Prediction of tuberculosis cases based on sociodemographic and environmental factors in gombak, Selangor, Malaysia: A comparative assessment of multiple linear regression and artificial neural network models.

Background: Early prediction of tuberculosis (TB) cases is very crucial for its prevention and control. This study aims to predict the number of TB cases in Gombak based on sociodemographic and environmental factors. Methods: The sociodemographic data of 3325 TB cases from January 2013 to December 2017 in Gombak district were collected from the MyTB web and TB Information System database. Environmental data were obtained from the Department of Environment, Malaysia; Department of Irrigation and Drainage, Malaysia; and Malaysian Metrological Department from July 2012 to December 2017. Multiple linear regression (MLR) and artificial neural network (ANN) were used to develop the prediction model of TB cases. The models that used sociodemographic variables as the input datasets were referred as MLR1 and ANN1, whereas environmental variables were represented as MLR2 and ANN2 and both sociodemographic and environmental variables together were indicated as MLR3 and ANN3. Results: The ANN was found to be superior to MLR with higher adjusted coefficient of determination (R2) values in predicting TB cases; the ranges were from 0.35 to 0.47 compared to 0.07 to 0.14, respectively. The best TB prediction model, that is, ANN3 was derived from nationality, residency, income status, CO, NO2, SO2, PM10, rainfall, temperature, and atmospheric pressure, with the highest adjusted R2 value of 0.47, errors below 6, and accuracies above 96%. Conclusions: It is envisaged that the application of the ANN algorithm based on both sociodemographic and environmental factors may enable a more accurate modeling for predicting TB cases.

Environment as the risk factor for tuberculosis in Malaysia: a systematic review of the literature.

OBJECTIVE: To investigate the prevalence and incidence of TB by focusing on its environmental risk factor in Malaysia. CONTENT: Databases search of Scopus, ScienceDirect, PubMed, Directory of Open Access Journals (DOAJ), Cumulative Index to Nursing and Allied Health Literature (CINAHL) Plus, MyJournal, Biblioteca Regional de Medicina (BIREME), BioMed Central (BMC) Public Health, Medline, Commonwealth Agricultural Bureaux (CAB), EMBASE (Excerpta Medica dataBASE) OVID, and Web of Science (WoS) was performed, which include the article from 1st January 2008 until 31st August 2018 using medical subject heading (MeSH). Articles initially identified were screened for relevance. SUMMARY: Out of 744 papers screened, nine eligible studies did meet our inclusion criteria. Prison and housing environments were evaluated for TB transmission in living environment, while the other factor was urbanization. However, not all association for these factors were statistically significant, thus assumed to be conflicting or weak to end up with a strong conclusion. OUTLOOK: Unsustainable indoor environment in high congregate setting and overcrowding remained as a challenge for TB infection in Malaysia. Risk factors for transmission of TB, specifically in high risk areas, should focus on the implementation of specialized program. Further research on health care environment, weather variability, and air pollution are urgently needed to improve the management of TB transmission.

Development of a web-geographical information system application for plotting tuberculosis cases.

In the last few decades, public health surveillance has increasingly applied statistical methods to analyze the spatial disease distributions. Nevertheless, contact tracing and follow up control measures for tuberculosis (TB) patients remain challenging because public health officers often lack the programming skills needed to utilize the software appropriately. This study aimed to develop a more user-friendly application by applying the CodeIgniter framework for server development, ArcGIS JavaScript for data display and a web application based on JavaScript and Hypertext Preprocessor to build the server's interface, while a webGIS technology was used for mapping. The performance of this approach was tested based on 3325 TB cases and their sociodemographic data, such as age, gender, race, nationality, country of origin, educational level, employment status, health care worker status, income status, residency status, and smoking status between 1st January 2013 and 31st December 2017 in Gombak, Selangor, Malaysia. These data were collected from the Gombak District Health Office and Rawang Health Clinic. Latitude and longitude of the location for each case was geocoded by uploading spatial data using Google Earth and the main output was an interactive map displaying location of each case. Filters are available for the selection of the various sociodemographic factors of interest. The application developed should assist public health experts to utilize spatial data for the surveillance purposes comprehensively as well as for the drafting of regulations aimed at to reducing mortality and morbidity and thus minimizing the public health impact of the disease.

