Bed Resources Research Articles

625 The Impact of COVID-19 on Burn Care at a Regional Burn Center

IntroductionThe COVID-19 pandemic has had a profound global impact, not least on hospital functioning. Institutions have all had to prepare and adapt to a large number of admissions, and the influence on elective and emergency surgical services, including burn care, has been significant; it may be some time before we know the full extent of this. While many centers were able to commence more normal activities for a while, we are now seeing an exponential rise in cases again, with potentially catastrophic consequences for the provision of burn care.MethodsA review of all admissions, operative cases and clinic visits between 1 April and 31 August 2020 was undertaken at an American Burn Association verified burn center. These data were compared with the same five-month period in the preceding two years.ResultsSelected data highlights are tabulated (Table 1). During the five months in question, fewer patients were admitted than the previous two years (N=81 versus 121). The mean total body surface area was slightly higher this year (13.7%), and the mean length of hospital stay longer (18 days). The male-to-female ratio of admitted patients was greater during the five months of 2020, at 2.9:1, compared to 1.7:1. No significant differences in terms of etiology were detected, however. As expected, clinic visits reduced dramatically from a mean of 160 patient visits per month to just 81 per month, with the majority conducted virtually. During 2020 the operative cases were similar in number to previous years (N=176), but the mean duration was significantly longer (190 minutes). The total time utilised for burn surgery was similar to previous years (572 hours). Table 1. Selected burn center data comparing 2020 with 2019 and 2018.ConclusionsThis study demonstrates that although total admissions were slightly reduced, the demands on Burn ICU bed resources and burn operating time were similar. The data supports the notion that removing scheduled operating time for our service resulted in less efficient execution of acute burn surgeries and longer hospital stays. Although formal clinic visits were significantly reduced and were mainly conducted virtually, several patients were satisfied by a novel and user-friendly email service conducted by our clinic nurse specialist.

Cope with the COVID-19 Pandemic: Dynamic Bed Allocation and Patient Subsidization in a Public Healthcare System

In many countries and territories, public hospitals play a major role in coping with the COVID-19 pandemic. For public hospital managers, on the one hand, they must best utilize their hospital beds to serve the COVID-19 patients immediately. On the other hand, they need to consider the need of bed resources from non-COVID-19 patients, including emergency and elective patients. In this work, we consider two control mechanisms for public hospital managers to maximize the overall utility of patients. One is the dynamic allocation of bed resources according to the evolution process of the COVID-19 pandemic. The other is the usage of a subsidy scheme to move elective patients from the public to private hospitals. We develop a dynamic programming model to study the allocation of isolation and ordinary beds and the effect of the subsidy policy in serving three types of patients, COVID-19, emergency, and elective-care. We first show that the dynamic allocation between isolation and ordinary beds can provide a better utilization of bed resources, by cutting down at least 33.5\% of the total cost compared with the static policy (i.e., keeping a fixed number of isolation beds) when facing a medium pandemic alert. Our results further show that subsidizing elective patients and referring them to private hospitals is an efficient way to ease the overcrowded situation in public hospitals. Our results demonstrate that, by dynamically conducting bed allocation and subsidy scheme in different phases of the COVID-19 pandemic, patient overall utility can be greatly improved.

Status and dynamics of parameters of use of bed capacity of oncological profile in Russian Federation

