Empowering women through intelligent care: a narrative review of AI-driven digital innovations for endometriosis diagnosis, education, and equity

Background Endometriosis is a chronic, inflammatory, and multifactorial gynecological disorder affecting approximately 10% of women of reproductive age worldwide. It is associated with debilitating pelvic pain, infertility, and significant socioeconomic burden. Despite its impact, diagnosis is often delayed due to nonspecific symptoms and the absence of non- invasive biomarkers.

This narrative review critically examines the current landscape of artificial intelligence (AI) applications in endo- metriosis diagnosis, education, and management, identifies existing barriers to clinical integration, and proposes a strategic framework for the development of inclusive and ethical digital health ecosystems.

A narrative synthesis of peer-reviewed literature and technical reports was conducted, focusing on AI-enabled tools in reproductive health, endometriosis-specific applications, ethical guidelines for AI in healthcare, and regulatory frameworks. Comparative analysis of current FemTech solutions was also included.

Despite promising developments in AI-based symptom-tracking, imaging analysis, and decision support, significant barriers persist. These include technical limitations (small and biased datasets), clinical misalignment, ethical concerns (pri- vacy risks, bias amplification), and sociocultural challenges (digital divide, stigma). Current FemTech platforms demonstrate limited readiness to address the complex needs of endometriosis patients.

To fully realize AI’s transformative potential in endometriosis care, future efforts must prioritize participatory design, real-world data integration, transparency, inclusivity, and regulatory compliance. Endometriosis must be elevated within digital health equity agendas to ensure that technological innovations effectively address the lived experiences of women affected by this condition.

Endometriosis · Artificial Intelligence · Digital Health · Health Equity

Endometriosis is a chronic, inflammatory, estrogen-depend- ent disease characterized by the ectopic presence of endo- metrial-like tissue outside the uterine cavity, predominantly affecting pelvic organs. It impacts approximately 10% of women of reproductive age worldwide, leading to chronic pelvic pain, dysmenorrhea, dyspareunia, gastrointestinal dis- turbances, fatigue, and infertility [1, 2]. Beyond its physical manifestations, endometriosis exerts profound psychological, emotional, and socioeconomic bur- dens. Studies have demonstrated a heightened prevalence of anxiety, depression, social isolation, and diminished work - force participation among affected women [3 –5]. From an economic standpoint, the global costs associated with endo- metriosis, including healthcare expenditures and productiv- ity loss, are estimated to exceed billions of dollars annually [2]. Despite its significant prevalence and impact, endome- triosis remains poorly understood, frequently underdiag- nosed, and underprioritized in healthcare systems. Diag- nostic delays, averaging between seven and twelve years * Kelnner Portela Luz [email protected] 1 Health Education and Educational Technologies, Centro Universitário Christus (Unichristus), Fortaleza, Ceará, Brazil 2 Hospital Geral de Fortaleza (HGF), Fortaleza, Ceará, Brazil Journal of Medical Imaging and Interventional Radiology (2025) 12:15 15 Page 2 of 7 from symptom onset, are commonly attributed to nonspe - cific clinical presentations, the normalization of menstrual pain, fragmented care pathways, and the lack of non-invasive diagnostic biomarkers [5]. Artificial intelligence (AI), encompassing machine learn- ing, deep learning, and natural language processing (NLP), has emerged as a transformative force within healthcare. AI technologies demonstrate the ability to recognize complex patterns, predict clinical outcomes, and personalize care strategies. In the context of endometriosis, AI holds particu- lar promise for revolutionizing early detection, enhancing patient education, optimizing symptom management, and fostering patient-centered care pathways [6–8]. However, the clinical translation of AI in endometriosis remains at an early stage, confronting numerous technical, ethical, and sociocultural challenges. This review aims to critically evaluate the landscape of AI-driven innovations relevant to endometriosis care, analyze barriers to imple- mentation, and propose a strategic framework grounded in ethical governance, participatory design, and real-world validation to guide future developments. AI in reproductive and gynecological health Artificial intelligence (AI) technologies have increasingly permeated reproductive medicine and gynecology, offering innovative solutions for diagnosis, treatment optimization, and patient engagement. In obstetrics, AI-driven risk stratification models have been implemented to predict adverse outcomes, such as preeclampsia, preterm birth, and gestational diabetes, ena- bling earlier and more targeted interventions [7]. In gyneco- logic oncology, machine learning algorithms have enhanced the accuracy of early detection for ovarian, endometrial, and cervical cancers by interpreting imaging studies and bio- marker patterns with higher sensitivity than conventional

