1
|
Mamo DN, Gebremariam YH, Adem JB, Kebede SD, Walle AD. Machine learning to predict unintended pregnancy among reproductive-age women in Ethiopia: evidence from EDHS 2016. BMC Womens Health 2024; 24:57. [PMID: 38263219 PMCID: PMC10804521 DOI: 10.1186/s12905-024-02893-8] [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: 03/25/2023] [Accepted: 01/08/2024] [Indexed: 01/25/2024] Open
Abstract
BACKGROUND An unintended pregnancy is a pregnancy that is either unwanted or mistimed, such as when it occurs earlier than desired. It is one of the most important issues the public health system is currently facing, and it comes at a significant cost to society both economically and socially. The burden of an undesired pregnancy still weighs heavily on Ethiopia. The purpose of this study was to assess the effectiveness of machine learning algorithms in predicting unintended pregnancy in Ethiopia and to identify the key predictors. METHOD Machine learning techniques were used in the study to analyze secondary data from the 2016 Ethiopian Demographic and Health Survey. To predict and identify significant determinants of unintended pregnancy using Python software, six machine-learning algorithms were applied to a total sample of 7193 women. The top unplanned pregnancy predictors were chosen using the feature importance technique. The effectiveness of such models was evaluated using sensitivity, specificity, accuracy, and area under the curve. RESULT The ExtraTrees classifier was chosen as the top machine learning model after various performance evaluations. The region, the ideal number of children, religion, wealth index, age at first sex, husband education, refusal sex, total births, age at first birth, and mother's educational status are identified as contributing factors in that predict unintended pregnancy. CONCLUSION The ExtraTrees machine learning model has a better predictive performance for identifying predictors of unintended pregnancies among the chosen algorithms and could improve with better policy decision-making in this area. Using these important features to help direct appropriate policy can significantly increase the chances of mother survival.
Collapse
Affiliation(s)
- Daniel Niguse Mamo
- Department of Health Informatics, School of Public Health, Arbaminch University, Arbaminch, Ethiopia.
| | - Yosef Haile Gebremariam
- Department of Public Health, School of Public Health, Arbaminch University, Arbaminch, Ethiopia
| | - Jibril Beshir Adem
- Department of Health Informatics, Institute of Public Health, Arsi University, Assela, Ethiopia
| | - Shimels Derso Kebede
- Department of Health Informatics, School of Public Health, College of Medicine and Health Science, Wollo University, Dessie, Ethiopia
| | - Agmasie Damtew Walle
- Department of Health Informatics, college of health science, Mettu University, Mettu, Ethiopia
| |
Collapse
|
2
|
Ayele A, Abdurashid N, Hailu M, Tefera B. Unintended Pregnancy and Associated Factors among Pregnant Women Attending Antenatal Care Unit in Public Health Facilities of Dire Dawa City, Eastern Ethiopia, 2021. Obstet Gynecol Int 2023; 2023:8100462. [PMID: 37701415 PMCID: PMC10495237 DOI: 10.1155/2023/8100462] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/10/2022] [Revised: 05/24/2023] [Accepted: 07/13/2023] [Indexed: 09/14/2023] Open
Abstract
Background Unintended pregnancy refers to a pregnancy that is either mistimed or unwanted. Unintended pregnancy has been a troubling public health and reproductive health issue, which imposes appreciable adverse consequences on the mother, child, and the public in general. Globally 121 million unplanned pregnancies occurred from 2015 to 2019. A significant proportion (61%) of these pregnancies ended in abortions each year. In Ethiopia, the challenges of unintended pregnancy and its related complications still exist because of the high rate of unmet need for contraceptives. In addition, no research has been conducted on unintended pregnancy among pregnant women in Dire Dawa city administration. Objective To determine the prevalence of unintended pregnancy and associated factors among pregnant women attending antenatal care public health facilities in Dire Dawa in 2021. Methods A facility-based cross-sectional study was conducted. After being chosen randomly, 382 pregnant women were interviewed at 9 urban public health facilities. A pretested questionnaire was used to collect data, entered into Epi Info 7, and exported into SPSS version 25 for analysis. The variables, which were significant at P ≤ 0.25 in bivariate analysis, were included in multivariable analysis. Statistical significance was declared at a P value <0.05 and a 95% CI. Results In this study, the prevalence of unintended pregnancy was 23.8% at 95% CI (19.8-28.3). The following factors were associated with unintended pregnancy: single women (AOR = 10.93, 95% CI 3.65-32.74), low family income (2000 ETB) (AOR = 4.01, 95% CI 1.73-9.28), parity 3 (AOR = 10.3, 95% CI 4.07-25.84), no history of family planning use (AOR = 5.91, 95% CI 2.46-14.21), and husband decision-making role on reproductive health (AOR = 2.956, 95% CI 1.048-8.340). Conclusion and Recommendations. The prevalence of unintended pregnancy was relatively high in this study. Efforts should be made to scale up women's decision-making power on family planning services and give support to empower women economically. There is the need to promote family planning services to minimize unintended pregnancy and to decrease parity and family size.
