









































33 J Global Clinical Engineering Vol.6 Issue 4: 2024

Received June 19, 2024, accepted December 13, 2024, date of publication December 20, 2024.

Original Research Article 

A Decision Support System for Rational Deployment of Medical 
Equipment Based on Real-world Data

Dingding Jia1, Haowei Zhang1, Yang You1, Yiming Li2, Shunxin Qian3, Qilin Tao4, Qi Su5 and Heqing Lu5,*

1 School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai, China.
2 Procurement Center, Xinhua Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China.
3 Equipment Department, North Campus of Huashan Hospital Affiliated to Fudan University, Shanghai, China.
4 Department of Medical Equipment, Children’s Hospital of Fudan University, Shanghai, China.
5 Department of Medical Equipment, Shanghai First Maternity and Infant Hospital, School of Medicine, Tongji University, Shanghai, China.

* Corresponding Author Email: luheqing0811@126.com

ABSTRACT

Objectives: To inform judgments about the efficient and rational deployment of medical equipment in hospitals and give 
decision support.

Methods: The information system for rational deployment of medical equipment (MERDIS) is based on ASP.NET MVC frame-
work and designed with SQL Server database and C# language. The analysis methods are based on clinical pathway demand and 
multiple regression data statistics. It uses big data collected from hospitals, including current equipment deployment, clinical 
pathways, and other basic information, to calculate and provide each hospital with a recommended equipment deployment.

Results: By analyzing the data of 52 hospitals through the MERDIS system, it is convenient, accurate, and intuitive to get the 
rational deployment plan, and suggestions of different types of hospitals affected by different factors can be given conveniently, 
accurately, and intuitively.

Conclusions: The MERDIS system’s design provides the basis for the subsequent development of medical equipment macro 
data management. In the process of continuous improvement and supplementing of data, the software model will become more 
and more accurate and reliable.

Keywords—Rational deployment of medical equipment, Big data, Decision support, ASP.NET.

Copyright © 2024. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY): Creative Commons - 
Attribution 4.0 International - CC BY 4.0. The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright 
owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduc-
tion is permitted which does not comply with these terms.

http://www.globalce.org
http://globalce.org
http://globalce.org
https://creativecommons.org/licenses/by/4.0/
https://creativecommons.org/licenses/by/4.0/


J Global Clinical Engineering Vol.6 Issue 4: 2024  34

Jia, Zhang, You, Li, Qian, Tao, Su, Lu: A Decision Support System for Rational Deployment of Medical Equipment Based on 
Real-world Data

INTRODUCTION

At present, medical and health resources are still scarce 
resources in China.1–3 The problem of inappropriate de-
ployment of medical equipment in hospitals is a significant 
issue. Irrational and excessive purchase or insufficient 
deployment of large-scale medical equipment is wide-
spread. However, there are limited studies on deploying 
and utilizing large-scale medical equipment.4–15 This 
paper aims to design a system that can enter the general 
information to provide a rational recommendation for the 
rational deployment of medical equipment in hospitals.

There are multiple advantages to addressing and 
solving the problem of irrational deployment of medical 
equipment in hospitals. Such benefits include, among 
others, an increase in the utilization efficiency of medical 
equipment resources, improving the care and health of 
patients, reducing medical appointment waiting lists for 
diagnosis and treatment, and ensuring that newly estab-
lished hospitals are adequately and efficiently equipped. 
As such, many benefits arise for patients, health practi-
tioners, and hospital management in establishing an ef-
fective medical equipment deployment planning system. 
This is particularly important in public hospitals where 
resources are limited, and capital expenditure needs to 
be carefully managed. 

The deployment of medical equipment is typically 
the remit of the hospital equipment department. Indeed, 
there is a body of domestic literature on the methods of 
medical equipment deployment. However, such literature 
tends to be limited to a certain hospital and does not 
consider the hospital as a unit.4,5 Furthermore, foreign 
research explicitly focuses on emergency medical equip-
ment control methods.3 Either for the special situation 
of medical resources allocation analysis7,8, to solve this 
problem ethically9, or for the allocation of scarce medi-
cal resources research. There are many domestic pieces 
of research on the purchase decision analysis of medical 
equipment10–13, but they are not based on much actual 
data research. There is a gap in the literature as it has not 
yet considered the potential role of detailed and complex 
statistical investigation in equipment deployment.

The information system for rational deployment of 
medical equipment, or MERDIS for short, is developed 

with C# language, and the main framework is ASP.NET 
MVC. This study investigated the basic information of 
52 hospitals in Shanghai and other provinces to provide 
a data basis. The investigated hospitals include various 
types. The MERDIS analyses the above data in the database 
and gives the corresponding deployment plan recording 
to the hospital parameters.

