Professional Documents
Culture Documents
Bed Allocation
Bed Allocation
In this corona pandemic situation the hospital bed occupancy levels have resulted into storage of
beds for increasing the demand. This paper describes the bed availability prediction and manages the
resources efficiency. The process of finding the occupied beds for the corona ward patients provided by
the hospital managements. In this bed booking process helps the both side of hospital management and
the patient using this process the patient can book his bed before the admission in the hospital. Using this
method we can gather the information about the bed has near by the o2 supply. So if the services are
already occupied then the patient can search the hospitals available nearby theirs location. These services
make admission process easier and the admission process easier and reduce the time of users. However,
to date few studies have evaluated the hospital bed shortage for COVID-19 during the lockdown and
none for non-COVID-19 patients, although such data are important for better preparedness of the future
outbreak. It is important for management to keep track of this figure to proactively avoid overcrowding
and maintain a high level of quality of care. The objective of this work consists in proposing a decision-
aid tool for hospital managers allowing to decide on the bed requirements for a given hospital or network
of hospitals on a short-medium term horizon. To that extent we propose a new data-driven discrete-event
simulation model based on data from a French university hospital to predict bed and staff requirements.
We propose a case study to illustrate the tool's ability to monitor bed occupancy in the recovery unit
given the admission rate of corona patients during the pandemic of covid-19. These results give an
interesting insight on the situation, providing decision makers with a powerful tool to establish an
enlightened response to this situation. It should also be possible for the hospitals executive board, as
well as the government, to monitor the performance of the hospitals regarding patient admissions.
CHAPTER – 1
INTRODUCTION
FACTORS:
The management of hospitals the bed occupancy ratio reflects the state of the hospital at a given
time.. In particular, the bed occupancy ratio of a service is a useful performance indicator for the
hospital. A relevant management of beds will also have advantages for the patient, as it will improve the
quality of care at the hospital and reduce the inpatients mean waiting time. The number of unoccupied
beds to keep is the element in which management can rely to be responsive when unexpected events
occur, such as the failure of a key device, or the departure of a surgeon. It is essential for caregivers to
keep a small number of beds available to address emergencies while having too much unoccupied bed
shows that the service is in overcapacity. Other factors can impact the hospital attendance, like
seasonality (epidemics such as flu in winter or heat waves in summer) or more persistent factors like the
ageing of the population.
Before defining those figures it is essential to have a mid-term vision on the patients attendance
to the hospital. The administration staff of the hospital needs to know the number of beds required to
state on annual closing of beds during holidays or on the exceptional opening of extra beds for emergent
patients. Industrial engineering and operational research approaches have been widely used to predict
bed occupancy in hospital, and Discrete-Event Simulation (DES) have proven useful to manage
resources in a process analysis. In this paper, we describe the development of a DES tool designed to
predict bed occupancy ratios for a healthcare center taking into account the history of patients’
attendance over the past years and predictions of future arrivals.
The objective of our work consists in proposing a decision-aid tool for hospital managers,
allowing them to decide on the bed requirements for all medical units of a given hospital on a medium
term horizon, using past hospitalization data such as medico-administrative data. The main contribution
consists in the development of a data-driven DES model, allowing the user to test different resource
scenarios and observe their consequences on bed occupancy prediction. The prediction of arrivals and
length of stays will be done analytically and then passed to the simulation model. This model can be set
up in different ways, to visualize the departure of a key resource at a precise time like the retirement of a
surgeon, or a sudden influx of patients due to an unexpected epidemic.
