1
|
Lv Y, Su H, Li R, Yang Z, Chen Q, Zhang D, Liang S, Hu C, Ni X. A cross-sectional study of the major risk factor at different levels of cognitive performance within Chinese-origin middle-aged and elderly individuals. J Affect Disord 2024; 349:377-383. [PMID: 38199420 DOI: 10.1016/j.jad.2024.01.069] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/12/2023] [Revised: 12/20/2023] [Accepted: 01/04/2024] [Indexed: 01/12/2024]
Abstract
OBJECTIVE Senior citizens suffering from cognitive impairment (CI) are on the East Asia rise. Multiple variables could lead to inter-/intra-individual cognition effectiveness variations, though previous research efforts did not consider weighting issues. METHODS This study scrutinized 5639 participants meeting required inclusion criteria by the CHARLS. Cognitive capacity was evaluated through Mini-Mental State Examination (MMSE). Considering that MMSE scorings were not following normal distribution, a non-parametric test and multiple linear regression were performed to screen candidate variables linked to cognitive capacity. Such applicability of candidate factors in the cumulative effect and the weighting of the impact on cognitive performance were evaluated by random forest (RF) algorithm. RESULTS Age, gender, education, marital status, residence, the type of residence, exercise, socialization level and drinking were correlated to MMSE scorings (p < 0.05). Among them, age, education, gender and sociality were correlated to individual MMSE items (p < 0.05). Regardless of MMSE scores and several MMSE items, age is always a prime factor. However, in the attention and computation item, education is better than age and ranks first. CONCLUSIONS This preliminary study prompted age, education, gender, and sociality with varying weightings to be linked to cognitive capacity within a Chinese cohort by differing cognitive aspects. At different levels of cognitive performance, the main risk factors are basically similar, but there are still some differences.
Collapse
Affiliation(s)
- Yuan Lv
- Jiangbin Hospital of Guangxi Zhuang Autonomous Region, 530021, PR China
| | - Huabin Su
- Jiangbin Hospital of Guangxi Zhuang Autonomous Region, 530021, PR China
| | - Rongqiao Li
- Jiangbin Hospital of Guangxi Zhuang Autonomous Region, 530021, PR China
| | - Ze Yang
- The Key Laboratory of Geriatrics, Beijing Institute of Geriatrics, Institute of Geriatric Medicine, Chinese Academy of Medical Sciences, Beijing Hospital/National Center of Gerontology of National Health Commission, 100730, PR China
| | - Qing Chen
- Jiangbin Hospital of Guangxi Zhuang Autonomous Region, 530021, PR China
| | - Di Zhang
- Jiangbin Hospital of Guangxi Zhuang Autonomous Region, 530021, PR China
| | - Shuolin Liang
- Jiangbin Hospital of Guangxi Zhuang Autonomous Region, 530021, PR China
| | - Caiyou Hu
- Jiangbin Hospital of Guangxi Zhuang Autonomous Region, 530021, PR China
| | - Xiaolin Ni
- Department of Biomedical Engineering, Institute of Basic Medical Sciences, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100005, PR China.
| |
Collapse
|
2
|
Muehlensiepen F, Petit P, Knitza J, Welcker M, Vuillerme N. Prediction of the acceptance of telemedicine among rheumatic patients: a machine learning-powered secondary analysis of German survey data. Rheumatol Int 2024; 44:523-534. [PMID: 38206379 PMCID: PMC10866795 DOI: 10.1007/s00296-023-05518-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/24/2023] [Accepted: 12/06/2023] [Indexed: 01/12/2024]
Abstract
Telemedicine (TM) has augmented healthcare by enabling remote consultations, diagnosis, treatment, and monitoring of patients, thereby improving healthcare access and patient outcomes. However, successful adoption of TM depends on user acceptance, which is influenced by technical, socioeconomic, and health-related factors. Leveraging machine learning (ML) to accurately predict these adoption factors can greatly contribute to the effective utilization of TM in healthcare. The objective of the study was to compare 12 ML algorithms for predicting willingness to use TM (TM try) among patients with rheumatic and musculoskeletal diseases (RMDs) and identify key contributing features. We conducted a secondary analysis of RMD patient data from a German nationwide cross-sectional survey. Twelve ML algorithms, including logistic regression, random forest, extreme gradient boosting (XGBoost), and neural network (deep learning) were tested on a subset of the dataset, with the inclusion of only RMD patients who answered "yes" or "no" to TM try. Nested cross-validation was used for each model. The best-performing model was selected based on area under the receiver operator characteristic (AUROC). For the best-performing model, a multinomial/multiclass ML approach was undertaken with the consideration of the three following classes: "yes", "no", "do not know/not answered". Both one-vs-one and one-vs-rest strategies were considered. The feature importance was investigated using Shapley additive