METHODS

Functional Requirements Analysis

The deployment quantity of medical equipment should 
be directly affected by the frequency of such equipment, 
and the frequency of equipment is directly affected by the 
frequency of surgeries and visits in the hospital. At the 
same time, the hospital’s level, built-up area, and physical 
resources cause differences in the frequency of surger-
ies and visits. The annual income of the hospital directly 
reflects the differences in the frequency of operations 
and visits among hospitals. Therefore, the deployment 
method can be designed based on the above informa-
tion. The different influence factors were analyzed and 
processed by collecting the above data. Then, a rational 
deployment plan of medical equipment in different hos-
pitals is provided to ensure the rational deployment plan 
of medical equipment in the hospital.

The main users of MERDIS are the hospital equip-
ment managers or the relevant personnel of the hospital 
procurement center. Ordinary users have the authority 
to log in, register, enter information, query the deploy-
ment plan, and other functions. Based on the functions 
of ordinary users, administrators have the authority to 
manage user information, hospital information, infor-
mation check, and modification. The information users 
enter includes the hospital’s basic influencing factors, 
the deployment information of medical equipment, and 
the clinical pathway information. Figure 1 is a usage case 
diagram of the MERDIS.

System Design Ideas and Architecture

The key technology on which the system is based is the 
ASP.NET MVC framework. ASP.NET MVC is a framework 
for building scalable, standards-based web applications 
using well-established design patterns and the power 



35 J Global Clinical Engineering Vol.6 Issue 4: 2024

Jia, Zhang, You, Li, Qian, Tao, Su, Lu: A Decision Support System for Rational Deployment of Medical Equipment Based on 
Real-world Data

of ASP.NET and the .NET Framework. The MVC-based 
framework is divided into model, view, and controller. 
This framework divides data and view independently 
and loses the coupling between modules. The browser 
sends the client request to the front-end controller in this 
framework. The controller forwards the request accord-
ing to the configuration file, and the back-end controller 
interacts with the processor mapper. After determining 
the view corresponding to the request, the data model is 
extracted from the database through the data interaction 
layer and processed. Finally, the model and view of the 
execution result are rendered, and the interface view with 
data is returned to the user. This mode fully applies each 
component in the whole operation process and realizes 
the traits of dynamic modular update of the system.14–21

Take data transmission, the deployment information of 
the hospital medical equipment used for various analyses 
in the system is stored in the database, the client requests 
the deployment recommendation from the system in the 
browser, the controller receives the operation instruction, 
and sends the data output command to the database. The 
corresponding part of the data in the database is taken out 
through the data model and then calculated by a series of 
algorithms in the controller. Finally, the recommended or 

theoretical minimum deployment quantity should be fed 
back to the user through the view (display layer). Figure 
2 is the diagram of MVC parts.

Function Module Design

The main application objects of MERDIS are medical 
equipment, and the main users are hospital staff. The 
target aim is to recommend and evaluate the deployment 
of medical equipment. For ordinary users, they should 
register before logging into the system. As the hospital 
data is highly confidential, for information security, the 
registration information should be checked by the admin-
istrator first, and then the users can log in to the system. 
After logging in, users can query deployment recommenda-
tions, query deployment evaluation, and upload hospital 
information, medical equipment information, and clinical 
pathway information. Administrator users can process 
user and hospital information in the database based on 
the functions that ordinary users can achieve. At the same 
time, the information check function is added to check 
and approve the newly uploaded user information and 
hospital information. The abnormal information of users 
and hospitals is rejected or deleted, and only the normal 
data can be input into the database. Figure 3 shows the 
functional flowchart of MERDIS.

FIGURE 1. Usage case diagram of the MERDIS. FIGURE 2. Relationship of MVC parts.



J Global Clinical Engineering Vol.6 Issue 4: 2024  36

Jia, Zhang, You, Li, Qian, Tao, Su, Lu: A Decision Support System for Rational Deployment of Medical Equipment Based on 
Real-world Data

Database Design

The main entities of MERDIS include users, hospitals, 
equipment, and diseases. Each entity is a table in the data-
base. The relational table between the hospital and medical 
equipment is the “deployment” table, and the relational 
table between “disease type” and “hospital” is the “DInfo” 
table, which is used to represent the frequency of diagno-
sis and treatment of hospital diseases. For disease types, 
equipment, and hospitals, the relationship between the 
three became a table “CP”, which stores clinical pathway 
information. What’s more, to facilitate the representation 
and save storage space, a “hospital-categories” table was 
set up for hospital classification, an “equipment-categories” 
table was set up for equipment classification, and a “daily 
work” table to record the daily workload of different types 
of hospitals to different kinds of equipment, a “variables” 
table was set up to store calculation information. Figure 4 
is the database class diagram of MERDIS, through which 
we can intuitively understand the logical relationship 
between various table items in the database.

