Predictions of the number of suspended surgeries using software Power BI® in a university hospital

José Guilhermo Berenguer Flores; Romero de Melo Silva; Daniel  Aragão Machado; Alexandre Sousa da Silva

doi:10.9789/2175-5361.rpcfo.v15.12750

Authors

José Guilhermo Berenguer Flores Hospital Universitário Gaffrée e Guinle https://orcid.org/0000-0001-9995-7758
Romero de Melo Silva Hospital Universitário Gaffrée e Guinle https://orcid.org/0000-0002-5743-2336
Daniel Aragão Machado Federal University of the State of Rio de Janeiro https://orcid.org/0000-0003-0680-5291
Alexandre Sousa da Silva Federal University of the State of Rio de Janeiro https://orcid.org/0000-0002-5573-4111

DOI:

https://doi.org/10.9789/2175-5361.rpcfo.v15.12750

Keywords:

University Hospital, Surgeries, Stages, Forecasts

Abstract

Objective: To analyze the suspended surgeries, making future predictions of three months, starting in October 2022, through a line graph using the Power BI Software. Method: We used the technique of weighted moving averages, simple exponential smoothing, using the Power BI^® line graph tool, with a confidence interval of 95% and predictions of three months. Results: The results showed that there are differences in the steps to construct predictions and some prerequisites must be fulfilled, the following predictions were found with their respective confidence intervals: November 134 (97,172), December 141 (102,180), January 147 (106,188). Conclusion: The use of forecasts can be a useful tool for decision making, predicting problems and always necessary in the management of a hospital. and can even suppress expenses in anticipation of a variety of problems.

Downloads

Download data is not yet available.

Author Biographies

José Guilhermo Berenguer Flores, Hospital Universitário Gaffrée e Guinle

Master in Health and Technology in the Hospital Space (UNIRIO), Specialization in Management in Public Health and Environment by the FACULTY OF IPATINGA- MG. in addition, he has a Degree in Biostatistics from the Metropolitan College of Ribeirão Preto and Improvement of Health Research Techniques from the same institution, a Degree in Statistics from the NATIONAL SCHOOL OF STATISTICAL SCIENCES (ENCE). He is currently Head of the Management Unit in Technological Innovation of the University Hospital Gafrée and Guinle/RJ. He has professional experience working as a Statistician at the National Cancer Institute - INCA - (2002 to 2003), Air Force Command - COMAER - (2003 to 2012), Brazilian Institute of Geography and Statistics - IBGE (2016 to 2019), and Brazilian Company of Hospital Services (EBSERH) since 2019.

Romero de Melo Silva, Hospital Universitário Gaffrée e Guinle

Master in Health and Technology in the Hospital Space (UNIRIO). MBA in Strategic Planning and Graduation in Law from Centro Universitário da Cidade, as well as an undergraduate course in Business Administration from Faculdade Moraes Junior. Specialization in Technology in Big Data. He is currently Head of the Research Management and Technological Innovation sector of the Gaffree University Hospital and Guinle/RJ. He has professional experience in the areas of Process Management, Quality, Projects, Research and Information Technology. Member of the following nuclei, commissions and committees of HUGG: LGPD implementation committee; Mediation and Conciliation Commission; Technical Member of NATS (Centers for Health Technology Assessment); Development and implementation committee of platform based on Business Intelligence-BI; member of the Working Group (WG) to update along the lines of Active Transparency/CGU; Coordinator of the RUTE Network (University Network of Telemedicine) at HUGG; Member of the Network GO FAIR BRASIL SAÚDE E VODAN BR. Coordinator of the Scientific Initiation Program HUGG-UNirio/Ebserh (2022)

Daniel Aragão Machado, Federal University of the State of Rio de Janeiro

Associate Professor I of the Department of Fundamental Nursing, Alfredo Pinto School of Nursing - EEAP/Unirio (entry: 2012). PhD in Biosciences (Federal University of the State of Rio de Janeiro, 2014). Master in Nursing (EEAP/Unirio, 2010). Specialist in Management of Federal University Hospitals at SUS (Hospital Sírio Libanês, 2016). Specialist in Clinical and General Surgical Nursing (Hospital dos Servidores do Estado - Residência, 2008), Postgraduate in High Complexity Intensive Nursing (Universidade Gama Filho, 2008). Degree in Nursing (Unirio, 2005). Permanent Professor of the Postgraduate Program in Health and Technology in the Hospital Space (since 2016). Researcher at the Laboratory of Economic Evaluation and Health Technologies (since 2016).

Alexandre Sousa da Silva, Federal University of the State of Rio de Janeiro

He holds a PhD in Statistics from the Federal University of Rio de Janeiro (2012), a Master's degree in Statistics and Agronomic Experimentation from the Escola Superior de Agricultura "Luiz de Queiroz" (2007) and a degree in Statistics from the Universidade Estadual Paulista Júlio de Mesquita Filho (2004). He is currently an associate professor at the Federal University of the State of Rio de Janeiro. He has experience in the area of Probability and Statistics, with emphasis on Spatial Analysis, Bayesian Space-Temporary Models and Statistical Education.

References

REFERÊNCIAS

World Health Organization (WHO). Guidelines for safe surgery 2009: safe surgery saves live[Internet].2009[cited 2022 Ago 1]. Available from: https://apps.who.int/iris/bitstream/handle/10665/44185/9789241598552_eng.pdf;jsessioid=B2D78%201262C7E26D33992E95EF2BA1020?sequence=1.%20[%20Links%20].

Lago K, Alves L. Dominando o Power BI. 3ed – São Paulo: Datab Inteligência e Estratégia; 2020.

Gartner. Magic Quadrant For Analytics and Business Intelligence Platforms[Internet] [cited 2023 Feb 15]. Available from: https://www.gartner.com/en/documents/3996944

Singh K, Shastri S, Bhadwal AS, Kour P, Kumari M, Sharma D, et al.. Implementation of exponential smoothing for forecasting time series data. International Journal of Scientic Research in Computer Science applications and Management Studies.[Internet]. [2019] [cited 2023 Jan 31] Available from: https://www.researchgate.net/publication/330970319_Implementation_of_Exponential_Smoothing_for_Forecasting_Time_Series_Data

Morettin PD, Toloi CL. (1987). Previsão de Séries Temporais. Editora Atual

Hyndman RJ, Athanasopoulos G. (2018). Forecasting: Principles and Practice [internet]. [cited 2022 Dez 15], Available from: https://otexts.com/fpp3/classical-decomposition.html

Evans JR. (2016). Business Analytics: Methods, Models and Decisions. Pearson [Internet] [cited 2023 jan 30], Available from: https://www.pearson.com/en-au/media/2628253/9781292339061-toc.pdf

Brownlee J. (2018). A gentle Introduction to Exponential Smoothing for Time Series Forecasting in Phyton.[Internet] [cited 2022 ago 20]. Available from: https://machinelearningmastery.com/exponential-smoothing-for-time-series-forecasting-in-python/

Powell B. (2017). Microsoft Power BI Cookbook: Creating Business Intelligence Solutions of Analytical Data Models, Reports, and Dashboards. Packt.

Guilfoyle P. (2017). Forecasting in Power BI.[Internet] [cited 2022 out 03] Available from: https://www.youtube.com/watch?v=XIlPkyyztho.

Microsoft. (2019). O que é Power BI? [Internet] [acesso em 05 de maio de 2022] disponível em: https://powerbi.microsoft.com/pt-br/what-is-power-bi/