Collapse
Affiliation(s)
| | | | - Mickiale Hailu
- Department of Midwifery, College of Medicine and Health Sciences, Dire Dawa University, Dire Dawa, Ethiopia
| | - Bereket Tefera
- Department of Midwifery, College of Medicine and Health Sciences, Dire Dawa University, Dire Dawa, Ethiopia
| |
Collapse
|
3
|
Yalew AZ, Olayemi OO, Yalew AW. Reasons and prevention strategies of unintended pregnancy in Addis Ababa, Ethiopia: a phenomenological qualitative study. BMJ Open 2023; 13:e072008. [PMID: 37491099 PMCID: PMC10373735 DOI: 10.1136/bmjopen-2023-072008] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 07/27/2023] Open
Abstract
OBJECTIVES To explore the reasons for unintended pregnancy and effective prevention measures from the perspectives of women and healthcare providers in Addis Ababa, Ethiopia. DESIGN Phenomenological qualitative study. SETTING AND PARTICIPANTS This study was conducted at three public health facilities found in Addis Ababa, Ethiopia. Women with unintended pregnancies and healthcare providers currently working in maternal health services were purposively recruited for in-depth interviews. Twenty in-depth interviews were conducted until data saturation was achieved. Data were analysed using thematic analysis. RESULTS Seven themes emerged from the transcribed interview data. These include: Personal characteristics (negligence; lower pregnancy expectation), family influence (fear of family), sociocultural and economic influence (stigma and discrimination), healthcare provider influence (disrespectful and abusive approach; disregard for women's contraceptive choice), preconception thoughts and behaviours (unprotected early sexual practice; myths and misunderstanding), lack of access to quality family planning services (lack of trained contraceptive counsellor, inappropriate contraceptive use), and preventive strategies for unintended pregnancy (comprehensive sexual education; sexual and reproductive health and rights service integration) CONCLUSIONS: This study identified multilevel reasons for unintended pregnancy from the perspective of the participants. Participants shared their views on preventive measures for unintended pregnancy, including comprehensive sexual education, service integration and male-inclusive contraceptive counselling. This study highlights the need to improve sexual and reproductive health services by shedding light on the viewpoints and experiences of women and healthcare providers.
Collapse
Affiliation(s)
- Ayalnesh Zemene Yalew
- Department of Obstetrics and Gynecology, Pan African University, Institutes of Life and Earth Sciences (including Agriculture and Health), College of Medicine, University of Ibadan, Addis Ababa, Ethiopia
- School of Nursing, St Paul's Hospital Millennium Medical College, Ibadan, Nigeria
| | - Oladapo O Olayemi
- Department of Obstetrics and Gynecology, University of Ibadan, Ibadan, Nigeria
| | | |
Collapse
|
4
|
Aragaw FM, Amare T, Teklu RE, Tegegne BA, Alem AZ. Magnitude of unintended pregnancy and its determinants among childbearing age women in low and middle-income countries: evidence from 61 low and middle income countries. FRONTIERS IN REPRODUCTIVE HEALTH 2023; 5:1113926. [PMID: 37533507 PMCID: PMC10393037 DOI: 10.3389/frph.2023.1113926] [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: 12/01/2022] [Accepted: 05/29/2023] [Indexed: 08/04/2023] Open
Abstract
Background Unintended pregnancy is one of the most serious health issues in low and Middle-Income Countries (LMICs), posing significant health, economic, and psychosocial costs to individuals and communities. However, there is limited evidence on the prevalence of unintended pregnancies and their determinants in LMICs. Hence, this study aimed to assess the prevalence of unintended pregnancy and its associated factors among childbearing-age women in LMICs. Method Data for the study were drawn from a recent 61 Demographic and Health Surveys (DHS) conducted in LMICs. A total sample of 187,347 mothers who gave birth in the five years preceding the survey was included. STATA version 16 was used to clean and analyze the data. Multilevel multivariable logistic regression was employed to identify individual and community-level factors of unintended pregnancy in LMICs. In the multivariable analysis, an adjusted odds