scholarly journals Integrating Deep Reinforcement Learning Networks with Health System Simulations.

2020 ◽  
Author(s):  
Michael Allen ◽  
Thomas Monks
Keyword(s):  
Reinforcement Learning ◽  
Health System ◽  
Health Systems ◽  
Learning Networks ◽  
Significant Potential ◽  
Hospital Bed Capacity ◽  
Capacity Model ◽  
Hospital Bed ◽  
Bed Capacity

Background and motivation: Combining Deep Reinforcement Learning (Deep RL) and Health Systems Simulations has significant potential, for both research into improving Deep RL performance and safety, and in operational practice. While individual toolkits exist for Deep RL and Health Systems Simulations, no framework to integrate the two has been established. Aim: Provide a framework for integrating Deep RL Networks with Health System Simulations, and to ensure this framework is compatible with Deep RL agents that have been developed and tested using OpenAI Gym. Methods: We developed our framework based on the OpenAI Gym framework, and demonstrate its use on a simple hospital bed capacity model. We built the Deep RL agents using PyTorch, and the Hospital Simulation using SimPy. Results: We demonstrate example models using a Double Deep Q Network or a Duelling Double Deep Q Network as the Deep RL agent. Conclusion: SimPy may be used to create Health System Simulations that are compatible with agents developed and tested on OpenAI Gym environments. GitHub repository of code: https://github.com/MichaelAllen1966/learninghospital

Managing Hospital Bed Capacity Through Partitioning Care into Focused Wings

2012 ◽  
Author(s):  
Thomas J Best ◽  
Burhaneddin Sandikci ◽  
Donald D. Eisenstein ◽  
David Owen Meltzer
Keyword(s):  
Hospital Bed Capacity ◽  
Hospital Bed ◽  
Bed Capacity

A network flow approach to optimizing hospital bed capacity decisions

2006 ◽  
Vol 9 (4) ◽  
pp. 391-404 ◽  
Author(s):  
Elif Akcali ◽  
Murray J Côté ◽  
Chin Lin
Keyword(s):  
Network Flow ◽  
Hospital Bed Capacity ◽  
Capacity Decisions ◽  
Hospital Bed ◽  
Bed Capacity

Successful Hospital Evacuation After the Kumamoto Earthquakes, Japan, 2016

2017 ◽  
Vol 11 (5) ◽  
pp. 517-521 ◽  
Author(s):  
Takashi Nagata ◽  
Shinkichi Himeno ◽  
Akihiro Himeno ◽  
Manabu Hasegawa ◽  
Alan Kawarai Lefor ◽  
...  
Keyword(s):  
Public Health ◽  
Adverse Events ◽  
Natural Disaster ◽  
Disaster Response ◽  
Timely Manner ◽  
Public Health Preparedness ◽  
Hospital Bed Capacity ◽  
Hospital Bed ◽  
The Future ◽  
Bed Capacity

AbstractTwo major earthquakes struck Kumamoto Prefecture in Japan in April 2016. Disaster response was immediately provided, including disaster medical services. Many hospitals were damaged and patients needed immediate evacuation to alternative facilities. The hospital bed capacity of Kumamoto Prefecture was overwhelmed, and transportation of more than 100 patients was needed. Hospital evacuation was carried out smoothly with the coordinated efforts of multiple agencies. The overall operation was deemed a success because patients were transported in a timely manner without any significant adverse events. Upon repair of facilities in Kumamoto Prefecture, patients were returned safely to their previous facilities. The management of inpatients after this natural disaster in Kumamoto Prefecture can serve as a model for hospital evacuation with multi-agency coordination in the future. Future efforts are needed to improve interfacility communications immediately following a natural disaster. (Disaster Med Public Health Preparedness. 2017;11:517–521)

scholarly journals EVALUATING THE USE OF HOSPITAL BED CAPACITY IN MEDICAL ORGANIZATIONS

2018 ◽  
Vol 10 (4) ◽  
pp. 37-43
Author(s):  
I. A. Zheleznyakova ◽  
L. A. Kovaleva ◽  
T. A. Khelisupali ◽  
M. A. Voinov ◽  
V. V. Omel’yanovskii
Keyword(s):  
Hospital Bed Capacity ◽  
Hospital Bed ◽  
Bed Capacity

Cancellation of Scheduled Procedures as a Mechanism to Generate Hospital Bed Surge Capacity—A Pilot Study

2011 ◽  
Vol 26 (3) ◽  
pp. 224-229 ◽  
Author(s):  
Olan A. Soremekun ◽  
Richard D. Zane ◽  
Andrew Walls ◽  
Matthew B. Allen ◽  
Kimberly J. Seefeld ◽  
...  
Keyword(s):  
Pilot Study ◽  
Future Research ◽  
Surge Capacity ◽  
Rater Reliability ◽  
Hospital Bed Capacity ◽  
Hospital Beds ◽  
Hospital Bed ◽  
Bed Capacity ◽  
Categorization Scheme ◽  
The Impact