Deployment Method Based on Clinical Pathway

The basic information of the 52 hospitals surveyed 
includes the attributes of the hospital, category, number 
of beds, the annual number of surgeries, the number of 
doctors, the annual medical income, and the building area 
of the hospital. The information on the clinical pathway 
includes the disease type, the medical equipment used in 
each pathway, the usage times of the equipment in each 
pathway, and the annual implementation times of each 
pathway. The annual demand of the clinical pathway is 
calculated first. Based on the clinical pathway data of a 
hospital in the database, according to the capacity of the 
equipment, the annual clinical pathway demand for each 
kind of medical equipment in each hospital can be ana-
lyzed. Because the clinical pathway on file in the hospital 
cannot cover all kinds of diseases, the proportion of the 
operational volume of the clinical pathway in the total 
operation quantity can be calculated according to the 
hospital’s annual operation quantity. The actual opera-
tion quantity of the hospital is approximately replaced 

FIGURE 3. The functional flowchart of MERDIS. FIGURE 4. Database diagram of MERDIS.



37 J Global Clinical Engineering Vol.6 Issue 4: 2024

Jia, Zhang, You, Li, Qian, Tao, Su, Lu: A Decision Support System for Rational Deployment of Medical Equipment Based on 
Real-world Data

by the total number of clinical pathways used divided by 
this proportion to improve the accuracy of the theoretical 
minimum deployment value. The formula is as follows:

where, “R”, “M”, “N”, “H”, “p”, “q”, and “k” are integers greater 
than or equal to 1. And “M” is the annual usage times of 
the clinical pathway, “H” is the annual operation quantity 
of the hospital, “N” is the usage times of a certain kind of 
equipment to be studied in the clinical pathway (calculated 
according to the theoretical times of examinations), “k” 
is the total quantity of clinical pathways in the hospital, 
“Rp,q” is the annual clinical pathway demand of equipment 
“q” in the hospital “p”.

Next, the equipment capacity of each kind of equipment 
is estimated. Due to the influence of the environment, 
work process, service life, maintenance times, and other 
factors, the working capacity of medical equipment in 
the hospital is different. This method, according to clini-
cal experience, estimates the average usage capacity of a 
certain type of equipment—“annual saturated working 
capacity” (calculated as “daily saturated workload (times) 
× annual start-up days”) in the form of “S”. It is worth not-
ing that the daily saturated workload here refers to the 
maximum workload of the equipment under moderate 
working conditions rather than the continuous working 
capacity.

Finally, the theoretical minimum deployment quantity 
of the equipment is estimated. For the equipment to be 
studied, the minimum theoretical deployment of the 
equipment can be obtained by dividing the annual clini-
cal pathway demand “R” by the annual saturated working 
capacity “S”. As:

where Tp,q is the theoretical minimum deployment quantity 
of equipment “q” in the hospital “p”. Here, the value of T 
refers to the minimum number of deployment quantities 
to meet the normal completion of the hospital’s in-patient 

operation, rather than the most rational number of the 
deployment.

Deployment Method Based on Big Data

Big Data analysis refers to advanced and efficient data 
mining and machine learning techniques applied to a 
large amount of data. Research work and results in big 
data analysis are continuously rising, and more and more 
new and efficient architectures, programming models, 
systems, and data mining algorithms are proposed.21–23 

In addition to the clinical pathway, this study also investi-
gated the deployment of medical equipment in hospitals, 
including the quantity, grade, annual frequency of tests, 
annual income, service time, and maintenance cycle of 
certain medical equipment in each hospital. At the same 
time, nine independent variables such as the attribute 
of these hospitals, annual operation quantity, medical 
income, number of beds, and built-up area were also in-
vestigated as the influencing factors of medical equipment 
deployment. Based on the big data of these hospitals, the 
recommended deployment plan of medical equipment in 
a hospital can be given on the premise that the medical 
equipment of all the hospitals investigated is rationally 
deployed. The Least Square Method is used to calculate 
the multiple regression equation in the following format:

where ai is the coefficient, xi is the basic parameter value, 
n is the number of impact factors, and T is the recom-
mended deployment quantity based on big data. After 
each calculation, the regression coefficient is stored in the 
database to facilitate the next calculation. This deployment 
method mainly applies to newly established hospitals or 
hospitals preparing for consultation.

