Evaluating Measles Incidence Rates Using Machine Learning and Time Series Methods in the Center of Iran, 1997-2020
-
Javad Nazari
,
Parnia-Sadat Fathi
,
Nahid Sharahi
,
Majid Taheri
,
Payam Amini
,
Amir Almasi-Hashiani
Abstract
Background: Measles is a feverish condition labeled among the most infectious viral illnesses in the globe. Despite the presence of a secure, accessible, affordable and efficient vaccine, measles continues to be a worldwide concern.
Methods: This epidemiologic study used machine learning and time series methods to assess factors that placed people at a higher risk of measles. The study contained the measles incidence in Markazi Province, the center of Iran, from Apr 1997 to Feb 2020. In addition to machine learning, zero-inflated negative binomial regression for time series was utilized to assess development of measles over time.
Results: The incidence of measles was 14.5% over the recent 24 years and a constant trend of almost zero cases were observed from 2002 to 2020. The order of independent variable importance were recent years, age, vaccination, rhinorrhea, male sex, contact with measles patients, cough, conjunctivitis, ethnic, and fever. Only 7 new cases were forecasted for the next two years. Bagging and random forest were the most accurate classification methods.
Conclusion: Even if the numbers of new cases were almost zero during recent years, age and contact were responsible for non-occurrence of measles. October and May are prone to have new cases for 2021 and 2022.
2. Bester JC (2016). Measles and measles vaccination: a review. JAMA pediatrics, 170(12):1209-1215.
3. Congera P, Maraolo AE, Parente S, et al (2019). Measles in pregnant women: a systematic review of clinical outcomes and a meta-analysis of antibodies seroprevalence. J Infect, 80(2):152-160.
4. Li S, Ma C, Hao L, Su Q, et al (2017). Demographic transition and the dynamics of measles in six provinces in China: A modeling study. PLoS Med, 14(4):e1002255.
5. Patel MK, Dumolard L, Nedelec Y, et al (2019). Progress Toward Regional Measles Elimination—Worldwide, 2000–2018. MMWR Morb Mortal Wkly Rep, 68(48):1105-1111.
6. Mohammadbeigi A, Zahraei SM, Sabouri A, et al (2019). The spatial analysis of annual measles incidence and transition threat assessment in Iran in 2016. Med J Islam Repub Iran, 33:130.
7. Namaki S, Gouya MM, Zahraei SM, et al (2020). The elimination of measles in Iran. Lancet Glob Health, 8(2):e173-e174.
8. Mohammadbeigi A, Zahraei SM, Asgarian A, et al (2018). Estimation of measles risk using the World Health Organization Measles Programmatic Risk Assessment Tool, Iran. Heliyon, 4:e00886.
9. Agresti A, Kateri M (2011). Categorical data analysis. ed. Springer.
10. Izenman AJ (2013). Linear discriminant analysis. In: Modern multivariate statistical techniques. Ed(s): Springer, pp. 237-280.
11. Cutler A, Cutler DR, Stevens JR (2012). Random forests. In: Ensemble machine learning. Ed(s): Springer, pp. 157-175.
12. Maroufizadeh S, Amini P, Hosseini M, et al (2018). Determinants of Cesarean Section among Primiparas: A Comparison of Classification Methods. Iran J Public Health, 47(12): 1913–1922.
13. Xiao T, Zhu J, Liu T (2013). Bagging and boosting statistical machine translation systems. Artificial Intelligence, 195:496-527.
14. Tapak L, Shirmohammadi-Khorram N, et al (2019). Prediction of survival and metastasis in breast cancer patients using machine learning classifiers. Clinical Epidemiology and Global Health, 7:293-299.
15. Amini P, Ahmadinia H, Poorolajal J, et al (2016). Evaluating the High Risk Groups for Suicide: A Comparison of Logistic Regression, Support Vector Machine, Decision Tree and Artificial Neural Network. Iran J Public Health, 45(9): 1179–1187.
16. Yang M, Zamba GK, Cavanaugh JE (2013). Markov regression models for count time series with excess zeros: A partial likelihood approach. Statistical Methodology, 14:26-38.
17. Yang M, Cavanaugh JE, Zamba GK (2015). State-space models for count time series with excess zeros. Statistical Modelling, 15:70-90.
18. Yang M, Zamba G, Cavanaugh J (2014). ZIM: Zero-inflated models for count time series with excess zeros. R package version, 1.
19. Xiong Y, Wang D, Lin W, et al (2014). Age-related changes in serological susceptibility patterns to measles: results from a seroepidemiological study in Dongguan, China. Hum Vaccin Immunother, 10(4):1097-03.
20. Zahraei SM, Eshrati B, Gouya MM, et al (2014). Is there still an immunity gap in high-level national immunization coverage, Iran? Arch Iran Med, 17(10):698-701.
21. World Health Organization (2019). New measles surveillance data for 2019. Retrieved August, 24:2019.
22. Prevention ECfD, Control (2018) Monthly measles and rubella monitoring report, September 2018. (ed)^(eds), ECDC Stockholm,
23. Hughes SL, Bolotin S, Khan S, et al (2020). The effect of time since measles vaccination and age at first dose on measles vaccine effectiveness–A systematic review. Vaccine, 38(3):460-469.
24. Soleimanpour S, Hamedi Asl D, Tadayon K, et al (2014). Extensive genetic diversity among clinical isolates of Mycobacterium tuberculosis in central province of Iran. Tuberc Res Treat, 2014:195287.
25. Velayati AA, Farnia P, Mirsaeidi M, et al (2006). The most prevalent Mycobacterium tuberculosis superfamilies among Iranian and Afghan TB cases. Scand J Infect Dis, 38(6-7):463-8.
26. Ahmad WMTW, Ab Ghani NL, Drus SM (2019). Minimizing False Negatives of Measles Prediction Model: An Experimentation of Feature Selection Based On Domain Knowledge and Random Forest Classifier. International Journal of Engineering and Advanced Technology, 9:3411-3414.
27. Mizumoto K, Kobayashi T, Chowell G (2018). Transmission potential of modified measles during an outbreak, Japan, March‒May 2018. Eurosurveillance, 23(24): 1800239.
| Files | ||
| Issue | Vol 51 No 4 (2022) | |
| Section | Original Article(s) | |
| DOI | https://doi.org/10.18502/ijph.v51i4.9252 | |
| Keywords | ||
| Measles Machine learning Time series Infection | ||
| Rights and permissions | |
|
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