One of the major problems within a hospital environment is dealing with the bottleneck of patient
allocation and the availability of beds (Ward 2004). Through increased public scrutiny there is also a
greater degree of accountability required from health care professionals with regard to facilities
management and information administration. Our hospitals are running at peak capacity which almost
guarantees queuing in the emergency department for available beds and other critical inpatient services
(Richardson 2003). Bed availability is significant as a bed can be viewed as “one of the most
fundamental inputs in the provision of acute health care” (Walsh 1998). Queensland Health is currently
managing major restructuring changes and resource difficulty within budget constraints. It also faces an
increasingly higher level of demand from an ageing population, community health needs and emergency
services. Substantial increases in the 2006 Federal Government Health budget acknowledge these
resource shortages within the medical arena and the need for efficiencies. Consequently, there is a
critical need to develop a more efficient and suitable universal technique, compatible with existing data
systems, to manage the bed allocation issues affecting hospital staff on a daily basis. There are a number
of health care companies in Australia providing a variety of health administration systems to both public
and private hospitals. These include such systems as iPAS, HBCIS, ibaPAS, OACIS, FastTrak, and
AusPAS, which are all electronic based, some web enabled, but all lacking the visual display and spatial
location advantages available from the ubiquitous GIS. Hence, the main focus of this study was to
investigate how the application of GIS can benefit the health care industry and provide a simple
universal graphical output system applicable and useful to all levels of medical careers in the hospital
environment.
The model should consider all medical units: such tool is relevant if patient transfers are taken
into account.
The model should be fed with patient traces extracted from hospital data history to take into
account patient’s journey complexity. To do so we use a data mining approach to extract past
patient traces that will be replayed in the model.
BED MANAGEMENT:
Specific problems
Shortage of beds due to lack of other options. Hospitals in developed countries cannot force a
patient to leave if the patient's home is reasonably believed to be unsafe. For example, if a frail,
elderly patient has recovered from an acute illness, but is unable to dress himself and prepare
simple meals on his own, then the hospital must ensure that the patient will have sufficient
assistance with these necessary activities of daily living, or the patient must remain in the
hospital. In places with a shortage of skilled nursing facilities, home health care workers, and
related support organizations, beds may be unavailable for new, acutely sick patients because of
the continued presence of the previous patients. This is sometimes known as a "bed
blocking".False appearance or unnecessary creation of a bed shortage. "Bed hiding", as it is
sometimes called, is the practice of delaying admissions due to a falsely claimed lack of beds in
the appropriate department. Bed hiding has several causes, including scheduling so many elective
procedures that there are inadequate beds left for emergency admissions; frequent changes from
ward to ward; inadequate communication, so that cleaning staff don't know when a bed has
become available and needs cleaning; misalignment of tasks, so that skilled nurses are expected
to take time away from direct patient care to clean beds; too few nurses scheduled for a shift; and
overworked staff, who may be inclined to mis-report a bed as full, especially at the end of a shift,
in an effort to shift the workload to another person. Bed hiding can be significantly reduced by
careful tracking of bed status, making cleaning after discharge the top priority for cleaning staff,
and even by physically moving patients to the ward as soon as they are ready for admission
rather than boarding them in the emergency department. Reducing bed hiding in regular wards
can reduce wait times in the emergency department.
PATIENTS:
(i) patients admitted directly into a ward, and (ii) patients admitted through the Emergency
Department. We considered patients of the first group as being "planned" by the hospital: although their
origins are varied, direct admission show that these pathways are under control. On the other hand,
patients admitted through the ED are managed on the run and the medical staff is reacting to their
pathologies. The information available through the patient record are the following:
Admission modalities and provenance.From this we computed each patient’s trace in the
hospital, defined as the chronological succession of wards visited by a patient during his stay at
the hospital.
We divided the available data in two subsets, patients admitted to the hospital through the ED (urgent
patients), that we will be referring to and elective patients, similarly. We used those data-sets to compute
several inputs for our simulation.
MEDICAL UNITS:
Medical Units (MU) are modelled as agents and their characteristics as parameters. Two kinds of
parameters are used: constants giving information about the existing MU such as the capacity of the
ward, and variable parameters used to keep track of the bed and staff demand. When a patient is
admitted to a new ward, the ward’s occupancy is incremented. The needed staff - doctors, nurses, and
caregivers - is calculated by multiplying the occupancy by a theoretical ratio. Those ratios are given by a
classification of wards established with health professionals.