In the Russian Federation (RF) a steady growth of morbidity with oncologic diseases is observed. An important factor of reduction of negative influence of oncopathology on the parameters of public health is provision of the population with specialists and beds of oncological profile, as well as their effective use.
 Aim. To determine the status and identify dynamics of the main parameters of use of beds of oncological profile of the state healthcare system of RF, federal districts and constituent entities of RF in comparison with tendencies of parameters of morbidity with malignant neoplasms, and also of provision of the population with medical personnel in the period from 2010 to 2019.
 Materials and Methods. Using the data of the Federal statistical observation forms (№30, 47, 14LC, 7) based on the calculation of absolute and relative parameters by the descriptive statistics method, the analysis of the main parameters of the use of bed resources of oncology profile was carried out in comparison with the parameters of morbidity with malignant neoplasms and provision of the population with medical personnel in 24-hour and day-stay hospitals in the Russian Federation, federal districts and constituent entities of the Russian Federation in 2010-2019.
 Results. During the study period, with the underlying increase in the morbidity of the population with diseases of neoplasm class (primarily, malignant) in the Russian Federation, there was found a regular increase in: the absolute number of oncological beds for 24-hour stay by 5.216 beds (+16.8%), provision with these beds from 2.17 to 2.47 per 10 000 population (+13.8%), hospitalization rate from 6.1 to 9.6 per 1000 population (+57.4%); and a decrease in: average stay in an oncological bed by 3.7 days (-30.6%, from 12.1 to 8.4 days), and the average bed occupancy by 15 days per year (-4.3%, from 345 to 330 days). Mortality in cancer beds increased from 0.76% in 2010 to 0.95% in 2019 (by 25.0%). There was an increase in the provision of the population with oncological beds in day-stay hospitals by 3.4 times, in day-stay hospitals of polyclinics by 63.6%.
 Conclusion. With the underlying growth of oncological morbidity in the country, the bed capacity of the oncological profile of 24-hour and day hospitals has significantly increased, with a high level of disproportional development of the bed capacity both between federal districts and between the subjects of the Russian Federation.

Optimization of Markov Queuing Model in Hospital Bed Resource Allocation.

Bed resources are the platform in which most medical and health resources in the hospital play a role and carry the core functions of the health service system. How to improve the efficiency of the use of bed resources through scientific management measures and methods and ultimately achieve the optimization of overall health resources is the focus of hospital management teams. This paper analyzes the previous research models of knowledge related to queuing theory in medical services. From the perspective of the hospital and the patient, several indicators such as the average total number of people, the utilization rate of bed resources, the patient stop rate, and the patient average waiting time are defined to measure the performance of the triage queue calling model, which makes the patient queue more reasonable. According to the actual task requirements of a hospital, a Markov queuing strategy based on Markov service is proposed. A mathematical queuing model is constructed, and the process of solving steady-state probability based on Markov theory is analyzed. Through the comparative analysis of simulation experiments, the advantages and disadvantages of the service Markov queuing model and the applicable scope are obtained. Based on the theory of the queuing method, a queuing network model of bed resource allocation is established in principle. Experimental results show that the queuing strategy of bed resource allocation based on Markov optimization effectively improves resource utilization and patient satisfaction and can well meet the individual needs of different patients. It does not only provide specific optimization measures for the object of empirical research but also provides a reference for the development of hospital bed resource allocation in theory.

Balancing revenue generation with capacity generation: case distribution, financial impact and hospital capacity changes from cancelling or resuming elective surgeries in the US during COVID-19

BackgroundTo increase bed capacity and resources, hospitals have postponed elective surgeries, although the financial impact of this decision is unknown. We sought to report elective surgical case distribution, associated gross hospital revenue and regional hospital and intensive care unit (ICU) bed capacity as elective surgical cases are cancelled and then resumed under simulated trends of COVID-19 incidence.MethodsA retrospective, cohort analysis was performed using insurance claims from 161 million enrollees from the MarketScan database from January 1, 2008 to December 31, 2017. COVID-19 cases were calculated using Institute for Health Metrics and Evaluation models. Centers for Disease Control (CDC) reports on the number of hospitalized and intensive care patients by age estimated the number of cases seen in the ICU, the reduction in elective surgeries and the financial impact of this from historic claims data, using a denominator of all inpatient revenue and outpatient surgeries.ResultsAssuming 5% infection prevalence, cancelling all elective procedures decreases ICU overcapacity from 160 to 130%, but these elective surgical cases contribute 78% (IQR 74, 80) (1.1 trillion (T) US dollars) to inpatient hospital plus outpatient surgical gross revenue per year. Musculoskeletal, circulatory and digestive category elective surgical cases compose 33% ($447B) of total revenue.ConclusionsProcedures involving the musculoskeletal, cardiovascular and digestive system account for the largest loss of hospital gross revenue when elective surgery is postponed. As hospital bed capacity increases following the COVID-19 pandemic, restoring volume of these elective cases will help maintain revenue. In these estimates, adopting universal masking would help to avoid overcapacity in all states.