ratio with a 95% confidence level was reported to indicate statistical association. Results The pooled magnitude of unintended pregnancy in LMICs was 26.46%% (95% CI: 25.30%, 27.62%), ranging from 19.25%% in Egypt to 61.71% in Bolivia. Working status (AOR = 1.03; 95% CI: 1.01, 1.06), having a husband with no education (AOR = 1.07; 95% CI: 1.00, 1.15), and primary education (AOR = 1.05; 95% CI: 1.01, 1.11), women from male-headed households (AOR = 1.04; 95% CI: 1.00, 1.08), media exposure (AOR = 1.05; 95% CI: 1.02, 1.08), unmet need for contraception (AOR = 1.05; 95% CI: 1.02, 1.08), distance from a health facility (AOR = 1.03; 95% CI: 1.00, 1.06) were significantly associated with unintended pregnancy. Conclusion Unintended pregnancy rates remain high in LMICs. Women whose husband has no education and primary education, women with media exposure, working status, women who live in a household headed by male, women with unmet need for contraception, and women with a big problem of distance to health facilities were variables that were significant predictors of unintended pregnancy. When attempting to minimize unintended pregnancy in LMICs, these factors need to be considered. Furthermore, most of these attempts should be driven by government entities in low and middle-income countries.
Collapse
Affiliation(s)
- Fantu Mamo Aragaw
- Department of Epidemiology and Biostatistics, Institute of Public Health, College of Medicine and Health Sciences, University of Gondar, Gondar, Ethiopia
| | - Tsegaw Amare
- Department of Health Systems and Policy, Institute of Public Health, College of Medicine and Health Sciences, University of Gondar, Gondar, Ethiopia
| | - Rediet Eristu Teklu
- Department of Epidemiology and Biostatistics, Institute of Public Health, College of Medicine and Health Sciences, University of Gondar, Gondar, Ethiopia
| | - Biresaw Ayen Tegegne
- Department of Anesthesia, College of Medicine and Health Sciences, University of Gondar, Gondar, Ethiopia
| | - Adugnaw Zeleke Alem
- Department of Epidemiology and Biostatistics, Institute of Public Health, College of Medicine and Health Sciences, University of Gondar, Gondar, Ethiopia
| |
Collapse
|
5
|
Guta NM, Ruksi ST, Gachana Midaksa Senbata, Seid K. Predictors of perceived poor social support status of pregnant women attending antiretroviral therapy clinics in south west Ethiopia, 2021. Heliyon 2023; 9:e18282. [PMID: 37519693 PMCID: PMC10372391 DOI: 10.1016/j.heliyon.2023.e18282] [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: 05/19/2022] [Revised: 07/10/2023] [Accepted: 07/13/2023] [Indexed: 08/01/2023] Open
Abstract
Background To improve pregnancy outcomes, a pregnant mother living with HIV/AIDS requires a high level of social and emotional support. However, women from low-income countries were subjected to low social support status despite adequate counseling and health messages to increase their social support. Therefore, this study aimed to investigate the predictors of the perceived poor social support status among pregnant women attending ART clinics in Southwest Ethiopia. Methods A hospital-based cross-sectional study with consecutive sampling was conducted to enroll 265 pregnant women on antiretroviral therapy (ART) from December 1 to 30, 2021. The data were collected using an interviewer-administered questionnaire. Epidata was used for data entry and analyzed after it was exported to a statistical package for the social sciences. Binary logistic regression was used and the level of significance was declared at P-value <0.05 using Adjusted odds ratio at 95% CI after candidate variables were identified in binary logistic regression at a P-value of <0.25. Results Finding from the study figured out that low level of poor social support is found to be 47.2%. Study revealed that income level[AOR = 5.1 95% CI [1.9,13.6]], disclosure status[AOR: 1.9 95% CI [1.1,3.3]], unwanted pregnancy [AOR = 2.3 CI; [ 1.4,3.9]], and low adherence level[AOR: 2.1 95% CI [1.1,3.1]] were strong predictors. Conclusion This study identified high levels of poor social support. Increasing access to information education and communications focusing on stigma, disclosure & refresher training that boosts the counseling skills of health care providers to enhance adherence level is strongly recommended.