Association of sociodemographic and environmental factors with spatial distribution of tuberculosis cases in Gombak, Selangor, Malaysia.

Tuberculosis (TB) cases have increased drastically over the last two decades and it remains as one of the deadliest infectious diseases in Malaysia. This cross-sectional study aimed to establish the spatial distribution of TB cases and its association with the sociodemographic and environmental factors in the Gombak district. The sociodemographic data of 3325 TB cases such as age, gender, race, nationality, country of origin, educational level, employment status, health care worker status, income status, residency, and smoking status from 1st January 2013 to 31st December 2017 in Gombak district were collected from the MyTB web and Tuberculosis Information System (TBIS) database at the Gombak District Health Office and Rawang Health Clinic. Environmental data consisting of air pollution such as air quality index (AQI), carbon monoxide (CO), nitrogen dioxide (NO2), sulphur dioxide (SO2), and particulate matter 10 (PM10,) were obtained from the Department of Environment Malaysia from 1st July 2012 to 31st December 2017; whereas weather data such as rainfall were obtained from the Department of Irrigation and Drainage Malaysia and relative humidity, temperature, wind speed, and atmospheric pressure were obtained from the Malaysia Meteorological Department in the same period. Global Moran's I, kernel density estimation, Getis-Ord Gi* statistics, and heat maps were applied to identify the spatial pattern of TB cases. Ordinary least squares (OLS) and geographically weighted regression (GWR) models were used to determine the spatial association of sociodemographic and environmental factors with the TB cases. Spatial autocorrelation analysis indicated that the cases was clustered (p<0.05) over the five-year period and year 2016 and 2017 while random pattern (p>0.05) was observed from year 2013 to 2015. Kernel density estimation identified the high-density regions while Getis-Ord Gi* statistics observed hotspot locations, whereby consistently located in the southwestern part of the study area. This could be attributed to the overcrowding of inmates in the Sungai Buloh prison located there. Sociodemographic factors such as gender, nationality, employment status, health care worker status, income status, residency, and smoking status as well as; environmental factors such as AQI (lag 1), CO (lag 2), NO2 (lag 2), SO2 (lag 1), PM10 (lag 5), rainfall (lag 2), relative humidity (lag 4), temperature (lag 2), wind speed (lag 4), and atmospheric pressure (lag 6) were associated with TB cases (p<0.05). The GWR model based on the environmental factors i.e. GWR2 was the best model to determine the spatial distribution of TB cases based on the highest R2 value i.e. 0.98. The maps of estimated local coefficients in GWR models confirmed that the effects of sociodemographic and environmental factors on TB cases spatially varied. This study highlighted the importance of spatial analysis to identify areas with a high TB burden based on its associated factors, which further helps in improving targeted surveillance.

Demographic, socio-economic and behavior as risk factors of tuberculosis in Malaysia: a systematic review of the literature.

Background Tuberculosis (TB) is making a comeback and has remained one of the main causes of mortality among the list of infectious diseases in Malaysia. Objective To evaluate the burden and demographic, socio-economic and behavior as risk factors of TB among communities in Malaysia. Method A comprehensive search of Scopus, Sciencedirect, PubMed, DOAJ, CINAHL Plus, MyJournal, BIREME, BMC Public Health, Medline, CAB, EMBASE (Excerpta Medica dataBASE), and Web of Science (WoS) was undertaken from the articles published from 1st January 2008 to 31st December 2017 using medical subject heading (MeSH) key terms. Results Of 717 papers screened, 31 eligible studies met our inclusion criteria. Gender, age, marriage status, ethnicity, area of living, being in prison and immigrant were evaluated as demographic factors, while educational level, occupation and household income were evaluated as socio-economic factors. For behavioral factors, smoking, drug abuse, alcohol consumption and other lifestyle practices were evaluated. However, not all the studies were statistically significantly associated with these risk factors. Studies on household income were few and too small to permit a conclusion. We also did not find any study that investigated TB infection among sex workers. Conclusion Immigrant in high density settings may increase the progression of disease infection in Malaysia. The risk factors for the development of TB, specifically in a high-risk population, should be targeted through the implementation of specialized interventions. Further research into the role of indoor and outdoor physical environments is required to better understand the association between the physical environment and the social environment with TB infection.