explanation (SHAP). A total of 438 RMD patients were included, with 26.5% of them willing to try TM, 40.6% not willing, and 32.9% undecided (missing answer or "do not know answer"). This dataset was used to train and test ML models. The mean accuracy of the 12 ML models ranged from 0.69 to 0.83, while the mean AUROC ranged from 0.79 to 0.90. The XGBoost model produced better results compared with the other models, with a sensitivity of 70%, specificity of 91% and positive predictive value of 84%. The most important predictors of TM try were the possibility that TM services were offered by a rheumatologist, prior TM knowledge, age, self-reported health status, Internet access at home and type of RMD diseases. For instance, for the yes vs. no classification, not wishing that TM services were offered by a rheumatologist, self-reporting a bad health status and being aged 60-69 years directed the model toward not wanting to try TM. By contrast, having Internet access at home and wishing that TM services were offered by a rheumatologist directed toward TM try. Our findings have significant implications for primary care, in particular for healthcare professionals aiming to implement TM effectively in their clinical routine. By understanding the key factors influencing patients' acceptance of TM, such as their expressed desire for TM services provided by a rheumatologist, self-reported health status, availability of home Internet access, and age, healthcare professionals can tailor their strategies to maximize the adoption and utilization of TM, ultimately improving healthcare outcomes for RMD patients. Our findings are of high interest for both clinical and medical teaching practice to fit changing health needs caused by the growing number of complex and chronically ill patients.
Collapse
Affiliation(s)
- Felix Muehlensiepen
- Univ. Grenoble Alpes, AGEIS, 38000, Grenoble, France.
- Faculty of Health Sciences Brandenburg, Center for Health Services Research, Brandenburg Medical School Theodor Fontane, Seebad 82/83, 15562, Rüdersdorf bei Berlin, Germany.
| | - Pascal Petit
- Univ. Grenoble Alpes, AGEIS, 38000, Grenoble, France
| | - Johannes Knitza
- Univ. Grenoble Alpes, AGEIS, 38000, Grenoble, France
- Institute for Digital Medicine, University Hospital of Giessen and Marburg, Philipps-University Marburg, Marburg, Germany
| | - Martin Welcker
- Medizinisches Versorgungszentrum für Rheumatologie Dr M Welcker GmbH, Planegg, Germany
| | - Nicolas Vuillerme
- Univ. Grenoble Alpes, AGEIS, 38000, Grenoble, France
- Institut Universitaire de France, Paris, France
- LabCom Telecom4Health, Orange Labs & Univ. Grenoble Alpes, CNRS, Inria, Grenoble INP-UGA, Grenoble, France
| |
Collapse
|
3
|
Sayeed MA, Ungar L, Chowdhury YH, Bari MS, Rahman MM, Anwer MS, Hoque MA. Gastrointestinal parasitosis in cattle: Unveiling the landscape across diverse production systems in Bangladesh. Vet Med Sci 2024; 10:e1325. [PMID: 38009452 PMCID: PMC10766017 DOI: 10.1002/vms3.1325] [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: 05/18/2023] [Revised: 09/06/2023] [Accepted: 11/07/2023] [Indexed: 11/28/2023] Open
Abstract
BACKGROUND Factors influencing parasitosis in cattle in Bangladesh remain inadequately explored, necessitating a comprehensive investigation for interventions and sustainable livestock farming. OBJECTIVES We conducted this study to estimate the prevalence and distribution of gastrointestinal parasites, exploring their intricate relationship with farm management practices across a spectrum of small-, medium-, and large-scale commercial farms. METHODS We conducted this study in the Chattogram district of Bangladesh. We collected a total of 189 freshly voided faecal samples from different farms. We recorded the age, breed, milking status, sex, body condition score, and anthelmintic use history of the sampled animals. We processed the samples using the direct smear method, with the identification of one egg per sample being considered positive. RESULTS We estimated the prevalence of gastrointestinal parasite infection in large-scale (52.1%), medium-scale (54.5%), and small-scale farms (70.0%), with statistically significant differences (p ≤ 0.05). Both pregnant and lactating cows, as well as indigenous cattle, were more likely to have gastrointestinal parasites (p ≤ 0.05). The predominant parasites across farms of all sizes were trematodes (Paramphistomum spp. and Schistosomas spp.) and protozoa (Balantidium coli and Coccidia spp.). CONCLUSION Poor farm management practices, such as no pasture management and inadequate deworming regimens, may contribute to the elevated prevalence and infection load observed on small-scale farms. The increased parasitosis in previously dewormed animals can be attributed to the development of anthelmintic resistance against gastrointestinal parasites. Implementing proper and effective deworming strategies is crucial to preventing gastrointestinal parasitosis and mitigating the risk of anthelmintic resistance.