Day-case pelvic osteotomy for developmental dysplasia of the hip.

Purpose:In this article we report the results of a pilot study analysing the implications of performing pelvic osteotomies for developmental dysplasia of the hip (DDH) as a day case. We assess the advantages of performing paediatric pelvic osteotomies as day-case procedures from a financial perspective and from an in-patient bed resource point of view.Methods:This was a prospective cohort study analysing Salter and Pemberton pelvic osteotomies performed for DDH over a three-year period from 1st January 2017 to 30th September 2019. All patients residing within 50 km of the hospital were eligible for day-case procedures. All other cases were performed as in-patients. A detailed financial costing analysis was performed and the in-patient resources utilized were documented and compared between the two models of care.Results:In total, 84 Salter and Pemberton osteotomies were performed between 1st January 2017 to 30th September 2019. Of these cases, 35 were performed as day-case procedures. A total reduction in 70 in-patient bed days was reported. Total costs for a single in-patient requiring two nights of admission amounted to €5,752, whereas the discharge cost of a day case was reported at €2,670. The savings made by our institution amounted to €3,082 per day case. A total saving of €102,696 was made over three years. In all, seven day-case patients re-attended due to inadequate pain control. They required overnight admission and were discharged uneventfully the following day.Conclusion:Day-case pelvic osteotomies significantly reduce the number of in-patient bed days used in an elective paediatric orthopaedic setting. Significant financial savings in excess of €3,000 per case are possible. The introduction of day-case pelvic osteotomy procedures can significantly improve the cost-effectiveness of managing DDH provided there are clear protocols in place with close clinical follow-up.Level of evidence:IV

A Closer Look Into Global Hospital Beds Capacity and Resource Shortages During the COVID-19 Pandemic

BackgroundAs the COVID-19 pandemic continues, there is a question of whether hospitals have adequate resources to manage patients. We aim to investigate global hospital bed (HB), acute care bed (ACB), and intensive care unit (ICU) bed capacity and determine any correlation between these hospital resources and COVID-19 mortality. MethodCross-sectional study utilizing data from the World Health Organization (WHO) and other official organizations regarding global HB, ACB, ICU bed capacity, and confirmed COVID-19 cases/mortality. Descriptive statistics and linear regression were performed. ResultsA total of 183 countries were included with a mean of 307.1 HBs, 413.9 ACBs, and 8.73 ICU beds/100,000 population. High-income regions had the highest mean number of ICU beds (12.79) and HBs (402.32) per 100,000 population whereas upper middle-income regions had the highest mean number of ACBs (424.75) per 100,000. A weakly positive significant association was discovered between the number of ICU beds/100,000 population and COVID-19 mortality. No significant associations exist between the number of HBs or ACBs per 100,000 population and COVID-19 mortality. ConclusionsGlobal COVID-19 mortality rates are likely affected by multiple factors, including hospital resources, personnel, and bed capacity. Higher income regions of the world have greater ICU, acute care, and hospital bed capacities. Mandatory reporting of ICU, acute care, and hospital bed capacity/occupancy and information relating to coronavirus should be implemented. Adopting a tiered critical care approach and targeting the expansion of space, staff, and supplies may serve to maximize the quality of care during resurgences and future disasters.

Ubiquitous measurement methods of long‐term nursing bed resource allocation based on multi‐sensor social internet of things

This article starts from the service population of long‐term care beds and estimates the spatial distribution of long‐term care beds in the area. At the same time, combined with the spatial distribution of beds in the area, the supply of long‐term care beds is based on the division of service areas. Long‐term care institutions are facilities for the care and care of disabled elderly people. The beds are long‐term care beds, and the clients are mainly elderly people who cannot take care of themselves. The demand for long‐term care beds is mainly related to the number of elderly people. The elderly population in this article mainly refers to the resident population aged 60 and above. Based on the layout map of the resident population aged 60 and above, combined with the area of the administrative divisions of the village committees, the population density of each village committee is calculated to produce a schematic diagram. We use the data connection analysis model and the pattern finding algorithm to optimize the traditional methodologies.

