematical optimization can improve OHCA survival.

Development and validation of the SARICA score to predict survival after return of spontaneous circulation in out of hospital cardiac arrest using an interpretable machine learning framework.

BACKGROUND: Accurate and timely prognostication of patients with out-of-hospital cardiac arrest (OHCA) who achieved the return of spontaneous circulation (ROSC) is crucial in clinical decision-making, resource allocation, and communications with next-of-kins. We aimed to develop the Survival After ROSC in Cardiac Arrest (SARICA), a practical clinical decision tool to predict survival in OHCA patients who attained ROSC. METHODS: We utilized real-world Singapore data from the population-based Pan-Asian Resuscitation Outcomes Study between 2010-2018. We excluded patients without ROSC. The dataset was segmented into training (60%), validation (20%) and testing (20%) cohorts. The primary endpoint was survival (to 30-days or hospital discharge). AutoScore, an interpretable machine-learning based clinical score generation algorithm, was used to develop SARICA. Candidate factors were chosen based on objective demographic and clinical factors commonly available at the time of admission. Performance of SARICA was evaluated based on receiver-operating curve (ROC) analyses. RESULTS: 5970 patients were included, of which 855 (14.3%) survived. A three-variable model was determined to be most parsimonious. Prehospital ROSC, age, and initial heart rhythm were identified for inclusion via random forest selection. Finally, SARICA consisted of these 3 variables and ranged from 0 to 10 points, achieving an area under the ROC (AUC) of 0.87 (95% confidence interval: 0.84-0.90) within the testing cohort. CONCLUSION: We developed and internally validated the SARICA score to accurately predict survival of OHCA patients with ROSC at the time of admission. SARICA is clinically practical and developed using an interpretable machine-learning framework. SARICA has unknown generalizability pending external validation studies.

The effectiveness of public health interventions against COVID-19: Lessons from the Singapore experience.

BACKGROUND: In dealing with community spread of COVID-19, two active interventions have been attempted or advocated-containment, and mitigation. Given the extensive impact of COVID-19 globally, there is international interest to learn from best practices that have been shown to work in controlling community spread to inform future outbreaks. This study explores the trajectory of COVID-19 infection in Singapore had the government intervention not focused on containment, but rather on mitigation. In addition, we estimate the actual COVID-19 infection cases in Singapore, given that confirmed cases are publicly available. METHODS AND FINDINGS: We developed a COVID-19 infection model, which is a modified SIR model that differentiate between detected (diagnosed) and undetected (undiagnosed) individuals and segments total population into seven health states: susceptible (S), infected asymptomatic undiagnosed (A), infected asymptomatic diagnosed (I), infected symptomatic undiagnosed (U), infected symptomatic diagnosed (E), recovered (R), and dead (D). To account for the infection stages of the asymptomatic and symptomatic infected individuals, the asymptomatic infected individuals were further disaggregated into three infection stages: (a) latent (b) infectious and (c) non-infectious; while the symptomatic infected were disaggregated into two stages: (a) infectious and (b) non-infectious. The simulation result shows that by the end of the current epidemic cycle without considering the possibility of a second wave, under the containment intervention implemented in Singapore, the confirmed number of Singaporeans infected with COVID-19 (diagnosed asymptomatic and symptomatic cases) is projected to be 52,053 (with 95% confidence range of 49,370-54,735) representing 0.87% (0.83%-0.92%) of the total population; while the actual number of Singaporeans infected with COVID-19 (diagnosed and undiagnosed asymptomatic and symptomatic infected cases) is projected to be 86,041 (81,097-90,986), which is 1.65 times the confirmed cases and represents 1.45% (1.36%-1.53%) of the total population. A peak in infected cases is projected to have occurred on around day 125 (27/05/2020) for the confirmed infected cases and around day 115 (17/05/2020) for the actual infected cases. The number of deaths is estimated to be 37 (34-39) among those infected with COVID-19 by the end of the epidemic cycle; consequently, the perceived case fatality rate is projected to be 0.07%, while the actual case fatality rate is estimated to be 0.043%. Importantly, our simulation model results suggest that there about 65% more COVID-19 infection cases in Singapore that have not been captured in the official reported numbers which could be uncovered via a serological study. Compared to the containment intervention, a mitigation intervention would have resulted in early peak infection, and increase both the cumulative confirmed and actual infection cases and deaths. CONCLUSION: Early public health measures in the context of targeted, aggressive containment including swift and effective contact tracing and quarantine, was likely responsible for suppressing the number of COVID-19 infections in Singapore.

Impact of COVID-19 on acute isolation bed capacity and nursing workforce requirements: A retrospective review.

AIM: To understand the impact of COVID-19 on isolation bed capacity requirements, nursing workforce requirements and nurse:patient ratios. BACKGROUND: COVID-19 created an increased demand for isolation beds and nursing workforce globally. METHODS: This was a retrospective review of bed capacity, bed occupancy and nursing workforce data from the isolation units of a tertiary hospital in Singapore from 23 January 2020 to 31 May 2020. R v4.0.1 and Tidyverse 1.3.0 library were used for data cleaning and plotly 4.9.2.1 library for data visualization. RESULTS: In January to March 2020, isolation bed capacity was low (=<203 beds). A sharp increase in bed capacity was seen from 195 to 487 beds during 25 March to 29 April 2020, after which it plateaued. Bed occupancy remained lower than bed capacity throughout January to May 2020. After 16 April 2020, we experienced a shortage of 1.1 to 70.2 nurses in isolation wards. Due to low occupancy rates, nurse:patient ratio remained acceptable (minimum nurse:patient ratio = 0.26). CONCLUSION: COVID-19 caused drastic changes in isolation bed capacity and nursing workforce requirements. IMPLICATIONS FOR NURSING MANAGEMENT: Building a model to predict nursing workforce requirements during pandemic surges may be helpful for planning and adequate staffing.