Collapse
Affiliation(s)
- Md. Abu Sayeed
- National Centre for Epidemiology and Population HealthThe Australian National UniversityCanberraAustralia
| | - Lauren Ungar
- Cummings School of Veterinary Medicine at Tufts UniversityMedfordMassachusettsUSA
| | | | - Md. Saiful Bari
- Chattogram Veterinary and Animal Sciences UniversityChattogramBangladesh
| | - Md. Mizanur Rahman
- Chattogram Veterinary and Animal Sciences UniversityChattogramBangladesh
| | - M. Sawkat Anwer
- Cummings School of Veterinary Medicine at Tufts UniversityMedfordMassachusettsUSA
| | - Md. Ahasanul Hoque
- Chattogram Veterinary and Animal Sciences UniversityChattogramBangladesh
| |
Collapse
|
4
|
Du M, Li M, Yu X, Wang S, Wang Y, Yan W, Liu Q, Liu M, Liu J. Development and validation of prediction models for poor sleep quality among older adults in the post-COVID-19 pandemic era. Ann Med 2023; 55:2285910. [PMID: 38010392 PMCID: PMC10836252 DOI: 10.1080/07853890.2023.2285910] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/23/2023] [Accepted: 11/15/2023] [Indexed: 11/29/2023] Open
Abstract
BACKGROUND Corona Virus Disease 2019 (COVID-19) has a significant impact on sleep quality. However, the effects on sleep quality in the post-COVID-19 pandemic era remain unclear, and there is a lack of a screening tool for Chinese older adults. This study aimed to understand the prevalence of poor sleep quality and determine sensitive variables to develop an effective prediction model for screening sleep problems during infectious diseases outbreaks. MATERIALS AND METHODS The Peking University Health Cohort included 10,156 participants enrolled from April to May 2023. The Pittsburgh Sleep Quality Index (PSQI) scale was used to assess sleep quality. The data were randomly divided into a training-testing cohort (n = 7109, 70%) and an independent validation cohort (n = 3027, 30%). Five prediction models with 10-fold cross validation including the Least Absolute Shrinkage and Selection Operator (LASSO), Stochastic Volatility Model (SVM), Random Forest (RF), Artificial Neural Network (ANN), and XGBoost model based on the area under curve (AUC) were used to develop and validate predictors. RESULTS The prevalence of poor sleep quality (PSQI >7) was 30.69% (3117/10,156). Among the generated models, the LASSO model outperformed SVM (AUC 0.579), RF (AUC 0.626), ANN (AUC 0.615) and XGBoost (AUC 0.606), with an AUC of 0.7. Finally, a total of 12 variables related to sleep quality were used as parameters in the prediction models. These variables included age, gender, ethnicity, educational level, residence, marital status, history of chronic diseases, SARS-CoV-2 infection, COVID-19 vaccination, social support, depressive symptoms, and cognitive impairment among older adults during the post-COVID-19 pandemic. The nomogram illustrated that depressive symptoms contributed the most to the prediction of poor sleep quality, followed by age and residence. CONCLUSIONS This nomogram, based on twelve-variable, could potentially serve as a practical and reliable tool for early identification of poor sleep quality among older adults during the post-pandemic period.