Other Influencing Factors

In this study, we can potentially enhance the deploy-
ment of medical equipment by integrating three key fac-
tors: average length of stay (ALOS), outpatient visits, and 
diagnosis procedure numbers. These factors have been 
shown to significantly influence the demand for medical 
resources.24–28

(1)

(2)

(3)



J Global Clinical Engineering Vol.6 Issue 4: 2024  38

Jia, Zhang, You, Li, Qian, Tao, Su, Lu: A Decision Support System for Rational Deployment of Medical Equipment Based on 
Real-world Data

Calculation of ALOS: ALOS is a critical indicator that 
reflects the hospital’s capacity usage and helps predict 
the demand for in-patient-related medical equipment. 
The formula used is as follows:

where LOSi is the length of stay for patient i, and n is the 
total number of patients. According to studies, ALOS di-
rectly correlates with the equipment needs of hospitals 
with longer in-patient stays.24,25,28 

Prediction of Outpatient Visits: Outpatient visits are 
essential for predicting the demand for outpatient medical 
equipment. We use regression analysis to forecast future 
outpatient visits based on historical data:

where  is the predicted outpatient visits, α is the inter-
cept, β is the trend coefficient, and ∈t  represents the error 
term. This model was influenced by previous studies that 
emphasize the importance of outpatient volume in medi-
cal resource allocation.

Diagnosis Procedure Numbers: Diagnosis-related 
procedures require different types and quantities of medi-
cal equipment. We model this as a linear programming 
optimization problem, considering the demand for each 
procedure type and the available hospital resources. The 
optimization model is as follows:

where cij is the cost associated with assigning equipment 
j to procedure i, and xij is the number of equipment units 
assigned to each procedure. This method is derived from 
existing models that allocate medical resources efficiently 
based on diagnostic needs.25–28

The final optimization model combines ALOS, outpa-
tient visits, and diagnosis procedure numbers to allocate 

(5)

resources dynamically. The goal is to minimize costs while 
satisfying the demand for each hospital’s medical equip-
ment based on real-time data.

RESULTS

After the user logs into MERDIS, the system will obtain 
the corresponding user’s information, including the name, 
the hospital where they work, and the user type, and then 
display the user information under the function bar of the 
home page, as shown in Figure 5 (taking the administrator 
home page as an example). At the top of the home page is 
the function bar. For ordinary users, there are new hos-
pital information imports, new equipment information 
imports, contact information, and logouts. On this basis, 
administrator users have user information management, 
hospital information management, and information check. 
The homepage has three main functions: deployment 
recommendation, evaluation, and settings. The deploy-
ment recommendation is to query the newly established 
hospital’s medical equipment deployment plan by giving 
this hospital’s basic information. Deployment evaluation 
evaluates the current deployment of medical equipment 
in the hospital, analyzes whether the deployment plan 
is rational, and offers suggestions. Users can click “home 
page” to return to the main interface during use.

Take the deployment of CT (64 detectors) and MR 
(1.5T) in a first-class hospital of Obstetrics and gynecol-
ogy as an example. The basic information and deployment 
of the two medical devices in the hospital are shown in 
Tables 1 and 2.

According to the data in Tables 1 and 2, formula (1) can 
be used to calculate the theoretical annual clinical pathway 
demand of CT (64 detectors) and MRI (1.5T), and then 
formula (2) can be used to calculate the theoretical mini-
mum deployment number based on the clinical pathway.

For example, the theoretical minimum deployment 
number of CT (64 detectors):

(4)

(6)



39 J Global Clinical Engineering Vol.6 Issue 4: 2024

Jia, Zhang, You, Li, Qian, Tao, Su, Lu: A Decision Support System for Rational Deployment of Medical Equipment Based on 
Real-world Data

The data in Table 3 shows that the number of CT (64 
detectors) deployments in the studied hospitals meets 
the demand of clinical pathways, and the deployment is 

more appropriate. The number of MR (1.5T) deployments 
is lower than the theoretical demand, which cannot meet 
the medical needs of patients in this hospital. 

Each hospital can get its own deployment plan rec-
ommendation and evaluation by filling in the relevant 
information. At the same time, the information in the 
database is becoming more and more complete in the 
user operation.

TABLE 1. Clinical data statistics of Shanghai First Maternity and 
Infant Hospital in 2019.

Hospital 
Level

Hospital Type
Operation 

Quantity (times)

Annual Clinical 
Pathway Usage 

(times)

First-class Maternity 
Hospital

65108 11881

FIGURE 5. Deployment evaluation page.

