The classification and epidemic data visualization analysis of Leptospirosis cases from tropical cyclones in Thailand

Name: Janya Uppamai

Organization : Mahidol University. Faculty of Public Health

Name: Prasong Kitidamrongsuk

Organization : Mahidol University. Faculty of Public Health

Email : prasong.kit@mahidol.ac.th

Name: Chukiat Viwatwongkasem

Organization : Mahidol University. Faculty of Public Health

Name: Pichitpong Soontornpipit

Organization : Mahidol University. Faculty of Public Health

ThaSH: Image analysis

ThaSH: Cyclones -- Tropics

ThaSH: Leptospirosis

ThaSH: Decision trees

ThaSH: Remote sensing

Abstract: Flood events in Thailand has been recorded based on the size of Tropical Cyclones (TCs), but did not focus on leptospirosis outbreak from TCs. The objective is to describe the epidemic data visualization situation of leptospirosis in humans that depends on many factors including gender, age, career and so on. Moreover, was to determine the prevalence of leptospirosis cases from TCs hit in Thailand that occur from 2015 to 2020. Classification And Regression Tree (CART) algorithm of Decision Tree approach was used to analyzed leptospirosis cases from TCs hit. From the past, Thailand had 13 experiences of TCs hits. This study divided TCs in Thailand into 5 groups (Group1: one Depression, Group2: one Tropical Storm, Group3: double Depression, Group4: combine group1 and group3, Groups 5: combine group1, group2 and group3). The TCs studied was conducted in 59 provinces from 4 regions consist of Northern, Central, Northeastern, and Southern. The results found that leptospirosis from TCs was predominantly reported among farmer (59 percent), male (82 percent) with a median age of 48 years (IQR = 36-58). The ages group (45-60 years) was most impacted in both genders. The highest prevalence of leptospirosis from TCs was founded in provinces of Northeastern region that was attacked by TCs group 5. The prevalence rate was peak in 2017 (39 percent of all leptospirosis cases). The classification of leptospirosis cases must have a period of 1 month apart from each group of storms. From CART algorithm of classification tree achieved very high accuracy (95.07 percent) in classifying leptospirosis cases from TCs, it has a sensitivity of 99.42 percent and a specificity of 93.47 percent. The rules of classification have 10 rules; windspeed is associated with the majority of the TCs's leptospirosis dataset and represents all observations.

King Mongkut's University of Technology North Bangkok. Central Library

Address: BANGKOK

Email: library@kmutnb.ac.th

Created: 2022

Modified: 2025-09-16

Issued: 2025-09-16

บทความ/Article

application/pdf

BibliograpyCitation : In King Mongkut's University of Technology North Bangkok Faculty of Applied Science, Thai Statistical Association (TSA) and Statistics Cooperative Research Network (Statistics CRN). The Proceeding of International Conference on Applied Statistics (ICAS 2022) (pp.193-199). Bangkok : King Mongkut's University of Technology North Bangkok

eng

©copyrights King Mongkut's University of Technology North Bangkok

ลำดับที่.	ชื่อแฟ้มข้อมูล	ขนาดแฟ้มข้อมูล	จำนวนเข้าถึง	วัน-เวลาเข้าถึงล่าสุด
1	ICAS 2022pp.193-199.pdf	1.22 MB	14	2026-05-26 18:16:01

ใช้เวลา

0.054489 วินาที