1
|
Kalayou MH, Kassaw AAK, Shiferaw KB. Empowering child health: Harnessing machine learning to predict acute respiratory infections in Ethiopian under-fives using demographic and health survey insights. BMC Infect Dis 2024; 24:338. [PMID: 38515014 PMCID: PMC10956296 DOI: 10.1186/s12879-024-09195-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/25/2023] [Accepted: 03/05/2024] [Indexed: 03/23/2024] Open
Abstract
BACKGROUND A dearth of studies showed that infectious diseases cause the majority of deaths among under-five children. Worldwide, Acute Respiratory Infection (ARI) continues to be the second most frequent cause of illness and mortality among children under the age of five. The paramount disease burden in developing nations, including Ethiopia, is still ARI. OBJECTIVE This study aims to determine the magnitude and predictors of ARI among under-five children in Ethiopia using used state of the art machine learning algorithms. METHODS Data for this study were derived from the 2016 Ethiopian Demographic and Health Survey. To predict the determinants of acute respiratory infections, we performed several experiments on ten machine learning algorithms (random forests, decision trees, support vector machines, Naïve Bayes, and K-nearest neighbors, Lasso regression, GBoost, XGboost), including one classic logistic regression model and an ensemble of the best performing models. The prediction ability of each machine-learning model was assessed using receiver operating characteristic curves, precision-recall curves, and classification metrics. RESULTS The total ARI prevalence rate among 9501 under-five children in Ethiopia was 7.2%, according to the findings of the study. The overall performance of the ensemble model of SVM, GBoost, and XGBoost showed an improved performance in classifying ARI cases with an accuracy of 86%, a sensitivity of 84.6%, and an AUC-ROC of 0.87. The highest performing predictive model (the ensemble model) showed that the child's age, history of diarrhea, wealth index, type of toilet, mother's educational level, number of living children, mother's occupation, and type of fuel they used were an important predicting factor for acute respiratory infection among under-five children. CONCLUSION The intricate web of factors contributing to ARI among under-five children was identified using an advanced machine learning algorithm. The child's age, history of diarrhea, wealth index, and type of toilet were among the top factors identified using the ensemble model that registered a performance of 86% accuracy. This study stands as a testament to the potential of advanced data-driven methodologies in unraveling the complexities of ARI in low-income settings.
Collapse
Affiliation(s)
- Mulugeta Hayelom Kalayou
- Department of Health Informatics, School of Public Health, College of Medicine and Health Sciences, Wollo University, Dessie, Ethiopia.
| | - Abdul-Aziz Kebede Kassaw
- Department of Health Informatics, School of Public Health, College of Medicine and Health Sciences, Wollo University, Dessie, Ethiopia
| | - Kirubel Biruk Shiferaw
- Department of Medical Informatics, Institute for Community Medicine, University Medicine Greifswald, Greifswald, Germany
| |
Collapse
|
2
|
Zhang X, Zhu X, Wang X, Wang L, Sun H, Yuan P, Ji Y. Association of Exposure to Biomass Fuels with Occurrence of Chronic Obstructive Pulmonary Disease in Rural Western China: A Real-World Nested Case-Control Study. Int J Chron Obstruct Pulmon Dis 2023; 18:2207-2224. [PMID: 37841748 PMCID: PMC10572384 DOI: 10.2147/copd.s417600] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/17/2023] [Accepted: 09/17/2023] [Indexed: 10/17/2023] Open
Abstract
Background This study investigated the potential contribution of biomass fuels exposure to the occurrence of chronic obstructive pulmonary disease (COPD) in rural areas of western China. Methods We analyzed data collected between October 2017 and October 2018 from a nested case-control study of individuals at least 40 years old in the general population in Mianyang City, Sichuan Province, China. Demographic information was collected using a custom-designed questionnaire, and lung function was measured using spirometry. We used multivariate logistic regression to explore the possible relationship between biomass fuels exposure and COPD, as well as between other potential risk factors and COPD. Bayes' theorem was used to estimate weights for different COPD risk factors. Results COPD was newly diagnosed in 500 of the 11398 adults surveyed, corresponding to an incidence of 4.39%. Individuals who were exposed to biomass fuels were at a significantly greater risk of developing COPD than those not exposed (OR 2.58, 95% CI 2.23-3.05). In subgroup analysis, exposure to biomass fuels increased the risk of COPD in men by 1.71 times (95% CI 1.09-2.68) and in women by 2.88 times (95% CI 2.01-3.48), in never-smokers by 2.18 times. Bayesian weights for COPD risk factors were highest for poor kitchen ventilation (W=31.13%) and biomass fuels exposure (W=18.08%). Conclusion Our data indicate that rural Chinese who are exposed to biomass fuels during cooking or heating are at greater risk of developing COPD. Efforts should be made to strengthen the construction of clean energy infrastructure, so as to reduce the use of biomass fuels and thereby help prevent COPD.
