Time series is a common tool that has successfully been used in medicine and other fields for forecasting due to its popularity and applicability in real-life issues. It is a statistical technique used to analyze data to extract meaningful data statistics and characteristics (Albright & Winston, 2017) . In medicine, a time series model has been successfully deployed to determine the progress of diseases and the mortality rate. The model involves numerous models; each applied in the evaluation of different conditions, such as mortality rate progress. The many techniques applied in time series makes it hard for a hospital administrator to determine the best model to suit the problem he/she wants to investigate. This paper evaluates different variable that can be predicted using the time series and the most appropriate models to measure these variables.
The time series could be used to measure numerous variables in healthcare. Some of the variables that could be predicted include hospital census, health informatics, and clinical decisions, and the number of hospital admissions. Accurate prediction of the hospital census is essential for planning and developing strategies to improve patient care and health outcomes. Forecasting of hospital census is often difficult because of the inadequate capacity to control the patient influx and healthcare trajectories. Various models, such as the ARIMA and seasonal linear regression techniques, could be used to forecast the hospital census. Capan et al., in their research, found out that deployment of these techniques in predicting the hospital census results in a 36.49% increase in prediction accuracy compared to other prediction models, like the fixed average approach (Capan et al., 2016). The high accuracy is essential for proper planning in the hospital to provide quality care to patients. For instance, this model could be handy in assisting me and the hospital management in identifying the number of diabetes patients expected in 6 months, which will help develop proper procedures to ensure that they receive quality care.
Delegate your assignment to our experts and they will do the rest.
The number of hospital admissions could be predicted using the hybrid ARIMA-ANN models of the time series. Hospital crowding has been a major problem in the modern world, which has triggered the need to develop methods to predict hospital admissions. According to research by Zhou et al., hospital admissions forecasting requires the hybrid of ARIMA and ANN due to its increased forecasting accuracy (ARIMA-NARNN) (Zhou et al., 2018). ARIMA prediction is limited due to its inability to obtain non-linear relationships between variables in the real world (Zhou et al., 2018). This, therefore, requires the application of artificial neural networks to capture the non-linear relationships between variables. This model's high accuracy makes it easy to keep track of all hospital admissions due to various problems that enable proper future planning. For example, this model could be essential in predicting the number of hospital admissions regarding chronic diseases, which will necessitate preparedness.
The artificial neural networks model (ANN) of the time series could be used for health informatics and proper clinical decisions. Proper health information and clinical decisions are essential in the provision of quality care to patients. A trained ANN model could be deployed in the hospital to help clinicians identify patients with certain conditions, like acute myocardial, which would be essential in reducing the clinicians' workload. Research by Shahid, Rappon, and Berta identified that ANN improves clinical decision making, which helps in improving the quality of care (Shahid et al., 2019; Bui et al., 2018). For instance, the ANN model could be applied in the hospital to provide information about the patients' illnesses based on the signs and symptoms. This information could be essential in improving accuracy hence the quality of care in patients.
In conclusion, time series analysis is an essential tool in medicine, particularly in predicting medical parameters. It is used in analyzing and measuring variables like hospital census and clinical decisions. This information is crucial in planning for the future and improving the quality of care. It can be done using various models, like ARIMA and ANN, depending on the investigated condition. As a healthcare administrator, it is essential to apply the time series models to analyze different healthcare variables to ensure quality care is provided.
References
Albright, C., & Winston, W. L. (2017). Business Analytics: Data Analysis and Decision Making. Stamford, CT: Cengage Learning.
Bui, C., Pham, N., Vo, A., Tran, A., & Nguyen, T. (2018). Time Series Forecasting for Healthcare Diagnosis and Prognostics with the Focus on Cardiovascular Diseases. 6th International Conference on the Development of Biomedical Engineering in Vietnam. 63. Singapore: Springer.
Capan, M., Hoover, S., Jackson, E. V., Paul, D., & Locke, R. (2016). Time Series Analysis for Forecasting Hospital Census: Application to the Neonatal Intensive Care Unit. Applied Clinical Informatics, 7 (2), 275-286. doi:10.4338/ACI-2015-09-RA-0127
Shahid, N., Rappon, T., & Berta, W. (2019). Applications of Artificial Neural Networks in Health Care Organizational Decision-Making: A Scoping Review. PloS, 14 (2). doi:10.1371/journal.pone.0212356
Zhou, L., Zhao, P., Wu, D., Cheng, C., & Huang, H. (2018). Time series model for forecasting the number of new admission inpatients. BMC Medical Informatics and Decision Making, 18 (39). doi:10.1186/s12911-018-0616-8