BENEFITS OF HBMS:
2. It helps in ending up patients’ long waiting hours, treatments in unhygienic environments, and
transferring to other hospitals.
3. It improves time management to eradicate delays in surgeries and operation cancellations due
to the unavailability of OT.
4. Better management of internal resources and provides guided instructions for housekeeping in
bedding that increases personal patient care.
5. Clear understanding of every patient through pre-designed diagnosis for each bed defined with
a distinct bed number.
6. Helps in bed assignment operations through data mismatch.
8. Helps in designing and developing new models for better management of inventory.
Hospital bed management is a crucial activity in any hospital. Inefficient and ineffective bed
management operations may lead to complex problems. The above article describes the importance,
benefits, and systems that help in a better understanding of bed management in hospital operations. Even
though HBMS is at initial stages of development at various hospitals, the fully developed HBMS will
unfold new strategies and advantages for better operation. HBMS presence impacts and improves
operations and systems in clinical and hospital management available today – from financial operations,
housekeeping, bed management, patient cure, etc. As every developing technology cant be recognized
until it revolutionizes the industry. HBMS is in the same phase and its integration in healthcare is driving
growth at a fast pace. If you resonate with our article please your thoughts.
The only exception to this rule is the Emergency Department, which is placed after the urgent
patient source. The patient is routed again to the unit’s block if his stay is not finished, creating a loop on
the medical unit block. When the stay is over, and all the medical units constituting the trace have been
visited, the patient is discharged.
RELATED WORK:
The analysis of patients’ stays in hospital is extensively covered in the literature. Predicting the
attendance in a healthcare delivery structure allows managers to become proactive regarding resource
management decisions. Forecasting models like time-series have been developed by (Farmer and Emami
1990) to give health service planners this opportunity. Numerous analytical models were designed as
decision support systems. For instance short-term bed occupancy can be predicted using autoregressive
integrated moving average according to (Abraham et al. 2009). Regression techniques also give good
results (Kumar et al. 2008) when predicting short-term bed demands for several classes of beds.
Similarly (Tan et al. 2019) implemented Principal Component Analysis and Multiple Linear Regression
methods to alert an Emergency Department (ED) of bed crunching risk on the short-term.
CHAPTER – 2
LITERATURE SURVEY
Year: 2010
Abstract:
In recent years, the arrangement of hospital beds, utilizing the rule of First Come, First Serve
(FCFS), reveals the common poor management of hospitals. Importantly, our proposed Six-stage
Hospital Beds Arrangement Management System (Six-stage HBAMS) uses General Utility Function
(utilizing Gray Correlation Analysis) to determine the hospitalization orders of patients. To verify Six-
stage HBAMS, we use our proposed History Repeating Method utilizing our proposed Modified
TOPOSIS Method as the evaluation method before we use Monte Carlo Simulation Algorithm for
further verification. The result of verification demonstrates that Six-stage HBAMS is a reliable approach
to improve the currently poor arrangement of hospital beds. At last, to achieve widely application of Six-
stage HBAMS, we offer the method of model modification according to the matter of fact for hospital
managers.
Year: 2017
Abstract:
Hospital information system is considered as one of the most important branches of the Medical
Informatics by the International Academia Community, with the essence of integrating all the hospital
departments into a large information network to facilitate the whole hospital system. Given the issue of
“difficult to be hospitalized” in China, a set of safe, stable and easy-to-handle beds resource management
information system was developed by the Hospital Information Department (HID) using PowerBuilder,
the MVC model and the Oracle database. according to this article HIS functional specifications. This
system improved the efficiency of bed resource management, enabled interdisciplinary collaboration
across departments, significantly reduced the average hospital stay of patients.
3. Hospital Bed Planning in a Single Department Based on Monte Carlo Simulation and Queuing
Theory.