Collapse
Affiliation(s)
- Xuan Zhang
- Department of Respiratory and Critical Care Medicine, Clinical Research Center for Respiratory Disease, West China Hospital, Sichuan University, Chengdu, Sichuan Province, 610041, People’s Republic of China
| | - Xia Zhu
- Center of Infectious Disease, West China Hospital, Sichuan University, Chengdu, Sichuan Province, 610041, People’s Republic of China
| | - Xiaoli Wang
- Department of Infectious disease Prevention and Control, Center for Disease Control and Prevention of Fucheng, Mianyang, Sichuan Province, 621000, People’s Republic of China
| | - Liping Wang
- Department of Disease Control, Health Bureau of Jiangyou, Jiangyou, Sichuan Province, 621700, People’s Republic of China
| | - Hongying Sun
- Department of Tuberculosis Prevention and Control, Center for Disease Control and Prevention of Mianyang, Mianyang, Sichuan Province, 621000, People’s Republic of China
| | - Ping Yuan
- Department of Epidemiology and Statistics, West China School of Public Health, Sichuan University, Chengdu, Sichuan Province, 610041, People’s Republic of China
| | - Yulin Ji
- Department of Respiratory and Critical Care Medicine, Clinical Research Center for Respiratory Disease, West China Hospital, Sichuan University, Chengdu, Sichuan Province, 610041, People’s Republic of China
| |
Collapse
|
3
|
Tesfaye SH, Seboka BT, Sisay D. Spatial patterns and spatially-varying factors associated with childhood acute respiratory infection: data from Ethiopian demographic and health surveys (2005, 2011, and 2016). BMC Infect Dis 2023; 23:293. [PMID: 37147575 PMCID: PMC10163815 DOI: 10.1186/s12879-023-08273-1] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/23/2022] [Accepted: 04/22/2023] [Indexed: 05/07/2023] Open
Abstract
BACKGROUND In Ethiopia, acute respiratory infections (ARIs) are a leading cause of morbidity and mortality among children under five years. Geographically linked data analysis using nationally representative data is crucial to map spatial patterns of ARIs and identify spatially-varying factors of ARI. Therefore, this study aimed to investigate spatial patterns and spatially-varying factors of ARI in Ethiopia. METHODS Secondary data from the Ethiopian Demographic Health Survey (EDHS) of 2005, 2011, and 2016 were used. Kuldorff's spatial scan statistic using the Bernoulli model was used to identify spatial clusters with high or low ARI. Hot spot analysis was conducted using Getis-OrdGi statistics. Eigenvector spatial filtering regression model was carried out to identify spatial predictors of ARI. RESULTS Acute respiratory infection spatially clustered in 2011 and 2016 surveys year (Moran's I:-0.011621-0.334486). The magnitude of ARI decreased from 12.6% (95%, CI: 0.113-0.138) in 2005 to 6.6% (95% CI: 0.055-0.077) in 2016. Across the three surveys, clusters with a high prevalence of ARI were observed in the North part of Ethiopia. The spatial regression analysis revealed that the spatial patterns of ARI was significantly associated with using biomass fuel for cooking and children not initiating breastfeeding within 1-hour of birth. This correlation is strong in the Northern and some areas in the Western part of the country. CONCLUSION Overall there has been a considerable decrease in ARI, but this decline in ARI varied in some regions and districts between surveys. Biomass fuel and early initiation of breastfeeding were independent predictors of ARI. There is a need to prioritize children living in regions and districts with high ARI.
