Reyhane Shahraki, Alireza Pooya,
Volume 13, Issue 4 (3-2015)
Abstract
Abstract:
Background: Recently, hospitals in order to improve strategic and operational work have been under a lot of pressure Nonetheless, lack of taxonomy researches have been noticed in Health care. The purpose is to present taxonomy of health care operational systems and strategies of Mashhad hospitals sections in correct order in the base of their aims and operational decisions and afterwards assign Proportionate strategies and systems with each other.
Materials and Methods: Considering its objective, this study is applied. It is exploratory and based on survey regarding its method. 84 samples of remedial hospitals sections in Mashhad have been chosen by chance and after final survey and justifiability implement research to analysis data using from k-means cluster analysis and in order to assess the validity of this analysis, the multiple discriminant analysis has been used. The test of independence was used to assess the correlation between strategies and recognized systems.
Results: for each strategies and operational systems 3 clusters have reconnoitered that each of them in a correct order is emphasizing on goals and different decisions. Also the results of performing independence test is expressive the proportion between Leaders of service- centric strategy with operation leading system and cost- based follower strategy with creative cautious system.
Conclusion: This study dose not only provides a useful description of the operational situation and operational position of a hospital, but also provides a necessary setting for more professional studies and theorizing.
Mohammadreza Shahraki, Hamidreza Esmaeili,
Volume 22, Issue 4 (1-2024)
Abstract
Background and Purpose: Artificial intelligence (AI) plays a crucial role in the optimal management of hospital waste, particularly in predicting the volume and type of waste generated. This study aims to identify and rank the risks associated with the use of AI systems in hospital waste management by employing a multi-criteria decision-making approach.
Methods: This descriptive, cross-sectional study was conducted in 2023 (1402 in the Iranian calendar) at two hospitals, Ali Ibn Abitaleb and Khatam al-Anbiah, in Zahedan. Ten hospital staff members were selected as expert participants for the Delphi panel. The Shannon entropy method was utilized for risk weighting, and the TOPSIS method was applied to rank the identified risks.
Results: Kendall's coordination coefficient was used to assess the level of consensus among the Delphi panel members, with the coefficient values for the first, second, and third Delphi rounds being 6.3, 7.1, and 7.3, respectively. The indicators were weighted using the Shannon entropy method, based on three criteria: impact intensity (0.3), probability of occurrence (0.4), and detection probability (0.32). The TOPSIS method was then employed to rank the identified risks, with the most significant risks being the need for necessary infrastructure (0.847), the requirement for accurate and complete data (0.751), and budget constraints (0.749).
Conclusion: By applying multi-criteria decision-making methods, healthcare managers can effectively identify and prioritize the risks associated with using AI systems in hospital waste management, enabling them to focus on strengthening waste management practices based on these priorities.