Number of long-term inpatients in Japanese psychiatric care beds: trend analysis from the patient survey and the 630 survey

BackgroundThe number of psychiatric care beds and the mean length of stay in psychiatric care beds in Japan have decreased over the past 10 years. However, as has long been indicated here and elsewhere, Japan lags behind other countries in terms of deinstitutionalization. Furthermore, the population of inpatients in psychiatric care beds is aging dramatically. In addition to the diversification of mental illness, the question of what measures to implement going forward regarding current psychiatric bed resources has emerged as a new challenge.MethodsUsing data from the Patient Survey and the 630 Survey, we examined trends in the number of long-term inpatients in psychiatric care beds in Japan through 2040. Population estimation was used for estimating long-term hospital bed demand because of small fluctuations in the admission and discharge of long-term inpatients.ResultsIn 2017, nearly one-third of all long-term hospitalized patients were aged ≥75 years, and an estimated 47% of the total are expected to die by 2040. Thus, the overall demand for long-term hospitalization is forecast to decrease sharply due to aging of currently hospitalized long-term inpatients. The number of long-term inpatients in 2017 was 167,579, and this is projected to decrease to 103,141 in 2040.ConclusionsWe believe it is necessary to adopt a multifaceted approach to promote hospital discharge and transition to the community, and to address the diversification of mental illness and the issue of psychiatric care bed supply/availability, which are forecast to decrease due to the natural decrease in long-term inpatients.

Lost bed capacity in emergency departments: A descriptive analysis and data visualisation exploration.

To map utilisation of bed resources within an ED over time, in order to determine the proportions of patient stay spent receiving emergency care versus non-emergent care. To produce visualisations that effectively convey this bed utilisation. This was a retrospective cohort study using routinely collected administrative data, derived from the ED electronic health record (FirstNet; Cerner, North Kansas City, MO, USA), on all patients presenting to a single tertiary-level ED during a 1-month period and who were triaged to an acute area bed in order to undergo their emergency care. Resuscitation, subacute, fast track and paediatric area patients were excluded from analysis as firstly, in our institution the acute area processing appears to contribute most to barriers to patient flow and secondly, using acute area patients allowed us to approximate standardisation of acuity. Lost bed capacity (LBC) was defined as the time spent in an ED bed after an emergency clinician indicated that they were ready to depart the ED, as recorded in the electronic medical record. The overall proportion of time spent in an ED bed after completion of emergency care was 38.5% (interquartile range 21.8-47.2%). This time differed significantly between 'discharged' (1 min), 'admitted-ward' (72 min) and 'admitted-critical care' (110 min) groups. This was clearly revealed in our novel LBC heatmaps. A considerable proportion of ED length of stay is because of patients remaining in an ED bed after their emergency care is concluded. Absolute time is much greater for admitted patients than for discharged patients, and therefore efforts to reduce LBC are likely to reduce overall ED length of stay. LBC heatmaps may provide an intuitively useful, potentially automated tool to understand these problems.

Research on forecasting coal bed methane demand and resource allocation system based on time series

The mining area is the main place for the development and utilization of Coalbed Methane (CBM), and there are a series of systems for the development and utilization of CBM. However, owing to lack of a clear understanding of demand-side gas consumption rules and a reasonable resource allocation system, a large amount of CBM resources in the mining area are wasted. In order to predict the demand for CBM dynamically, the Seasonal Auto Regressive Integrated Moving Average (SARIMA) model, Additive Holt-Winters (AHW) model and Multiplicative Holt-Winters (MHW) model based on time series are used to predict the monthly demand for CBM in Yangquan Mine Area in 2020, respectively. Then the predicted results are evaluated by using the prediction model parameters combined with the characteristics of actual demand for CBM. Finally, a resource allocation system under different supply and demand conditions is built to reduce the waste of resources. In this paper, it is found that the information of the actual data is not sufficiently extracted in the MHW model while the SARIMA model can reflect the cyclical trend of monthly demand for CBM under ideal conditions. Furthermore, the AHW model can reasonably predict the demand for CBM under the influence of COVID-19, with a mean relative error of 0.099. The supply and demand distribution system built based on the proposed models can solve the problem of seasonal unevenness of CBM demand in mining areas and ensure the economic benefits of mining areas.

