Precision Women’s Health: Integrating Clinical Research, Artificial Intelligence, Digital Innovation, and Personalized Care
Download PDF
ABSTRACT
Background: Women’s health is a multidimensional field influenced by biological, reproductive, psychological, social, environmental, and technological factors. Recent advances in artificial intelligence (AI), digital health, predictive analytics, and personalized medicine provide new opportunities to improve prevention, diagnosis, monitoring, and individualized care.
Aim: This review examines the contribution of clinical research and technological innovation to precision women’s health, with emphasis on artificial intelligence, digital health, maternal and reproductive health, gynecological disease, personalized care, and patient-centered innovation.
Methods: An integrative narrative review was undertaken using recent peer-reviewed literature identified through biomedical literature sources and reports from the World Health Organization, with emphasis on publications from 2020–2026. Evidence addressing AI, machine learning, digital health, obstetrics, gynecology, reproductive health, maternal health, fertility, and women’s health innovation was synthesized thematically.
Results: Recent evidence demonstrates rapid growth in AI applications across sexual and reproductive health. A comprehensive 2025 scoping review identified 2,666 primary studies applying AI to sexual and reproductive health; maternal health, reproductive cancers, and infertility/fertility care were major areas of research (Mengistu et al., 2025). Digital health technologies may improve access to healthcare, maternal health, health information, and women’s empowerment (WHO Regional Office for Europe, 2024). However, algorithmic bias, limited external validation, privacy concerns, digital inequity, transparency, and insufficient real-world implementation evidence remain important challenges.
Conclusion: Precision women’s health requires integration of high-quality clinical research, responsible AI, digital innovation, professional expertise, patient participation, and ethical governance. This review proposes a Precision Women’s Health Innovation Framework linking clinical need, evidence, technological innovation, human-centered design, ethical implementation, and measurable clinical impact.
Keywords: Women’s Health; Digital Innovation; Artificial Intelligence; Clinical Research; Personalized Care
INTRODUCTION
Women’s health encompasses health conditions and experiences across the life course, including adolescence, reproductive years, pregnancy, postpartum, menopause, and later life. Although reproductive health is central, women’s health also includes cardiovascular, metabolic, neurological, psychological, oncological, and chronic health conditions. The complexity of women’s health requires approaches that recognize biological characteristics alongside social, cultural, environmental, and healthcare-system factors [1].
Technological innovation is changing how health information is collected, interpreted, communicated, and used for clinical decision-making. Artificial intelligence (AI), machine learning, digital health applications, wearable devices, telehealth, predictive analytics, and large language models have expanded possibilities for prevention, diagnosis, monitoring, and personalized care.
The expansion of AI research in sexual and reproductive health is particularly notable. Mengistu et al. (2025) identified 2,666 primary studies involving AI and sexual and reproductive health. Maternal health, reproductive cancers, and infertility/fertility care were prominent research areas, while screening and diagnosis represented the predominant application.
Digital health is another major component of innovation. The World Health Organization reported that digital health technologies can contribute to improved access to healthcare, maternal health, health information, and women’s empowerment (WHO Regional Office for Europe, 2024).
Therefore, the future of women’s healthcare should not simply involve adopting more technology. It should involve integrating technology with rigorous clinical research, professional expertise, patient participation, ethical governance, and measurable improvements in health outcomes [2].
AIM AND OBJECTIVES
The aim of this review is to examine how clinical research and technological innovation can advance precision women’s health.
- Examine current applications of AI in women’s health.
- Explore the role of digital health in improving access and continuity of care.
- Discuss AI applications in maternal and reproductive health.
- Examine innovations in gynecological diagnosis and cancer screening.
- Explore AI contributions to personalized and precision care.
- Identify ethical, social, and equity challenges.
- Discuss the role of nurses and healthcare professionals in implementing innovation.
- Propose a framework for translating women’s health innovation into measurable clinical outcomes.
METHODS
Review Design
An integrative narrative review design was used to synthesize contemporary evidence concerning clinical research and innovation in women’s health. A narrative approach was selected because the review integrates rapidly developing domains, including AI, digital health, maternal health, reproductive medicine, gynecological oncology, and personalized care.