Collapse
Affiliation(s)
| | - Binyam Tariku Seboka
- School of Public Health, college of health sciences and medicine, Dilla University, Dilla, Ethiopia
| | - Daniel Sisay
- School of Public Health, college of health sciences and medicine, Dilla University, Dilla, Ethiopia
| |
Collapse
|
4
|
Ekholuenetale M, Nzoputam CI, Okonji OC, Barrow A, Wegbom AI, Edet CK. Differentials in the Prevalence of Acute Respiratory Infections Among Under-Five Children: An Analysis of 37 Sub-Saharan Countries. Glob Pediatr Health 2023; 10:2333794X231156715. [PMID: 36814530 PMCID: PMC9940173 DOI: 10.1177/2333794x231156715] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/16/2022] [Accepted: 01/26/2023] [Indexed: 02/19/2023] Open
Abstract
Objective We investigated the prevalence and risk factors of ARI in children under 5 years old in 37 SSA countries. Methods Data from Demographic and Health Survey (DHS) of 37 African countries was examined in this analysis. Data from children under the age of 5 years old were examined. Forest plot was used to identify disparities in the occurrence of ARIs across SSA countries. Results We observed a higher prevalence of ARI among children under 5 in Uganda, Kenya, Sao Tome and Principe (9% each), Gabon, Chad, Eswatini (8% each), Burundi, Ethiopia, Congo Democratic Republic (7.0% each). The prevalence of ARI among under-five children who sought medical advice/treatment from health facility was higher in South Africa (88%), Sierra Leone (86%), Tanzanian (85%), Guinea (83%) and Uganda (80%). The prevalence rate of ARI among under-five children who received antibiotics was higher in Tanzania (61%), Sao Tome and Principe (60%), Rwanda and Congo (58% each), Angola (56.0%), Mozambique (54.0%), Kenya (53.0%), Namibia (52.0%) and Gabon (50.0%). This study found that the household wealth index, maternal education, and urban residence were significantly associated with ARI (p <0.001). A higher prevalence of ARI was observed among urban residents, low income families, and those with mothers with lower education. Conclusion ARI prevalence could be reduced by improving household socioeconomic status, child nutrition and community awareness of indoor and outdoor pollution. Interventions and programs focused on early diagnosis, treatment and prevention of ARIs are crucial in reducing ARIs particularly in developing countries.
Collapse
Affiliation(s)
| | | | | | - Amadou Barrow
- University of The Gambia, Kanifing, The Gambia,Amadou Barrow, University of the Gambia, Kanifing, P.O Box 3530, Serrekunda, The Gambia.
| | | | | |
Collapse
|
5
|
Islam MA, Hasan MN, Ahammed T, Anjum A, Majumder A, Siddiqui MNEA, Mukharjee SK, Sultana KF, Sultana S, Jakariya M, Bhattacharya P, Sarkodie SA, Dhama K, Mumin J, Ahmed F. Association of household fuel with acute respiratory infection (ARI) under-five years children in Bangladesh. Front Public Health 2022; 10:985445. [PMID: 36530721 PMCID: PMC9752885 DOI: 10.3389/fpubh.2022.985445] [Citation(s) in RCA: 9] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/04/2022] [Accepted: 10/17/2022] [Indexed: 12/04/2022] Open
Abstract
In developing countries, acute respiratory infections (ARIs) cause a significant number of deaths among children. According to Bangladesh Demographic and Health Survey (BDHS), about 25% of the deaths in children under-five years are caused by ARI in Bangladesh every year. Low-income families frequently rely on wood, coal, and animal excrement for cooking. However, it is unclear whether using alternative fuels offers a health benefit over solid fuels. To clear this doubt, we conducted a study to investigate the effects of fuel usage on ARI in children. In this study, we used the latest BDHS 2017-18 survey data collected by the Government of Bangladesh (GoB) and estimated the effects of fuel use on ARI by constructing multivariable logistic regression models. From the analysis, we found that the crude (the only type of fuel in the model) odds ratio (OR) for ARI is 1.69 [95% confidence interval (CI): 1.06-2.71]. This suggests that children in families using contaminated fuels are 69.3% more likely to experience an ARI episode than children in households using clean fuels. After adjusting for cooking fuel, type of roof material, child's age (months), and sex of the child-the effect of solid fuels is similar to the adjusted odds ratio (AOR) for ARI (OR: 1.69, 95% CI: 1.05-2.72). This implies that an ARI occurrence is 69.2% more likely when compared to the effect of clean fuel. This study found a statistically significant association between solid fuel consumption and the occurrence of ARI in children in households. The correlation between indoor air pollution and clinical parameters of ARI requires further investigation. Our findings will also help other researchers and policymakers to take comprehensive actions by considering fuel type as a risk factor as well as taking proper steps to solve this issue.