Year: 2019
Abstract:
His paper investigates hospital bed planning problem in a single department, proposing a method
combining Monte Carlo simulation and queuing theory to determine bed scale and allocation. Firstly, we
establish a multi-type patient mixed queuing system and simulate it via Monte Carlo simulation,
obtaining major performances of the queue. Then, bed scale is determined based on average waiting time
of patients as well as bed utilization constraint. Furthermore, a mathematical model is constructed to
minimize the total waiting time of all patients, thereby solving the bed allocation problem. Finally, the
model is validated on MATLAB using ophthalmology department as an example. This study shows that
Monte Carlo simulation is an efficient method for determining and controlling the scale of hospital beds
when considering complexities, such as different arrival rates of patients and length of hospital stay
distributions. This work provides hospital managers with an effective approach for hospital bed
planning.
4. NFC-based Smart Notification System for Hospital Discharge Process and Bed Management
Year: 2018
Abstract:
An efficient discharge workflow with objective to minimize the turnaround time upon discharge
of a patient in a typical hospital environment is proposed. The implemented workflow, which relies on a
near-field-communication (NFC)-based patient discharge event, triggers a sequence of notifications and
actions both by the nurses and housekeepers till the bed is cleared for occupancy by the next patient. The
notifications are automated through Telegram Bot API. Android-based mobile applications are
developed for both nurses and housekeepers. The mobile apps allow for follow-up actions and the status
of the bed to be captured and sent to the cloud. Key functionalities of the system include immediate
notification send to the housekeepers when a patient leaves the hospital, simple sending of cleaning
requests and viewing of bed status. The system has been deployed in a hospital and evaluation is carried
out in terms of improvement in the turnaround time of hospital beds.
5. A Web-based Information System for the Management of ICU Beds During the Corona virus
Outbreak
Authors: Itamir de Morais Barroca Filho; Silvio Costa Sampaio; Anderson Paiva Cruz; Victor Hugo Freire
Ramalho; Jefferson Augusto Ro
Year: 2020
Abstract:
With the world pandemic generated by Covid-19, many places in the world are not able to
rapidly measure the number of intensive care unit (ICU) beds existing and available in a city, state, or
country. Knowing precisely the number of ICU beds in real-time is very important to estimate the health
system collapse and to create strategies for the government to provide new ICU beds for patients. Thus,
at Rio Grande do Norte, a state in Brazil, the State Health Department requested us to rapidly develop a
technology to integrate ICU beds and patient data related explicitly to Covid-19 from the 58 health units
(hospitals and clinics) in the state. Thus, this article presents the methodology and strategies used for the
development and implementation of a web information system, called Leitos, for the management of
ICU and semi-ICU beds assigned to Covid-19 patients. Nowadays, more than 200 government agents
and clinical unit staff are using this system that presents the real-time situation of the ICU beds in this
state.
Year: 2017
Abstract:
We consider the problem of partitioning clinical services in hospitals into groups with the goal of
efficiently allocating existing inpatient beds. At the strategic level, there are two major possibilities:
pooling versus focusing. Pooling the bed capacity allows one to achieve an overall high occupancy level
for a fixed number of beds. On the other hand, focusing by dividing the capacity into groups with
restricted access may offer increased efficiency and better resource utilization. We derive a two-stage
schema to address the 3-fold problem: 1) how many groups of services to form; 2) how many beds to
allocate to each group; and 3) how to partition services among the groups. Stage 1 uses cluster analysis
utilizing the similarity principle for possible advantages of economies of scale, coupled with queueing-
based optimization models to obtain a set of candidate groups. Three full-scale examples demonstrate
the flexibility and diverse application of our framework with managerial insights for different utility
optimization goals and queuing systems.
