- A Comparison of Green, Delta, and Monte Carlo Methods to Select an Optimal Approach for Calculating the 95% Confidence Interval of the Population-attributable Fraction: Guidance for Epidemiological Research
-
Sangjun Lee, Sungji Moon, Kyungsik Kim, Soseul Sung, Youjin Hong, Woojin Lim, Sue K. Park
-
J Prev Med Public Health. 2024;57(5):499-507. Published online September 6, 2024
-
DOI: https://doi.org/10.3961/jpmph.24.272
-
-
Abstract
Summary
PDFSupplementary Material
- Objectives
This study aimed to compare the Delta, Greenland, and Monte Carlo methods for estimating 95% confidence intervals (CIs) of the population-attributable fraction (PAF). The objectives were to identify the optimal method and to determine the influence of primary parameters on PAF calculations.
Methods A dataset was simulated using hypothetical values for primary parameters (population, relative risk [RR], prevalence, and variance of the beta estimator ) involved in PAF calculations. Three methods (Delta, Greenland, and Monte Carlo) were used to estimate the 95% CIs of the PAFs. Perturbation analysis was performed to assess the sensitivity of the PAF to changes in these parameters. An R Shiny application, the “GDM-PAF CI Explorer,” was developed to facilitate the analysis and visualization of these computations.
Results No significant differences were observed among the 3 methods when both the RR and p-value were low. The Delta method performed well under conditions of low prevalence or minimal RR, while Greenland’s method was effective in scenarios with high prevalence. Meanwhile, the Monte Carlo method calculated 95% CIs of PAFs that were stable overall, though it required intensive computational resources. In a novel approach that utilized perturbation for sensitivity analysis, was identified as the most influential parameter in the estimation of CIs.
Conclusions This study emphasizes the necessity of a careful approach for comparing 95% CI estimation methods for PAFs and selecting the method that best suits the context. It provides practical guidelines to researchers to increase the reliability and accuracy of epidemiological studies.
-
Summary
Korean summary
본 연구는 인구 기여 분율(PAF)의 95% 신뢰구간을 추정하는 데 있어 Delta, Greenland, Monte Carlo 방법을 비교하여 최적의 방법을 찾고, 주요 매개변수의 변화가 PAF 계산에 미치는 영향을 분석했음. Delta 방법은 상대적으로 낮은 유병률이나 위험도(RR)가 낮을 때 적합하며, Greenland 방법은 높은 유병률에서 효과적이고, Monte Carlo 방법은 전반적으로 안정적인 결과를 제공하지만, 많은 계산 자원이 필요할 수 있음.
Key Message
This study compared Delta, Greenland, and Monte Carlo methods for calculating the 95% confidence intervals (CIs) of population-attributable fractions (PAFs). While all three methods demonstrated comparable performance under conditions of low prevalence or relative risk (RR), they diverged under other scenarios. The Delta method is effective for low-prevalence or minimal RR, Greenland for high-prevalence scenarios, and Monte Carlo is robust but computationally intensive. This research offers practical guidance for selecting the appropriate method based on study conditions, enhancing the reliability of epidemiological studies in estimating PAFs.
- Projection of Cancer Incidence and Mortality From 2020 to 2035 in the Korean Population Aged 20 Years and Older
-
Youjin Hong, Sangjun Lee, Sungji Moon, Soseul Sung, Woojin Lim, Kyungsik Kim, Seokyung An, Jeoungbin Choi, Kwang-Pil Ko, Inah Kim, Jung Eun Lee, Sue K. Park
-
J Prev Med Public Health. 2022;55(6):529-538. Published online October 17, 2022
-
DOI: https://doi.org/10.3961/jpmph.22.128
-
-
4,223
View
-
214
Download
-
2
Crossref
-
Abstract
Summary
PDFSupplementary Material
- Objectives
This study aimed to identify the current patterns of cancer incidence and estimate the projected cancer incidence and mortality between 2020 and 2035 in Korea.
Methods Data on cancer incidence cases were extracted from the Korean Statistical Information Service from 2000 to 2017, and data on cancer-related deaths were extracted from the National Cancer Center from 2000 to 2018. Cancer cases and deaths were classified according to the International Classification of Diseases, 10th edition. For the current patterns of cancer incidence, age-standardized incidence rates (ASIRs) and age-standardized mortality rates were investigated using the 2000 mid-year estimated population aged over 20 years and older. A joinpoint regression model was used to determine the 2020 to 2035 trends in cancer.
Results Overall, cancer cases were predicted to increase from 265 299 in 2020 to 474 085 in 2035 (growth rate: 1.8%). The greatest increase in the ASIR was projected for prostate cancer among male (7.84 vs. 189.53 per 100 000 people) and breast cancer among female (34.17 vs. 238.45 per 100 000 people) from 2000 to 2035. Overall cancer deaths were projected to increase from 81 717 in 2020 to 95 845 in 2035 (average annual growth rate: 1.2%). Although most cancer mortality rates were projected to decrease, those of breast, pancreatic, and ovarian cancer among female were projected to increase until 2035.
Conclusions These up-to-date projections of cancer incidence and mortality in the Korean population may be a significant resource for implementing cancer-related regulations or developing cancer treatments.
-
Summary
Korean summary
최근 고령화 시대로 접어들고 암의 위험요인들에 대한 노출률이 변화함에 따라 암의 발생률 및 사망률에 대해서 관찰하는 것은 중요한 일이 되었다. 따라서, 본 연구는 한국인에서 2035년까지의 암에 대한 발생률과 사망률을 Joinpoint regression 모델을 이용하여 예측하였다. 남성에서는 전립선암, 여성에서는 유방암이 연령표준화 발생률이 가장 높았으며 대부분의 연령표준화 사망률은 감소하는 것으로 예상되지만 여성의 유방암, 췌장암, 난소암이 증가될 것으로 예상된다.
-
Citations
Citations to this article as recorded by
- A Comparison of Green, Delta, and Monte Carlo Methods to Select an Optimal Approach for Calculating the 95% Confidence Interval of the Population-attributable Fraction: Guidance for Epidemiological Research
Sangjun Lee, Sungji Moon, Kyungsik Kim, Soseul Sung, Youjin Hong, Woojin Lim, Sue K. Park Journal of Preventive Medicine and Public Health.2024; 57(5): 499. CrossRef - Changes in metabolic syndrome and the risk of breast and endometrial cancer according to menopause in Korean women
Thi Xuan Mai Tran, Soyeoun Kim, Boyoung Park Epidemiology and Health.2023; 45: e2023049. CrossRef
|