Collapse
Affiliation(s)
- Min Du
- Department of Epidemiology and Biostatistics, School of Public Health, Peking University, Beijing, China
| | - Manchang Li
- Anning First People’s Hospital, Kunming University of Science and Technology, Yunan, China
| | - Xuejun Yu
- Jinfang Community Health Center, Anning Medical Community, Yunan, China
| | - Shiping Wang
- Anning First People’s Hospital, Kunming University of Science and Technology, Yunan, China
| | - Yaping Wang
- Department of Epidemiology and Biostatistics, School of Public Health, Peking University, Beijing, China
| | - Wenxin Yan
- Department of Epidemiology and Biostatistics, School of Public Health, Peking University, Beijing, China
| | - Qiao Liu
- Department of Epidemiology and Biostatistics, School of Public Health, Peking University, Beijing, China
| | - Min Liu
- Department of Epidemiology and Biostatistics, School of Public Health, Peking University, Beijing, China
- Institute for Global Health and Development, Peking University, Beijing, China
| | - Jue Liu
- Department of Epidemiology and Biostatistics, School of Public Health, Peking University, Beijing, China
- Institute for Global Health and Development, Peking University, Beijing, China
- Ministry of Education, Key Laboratory of Epidemiology of Major Diseases (Peking University), Beijing, China
- Department of Global Health and Population, Harvard TH Chan School of Public Health, Boston, MA, USA
| |
Collapse
|
5
|
Demsash AW, Chereka AA, Walle AD, Kassie SY, Bekele F, Bekana T. Machine learning algorithms' application to predict childhood vaccination among children aged 12-23 months in Ethiopia: Evidence 2016 Ethiopian Demographic and Health Survey dataset. PLoS One 2023; 18:e0288867. [PMID: 37851705 PMCID: PMC10584162 DOI: 10.1371/journal.pone.0288867] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/06/2023] [Accepted: 07/06/2023] [Indexed: 10/20/2023] Open
Abstract
INTRODUCTION Childhood vaccination is a cost-effective public health intervention to reduce child mortality and morbidity. But, vaccination coverage remains low, and previous similar studies have not focused on machine learning algorithms to predict childhood vaccination. Therefore, knowledge extraction, association rule formulation, and discovering insights from hidden patterns in vaccination data are limited. Therefore, this study aimed to predict childhood vaccination among children aged 12-23 months using the best machine learning algorithm. METHODS A cross-sectional study design with a two-stage sampling technique was used. A total of 1617 samples of living children aged 12-23 months were used from the 2016 Ethiopian Demographic and Health Survey dataset. The data was pre-processed, and 70% and 30% of the observations were used for training, and evaluating the model, respectively. Eight machine learning algorithms were included for consideration of model building and comparison. All the included algorithms were evaluated using confusion matrix elements. The synthetic minority oversampling technique was used for imbalanced data management. Informational gain value was used to select important attributes to predict childhood vaccination. The If/ then logical association was used to generate rules based on relationships among attributes, and Weka version 3.8.6 software was used to perform all the prediction analyses. RESULTS PART was the first best machine learning algorithm to predict childhood vaccination with 95.53% accuracy. J48, multilayer perceptron, and random forest models were the consecutively best machine learning algorithms to predict childhood vaccination with 89.24%, 87.20%, and 82.37% accuracy, respectively. ANC visits, institutional delivery, health facility visits, higher education, and being rich were the top five attributes to predict childhood vaccination. A total of seven rules were generated that could jointly determine the magnitude of childhood vaccination. Of these, if wealth status = 3 (Rich), adequate ANC visits = 1 (yes), and residency = 2 (Urban), then the probability of childhood vaccination would be 86.73%. CONCLUSIONS The PART, J48, multilayer perceptron, and random forest algorithms were important algorithms for predicting childhood vaccination. The findings would provide insight into childhood vaccination and serve as a framework for further studies. Strengthening mothers' ANC visits, institutional delivery, improving maternal education, and creating income opportunities for mothers could be important interventions to enhance childhood vaccination.