Literature Identification
Relevant literature was identified through PubMed and biomedical literature sources, supplemented by reports from the World Health Organization. Search concepts included combinations of artificial intelligence and women’s health; artificial intelligence and obstetrics; artificial intelligence and gynecology; machine learning and maternal health; digital health and women’s health; AI and reproductive health; AI and fertility; AI and gynecological cancer; and precision medicine and women’s health [3]. Emphasis was placed on publications from 2020–2026.
Synthesis
Evidence was synthesized under six themes: AI and clinical diagnosis; AI and maternal/reproductive health; digital health and remote care; precision and personalized women’s healthcare; ethics, equity, and patient-centered innovation; and translation of innovation into clinical practice.
ARTIFICIAL INTELLIGENCE IN WOMEN’S HEALTH
Artificial intelligence includes computational approaches capable of recognizing patterns, generating predictions, processing complex information, and supporting decision-making. Machine learning and deep learning are among the most frequently investigated approaches in healthcare.
The growing evidence indicates that AI is increasingly relevant to women’s health. Mengistu et al. (2025) identified 2,666 primary studies involving AI and sexual and reproductive health. The predominance of screening and diagnosis suggests that AI is currently used primarily to support recognition and classification rather than autonomous treatment [4].
The next stage of research should therefore move from algorithm development toward clinical effectiveness, external validation, implementation, and patient outcomes.
ARTIFICIAL INTELLIGENCE IN MATERNAL HEALTH
Maternal health is one of the most extensively studied areas of AI in women’s healthcare. Potential applications include prediction of pre-eclampsia, preterm birth, gestational diabetes, postpartum hemorrhage, fetal growth abnormalities, hypertensive disorders, and adverse perinatal outcomes.
Recent reviews indicate substantial growth in AI model development in obstetrics, particularly risk prediction. However, variation in model performance and limited generalizability across populations remain important concerns (Devoe et al., 2025) [5]. Other reviews describe applications across pregnancy-risk assessment, fetal monitoring, mode of birth, postpartum hemorrhage, hypertensive disorders, and neonatal outcomes (Tadepalli et al., 2025).
AI may become an important component of future maternal risk stratification, but predictive performance must be evaluated alongside clinical usefulness, safety, interpretability, and effects on maternal and neonatal outcomes [6].
AI AND REPRODUCTIVE HEALTH
Reproductive health is a rapidly expanding area of AI research, including infertility assessment, assisted reproductive technology, embryo selection, prediction of treatment outcomes, polycystic ovary syndrome, endometriosis, reproductive cancers, menstrual health, and personalized fertility care.
A systematic review of AI in assisted reproductive technology examined applications involving treatment efficacy, process optimization, and outcome prediction (Wu et al., 2025). AI may eventually support individualized reproductive care by integrating demographic, clinical, laboratory, imaging, and treatment-response data.
Because reproductive healthcare involves highly personal information, implementation requires privacy protection, informed consent, transparency, and patient autonomy [7].
AI IN GYNECOLOGICAL CANCER DETECTION
Gynecological oncology is another area in which AI may support earlier diagnosis [8]. Potential applications include cervical cancer screening, cervical image interpretation, histopathological classification, ovarian cancer risk prediction, endometrial cancer assessment, and treatment-response prediction.
Recent work on AI-supported diagnostic innovation has emphasized its potential contribution to global women’s health, particularly where specialist diagnostic resources are limited (Linder et al., 2025). External validation remains essential because disease prevalence, imaging equipment, patient characteristics, and clinical practices differ across settings [9].
DIGITAL HEALTH AND WOMEN’S HEALTH
Digital health technologies include mobile applications, telemedicine, electronic health records, remote monitoring, wearable devices, patient portals, and digital education platforms [10]. The WHO Regional Office for Europe (2024) reported that digital health technologies can contribute to improved access to healthcare, maternal health, health information, and women’s empowerment.
Potential applications include antenatal education, postpartum follow-up, reproductive health education, menstrual health tracking, medication reminders, chronic disease monitoring, teleconsultation, mental health screening, and patient decision support [11]. Digital health should complement rather than automatically replace face-to-face healthcare.
REMOTE MONITORING AND WEARABLE TECHNOLOGY
Wearable and connected devices enable collection of health information outside conventional healthcare facilities [12]. Potentially relevant measurements include blood pressure, blood glucose, heart rate, physical activity, sleep, body weight, temperature, and menstrual or reproductive patterns.