TABLE 2. Usage of CT (64 detectors) and MRI (1.5T).

Equipment 
Name

Total Number 
of Clinical 

Pathways Used

Annual
Start-Up Days

Daily Saturated 
Workload (times)

CT* 

(64 detectors)
2714 250 120

MR** (1.5T) 4182 250 40

*CT = computed tomography; **MR = magnetic resonance.

TABLE 3. Comparison of actual equipment deployment quan-
tity and calculation results.

Equipment 
Name

R S

Actual 
Equipment 
Deployment 

Quantity

Theoretical 
Minimum 

Deployment 
Quantity

Recommended 
Deployment 

Quantity

CT* 
(64 detectors)

14873 30000 1 0.4958 1.3384

MR** (1.5T) 22918 10000 1 2.2918 2.3146

*CT = computed tomography; **MR = magnetic resonance.



J Global Clinical Engineering Vol.6 Issue 4: 2024  40

Jia, Zhang, You, Li, Qian, Tao, Su, Lu: A Decision Support System for Rational Deployment of Medical Equipment Based on 
Real-world Data

Including ALOS, Outpatient Visits, and diagnosis 
procedure numbers in the medical equipment deploy-
ment model has significantly improved the efficiency of 
resource allocation. ALOS, in the decision-making process 
for allocating medical equipment, hospitals with longer 
average lengths of stay may require increased medical 
equipment resources or optimization of their treatment 
processes. Our system can effectively reduce hospital stays 
and improve hospital efficiency through the rational use 
of medical devices and resource allocation.

Outpatient Visits: Hospitals with high outpatient 
volumes require more equipment to meet patient needs 
effectively. This is consistent with other literature, em-
phasizing the importance of forecasting outpatient visits 
for better resource planning. When deploying medical 
equipment, the quantity or type of equipment should be 
allocated based on the hospital’s outpatient visit volume, 
such as increasing outpatient equipment in high-volume 
hospitals or updating equipment.

Number of Diagnostic Procedures by Type: Diagnostic 
procedures directly influence the type and quantity of 
medical equipment required. By incorporating the demand 
for specific procedures into the optimization model, we 
can ensure that resources are allocated according to the 
varying needs of different procedures. This approach en-
sures that hospitals are better prepared for both routine 
and complex procedures. For example, some hospitals may 
specialize in cardiology or orthopedics, and the equipment 
needs of these departments may differ significantly from 
others. The allocation strategy can be adjusted based on 
the hospital’s specific needs.

In conclusion, this study highlights the importance 
of integrating multiple real-world data factors—ALOS, 
outpatient visits, and diagnosis procedure numbers—into 
a decision support system for medical equipment deploy-
ment. The model improves resource utilization, helps 
reduce wastage, and ensures that hospitals are better 
equipped to handle fluctuating demands.

To validate the practicality and reliability of our system, 
a satisfaction survey was conducted among doctors and 
patients at the Shanghai First Maternity and Infant Health 
Hospital. The survey assessed various aspects including 
the rationality of equipment layout, user convenience, 

and User Satisfaction, with each aspect rated on a scale 
of 1 to 5, where 5 indicates very satisfied and 1 indicates 
very dissatisfied.

It can be observed from the table that our system 
has provided a certain level of assistance in the rational 
placement of medical equipment.

Physicians, as professionals, tend to rate the rational-
ity and convenience of equipment layout more highly, 
while patients, as recipients of services, focus more on 
the convenience and comfort of the medical process. Con-
sequently, there is a certain degree of variation in these 
ratings, which also suggests that as medical institutions, 
we need to pay attention to the needs of patients, improve 
the layout of equipment, enhance patient convenience, 
and thereby increase overall user satisfaction.

DISCUSSION

The MERDIS system makes it convenient, accurate, and 
intuitive to get a rational deployment plan and sugges-
tions for medical equipment in the hospital. According to 
the frequency of clinical pathways on medical equipment 
and the working ability of the equipment, the theoretical 
minimum number of medical equipment deployments 
in different influencing factors can be calculated by the 
formula, and the recommended deployment quantity of 
medical equipment can be obtained through the calcula-
tion method of big data.

Due to the difficulty of data research, the current data 
of 52 hospitals is not complete enough, and the deploy-
ment of medical equipment is only limited to large medical 
equipment. In the case of continuous data input and enrich-
ment, the calculation model will become more accurate 
and expand the scope of medical equipment covered.

TABLE 4. Survey results.