Collapse
Affiliation(s)
| | - Alex Ayenew Chereka
- Department of Health Informatics, College of Health Science, Mettu University, Mettu, Ethiopia
| | - Agmasie Damtew Walle
- Department of Health Informatics, College of Health Science, Mettu University, Mettu, Ethiopia
| | - Sisay Yitayih Kassie
- Department of Health Informatics, College of Health Science, Mettu University, Mettu, Ethiopia
| | - Firomsa Bekele
- Department of Pharmacy, College of Health Science, Mettu University, Mettu, Ethiopia
| | - Teshome Bekana
- Biomedical Science Department, College of Health Science, Mettu University, Mettu, Ethiopia
| |
Collapse
|
6
|
Oehm AW, Leinmueller M, Zablotski Y, Campe A, Hoedemaker M, Springer A, Jordan D, Strube C, Knubben-Schweizer G. Multinomial logistic regression based on neural networks reveals inherent differences among dairy farms depending on the differential exposure to Fasciola hepatica and Ostertagia ostertagi. Int J Parasitol 2023; 53:687-697. [PMID: 37355196 DOI: 10.1016/j.ijpara.2023.05.006] [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: 03/31/2023] [Revised: 05/17/2023] [Accepted: 05/18/2023] [Indexed: 06/26/2023]
Abstract
Fasciola hepatica and Ostertagia ostertagi are cattle parasites with worldwide relevance for economic outcome as well as animal health and welfare. The on-farm exposure of cattle to both parasites is a function of host-associated, intrinsic, as well as environmental and farm-specific, extrinsic, factors. Even though knowledge on the biology of both parasites exists, sophisticated and innovative modelling approaches can help to deepen our understanding of key aspects fostering the exposure of dairy cows to these pathogens. In the present study, multiple multinomial logistic regression models were fitted via neural networks to describe the differences among farms where cattle were not exposed to either F. hepatica or O. ostertagi, to one parasite, or to both, respectively. Farm-specific production and management characteristics were used as covariates to portray these differences. This elucidated inherent farm characteristics associated with parasite exposure. In both studied regions, pasture access for cows, farm-level milk yield, and lameness prevalence were identified as relevant factors. In region 'South', adherence to organic farming principles was a further covariate of importance. In region 'North', the prevalence of cows with a low body condition score, herd size, hock lesion prevalence, farm-level somatic cell count, and study year appeared to be of relevance. The present study broadens our understanding of the complex epidemiological scenarios that could predict differential farm-level parasite status. The analyses have revealed the importance of awareness of dissimilarities between farms in regard to the differential exposure to F. hepatica and O. ostertagi. This provides solid evidence that dynamics and relevant factors differ depending on whether or not cows are exposed to F. hepatica, O. ostertagi, or to both.
Collapse
Affiliation(s)
- Andreas W Oehm
- Institute of Parasitology, Vetsuisse Faculty of Zurich, University of Zurich, Zurich, Switzerland; Clinic for Ruminants with Ambulatory and Herd Health Services, Ludwig-Maximilians-Universität Munich, Oberschleissheim, Germany.
| | - Markus Leinmueller
- Clinic for Ruminants with Ambulatory and Herd Health Services, Ludwig-Maximilians-Universität Munich, Oberschleissheim, Germany
| | - Yury Zablotski
- Clinic for Ruminants with Ambulatory and Herd Health Services, Ludwig-Maximilians-Universität Munich, Oberschleissheim, Germany
| | - Amely Campe
- Department of Biometry, Epidemiology and Information Processing, WHO Collaborating Center for Research and Training for Health at the Human-Animal-Environment Interface, University of Veterinary Medicine, Foundation, Hannover, Germany
| | - Martina Hoedemaker
- Clinic for Cattle, University of Veterinary Medicine Hannover Foundation, Hannover, Germany
| | - Andrea Springer
- Institute for Parasitology, Centre for Infection Medicine, University of Veterinary Medicine Hannover, Hannover, Germany
| | - Daniela Jordan
- Institute for Parasitology, Centre for Infection Medicine, University of Veterinary Medicine Hannover, Hannover, Germany
| | - Christina Strube
- Institute for Parasitology, Centre for Infection Medicine, University of Veterinary Medicine Hannover, Hannover, Germany
| | - Gabriela Knubben-Schweizer
- Clinic for Ruminants with Ambulatory and Herd Health Services, Ludwig-Maximilians-Universität Munich, Oberschleissheim, Germany
| |
Collapse
|
7
|
Russel WA, Perry J, Bonzani C, Dontino A, Mekonnen Z, Ay A, Taye B. Feature selection and association rule learning identify risk factors of malnutrition among Ethiopian schoolchildren. FRONTIERS IN EPIDEMIOLOGY 2023; 3:1150619. [PMID: 38455884 PMCID: PMC10910994 DOI: 10.3389/fepid.2023.1150619] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 01/24/2023] [Accepted: 06/20/2023] [Indexed: 03/09/2024]
Abstract
Introduction Previous studies have sought to identify risk factors for malnutrition in populations of schoolchildren, depending on traditional logistic regression methods. However, holistic machine learning (ML) approaches are emerging that may provide a more comprehensive analysis of risk factors. Methods This study employed feature selection and association rule learning ML methods in conjunction with logistic regression on epidemiological survey data from 1,036 Ethiopian school children. Our first analysis used the entire dataset and then we reran this analysis on age, residence, and sex population subsets. Results Both logistic regression and ML methods identified older childhood age as a significant risk factor, while females and vaccinated individuals showed reduced odds of stunting. Our machine learning analyses provided additional insights into the data, as feature selection identified that age, school latrine cleanliness, large family size, and nail trimming habits were significant risk factors for stunting, underweight, and thinness. Association rule learning revealed an association between co-occurring hygiene and socio-economical variables with malnutrition that was otherwise missed using traditional statistical methods. Discussion Our analysis supports the benefit of integrating feature selection methods, association rules learning techniques, and logistic regression to identify comprehensive risk factors associated with malnutrition in young children.