CHAPTER - 3
SYSTEM ANALYSIS
EXISTING SYSTEM
The hospitals currently using the manual system on these web applications it is for the
management and maintenance process of bed allocation. The current system requires numerous paper
with data storages. in this process they only can allocate the bed and room and other facilities and we
also doesn’t known about the treatment details and available doctors details these details are only we can
access by go live and get that details. Shortage of beds due to lack of other options. Hospitals in
developed countries cannot force a patient to leave if the patient's home is reasonably believed to be
unsafe. For example, if a frail, elderly patient has recovered from an acute illness, but is unable to dress
himself and prepare simple meals on his own, then the hospital must ensure that the patient will have
sufficient assistance with these necessary activities of daily living, or the patient must remain in the
hospital. In places with a shortage of skilled nursing facilities, home health care workers, and related
support organizations, beds may be unavailable for new, acutely sick patients because of the continued
presence of the previous patients. This is sometimes known as a "bed blocking”. False appearance or
unnecessary creation of a bed shortage. "Bed hiding", as it is sometimes called, is the practice of
delaying admissions due to a falsely claimed lack of beds in the appropriate department. Bed hiding has
several causes, including scheduling so many elective procedures that there are inadequate beds left for
emergency admissions; frequent changes from ward to ward; inadequate communication, so that
cleaning staff don't know when a bed has become available and needs cleaning; misalignment of tasks,
so that skilled nurses are expected to take time away from direct patient care to clean beds; too few
nurses scheduled for a shift; and overworked staff, who may be inclined to mis-report a bed as full,
especially at the end of a shift, in an effort to shift the workload to another person. Bed hiding can be
significantly reduced by careful tracking of bed status, making cleaning after discharge the top priority
for cleaning staff, and even by physically moving patients to the ward as soon as they are ready for
admission rather than boarding them in the emergency department. Reducing bed hiding in regular
wards can reduce wait times in the emergency department.
Disadvantages
PROPOSED SYSTEM
The hospital management has web applications these designed for any hospital to replace their existing
manual paper based system .the new system is to control the information of patients, bed and room
availability,staff and operating room schedules and invoices. These services are to be provided in an
efficient, cost effective manner with the goal of reducing the time and resources currently required for
such tasks. Hospital bed management systems became a pivotal practice after the National Health
Service’s statement rule on patient’s emergency trolly waiting hours. After an accident, inconvenient
waiting hours in hospital waiting halls due to improper operational capacity planning and control over
managing, allotting, and maintaining beds may turn frustrating when emergency care is required. The
lack of real-time data analysis provides a disadvantage resulting in patient overcrowding and
malefactions in inpatient bed management services during emergencies. Monitoring and managing
inpatient-outpatient capacity & patient inflows can be challenging tasks during emergencies. Unplanned
inventory, the inability of beds, and other scarce resources may lead to poor operations, and that affects
the hospital’s goodwill. The data integrated robust bed management systems improve healthcare services
by optimizing operations. The digitalized data-driven hospital bed management system provides an
advantage with the accessibility of real-time data. It includes predictive planning, altering beds during
emergencies, improved individual patient care, efficiency in diagnosis, and systematized operations.
Hospital bed management is a crucial activity in any hospital. Inefficient and ineffective bed
management operations may lead to complex problems. The above article describes the importance,
benefits, and systems that help in a better understanding of bed management in hospital operations. Even
though HBMS is at initial stages of development at various hospitals, the fully developed HBMS will
unfold new strategies and advantages for better operation.
Advantages
We can reserve the bed in anywhere and also the admission process. It will save our time and
life.
Before the registration we can verify the doctors are available or not.
And also we can see more information about the other treatment services providing.
Online Appointment – Doctor or Staff can create and manage appointments fixed with patients.
Appointment Schedule – Doctors can view all appointments scheduled at a glance.
Appointment Application – Patients can apply for their check-up with the doctor.
SMS Notification – Patients get appointment approval notification through SMS.
Prescription and Reports – The doctor assigned to patients their prescription and diagnosis
reports need to do.
Time-saving Technology.
Software Environment
PHP
PHP: Hypertext Preprocessor (or simply PHP) is a general-purpose programming language
originally designed for web development. It was originally created by Rasmus Lerdorf in 1994 the PHP
reference implementation is now produced by The PHP Group. PHP originally stood for Personal Home
Page, but it now stands for the recursive initialism PHP: Hypertext Preprocessor.