Research has examined combinations of AI and Internet-of-Medical-Things technologies in pregnancy-related diabetes management (Murrin et al., 2025) [13]. Future studies should determine which measurements are clinically meaningful and how monitoring can be integrated into healthcare workflows.
PRECISION WOMEN’S HEALTH
Precision healthcare aims to tailor prevention and treatment according to individual characteristics [14]. In women’s health, these may include reproductive history, hormonal profile, genetic factors, comorbidities, lifestyle, environmental exposures, previous treatment response, socioeconomic circumstances, and patient preferences.
AI may facilitate precision care by integrating multiple data sources that are difficult to analyze simultaneously using conventional approaches. Recent literature describes potential applications across obstetrics and gynecology, including imaging, maternal-fetal medicine, fertility, gynecological oncology, and surgical care (Aftab, 2025) [15].
LARGE LANGUAGE MODELS AND WOMEN’S HEALTH
Large language models (LLMs) can process and generate natural language and may support patient education, research assistance, health communication, clinical documentation, information retrieval, translation, and decision-support communication [16].
Recent research has examined LLMs as potential digital companions for informed decision-making in obstetrics and gynecology (Recker et al., 2025) [17]. Nevertheless, LLMs can generate inaccurate or incomplete information and may lack complete clinical context. They should therefore function as supportive tools rather than autonomous clinical decision-makers.
PATIENT-CENTERED INNO
Innovation should begin with a clinical problem rather than with technology [18]. Patient-centered innovation should consider women’s preferences, accessibility, cultural appropriateness, health literacy, digital literacy, affordability, privacy, convenience, trust, and shared decision-making.
Human-centered research is increasingly important in digital health. A multipartner perinatal digital-health research agenda emphasized collaborative and human-centered approaches to identifying research priorities (Amhaz et al., 2025) [19]. Women should participate in design, testing, implementation, and evaluation of technologies intended for their healthcare.
DIGITAL HEALTH EQUITY
Technological innovation can reduce healthcare inequalities but may also increase them. The digital divide can affect women with limited access to smartphones, reliable internet, digital devices, digital literacy, financial resources, or culturally appropriate information [20].
The WHO has emphasized digital health literacy and engagement in the use of digital technologies for women’s health and empowerment (WHO Regional Office for Europe, 2024). Innovation should therefore reduce rather than reproduce existing health inequalities.
ETHICAL CONSIDERATIONS
Privacy and Data Protection
Women’s health data may include highly sensitive information concerning fertility, pregnancy, contraception, sexual health, reproductive history, genetic characteristics, and mental health [21]. Data protection should be incorporated into technology design from the beginning.
Algorithmic Bias
AI systems learn from datasets. If datasets do not adequately represent diverse populations, algorithms may perform differently across groups. Geographic and methodological gaps remain important issues in AI research in sexual and reproductive health (Mengistu et al., 2025) [22].
Transparency and Accountability
Patients and healthcare professionals should have appropriate information about when AI contributes to healthcare decisions. Responsibility for clinical decisions should remain clearly defined.
Human Oversight
AI should support professional judgment rather than replace the clinician–patient relationship. Responsible implementation requires professional training, ethical safeguards, and governance (Sengupta et al., 2025) [23].
THE ROLE OF NURSES IN WOMEN’S HEALTH INNOVATION
Nurses occupy a central position in women’s healthcare because they provide continuous contact across pregnancy, childbirth, postpartum care, reproductive health, chronic disease management, and health education.
- Identifying unmet patient needs.
- Participating in technology design.
- Educating women about digital tools.
- Supporting remote monitoring.
- Assessing usability and acceptability.
- Protecting patient privacy.
- Collecting high-quality clinical data.
- Conducting implementation research.
- Supporting shared decision-making.
- Evaluating patient outcomes.
Nursing research should therefore examine how technology affects patient experience, safety, equity, workload, and clinical outcomes [24].
FROM INNOVATION TO CLINICAL IMPLEMENTATION
A major gap in women’s health innovation is the transition from research to routine clinical practice. Many AI studies remain focused on model development and prediction rather than real-world implementation (Mengistu et al., 2025; Devoe et al., 2025) [25].