Influence of isolation measures for patients with mild symptoms on the spread of COVID-19.

During the transmission of COVID-19, the hospital isolation of patients with mild symptoms has been a concern. In this paper, we use a differential equation model to describe the propagation of COVID-19, and discuss the effects of intensity of hospital isolation and moment of taking measures on development of the epidemic. The results show that isolation measures can significantly reduce the epidemic final size and the number of dead, and the greater the intensity of measures, the better, but duration of the epidemic will be prolonged. Whenever isolation measures are taken, the epidemic final size and the number of dead can be reduced. In early stage of the epidemic, taking measures one day later has little impact, but after a certain period, if taking measures one day later, the epidemic final size and the number of dead increase sharply. Taking measures as early as possible makes the maximum number of patients appear later, which is conducive to expanding medical bed resources and reducing the pressure on medical resource demand. As long as possible, high-intensity isolation measures should be taken in time for patients with mild symptoms.

Statewide Real-Time Tracking of Beds and Ventilators During Coronavirus Disease 2019 and Beyond.

This brief report describes the rapid deployment of a real-time electronic tracking board for all hospitals in the state of Oregon. In preparation for the coronavirus disease 2019 surge on hospital resources, and in collaboration across health systems, with health authorities and an industry partner, we combined existing infrastructures to create the first automated tracking board for our entire state, including bed types by health system and geographic area, and with granularity to the individual unit level for each participating hospital. At the time of submission, we have a live snapshot of 87% of beds in the state, including real-time ventilator data across eight health systems. The tracking board allows for rapid assessment of available bed and ventilator resources and pulls electronic health record data that is created through normal care processes rather than relying upon manual entry. It is updated every 5 minutes and is drillable from state to unit level. Together these factors make the data actionable, which is essential in a crisis. The new tracking system integrates seamlessly with our preexisting statewide, manually updated tracking board via bidirectional data sharing to ensure existing processes across the state can continue. This new tool allows any health system in our state to visualize occupancy by type and location in real time. Amid pandemic uncertainty, having a reliable tool for tracking critical hospital resources will enhance our statewide ability to maintain healthcare functionality in a world with coronavirus disease 2019.

Adjusting Daily Inpatient Bed Allocation to Smooth Emergency Department Occupancy Variation.

Study Objective: Overcrowding in emergency departments (ED) is an increasingly common problem in Taiwanese hospitals, and strategies to improve efficiency are in demand. We propose a bed resource allocation strategy to overcome the overcrowding problem. Method: We investigated ED occupancy using discrete-event simulation and evaluated the effects of suppressing day-to-day variations in ED occupancy by adjusting the number of empty beds per day. Administrative data recorded at the ED of Taichung Veterans General Hospital (TCVGH) in Taiwan with 1500 beds and an annual ED volume of 66,000 visits were analyzed. Key indices of ED quality in the analysis were the length of stay and the time in waiting for outward transfers to in-patient beds. The model is able to analyze and compare several scenarios for finding a feasible allocation strategy. Results: We compared several scenarios, and the results showed that by reducing the allocated beds for the ED by 20% on weekdays, the variance of daily ED occupancy was reduced by 36.25% (i.e., the percentage of reduction in standard deviation). Conclusions: This new allocation strategy was able to both reduce the average ED occupancy and maintain the ED quality indices.

Indication-specific event rates among hospitalized patients undergoing continuous cardiac monitoring.

