Volume 7, Issue 2 (9-2020)
jhbmi 2020, 7(2): 124-132 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Tavakol E, Nowzari V, Pirzad A, Amirhosseini S E, Abdolahi A. Providing a Model for Cost Estimation of Hospital Information System Software Design Using Continuous Decision Tree Algorithm. jhbmi 2020; 7 (2) :124-132
URL: http://jhbmi.ir/article-1-425-en.html
URL: http://jhbmi.ir/article-1-425-en.html
M.Sc. in Computer Engineering, Instructor, Sama Technical and Vocational Training College, Islamic Azad University, Mahshahr Branch, Mahshar, Iran
Abstract: (3392 Views)
Introduction: The cost estimation of a hospital information system software refers to estimating the cost and time required to develop the hospital information system software prior to the start of the project, which will continue until the end of production and development of the system. Estimating the cost of software to produce hospital information system is one of the major concerns of project management in health companies. Cost estimation models that estimate the cost of system construction in the early stages of project construction, with minimal information available from the project, are useful and needed. Selection of an appropriate cost estimation method enables efficient control of time and cost of system construction.
Method: In this retrospective study, 23 open source software projects for hospital information system were selected and the cost of software design and 16 independent variables of each hospital information system software were extracted. The data were then transformed into a test and training set and using a continuous decision tree algorithm, a prediction model was proposed to estimate the cost of designing a hospital information system. The algorithm was then evaluated with four other continuous algorithms.
Results: In this study, the continuous decision tree algorithm was implemented using the 10-fold method and two parameters including mean squared error and mean absolute percentage error were used for evaluation. In the proposed model, error of 74.31 units was obtained for the mean squared error and 17% for the mean absolute percentage error.
Conclusion: It was shown in this study that the proposed model had an acceptable error rate indicating that it performed better than similar methods and can be used to estimate the cost of اhospital information systems
Method: In this retrospective study, 23 open source software projects for hospital information system were selected and the cost of software design and 16 independent variables of each hospital information system software were extracted. The data were then transformed into a test and training set and using a continuous decision tree algorithm, a prediction model was proposed to estimate the cost of designing a hospital information system. The algorithm was then evaluated with four other continuous algorithms.
Results: In this study, the continuous decision tree algorithm was implemented using the 10-fold method and two parameters including mean squared error and mean absolute percentage error were used for evaluation. In the proposed model, error of 74.31 units was obtained for the mean squared error and 17% for the mean absolute percentage error.
Conclusion: It was shown in this study that the proposed model had an acceptable error rate indicating that it performed better than similar methods and can be used to estimate the cost of اhospital information systems
Audio File [MP3 4209 KB] (89 Download)
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