A clinically useful pathway can be represented as: Clinical problem → Research question → Innovation → Validation → Clinical evaluation → Implementation → Outcome assessment → Continuous improvement [26].
At every stage, researchers should evaluate accuracy, safety, clinical effectiveness, usability, patient acceptance, clinician acceptance, cost, equity, sustainability, and patient outcomes.
PROPOSED PRECISION WOMEN’S HEALTH INNOVATION FRAMEWORK
Based on the evidence reviewed, this article proposes a Precision Women’s Health Innovation Framework consisting of six interconnected domains.
Domain 1: Clinical Need
Identify a meaningful health problem affecting women, such as delayed diagnosis, maternal complications, infertility, cancer screening, chronic disease, or inadequate postpartum follow-up.
Domain 2: High-Quality Clinical Evidence
Develop and evaluate innovation using scientifically rigorous research and appropriate clinical evidence.
Domain 3: Technological Innovation
Apply appropriate technologies, including AI, machine learning, predictive analytics, telehealth, wearable devices, digital applications, and clinical decision-support systems.
Domain 4: Human-Centered Design
Include women, families, nurses, physicians, researchers, and other stakeholders in design and evaluation.
Domain 5: Ethical and Equitable Implementation
Address privacy, informed consent, transparency, algorithmic bias, accessibility, and digital equity [27].
Domain 6: Measurable Clinical Impact
Evaluate outcomes such as earlier diagnosis, reduced complications, quality of care, patient experience, access, disparities, and health outcomes.
Framework: Clinical Need → High-Quality Clinical Research → Technological Innovation → Human-Centered Design → Ethical & Equitable Implementation → Measurable Clinical Impact.
EVIDENCE-TO-INNOVATION MATRIX
|
Women’s Health Challenge |
Potential Innovation |
Potential Clinical Benefit |
Key Research Requirement |
|
Pre-eclampsia risk |
Machine-learning prediction |
Earlier identification of high-risk women |
Prospective external validation |
|
Preterm birth |
Predictive analytics |
Earlier risk assessment |
Multicenter validation |
|
Gestational diabetes |
AI-assisted prediction/remote monitoring |
Earlier intervention |
Clinical outcome evaluation |
|
Cervical cancer |
AI-assisted screening |
Improved detection |
Diverse population validation |
|
Infertility |
AI-assisted prediction/ART |
Treatment optimization |
Prospective clinical trials |
|
Menstrual health |
Digital applications |
Symptom monitoring and education |
Accuracy and usability |
|
Postpartum care |
Telehealth/remote monitoring |
Improved continuity of care |
Patient outcome studies |
|
Chronic disease |
Wearable monitoring |
Continuous health assessment |
Clinical integration studies |
|
Patient education |
LLM/digital platforms |
Improved access to information |
Safety and accuracy assessment |
|
Rural women’s health |
Telemedicine |
Improved access to specialists |
Equity and accessibility studies |
FUTURE RESEARCH PRIORITIES
Diverse Data
AI systems should be trained and tested using diverse populations. Geographic representation remains an important gap (Mengistu et al., 2025) [28].
External Validation
Models should be evaluated in populations and healthcare systems different from those used during development.
Prospective Studies
Future studies should increasingly use prospective designs to determine clinical effectiveness.
Implementation Science
Research should examine how to incorporate innovations into routine healthcare.
Patient Participation
Women should help identify research priorities and evaluate technological solutions.
Interdisciplinary Collaboration
Successful innovation requires collaboration among physicians, nurses, midwives, epidemiologists, data scientists, engineers, ethicists, policymakers, and patient representatives [29].
Equity-Oriented Research
Innovation should be evaluated according to whether it improves outcomes across socioeconomic and geographic populations.
DISCUSSION
The evidence demonstrates a rapid transformation in women’s health research. AI research has expanded across maternal health, reproductive cancers, fertility, diagnosis, screening, and clinical decision support (Mengistu et al., 2025) [30]. This expansion reflects AI’s capacity to analyze complex datasets and identify patterns that may be difficult to recognize using conventional approaches.
Maternal health is a particularly important application. AI models have been investigated for pre-eclampsia, preterm birth, gestational diabetes, fetal monitoring, and other outcomes (Devoe et al., 2025; Tadepalli et al., 2025). However, technical development is occurring faster than clinical implementation.