BackgroundCardiac telemetry monitoring is widely utilized for a variety of clinical indications, yet indication‐specific event rates for monitored patients are seldomly reported.HypothesisHigh‐risk hospitalized patients for clinical deterioration can be identified using standardized telemetry monitoring indications.MethodsAdjudicated data from events triggering emergency response team (ERT) activation were systematically characterized at the Cleveland Clinic from among standardized telemetry indications ordered over a 13‐month period.ResultsAmong 72 199 orders created for telemetry monitored patients, ERT activation occurred in 2677 patients (3.7%), of which 1326 (49.5%) were cardiac‐related. Patients with deep venous thrombosis or pulmonary embolism (DVT/PE) demonstrated the highest overall event rate (ERT: n = 41 of 593 pts [6.9%]; 25/41 cardiac related [61%]). Cardiac‐related events were proportionally highest among patients with coronary disease awaiting revascularization (ERT: n = 19 of 847 patients [2.2%]; 13/19 cardiac‐related [68.4%]). Arrhythmia‐specific events were highest among patients who underwent cardiac surgery (n = 78 of 193 cardiac‐related ERT [40.4%]), and patients with known or suspected tachyarrhythmias (n = 318 of 788 cardiac‐related ERT [40.4%]). Bubble plot analysis identified patients hospitalized with DVT/PE, drug or alcohol exposures, and acute coronary syndrome as among the highest overall and cardiac‐related events while identifying patients with respiratory disorder monitoring indications as carrying the highest noncardiac event rate.ConclusionHigh‐risk hospitalized patients can be identified by telemetry indication and prioritized according to concerns for cardiac, arrhythmia‐specific and noncardiac clinical deterioration. This is particularly useful when monitored bed resources are constrained.

Availability of Hospital Resources and Specialty Services for Stroke Care in North Carolina.

Effective regionalization of acute stroke care requires assessment and coordination of limited hospital resources. We described the availability of stroke-specific hospital resources (neurology specialty physicians and neuro-intensive care unit [neuro-ICU] bed capacity) for North Carolina overall and by region and population density. We also assessed daily trends in hospital bed availability. This statewide descriptive study was conducted with data from the State Medical Asset Resource Tracking Tool (SMARTT), a Web-based system used by North Carolina to track available medical resources within the state. The SMARTT system was queried for stroke-specific physician and bed resources at each North Carolina hospital during a 1-year period (June 2015-May 2016), including daily availability of neuro-ICU beds. We compared hospital resources by geographic region and population density (metropolitan, urban, and rural). Data from 108 acute care hospitals located in 75 of 100 counties in North Carolina were included in the analysis. Fifty-seven percent of hospitals had no neurology specialty physicians. Western and eastern North Carolina had the lowest prevalence of these physicians. Most hospitals (88%) had general ICUs, whereas only 17 hospitals (16%) had neuro-ICUs. Neuro-ICUs were concentrated in metropolitan areas and in central North Carolina. On average, there were 276 general ICU and 27 neuro-ICU beds available statewide each day. Daily neuro-ICU bed availability was lowest in eastern and southeastern regions and during the week compared with weekends. In North Carolina, stroke-specific hospital subspecialists and resources are not distributed evenly across the state. Daily bed availability, particularly in neuro-ICUs, is lacking in rural areas and noncentral regions and appears to decrease on weekdays. Regionalization of stroke care needs to consider the geographic distribution and daily variability of hospital resources.

A Data-Driven Hybrid Three-Stage Framework for Hospital Bed Allocation: A Case Study in a Large Tertiary Hospital in China.

Beds are key, scarce medical resources in hospitals. The bed occupancy rate (BOR) amongst different departments within large tertiary hospitals is very imbalanced, a situation which has led to problems between the supply of and the demand for bed resources. This study aims to balance the utilization of existing beds in a large tertiary hospital in China. We developed a data-driven hybrid three-stage framework incorporating data analysis, simulation, and mixed integer programming to minimize the gaps in BOR among different departments. The first stage is to calculate the length of stay (LOS) and BOR of each department and identify the departments that need to be allocated beds. In the second stage, we used a fitted arrival distribution and median LOS as the input to a generic simulation model. In the third stage, we built a mixed integer programming model using the results obtained in the first two stages to generate the optimal bed allocation strategy for different departments. The value of the objective function, Z, represents the severity of the imbalance in BOR. Our case study demonstrated the effectiveness of the proposed data-driven hybrid three-stage framework. The results show that Z decreases from 0.7344 to 0.0409 after re-allocation, which means that the internal imbalance has eased. Our framework provides hospital bed policy makers with a feasible solution for bed allocation.