Collapse
Affiliation(s)
- Md. Aminul Islam
- COVID-19 Diagnostic Lab, Department of Microbiology, Noakhali Science and Technology University, Noakhali, Bangladesh
- Advanced Molecular Lab, Department of Microbiology, President Abdul Hamid Medical College, Karimganj, Bangladesh
| | - Mohammad Nayeem Hasan
- Department of Statistics, Shahjalal University of Science and Technology, Sylhet, Bangladesh
- Joint Rohingya Response Program, Food for the Hungry, Cox's Bazar, Bangladesh
| | - Tanvir Ahammed
- Department of Statistics, Shahjalal University of Science and Technology, Sylhet, Bangladesh
| | - Aniqua Anjum
- Department of Statistics, Shahjalal University of Science and Technology, Sylhet, Bangladesh
| | - Ananya Majumder
- Department of Applied Chemistry and Chemical Engineering, Noakhali Science and Technology University, Noakhali, Bangladesh
| | - M. Noor-E-Alam Siddiqui
- Department of Statistics, Shahjalal University of Science and Technology, Sylhet, Bangladesh
| | - Sanjoy Kumar Mukharjee
- COVID-19 Diagnostic Lab, Department of Microbiology, Noakhali Science and Technology University, Noakhali, Bangladesh
| | - Khandokar Fahmida Sultana
- COVID-19 Diagnostic Lab, Department of Microbiology, Noakhali Science and Technology University, Noakhali, Bangladesh
| | - Sabrin Sultana
- Department of Banking and Insurance, University of Chittagong, Chittagong, Bangladesh
| | - Md. Jakariya
- Department of Environmental Science and Management, North South University, Bashundhara, Dhaka, Bangladesh
| | - Prosun Bhattacharya
- COVID-19 Research, Department of Sustainable Development, Environmental Science and Engineering, KTH Royal Institute of Technology, Stockholm, Sweden
| | | | - Kuldeep Dhama
- Division of Pathology, ICAR-Indian Veterinary Research Institute, Bareilly, Uttar Pradesh, India
| | - Jubayer Mumin
- Platform of Medical and Dental Society, Dhaka, Bangladesh
| | - Firoz Ahmed
- COVID-19 Diagnostic Lab, Department of Microbiology, Noakhali Science and Technology University, Noakhali, Bangladesh
| |
Collapse
|
6
|
Association between the Use of Biomass as Fuel for Cooking and Acute Respiratory Infections in Children under 5 Years of Age in Peru: An Analysis of a Population-Based Survey, 2019. JOURNAL OF ENVIRONMENTAL AND PUBLIC HEALTH 2022; 2022:4334794. [PMID: 35646128 PMCID: PMC9142288 DOI: 10.1155/2022/4334794] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/01/2022] [Revised: 04/08/2022] [Accepted: 05/03/2022] [Indexed: 11/21/2022]
Abstract
Background Acute respiratory infections (ARIs) are the most frequent respiratory diseases associated with the use of biomass as fuel within the home. ARIs are the main cause of mortality in children under 5 years of age. We aimed to evaluate the association between the use of biomass as cooking fuel and ARI in children under 5 years of age in Peru in 2019. Methods A secondary data analysis of the 2019 Peru Demographic and Family Health Survey (ENDES) has been performed. The outcome variable was a history of ARI. The exposure variable was the use of biomass as fuel for cooking food. To evaluate the association of interest, generalized linear models from the Poisson family with logarithmic link function considering complex sampling to estimate crude prevalence ratio (cPR) and adjusted prevalence ratio (aPR) with their respective 95% confidence intervals have been performed. P values <0.05 were considered statistically significant. Results A total of 16,043 children were included in the analysis. Of the total, biomass was used as fuel to cook food in the homes of 3,479 (20.0%) children. Likewise, 2,185 (14.3%) of the children had a history of ARI. In the adjusted model, it was found that children living in homes in which biomass was used as cooking fuel had a greater probability of presenting ARI (aPR = 1.13; 95% CI: 1.01–1.28). Conclusions It has been found that biomass was used to cook food in two of every 10 households. Likewise, almost one-seventh of children under 5 years old presented an ARI. The use of biomass as a source of energy for cooking in the home was associated with a higher probability of presenting ARIs.