Collapse
Affiliation(s)
- Nuredin Mohammed Guta
- Department of Nursing, College of Health Science, Mizan Tepi University, Mizan-Aman, Ethiopia
| | - Sisay Tulu Ruksi
- Department of Nursing, College of Health Science, Mizan Tepi University, Mizan-Aman, Ethiopia
| | - Gachana Midaksa Senbata
- Department of Public Health, College of Health Science, Mizan Tepi University, Mizan-Aman, Ethiopia
| | - Kalid Seid
- Department of Nursing, College of Health Science, Mizan Tepi University, Mizan-Aman, Ethiopia
| |
Collapse
|
6
|
Yalew AZ, Olayemi OO, Yalew AW. Association between unintended pregnancy and maternal antenatal care services use in Ethiopia: analysis of Ethiopian demographic and health survey 2016. Front Med (Lausanne) 2023; 10:1151486. [PMID: 37153096 PMCID: PMC10155231 DOI: 10.3389/fmed.2023.1151486] [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: 01/26/2023] [Accepted: 04/03/2023] [Indexed: 05/09/2023] Open
Abstract
Introduction Unintended pregnancy disproportionately affects women in low and middle-income countries including Ethiopia. Previous studies identified the magnitude and negative health outcomes of unintended pregnancy. However, studies that examined the relationship between antenatal care (ANC) utilization and unintended pregnancy are scarce. Objective This study aimed to examine the relationship between unintended pregnancy and ANC utilization in Ethiopia. Methods This is a cross-sectional study conducted using the fourth and most recent Ethiopian Demographic Health Survey (EDHS) data. The study comprised a weighted sample of 7,271 women with last alive birth and responded to questions on unintended pregnancy and ANC use. The association between unintended pregnancy and ANC uptake was determined using multilevel logistic regression models adjusted for possible confounders. Finally p < 5% was considered significant. Results Unintended pregnancy accounted for nearly a quarter of all pregnancies (26.5%). After adjusting for confounders, a 33% (AOR: 0.67; 95% CI, 0.57-0.79) lower odds of at least one ANC uptake and a 17% (AOR: 0.83; 95% CI, 0.70-0.99) lower odds of early ANC booking were found among women who had unintended pregnancy compared to women with intended pregnancy. However, this study founds no association (AOR: 0.88; 95% CI, 0.74, 1.04) between unintended pregnancy and four or more ANC visits. Conclusion Our study found that having unintended pregnancy was associated with a 17 and 33% reduction in early initiation and use of ANC services, respectively. Policies and programs designed to intervene against barriers to early initiation and use of ANC should consider unintended pregnancy.
Collapse
Affiliation(s)
- Ayalnesh Zemene Yalew
- Pan African University for Life and Earth Science Institute (Including Agriculture and Health), University of Ibadan, Ibadan, Nigeria
- School of Nursing, St. Paul’s Hospital Millennium Medical College, Addis Ababa, Ethiopia
- *Correspondence: Ayalnesh Zemene Yalew, ;
| | - Oladapo O. Olayemi
- Department of Obstetrics and Gynecology, College of Medicine, University of Ibadan, Ibadan, Nigeria
| | - Alemayehu Worku Yalew
- School of Public Health, College of Health Science, Addis Ababa University, Addis Ababa, Ethiopia
| |
Collapse
|
7
|
Utilization of long acting and permanent contraceptive methods and associated factor among women of reproductive age in west Guji zone, Southwest Ethiopia. Reprod Health 2022; 19:31. [PMID: 35101057 PMCID: PMC8805251 DOI: 10.1186/s12978-022-01337-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/20/2021] [Accepted: 01/10/2022] [Indexed: 11/10/2022] Open
Abstract
Background Increasing access to family planning helps to ensure the reproductive right, decrease unintended pregnancy, improve the health and nutritional status of children, reduction of maternal mortality, and enhance longer birth spacing. However, there is continually low utilization of long acting and permanent contraceptive methods among low and middle-income countries. This study aimed to assess the utilization of long acting and permanent contraceptive methods (LAPMs) and associated factors among women of reproductive age in the West Guji Zone, Ethiopia. Methods An institution-based cross-sectional study was carried out among 507 women of reproductive age in the West Guji Zone, Southwest Ethiopia from April 15 to May 15, 2018. Data were collected by a structured, pretested, and interview-based questionnaire with open ended and closed ended questionnaire, then entered, and analyzed by SPSS Version 20. Bivariable and multivariate logistic regression analyses were carried out. A 95% confidence interval (CI) AND P-value < 0.05 was considered