Diagrama de Barber y Johnson y reserva latente como herramientas para optimizar la gestión de camas hospitalarias

IntroductionThe measurement, evaluation and analysis of the bed resources are functions of the Admission and Clinical Documentation Department and are a challenge for the management of acute hospital admissions.The aim of the present study was to analyse the management of bed resources using the Barber and Johnson Diagram (B&J) and latent reserve, during epidemiological contingencies in the Hospital Universitario Río Hortega. Materials and methodsA retrospective review was carried out on hospital admission indicators, from 2008 to February 2017, using the B&J diagram as a graphic tool to compare length of stay, replacement interval, turnover rate, monthly and annual occupancy rate for the hospital and services.The latent and manifest reserve was calculated. ResultsThe B&J diagram showed differences in occupancy rate and provision of functional beds between the years reviewed and the approaches used. A lower provision of beds and higher length of stay corresponded with an increase in occupancy, decrease in replacement interval, and increase in turnover rate. The latent reserve showed that, between a discharge and a new entry into the same bed, 14 inappropriately occupied beds could be available. ConclusionsThe review of the hospital admission indicators, their integration into the B&J diagram, and use of latent reserve could be included in the hospital information system and benefit the decision-making in the operational management of beds.

Predictors of in-hospital length of stay among cardiac patients: A machine learning approach

ObjectiveThe In-hospital length of stay (LOS) is expected to increase as cardiovascular diseases complexity increases and the population ages. This will affect healthcare systems especially with the current situation of decreased bed capacity and increasing costs. Therefore, accurately predicting LOS would have a positive impact on healthcare metrics. The aim of this study is to develop a machine learning-based model approach for predicting in-hospital LOS for cardiac patients. DesignUsing electronic medical records, we retrospectively extracted all records of patients' visits that were admitted under adult cardiology service. Admission diagnosis and primary treating physician were reviewed to verify selection criteria. A predictive machine learning-based model approach was applied to incorporate simple baseline health data at admission time to predict LOS. Patients were divided into three groups based on their LOS: short (<3 days), intermediate (3–5 days) and long (>5 days). Information gain algorithm was utilized to select the most relevant attributes. Only attributes with information gain of more than zero were used in model building. Four different machine learning techniques were evaluated and their diagnostic accuracy measures were compared. SettingThe dataset of this study included adult patients who were admitted between 2008 and 2016 in King Abdulaziz Cardiac Center (KACC). The center is located in King Abdulaziz Medical City Complex in Riyadh, the capital of Saudi Arabia. Participants (dataset)A total of 16,414 consecutive inpatient visits for 12,769 unique patients (mean age of 58.8 ± 16 years of which 68.2% were males) between 2008 and 2016 were included. The study cohort had a high prevalence of cardiovascular risk factors (hypertension 56%, diabetes 56%, dyslipidemia 52%, obesity 33% and smoking 24%). The most common admitting diagnosis was acute coronary syndrome (36%). ResultsThe variables with highest impact on the prediction of in-hospital LOS were on admission heart rate, on admission systolic and diastolic blood pressure, age and insurance status (eligibility). Using machine learning models; Random Forest (RF) model outperformed among all other models (sensitivity (0.80), accuracy (0.80), and AUROC (0.94)). ConclusionWe showed that machine learning methods provide accurate prediction of LOS for cardiac patients. This is can be used in clinical bed management and resources allocation.

AB099. 16. Clinical effectiveness of dedicated ultrasound slots in a surgical assessment unit

Background: The bed crisis and resource limitations continue to plague the Health Service Executive, with surgical patients being admitted for next day radiologic investigations. Ultrasound scan (USS) is a cheap and non-invasive modality for assessing acute surgical presentations. The acute surgical assessment unit (ASAU) in Limerick has two dedicated USS slots daily. The aim of the current study was to investigate the clinical impact on patient care and the cost-effectiveness of such an ASAU USS access.