Interviewee
Rationality of 

Equipment 
Layout

User 
Convenience

User Satisfaction 
(%)

Physicians 4.6 4.7 95.2

Patients 3.8 3.2 82.1



41 J Global Clinical Engineering Vol.6 Issue 4: 2024

Jia, Zhang, You, Li, Qian, Tao, Su, Lu: A Decision Support System for Rational Deployment of Medical Equipment Based on 
Real-world Data

When the data tends to be complete and the number 
of statistical years increases, the function of forecasting 
the purchased quantity of equipment can be added to the 
later system version. By the annual average growth rate 
method, the annual growth rate of equipment deployment 
can be analyzed, and the annual deployment quantity of 
the next year or even several years can be estimated ac-
cording to the equipment deployment base at the end of 
the previous year.5 The formula is as follows:

where y0 represents the initial number of devices con-
figured in the starting year of recording, yn denotes the 
number of devices configured in the most recent year, n 
is the number of years for which statistics are compiled, 
and R represents the annual average growth rate of device 
configuration.

The working capacity of different equipment is also 
different, and the same kind of equipment is used in dif-
ferent models and working environments. Later research 
can be closer to the direction of full-cycle management 
of medical equipment, real-time monitoring of the use of 
medical equipment, and increase the accuracy of statistics.

CONCLUSION

The MERDIS system represents a groundbreaking ad-
vancement in medical equipment management, providing 
a solid foundation for the future development of macro 
data management in this sector. Its ability to analyze vast 
amounts of hospital data, encompassing equipment deploy-
ment and clinical practices, offers significant insights and 
improvements in the field. The system’s intuitive interface 
and analytical capabilities enable healthcare institutions 
to conveniently and accurately devise rational deployment 
plans tailored to their specific needs and influenced by 
various factors. This technology-driven approach promises 
to streamline the decision-making process for medical 
equipment resource allocation, leading to more efficient 
and effective utilization of medical assets.

As the MERDIS system progresses, with ongoing refine-
ments and the accumulation of more data, its predictive 
models are expected to become increasingly accurate 
and dependable. This evolution will further empower 
healthcare decision-makers, enhancing their ability to 
allocate resources optimally. The success of the MERDIS 
system is also a credit to the collaborative efforts of par-
ticipating hospitals, individuals, and various supporting 
organizations, including the Shanghai Municipal Health 
Commission’s Policy Research Project, the National Natu-
ral Science Foundation of China, and the SHDC Clinical 
Research Plan. Their contributions have been pivotal in 
realizing this innovative project, which exemplifies the 
power of integrating technology with practical data to 
revolutionize hospital resource management.

ACKNOWLEDGMENT

The authors wish to thank the study participants for 
their contribution to the research and current and former 
investigators and staff. The authors would specifically 
like to thank North Hospital of Huashan Hospital-Fudan 
University, North Hospital of Ruijin Hospital-Shanghai 
Jiaotong University School of Medicine, Shanghai Mu-
nicipal Hospital of Traditional Chinese Medicine, and 
International Peace Maternity & Child Health Hospital 
of China for their research and administrative assistance.

FUNDING

This work was supported by the Planning Project of 
Shanghai Science and Technology [21S31902100], the 
National Natural Science Foundation of China [82073474], 
the Management Project of Shanghai Hospital Develop-
ment Center [2024SKMR-27], and the National Institute 
of Hospital Administration [2022MEB108].

REFERENCES

1. Yuan, L., Cao, J., Wang, D., et al. Regional disparities and 
influencing factors of high quality medical resources 
distribution in China. Int J Equity Health. 2023;22(1):8.
https://doi.org/10.1186/s12939-023-01825-6.

(7)

https://doi.org/10.1186/s12939-023-01825-6


J Global Clinical Engineering Vol.6 Issue 4: 2024  42

Jia, Zhang, You, Li, Qian, Tao, Su, Lu: A Decision Support System for Rational Deployment of Medical Equipment Based on 
Real-world Data

2. Wu, F., Chen, W., Lin, L., et al. The Balanced allocation of 
medical and health resources in urban areas of China 
from the perspective of sustainable development: a 
case study of Nanjing. Sustainability. 2022;14(11):6707.
https://doi.org/10.3390/su14116707.

3. Gao, J., Fan, C., Chen, B.,et al. Telemedicine is becoming 
an increasingly popular way to resolve the unequal 
distribution of healthcare resources: evidence from 
China. Front Public Health. 2022;10:916303. https://
doi.org/10.3389/fpubh.2022.916303.