Collapse
|
7
|
Abayneh M, Muleta D, Simieneh A, Duguma T, Asnake M, Teressa M, Endalkachew B, Toru M. Acute respiratory infections (ARIs) and factors associated with their poor clinical outcome among children under-five years attending pediatric wards of public hospital in Southwest district of Ethiopia: A prospective observational cohort study. EUR J INFLAMM 2022. [DOI: 10.1177/1721727x221139266] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/11/2022] Open
Abstract
This study was designed to assess the prevalence and factors associated with poor clinical outcome of acute respiratory infections (ARIs) among children less than five years of age at Mizan-Tepi university teaching public hospital in southwest district of Ethiopia. A prospective observational cohort study design was conducted from 01 June to August 30, 2020. Data related to socio-demographics, child nutritional status, clinical and environmental characteristics of patients were collected with structured questionnaire. Follow-up data were gathered from patient’s medical records using standard data collection tool. The data were analyzed using SPSS versions 25.0. In this study, 305 children of age less than five years were included. Of these, 124 (40.7%) of children were diagnosed with ARIs, of which 66 (53.2%) were female and 69 (55.6%) were age of 24–59 months. Of children diagnosed with ARIs, 21 (16.9%) were ended with poor clinical outcomes after completion of their treatment. In the multivariate analysis, age of children and presence of any other disease conditions (OR = 0.331; 95% CI: 0.123– 0.880; p= 0.024), exposure to indoor air pollution (OR = 0.344; 95% CI: 0.128– 0.925; p= 0.030), malnutrition (OR = 0.175; 95% CI: 0.058– 0.523; p= 0.002) and end point pneumonia (OR = 0.305; 95% CI: 0.113–0.821; p= 0.015) were found to be independent factors for poor outcome of under-five children with ARIs. Our findings highlight that timely detection, proper management and treatments as well as addressing other contributing factors are essentials in order to reduce prevalence and poor clinical outcomes of under five children with ARIs.
Collapse
Affiliation(s)
- Mengistu Abayneh
- College of Medicine and Health Science, Department of Medical Laboratory Sciences, Mizan-Tepi University, Mizan-Aman, Ethiopia
| | - Dassaleng Muleta
- College of Medicine and Health Science, Department of Medical Laboratory Sciences, Mizan-Tepi University, Mizan-Aman, Ethiopia
| | - Asnake Simieneh
- College of Medicine and Health Science, Department of Medical Laboratory Sciences, Mizan-Tepi University, Mizan-Aman, Ethiopia
| | - Tadesse Duguma
- College of Medicine and Health Science, Department of Medical Laboratory Sciences, Mizan-Tepi University, Mizan-Aman, Ethiopia
| | - Molla Asnake
- College of Medicine and Health Science, Department of Medicine, Mizan-Tepi University, Mizan-Aman, Ethiopia
| | - Murtii Teressa
- College of Medicine and Health Science, Department of Medicine, Mizan-Tepi University, Mizan-Aman, Ethiopia
| | - Biruk Endalkachew
- College of Medicine and Health Science, Department of Biomedical Science, Mizan-Tepi University, Mizan-Aman, Ethiopia
| | - Milkiyas Toru
- College of Health Science, Department of Medical Laboratory Sciences, Debre Markos University, Debre Marqos, Ethiopia
| |
Collapse
|