Forecasting Seasonal Trends in Ear Nose Throat Diseases: A Comparative Analysis of Statistical and Machine Learning Models
Forecasting Seasonal Trends in ENT Diseases: A Comparative Analysis of Statistical and Machine Learning Models
Abstract
This study examines patterns of seasonal illnesses at an ENT hospital using statistical methods and
advanced machine learning techniques to improve disease prediction and support healthcare planning. The
data underwent careful cleaning to ensure accuracy, which involved identifying outliers, managing missing
values, and normalizing information. The study looked at how seasonal illnesses develop, using a mix of
techniques. This research used advanced tools like Long Short-Term Memory (LSTM) networks and
Prophet, as well as simpler models such as Holt-Winters and SARIMA. To make the models easier to
understand, there is an application of SHAP (SHapley Additive Explanations) values. Finally, these
statistical measures like Mean Absolute Error (MAE) and confidence periods had been used to check the
accuracy of the forecasts at some stage in the overall performance assessment. Moreover, to discover how
weather influences sickness seasonality, connections between patterns of contamination and environmental
variables like temperature, humidity, and rainfall have been additionally looked at with the aid of the usage
of correlation prediction. In well-known, this blended method shows how conventional and system gaining
knowledge of models can monitor seasonal illness traits. The effects not simplest display disorder styles,
but in addition they assist with allocating resources and making guidelines for better healthcare
management.
References
S. Wang, C. H. Lai, and W. Y. Shih, “Forecasting weekly outpatient visits using arima and holt–winters,” PLoS One, vol. 15, no. 5, p. e0232270, 2020.
C. Li, J. Lin, and W. Cao, “Time series analysis of infectious diseases in china: forecasting using the arima and holt–winters methods,” Infectious Diseases of Poverty, vol. 8, no. 1, p. 7, 2019.
T. H. Musa, S. T. Tay, Y. Lim, and M. R. Jumat, “Time series analysis of dengue fever in malaysia: comparison between arima and holt–winters models,” PLoS Neglected Tropical Diseases, vol. 14, no. 10, p. e0008680, 2020.
X. Zhou, Y. Zhang, Z. Li, et al., “Comparison of arima and holt–winters methods for predicting influenza outpatients in china,” Scientific Reports, vol. 8, no. 1, p. 16485, 2018.
M. Llamas-Nistal, J. A. Guitián, and V. Ríos, “Predicting the incidence of covid-19 using holt–winters and arima: the case of spain,” PLoS One, vol. 16, no. 4, p. e0250406, 2021.
Y. Liu, X. Zhang, Z. Wang, et al., “Comparison of arima and holt–winters models for predicting tuberculosis incidence in a chinese province,” BMC Infectious Diseases, vol. 20, no. 1, p. 50, 2020.
P. Guo, X. Li, Y. Zhang, et al., “A comparative study on time series forecasting models for hand, foot and mouth disease,” Frontiers in Public Health, vol. 8, p. 251, 2020.
N. D. Thanh, N. T. Luan, N. T. Thu, and N. T. Van, “Comparison of arima and holt–winters models for forecasting dengue fever in hanoi, vietnam,” International Journal of Infectious Diseases, vol. 85, pp. 117–124, 2019.
C. L. Poh, K. L. Thong, and H. Y. Chee, “Time series analysis of dengue fever cases in malaysia using the holt–
winters method,” Asia Pacific Journal of Public Health, vol. 31, no. 6, pp. 545–552, 2019.
W. Pan and Y. Li, “Comparison of the holt–winters and arima models in forecasting infectious disease,” Journal of Computer Science & Health Informatics, vol. 12, no. 1, pp. 44–50, 2019.
S. M. Lundberg and S. I. Lee, “A unified approach to interpreting model predictions,” Advances in Neural Information Processing Systems, vol. 30, pp. 4765–4774, 2017.
R. J. Hyndman and G. Athanasopoulos, Forecasting: Principles and Practice. OTexts, 3rd ed., 2021.