4. Feng, S.L. and Liu, Z.C. Preliminary Discussion on Clini-
cal Pathway-based Configuration Method of Medical 
Devices. China Med Devices. 2014;29:(2):47–49. https://
doi.org/10.3969/j.issn.1674-1633.

5. Feng, X. The Principles And Evaluation System of Large 
Scale Medical Equipment Configuration (Published 
work in Chinese). Chin Hospital Architecture Equip  
2019;20:29–32.

6. Noriyuki, K., Masahiko, N., Takashi, M., et al. Medical 
equipment deployment in pediatric emergency prehospital 
medical units in Japan. Pediatr Int. 2018;60(1):93–95.
https://doi.org/10.1111/ped.13432.

7. Emanuel, E.J., Persad, G., Upshur, R., et al. Fair Alloca-
tion of Scarce Medical Resources in the Time of Co-
vid-19. N Engl J Med. 2020;382:2049–2055. https://
doi.org/10.1056/NEJMsb2005114.

8. Teutsch, S. and Rechel, B. Ethics of Resource Al-
location and Rationing Medical Care in a Time of 
Fiscal Restraint—US and Europe. Public Health Rev. 
2012;34(1):15. https://doi.org/10.1007/BF03391667.

9. Krütli, P., Rosemann, T., Törnblom, K.Y., et al. How to 
Fairly Allocate Scarce Medical Resources: Ethical Argu-
mentation under Scrutiny by Health Professionals and 
Lay People. PloS One. 2016;11(7):e0159086. https://
doi.org/10.1371/journal.pone.0159086.

10. Zhao, S. and Liu, Z.W. A study on the evaluation of 
medical equipment allocation dependent on evidence-
based and decision-making tree. China Med Equip. 
2018;15(2):108–111.https://doi.org/10.3969/J.
ISSN.1672-8270.2018.02.029.

11. Peng, Y.Y. On audit suggestions of medical equipment 
procurement in large-scale third class hospital. Ac-
countant (Published work in Chinese). Guangzhou 
First People’s Hospital, Guangzhou, China. 2019:51–52. 

12. Yu, S.J., Xu, F., Chen, W.W., et al. Scientific management 
and rational configuration of large medical equipment in 
hospital. China Med Equip. 2014;11(4):71–73. https://
doi.org/10.3969/J.ISSN.1672-8270.2014.04.024.

13. Althammer, E. and Pree, W. Design and Implementa-
tion of an MVC-Based Architecture for E-Commerce 
Applications. Int J Comput Appl. 2001;23(3):173–185.
https://doi.org/10.1080/1206212X.2001.11441649.

14. Jukic, B. and Jukic, N. Information System Planning 
and Decision Making Framework: A Case Study. 
Inf Syst Manag. 2010;27(1):61–71. https://doi.
org/10.1080/10580530903455221.

15. Yu, Q., Liao, X., Lin, J. Development of Modern Medical 
Equipment Management System Based on Web. Chin J 
Med Instrum. 2017;41:70–72. https://doi.org/10.3969/j.
issn.1671-7104.2017.01.019.

16. Sundaram, D., Dong, J., Srinivasan, A. The Design and 
Implementation of a Flexible Web-based Decision 
System. J Decis Syst. 2003;12(2):159–176. https://
doi.org/10.3166/jds.12.159-176.

17. Whitesell, S., Richardson, R., Groves, M.D., et al. Pro 
Microservices in .NET 6: With Examples Using ASP.
NET Core 6, MassTransit, and Kubernetes. Apress: 
New York, USA; 2022; pp. 29–49. https://doi.
org/10.1007/978-1-4842-7833-8.

18. Whitley, M.A. and Walsh, D.S. A Framework for the De-
sign and Implementation of Service-learning Courses. 
J Phys Educ Recreat Dance. 2014;85(4):34–39. https://
doi.org/10.1080/07303084.2014.884835.

19. Kaminski, R., Romero, J., Schaub, T., et al. How to build 
your own ASP-based system?! Theory Pract Log Pro-
gram. 2023;23(1):299–361. https://doi.org/10.1017/
S1471068421000508.