Collapse
Affiliation(s)
- William A. Russel
- Department of Biology, Colgate University, Hamilton, NY, United States
| | - Jim Perry
- Department of Computer Science, Colgate University, Hamilton, NY, United States
| | - Claire Bonzani
- Department of Mathematics, Colgate University, Hamilton, NY, United States
| | - Amanda Dontino
- Department of Biology, Colgate University, Hamilton, NY, United States
| | - Zeleke Mekonnen
- Institute of Health, School of Medical Laboratory Sciences, Jimma University, Jimma, Ethiopia
| | - Ahmet Ay
- Department of Biology, Colgate University, Hamilton, NY, United States
- Department of Mathematics, Colgate University, Hamilton, NY, United States
| | - Bineyam Taye
- Department of Biology, Colgate University, Hamilton, NY, United States
| |
Collapse
|
8
|
Kebede SD, Sebastian Y, Yeneneh A, Chanie AF, Melaku MS, Walle AD. Prediction of contraceptive discontinuation among reproductive-age women in Ethiopia using Ethiopian Demographic and Health Survey 2016 Dataset: A Machine Learning Approach. BMC Med Inform Decis Mak 2023; 23:9. [PMID: 36650511 PMCID: PMC9843668 DOI: 10.1186/s12911-023-02102-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/29/2022] [Accepted: 01/05/2023] [Indexed: 01/19/2023] Open
Abstract
BACKGROUND Globally, 38% of contraceptive users discontinue the use of a method within the first twelve months. In Ethiopia, about 35% of contraceptive users also discontinue within twelve months. Discontinuation reduces contraceptive coverage, family planning program effectiveness and contributes to undesired fertility. Hence understanding potential predictors of contraceptive discontinuation is crucial to reducing its undesired outcomes. Predicting the risk of discontinuing contraceptives is also used as an early-warning system to notify family planning programs. Thus, this study could enable to predict and determine the predictors for contraceptive discontinuation in Ethiopia. METHODOLOGY Secondary data analysis was done on the 2016 Ethiopian Demographic and Health Survey. Eight machine learning algorithms were employed on a total sample of 5885 women and evaluated using performance metrics to predict and identify important predictors of discontinuation through python software. Feature importance method was used to select top predictors of contraceptive discontinuation. Finally, association rule mining was applied to discover the relationship between contraceptive discontinuation and its top predictors by using R statistical software. RESULT Random forest was the best predictive model with 68% accuracy which identified the top predictors of contraceptive discontinuation. Association rule mining identified women's age, women's education level, family size, husband's desire for children, husband's education level, and women's fertility preference as predictors most frequently associated with contraceptive discontinuation. CONCLUSION Results have shown that machine learning algorithms can accurately predict the discontinuation status of contraceptives, making them potentially valuable as decision-support tools for the relevant stakeholders. Through association rule mining analysis of a large dataset, our findings also revealed previously unknown patterns and relationships between contraceptive discontinuation and numerous predictors.
Collapse
Affiliation(s)
- Shimels Derso Kebede
- Department of Health Informatics, School of Public Health, College of Medicine and Health Science, Wollo University, Dessie, Ethiopia.
| | - Yakub Sebastian
- Department of Information Technology, College of Engineering, IT and Environment, Charles Darwin University, Darwin, Australia
| | - Abraham Yeneneh
- Department of Health Informatics, Institute of Public Health, College of Medicine and Health Science, University of Gondar, Gondar, Ethiopia
| | - Ashenafi Fentahun Chanie
- Department of Health Informatics, Institute of Public Health, College of Medicine and Health Science, University of Gondar, Gondar, Ethiopia
| | - Mequannent Sharew Melaku
- Department of Health Informatics, Institute of Public Health, College of Medicine and Health Science, University of Gondar, Gondar, Ethiopia
| | - Agmasie Damtew Walle
- Department of Health Informatics, Institute of Public Health, College of Medicine and Health Sciences, Mettu University, Mettu, Ethiopia
| |
Collapse
|