PHP code may be executed with a command line interface (CLI), embedded into HTML code, or
used in combination with various web template systems, web content management systems, and web
frameworks. PHP code is usually processed by a PHP interpreter implemented as a module in a web
server or as a Common Gateway Interface (CGI) executable. The web server outputs the results of the
interpreted and executed PHP code, which may be any type of data, such as generated HTML code or
binary image data. PHP can be used for many programming tasks outside of the web context, such as
standalone graphical applications and robotic drone control.
The standard PHP interpreter, powered by the Zend Engine, is free software released under the
PHP License. PHP has been widely ported and can be deployed on most web servers on almost every
operating system and platform, free of charge.
The PHP language evolved without a written formal specification or standard until 2014, with the
original implementation acting as the de facto standard which other implementations aimed to follow.
Since 2014, work has gone on to create a formal PHP specification.
PHP Objects
Basic object-oriented programming functionality was added in PHP 3 and improved in PHP 4.
This allowed for PHP to gain further abstraction, making creative tasks easier for programmers using the
language. Object handling was completely rewritten for PHP 5, expanding the feature set and enhancing
performance. In previous versions of PHP, objects were handled like value types. The drawback of this
method was that code had to make heavy use of PHP's "reference" variables if it wanted to modify an
object it was passed rather than creating a copy of it. In the new approach, objects are referenced by
handle, and not by value.
Implementations
The only complete PHP implementation is the original, known simply as PHP. It is the most
widely used and is powered by the Zend Engine. To disambiguate it from other implementations, it is
sometimes unofficially called "Zend PHP". The Zend Engine compiles PHP source code on-the-fly into
an internal format that it can execute, thus it works as an interpreter. It is also the "reference
implementation" of PHP, as PHP has no formal specification, and so the semantics of Zend PHP define
the semantics of PHP. Due to the complex and nuanced semantics of PHP, defined by how Zend works,
it is difficult for competing implementations to offer complete compatibility.
Licensing
PHP is free software released under the PHP License, which stipulates that: Products derived
from this software may not be called "PHP", nor may "PHP" appear in their name, without prior written
permission from group@php.net. You may indicate that your software works in conjunction with PHP
by saying "Foo for PHP" instead of calling it "PHP Foo" or "phpfoo". This restriction on use of "PHP"
makes the PHP License incompatible with the General Public License (GPL), while the Zend License is
incompatible due to an advertising clause similar to that of the original BSD license.
Use
A broad overview of the LAMP software bundle, displayed here together with Squid
PHP is a general-purpose scripting language that is especially suited to server-side web
development, in which case PHP generally runs on a web server. Any PHP code in a requested file is
executed by the PHP runtime, usually to create dynamic web page content or dynamic images used on
websites or elsewhere. It can also be used for command-line scripting and client-side graphical user
interface (GUI) applications. PHP can be deployed on most web servers, many operating systems and
platforms, and can be used with many relational database management systems (RDBMS). Most web
hosting providers support PHP for use by their clients. It is available free of charge, and the PHP Group
provides the complete source code for users to build, customize and extend for their own use.
SYSTEM DESIGN
ARCHITECTURE DIAGRAM
Allocate
Login to your the bed
account confirmation
notification
Ward
management
Bed allocation
USECASE DIAGRAM
A use case diagram is a group of actors, a set of use cases enclosed by a system
boundary communication, association between the actors and the use cases and also
generalization among the use cases. A use case diagram shows the relationship among the
actors and the use cases within the system.
User login
Register
Server response
Communicate with
server
Patient Server
Admin
Provide information
Conformation
Bed allocated
Request feedback
Send feedback
CLASS DIAGRAM
Class diagram provides an overview of the target system by describing the objects and
classes inside the system and the relationships between them. It provides a wide variety of
usages; from modeling the domain specific data structure to detailed design of the target
system.