20. Zhang, C., Xu, W., Liu, J., et al. Digital twin-enabled recon-
figurable modeling for smart manufacturing systems. 
Int J Comput Integr Manuf. 2019;34(7–8):709–733.
https://doi.org/10.1080/0951192X.2019.1699256.

https://doi.org/10.3390/su14116707
https://doi.org/10.3389/fpubh.2022.916303
https://doi.org/10.3389/fpubh.2022.916303
https://doi.org/10.3969/j.issn.1674-1633.2014.02.012
https://doi.org/10.3969/j.issn.1674-1633.2014.02.012
https://doi.org/10.1111/ped.13432
 https://doi.org/10.1056/NEJMsb2005114
 https://doi.org/10.1056/NEJMsb2005114
https://doi.org/10.1007/BF03391667
https://doi.org/10.1371/journal.pone.0159086
https://doi.org/10.1371/journal.pone.0159086
https://doi.org/10.3969/J.ISSN.1672-8270.2018.02.029
https://doi.org/10.3969/J.ISSN.1672-8270.2018.02.029
https://doi.org/10.3969/J.ISSN.1672-8270.2014.04.024
https://doi.org/10.3969/J.ISSN.1672-8270.2014.04.024
https://doi.org/10.1080/1206212X.2001.11441649
https://doi.org/10.1080/10580530903455221
https://doi.org/10.1080/10580530903455221
https://doi.org/10.3969/j.issn.1671-7104.2017.01.019
https://doi.org/10.3969/j.issn.1671-7104.2017.01.019
https://doi.org/10.3166/jds.12.159-176
https://doi.org/10.3166/jds.12.159-176
https://doi.org/10.1007/978-1-4842-7833-8
https://doi.org/10.1007/978-1-4842-7833-8
https://doi.org/10.1080/07303084.2014.884835
https://doi.org/10.1080/07303084.2014.884835
https://doi.org/10.1017/S1471068421000508
https://doi.org/10.1017/S1471068421000508
https://doi.org/10.1080/0951192X.2019.1699256


43 J Global Clinical Engineering Vol.6 Issue 4: 2024

Jia, Zhang, You, Li, Qian, Tao, Su, Lu: A Decision Support System for Rational Deployment of Medical Equipment Based on 
Real-world Data

25. Adetunji, O., Ottino, K., Tucker, A., et al. Variations in 
pediatric hospitalization in seven European countries. 
Health Policy. 2020;124(11):1165–1173. https://doi.
org/10.1016/j.healthpol.2020.07.002.

26. Marino, D. and Quattrone, G. A proposal for a new 
index to evaluate hospital resource allocation: The 
case of Italian NHS rationalisation. Eur Res Manag Bus 
Econ. 2019;25(1):23–29. https://doi.org/10.1016/j.
iedeen.2018.10.001.

27. Bala, C., Rusu, A., Ciobanu, D., et al. Length of Hospital 
Stay, Hospitalization Costs, and Their Drivers in Adults 
with Diabetes in the Romanian Public Hospital System. 
Int J Environ Res Public Health. 2022;19(16):10035.
https://doi.org/10.3390/ijerph191610035.

28. Modica, C. The Value Transformation Framework: An 
Approach to Value-Based Care in Federally Qualified 
Health Centers. J Healthc Qual. 2020;42(2):106–112. 
https://doi.org/10.1097/JHQ.0000000000000239.

21. Belcastro, L., Marozzo, F., Talia, D. Programming models 
and systems for Big Data analysis. Int J Parallel Emer-
gent Distrib Syst. 2018;34(6):632–652. https://doi.or
g/10.1080/17445760.2017.1422501.

22. Belcastro, L., Cantini, R., Marozzo, F., et al. Program-
ming big data analysis: principles and solutions. J 
Big Data. 2022;9(1):4. https://doi.org/10.1186/
s40537-021-00555-2.

23. Fanelli, S., Pratici, L., Salvatore, F.P., et al. Big data 
analysis for decision-making processes: challenges 
and opportunities for the management of healthcare 
organizations. Manag Res Rev. 2023;46(3):369–389.
https://doi.org/10.1108/MRR-09-2021-0648.

24. Ippoliti, R., Falavigna, G., Zanelli, C. et al. Neural networks 
and hospital length of stay: An application to support 
healthcare management with national benchmarks 
and thresholds. Cost Eff Resour Alloc. 2021;19(1):67.
https://doi.org/10.1186/s12962-021-00322-3.

https://doi.org/10.1016/j.healthpol.2020.07.002
https://doi.org/10.1016/j.healthpol.2020.07.002
https://doi.org/10.1016/j.iedeen.2018.10.001
https://doi.org/10.1016/j.iedeen.2018.10.001
https://doi.org/10.3390/ijerph191610035
https://doi.org/10.1097/JHQ.0000000000000239
https://doi.org/10.1080/17445760.2017.1422501
https://doi.org/10.1080/17445760.2017.1422501
https://doi.org/10.1186/s40537-021-00555-2
https://doi.org/10.1186/s40537-021-00555-2
https://doi.org/10.1108/MRR-09-2021-0648
https://doi.org/10.1186/s12962-021-00322-3