to declare statistically significant variables. Result The current utilization of LAPMs at West Guji zone among the reproductive-aged group was found to be 51.1%. More than the median of participants had negative altitude (72.4%) and poor knowledge (57%) towards the LAPMs. Educational status of women, the number of alive children, acceptance of utilization of LAPMs, how treated by other staff, and waiting time during service delivery are significant determinant factors of LAPMs. Conclusion Overall, more than half of women had a negative attitude and poor knowledge of LAPMs. Educational status of women, the number of alive children, acceptance of utilization of LAPMs, how treated by other staff, and waiting time during service delivery were factors affecting utilization of LAPMs. Therefore, sustained, and appropriate information on LAPMs should be provided to raise knowledge and build the attitude of women and the community. Treating the clients with respect, reducing the waiting time, and collaborative work with health extension worker will enhance utilization of LAPMs. Low utilization of LAPMs has been continually reported in low- and middle-income countries. Unintended pregnancy and unsafe abortion might be related with unmet need of contraceptive. This study aimed to assess level of utilization of LAPMs among reproductive aged women in West Guji Zone Ethiopia. The findings from this research will help different stake holder by providing the level of current utilization of LAPMs and help them on planning how to strength the utilization by refereeing the associated factors. 507 Respondents were selected systematically: of which 51.1% of them utilize one of LAPMs currently. In conclusion the utilization may be affected by educational status of women, number of alive children, acceptance LAPMs by women, how treated by other staff during service delivery, and waiting time to get the service.
Collapse
|
8
|
Molla W, Hailemariam S, Mengistu N, Madoro D, Bayisa Y, Tilahun R, Wudneh A, Ayele GM. Unintended pregnancy and associated factors during COVID-19 pandemic in Ethiopia: Community-based cross-sectional study. WOMEN'S HEALTH 2022; 18:17455057221118170. [PMID: 35972047 PMCID: PMC9382576 DOI: 10.1177/17455057221118170] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 11/17/2022]
Abstract
Introduction: The term ‘unintended pregnancy’ refers to a pregnancy that occurred when no children were desired or occurred earlier than desired. Unintended births account for one out of every three births in Ethiopia, and they are the leading cause of maternal morbidity and mortality. During the coronavirus disease (COVID-19) pandemic, this could be useful. COVID-19 has a significant impact on maternal health care utilization, including family planning services. As a result, this study aimed to assess unintended pregnancy and associated factors in Ethiopia during the COVID-19 pandemic. Method: A community-based cross-sectional study was conducted in Gedeo zone, Ethiopia, from April 1 to May 30, 2021. A simple random sampling technique was utilized to get 383 pregnant women from their respective kebeles. A structured questionnaire was used to collect data during a face-to-face interview. The data were coded, cleaned, and entered into Epidemiological Data Version 3.1 before being exported to the Statistical Package for Social Science Version 23.0 for analysis. A bivariate and multivariable logistic regression model was used to identify statistically significant associations between dependent and independent variables. The odds ratio, with a 95% confidence interval and a P value of 0.05%, was considered statistically significant. Result: A total of 383 pregnant women participated in the study, giving a response rate of 90.8%. During the COVID-19 pandemic, 140 (36.6%) participants stated that their current pregnancy was unintended. Unintended pregnancy was significantly associated with respondents’ age (adjusted odds ratio (AOR) = 5.214 (1.449–18.762)), primary decision maker for family planning services (AOR = 9.510 (5.057–17.887)), and fear of COVID-19 to visit a health care facility (AOR = 7.061 (2.665–18.710)). Conclusion: During the COVID-19 era, more than one-third of women had unintended pregnancies. Unintended pregnancy was significantly associated with respondents’ age, autonomy to use contraceptive methods, and fear of COVID-19, which required them to attend a health care institution.
Collapse
Affiliation(s)
| | | | | | - Derebe Madoro
- Department of Psychiatry, Dilla University, Dilla, Ethiopia
| | | | - Ruth Tilahun
- Department of Midwifery, Dilla University, Dilla, Ethiopia
| | | | | |
Collapse
|