The future priority should therefore not simply be increasingly complex algorithms. Research should determine whether AI-assisted care produces better outcomes than current standards of care.
Digital health provides another opportunity. WHO evidence indicates that digital technologies may improve access to healthcare and health information while supporting women’s empowerment (WHO Regional Office for Europe, 2024) [31]. However, these benefits will not automatically reach all women. Equity should therefore be treated as a core outcome of innovation.
The proposed Precision Women’s Health Innovation Framework connects clinical need with evidence, innovation, human-centered design, ethical implementation, and measurable outcomes. AI should augment rather than eliminate clinical expertise; communication, empathy, contextual judgment, cultural understanding, and shared decision-making remain essential [32].
The author gratefully acknowledges the researchers, healthcare professionals, patients, and international organizations whose published work has contributed to the growing evidence base in women’s health, clinical research, artificial intelligence, and digital health. The author also acknowledges the editorial team for the opportunity to contribute to this topic.
DECLARATION
Ethics Approval
Not applicable. This manuscript is based on previously published literature and does not involve human participants or identifiable patient data.
CONSENT FOR PUBLICATION
Not applicable.
FUNDING
No specific funding was received for this manuscript.
CONFLICT OF INTEREST
The author declares no conflict of interest.
AUTHOR CONTRIBUTIONS
The author conceptualized the review, conducted the literature synthesis, developed the proposed framework, and prepared the manuscript.
DATA AVAILABILITY
No original dataset was generated or analyzed.
REFERENCES
- Aftab N. Artificial intelligence in obstetrics and Gynaecology: advancing precision and personalised care. Cureus. 2025 Jun 28;17(6). [Google Scholar] [PubMed]
- Amhaz H, Chen SX, Elchehimi A, Han KJ, Gil JM, Yao L, et al. The Research Agenda for Perinatal Innovation and Digital Health Project: Human-Centered Approach to Multipartner Research Agenda Codevelopment. JMIR Human Factors. 2025 Jan 30;12(1):e60825. [Google Scholar] [PubMed]
- Devoe LD, Muhanna M, Maher J, Evans MI, Klein-Seetharaman J. Current state of artificial intelligence model development in obstetrics. Obstetrics & Gynecology. 2025 Aug;146(2):233-43. [Google Scholar] [PubMed]
- Linder N, Nyirenda D, Mårtensson A, Kaingu H, Ngasala B, Lundin J. AI supported diagnostic innovations for impact in global women’s health. bmj. 2025 Oct 10;391. [Google Scholar] [PubMed]
- Mengistu S, Tamrat T, Betran AP, Pirsch S, Ferretti A, Mburu G, Alemu MB, Malpani R, Barreix M, Massonneau C, Zhao Y. The use of artificial intelligence in sexual and reproductive health: a comprehensive scoping review. npj Women's Health. 2025 Dec 18;3(1):70. [Google Scholar] [PubMed]
- Murrin EM, Saad AF, Sullivan S, Millo Y, Miodovnik M. Innovations in diabetes management for pregnant women: artificial intelligence and the internet of medical things. American journal of perinatology. 2025 Sep;42(12):1540-9. [Google Scholar] [PubMed]
- Recker F, Neubauer R, Wittek A, Scholten N. Large language models and women’s health: a digital companion for informed decision-making. Archives of gynecology and obstetrics. 2025 Sep;312(3):663-70. [Google Scholar] [PubMed]
- Sengupta, P., Dutta, S., Bagchi, S., Hegde, P., Sebastian, S., Taylor, D. C. M., & Henkel, R. (2025). Strategic guidelines to integrate artificial intelligence in obstetrics and gynecology: Best practices and ethical considerations. Journal of Assisted Reproduction and Genetics, 32(7), 2244–2251. [Google Scholar] [PubMed]
- Tadepalli, K., Das, A., Meena, T., & Roy, S. (2025). Bridging gaps in artificial intelligence adoption for maternal-fetal and obstetric care: Unveiling transformative capabilities and challenges. Computer Methods and Programs in Biomedicine, 263, 108682. [Google Scholar] [PubMed]