Users
Department Admin
Register
Register
Login
Login
Search
View
request
Provide
View
Reports
Feedback
Register Details()
Register Details()
Login()
Login()
View Reviews()
Search bed()
Process Reviews & Ratings()
Request bed()
Provide Response()
Recive notification()
Maintain Reports()
Provide Feedbacks()
Database Server
Store
Access
Store Data()
Access Data()
Confirmation
notificationRequ
est feedback
ACTIVITY DIAGRAM
Activity diagram visually present a series of actions or flow of control in a system
similar to flowchart or a data flow diagram. Activity diagrams are often used in business
process modelling. They can also be described the steps in a use case diagram.
User login
register
request
Server responce
Bed alocate
Send notification
Conformation
feedback
CHAPTER - 7
PROJECT DESCRIPTION
Modules List
Admin.
Allotted information.
Server receive request.
User request.
User registration.
User login.
Review & rating.
ADMIN
Admin control the entire process and provide the information about bed allocation,
treatments, and doctor’s availability regarding and then admin needs the user reviews and
feedbacks also.
ALLOTTED INFORMATION
The information about the hospital management regarding and updates are stored in the
server. The details are updated frequently. the user and hospital management also can see the
all information about provided information’s.
Conclusion
The fast-spreading COVID-19 pandemic poses new questions, challenges and opportunities
for the healthcare systems worldwide. This has led healthcare systems, both public and
private, to face an unprecedented challenge to meet the needs of people becoming infected
and eventually needing hospitalization and ICU care. Bed crunch is an important problem
plaguing many major public healthcare systems which hospitals need to take proactive action
against it. However, the hospital information systems with diversity of data required
laborious efforts to put together holistic view of the bed situations for accurate and timely
decision making. Making decisions on bed allocation is a fundamentally challenging problem
dependent on the decisions of multiple stakeholders operating in different departments. In
this work, we shared our experiences and strategies for improving processes in the bed
management and to build an evidence-based data analytics solution for supporting bed
occupancy analysis. Our solution used not just a single dataset, but high-dimensional
heterogenous datasets from three hospital information systems. The study enabled SH to gain
insights into the factors with high impact on the bed occupancy in the hospital. Our
automated analytic solution reduced the cycle time from at least four days to less than half a
day, and empowered bed management decisionmakers with forecast of key indicators and
prediction of bed occupancy rate for better decision-making. The solution allows preventive
actions to be taken before an occurrence of bed crunch. Our approach to process
improvement and prediction modeling was designed with consistency in mind, co-created
with the bed management users and had led to positive adoption.
References
[3] E. Grigoroudis and Y. Siskos, “Preference disaggregation for measuring and analysing
customer satisfaction: The MUSA method,” EuropeanJournal of Operational Research, vol.
143, no. 1, pp. 148–170, 2002.
[5] C. Miani, E. Robin, V. Horvath, C. Manville, J. Cave, and J. Chataway, “Health and
healthcare: assessing the real world data policy landscape in Europe,” Rand health quarterly,
vol. 4, no. 2, 2014.
[6] S. Consoli, D. R. Recupero, and M. Petkovic, Data Science for Healthcare. Springer,
2019.
[7] L. N. Sanchez-Pinto, Y. Luo, and M. M. Churpek, “Big data and data science in critical
care,” Chest, vol. 154, no. 5, pp. 1239–1248, 2018.
[13] A. Cheng, W. Eppich, T. Sawyer, and V. Grant, “Debriefing: the state of the art and
science in healthcare simulation,” Healthcare simulation education: evidence, theory and
practice. Chichester: Wiley, pp. 158–64, 2018.
[14] S. Brailsford and J. Klien, “The value of modeling and simulation in healthcare: A
review of the evidence and some possible ways forward,” in Cumberland Initiative. Brunel
University, 2015.
[19] H. Li, S. Dong, Z. Liao, Y. Yao, S. Yuan, Y. Cui, and G. Li, “Retrospective analysis of
medical malpractice claims in tertiary hospitals of China: the view from patient safety,” BMJ
open, vol. 10, no. 9, p.e034681, 2020.