AbstractBackground: The ability to generate hospital beds in response to a mass-casualty incident is an essential component of public health preparedness. Although many acute care hospitals' emergency response plans include some provision for delaying or canceling elective procedures in the event of an inpatient surge, no standardized method for implementing and quantifying the impact of this strategy exists in the literature. The aim of this study was to develop a methodology to prospectively emergency plan for implementing a strategy of delaying procedures and quantifying the potential impact of this strategy on creating hospital bed capacity.Methods: This is a pilot study. A categorization methodology was devised and applied retrospectively to all scheduled procedures during four one-week periods chosen by convenience. The categorization scheme grouped procedures into four categories: (A) procedures with no impact on inpatient capacity; (B) procedures that could be delayed indefinitely; (C) procedures that could be delayed by one week; and (D) procedures that could not be delayed. The categorization scheme was applied by two research assistants and an emergency medicine resident. All three raters categorized the first 100 cases to allow for calculation of inter-rater reliability. Maximal hospital bed capacity was defined as the 95th percentile weekday occupancy, as this is more representative of functional bed capacity than is the number of licensed beds. The main outcome was the number of hospital beds that could be created by postponing procedures in categories B and C.Results: Maximal hospital bed capacity was 816 beds. Mean occupancy during weekdays was 759 versus 694 on weekends. By postponing Group B and C procedures, a mean of 60 beds (51 general medical/surgical and nine intensive care unit (ICU)) could be created on weekdays, and four beds (three general medical/surgical and one ICU) on weekends. This represents 7.3% and 0.49% of maximal hospital bed capacity and ICU capacity, respectively. In the event that sustained surge is needed, delaying all category B and C procedures for one week would lead to the generation of 1,235 hospital-bed days. Inter-rater reliability was high (kappa = 0.74) indicating good agreement between all three raters.Conclusions: For the institution studied, the strategy of delaying scheduled procedures could generate inpatient capacity with maximal impact during weekdays and little impact on weekends. Future research is needed to validate the categorization scheme and increase the ability to predict inpatient surge capacity across various hospital types and sizes.

scholarly journals Leveraging community mortality indicators to infer COVID-19 mortality and transmission dynamics in Damascus, Syria

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Oliver J. Watson ◽  
◽  
Mervat Alhaffar ◽  
Zaki Mehchy ◽  
Charles Whittaker ◽  
...  
Keyword(s):  
Mathematical Model ◽  
Middle East ◽  
Health System ◽  
Mortality Rates ◽  
Transmission Dynamics ◽  
Mortality Data ◽  
Sensitivity Range ◽  
Hospital Bed ◽  
All Cause Mortality ◽  
Bed Capacity

AbstractThe COVID-19 pandemic has resulted in substantial mortality worldwide. However, to date, countries in the Middle East and Africa have reported considerably lower mortality rates than in Europe and the Americas. Motivated by reports of an overwhelmed health system, we estimate the likely under-ascertainment of COVID-19 mortality in Damascus, Syria. Using all-cause mortality data, we fit a mathematical model of COVID-19 transmission to reported mortality, estimating that 1.25% of COVID-19 deaths (sensitivity range 1.00% – 3.00%) have been reported as of 2 September 2020. By 2 September, we estimate that 4,380 (95% CI: 3,250 – 5,550) COVID-19 deaths in Damascus may have been missed, with 39.0% (95% CI: 32.5% – 45.0%) of the population in Damascus estimated to have been infected. Accounting for under-ascertainment corroborates reports of exceeded hospital bed capacity and is validated by community-uploaded obituary notifications, which confirm extensive unreported mortality in Damascus.

scholarly journals Implementation of Electronic Patient Discharge: A Successful Strategy to Increase Hospital Bed Capacity During the COVID-19 Pandemic

2021 ◽  
Keyword(s):  
Six Sigma ◽  
Patient Discharge ◽  
Management Tool ◽  
Discharge Process ◽  
Care Hospital ◽  
Discharge Time ◽  
Post Intervention ◽  
Hospital Bed Capacity ◽  
Hospital Bed ◽  
Bed Capacity

Background: The ongoing COVID-19 pandemic increased the need for inpatient beds, indicating the need for hospitals to increase the efficiency of beds. Objectives: This study aimed to increase hospital bed capacity using the implementation of Electronic Patient Discharge (EPD). Methods: This qualitative-quantitative study was conducted in a tertiary care hospital using the pre-and post-intervention designs, and the main outcome was patient discharge time. By applying the Six Sigma model, including definition, measurement, analysis, improvement, and control, the patient discharge process was assessed and improved by some interventions such as EPD. All hospitalized patients with COVID-19 from 21 March 2020 to 22 July 2021 were examined for the post-intervention. In addition, data were collected from the hospital information system (HIS). Results: By the use of EPD, patient discharge time decreased to 47.70% (from 10.19 h to 5.33 h) (P < 0.000). According to the Sigma level, the yield and defects per million opportunities of the discharge process also increased to 55%. Conclusion: Six Sigma methodology can be an effective change management tool to improve discharge time to cover the demand created during pandemics. According to the results of the present study and the obtained saved time, one bed is added to the hospital capacity for every five discharges.

Sign in / Sign up

Export Citation Format

Share Document