- Wu YC, Su EC, Hou JH, Lin CJ, Lin KB, Chen CH. Artificial intelligence and assisted reproductive technology: A comprehensive systematic review. Taiwanese journal of obstetrics and gynecology. 2025 Jan 1;64(1):11-26. [Google Scholar] [PubMed]
- World Health Organization. Global strategy on digital health 2020-2027. World Health Organization; 2025 Dec 1. [Google Scholar]
- World Health Organization. (2021). Ethics and governance of artificial intelligence for health. World Health Organization. [Google Scholar]
- Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nature medicine. 2019 Jan;25(1):44-56. [Google Scholar] [PubMed]
- Rajkomar A, Dean J, Kohane I. Machine learning in medicine. New England Journal of Medicine. 2019 Apr 4;380(14):1347-58. https://doi.org/10.1056/NEJMra1814259. [Google Scholar] [PubMed]
- Esteva A, Robicquet A, Ramsundar B, Kuleshov V, DePristo M, Chou K, et al. A guide to deep learning in healthcare. Nature medicine. 2019 Jan;25(1):24-9. [Google Scholar] [PubMed]
- Beam AL, Kohane IS. Big data and machine learning in health care. Jama. 2018 Apr 3;319(13):1317-8. [Google Scholar] [PubMed]
- Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nature medicine. 2019 Jan;25(1):44-56.[Google Scholar]
- Jiang F, Jiang Y, Zhi H, Dong Y, Li H, Ma S, et al. Artificial intelligence in healthcare: past, present and future. Stroke and vascular neurology. 2017 Dec;2(4):230-43. [Google Scholar] [PubMed]
- Shickel B, Tighe PJ, Bihorac A, Rashidi P. Deep EHR: a survey of recent advances in deep learning techniques for electronic health record (EHR) analysis. IEEE journal of biomedical and health informatics. 2017 Oct 27;22(5):1589-604. [Google Scholar] [PubMed]
- Miotto R, Wang F, Wang S, Jiang X, Dudley JT. Deep learning for healthcare: review, opportunities and challenges. Briefings in bioinformatics. 2018 Nov;19(6):1236-46. [Google Scholar] [PubMed]
- Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, et al. Dermatologist-level classification of skin cancer with deep neural networks. nature. 2017 Feb 2;542(7639):115-8. [Google Scholar] [PubMed]
- Sendak MP, D’Arcy J, Kashyap S, Gao M, Nichols M, Corey K, et al. A path for translation of machine learning products into healthcare delivery. EMJ Innov. 2020 Jan 27;10(1):1-4. [Google Scholar]
- Kelly CJ, Karthikesalingam A, Suleyman M, Corrado G, King D. Key challenges for delivering clinical impact with artificial intelligence. BMC medicine. 2019 Oct 29;17(1):195. https://doi.org/10.1186/s12916-019-1426-2. [Google Scholar] [PubMed]
- Vasey B, Nagendran M, Campbell B, Clifton DA, Collins GS, Denaxas S, et al. Reporting guideline for the early-stage clinical evaluation of decision support systems driven by artificial intelligence: DECIDE-AI. Nature medicine. 2022 May;28(5):924-33. [Google Scholar] [PubMed]
- Collins GS, Moons KG, Dhiman P, Riley RD, Beam AL, Van Calster B, et al. TRIPOD+ AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. bmj. 2024 Apr 16;385. [Google Scholar] [PubMed]
- Act EA. The eu artificial intelligence act. European Union. 2024 May. [Google Scholar]
- of Nurses IC. The ICN code of ethics for nurses. Nursing ethics. 2001 Jul;8(4):375-9. [Google Scholar] [PubMed]
- World Health Organization. Working for health 2022-2030 action plan. World Health Organization; 2022 Nov 30. [Google Scholar]
- World Health Organization. Health equity for persons with disabilities: guide for action. World Health Organization; 2024 Nov 7. [Google Scholar]
- United Nations Population Fund. (2024). State of world population 2024: Interwoven lives, threads of hope. UNFPA. [Google Scholar]
- World Health Organization. Annual report on monitoring progress on UHC and health-related SDGs. World Health Organization. Regional Office for South-East Asia; 2024 Sep 20. [Google Scholar]
- World Health Organization. Trends in maternal mortality 2000 to 2020: estimates by WHO, UNICEF, UNFPA, World Bank Group and UNDESA/Population Division. World Health Organization; 2023 Feb 22. [Google Scholar]