[9]. Deep learning, particularly through convolutional neural networks (CNNs), has substantially improved diagnostic performance in imaging modalities. Applications include the automated identification of ovarian cysts, uterine abnor- malities, and pelvic adhesions on ultrasound and magnetic resonance imaging (MRI) scans [10– 13]. In reproductive endocrinology, AI algorithms have been utilized to predict outcomes in in vitro fertilization (IVF) cycles, improving embryo selection and success rates. Natural language processing (NLP) techniques have facilitated the extraction of patient-reported symptoms from unstructured clinical narratives, enhancing the detection of underdocumented conditions, such as chronic pelvic pain and menstrual disorders [14]. Mobile health applications powered by machine learning have empowered users to track menstrual cycles, monitor fertility windows, and log gynecological symptoms. How - ever, despite the proliferation of FemTech solutions, few platforms are specifically designed to address the complex and heterogeneous symptomatology of endometriosis. Most tools lack condition-specific algorithms, real-world valida- tion, or ethical design frameworks that prioritize the needs of women living with chronic gynecological conditions [15, 16]. Thus, although AI has demonstrated considerable prom- ise across reproductive health domains, its targeted appli- cation to endometriosis remains limited, highlighting a critical opportunity for innovation tailored to this complex condition. Barriers to implementation in endometriosis care Despite the promising potential of artificial intelligence (AI) applications in endometriosis care, several interrelated bar - riers currently impede their clinical translation and large- scale deployment. These barriers can be categorized into technical, clinical, ethical and regulatory, and sociocultural domains. Technical barriers The development of robust AI models depends heavily on the availability of large, diverse, and well-annotated datasets. However, in endometriosis research, datasets are often: • Small and fragmented, typically derived from single institutions or specific demographic groups; • Heterogeneous in diagnostic criteria and outcome meas- ures, hindering standardization and model interoperabil- ity; • Lacking longitudinal data, which limits predictive mod- eling for disease progression and treatment outcomes. Moreover, interoperability challenges among electronic health record (EHR) systems restrict the integration of mul- timodal datasets encompassing clinical, imaging, symptom- tracking, and genomic information, all of which are essential for dynamic AI-driven personalization [6, 17]. Model generalizability remains a critical concern, with most algorithms trained and validated on homogeneous populations. This raises significant issues regarding perfor- mance disparities across different racial, ethnic, and socio- economic groups. Journal of Medical Imaging and Interventional Radiology (2025) 12:15 Page 3 of 7 15 Clinical barriers Successful clinical adoption of AI technologies requires seamless integration into existing healthcare workflows and alignment with clinical decision-making processes. Key barriers include: • Disruption of traditional workflows: AI solutions often lack alignment with the realities of clinical practice, resulting in poor usability and clinician resistance [18]; • Skepticism and trust deficits among clinicians: Black box algorithms with limited explainability erode clini- cian confidence in AI-generated outputs [19]; • Scarcity of prospective validation studies: Few AI applications in gynecology, particularly for endome- triosis, have undergone rigorous prospective clinical trials, hindering evidence-based adoption into guide- lines [20]. Additionally, the multidisciplinary nature of endome- triosis management, encompassing gynecology, radiology, pain medicine, mental health, and physiotherapy, neces - sitates AI systems capable of integrating and coordinating across specialties. Ethical and regulatory barriers Ethical challenges are paramount in deploying AI solu- tions for sensitive health domains such as endometriosis. Major concerns include: • Privacy and data security risks: Endometriosis-related data often involve intimate details about reproductive and sexual health, necessitating stringent privacy pro- tections [4 , 21]; • Algorithmic bias and inequities: AI models trained on non-representative datasets risk perpetuating or exac- erbating existing healthcare disparities [22]; • Opacity and accountability gaps: Without transparent decision-making and clear accountability mechanisms, patients may face difficulty contesting erroneous AI- driven recommendations. Regulatory frameworks, including the United States Food and Drug Administration (FDA) guidance on Soft- ware as a Medical Device (SaMD), Brazil’s Lei Geral de Proteção de Dados (LGPD), and the European Union’s General Data Protection Regulation (GDPR), mandate transparency, consent, and post-market surveillance. How - ever, specific regulatory pathways tailored to AI applica- tions in gynecology remain underdeveloped [23– 25]. Sociocultural and educational barriers Sociocultural dynamics profoundly influence the adoption and effectiveness of digital health innovations. In the context of endometriosis: • The digital divide remains a significant barrier, with women in low-resource settings having limited access to AI-driven healthcare tools [26]; • Health literacy gaps impact the ability to interpret AI outputs and engage with digital health technologies; • Cultural stigmas surrounding menstruation and chronic pelvic pain contribute to diagnostic delays and may inhibit patient engagement with symptom-tracking tech- nologies [27]. Furthermore, many AI applications are developed without adequate participatory input from diverse patient popula- tions, resulting in culturally insensitive designs, inaccessible interfaces, and unmet user needs [16]. Comparative analysis: FemTech and AI frameworks The rapid expansion of FemTech, technologies focused on women's health, has generated numerous mobile applica - tions and digital platforms addressing menstruation, fertility, and pregnancy management. However, a critical evaluation reveals that relatively few FemTech solutions specifically target the complex and heterogeneous needs of women with endometriosis. Table  1 presents a comparative overview of selected FemTech platforms with relevance to gynecological health, evaluating their primary focus, integration of artificial intel- ligence, specificity to endometriosis, regulatory validation, and ethical safeguards. Key observations include: • Most mainstream FemTech apps (e.g., Flo Health, Sympto) focus primarily on general menstrual or fertil- ity tracking and are not specifically tailored to the diverse symptom profiles of endometriosis; • Few initiatives, such as EndoMind (hypothetical), directly target endometriosis symptom triage through AI-driven models; • Regulatory readiness varies significantly, with few plat- forms achieving the certifications necessary for clinical- grade deployment, such as FDA clearance or CE mark - ing; • Ethical, privacy, and data protection standards are incon- sistently applied across platforms, raising concerns about user data vulnerabilities. Journal of Medical Imaging and Interventional Radiology (2025) 12:15 15 Page 4 of 7 This analysis highlights the urgent need for dedicated, ethically designed, and clinically validated AI platforms spe- cifically addressing the fluctuating and multifactorial nature of endometriosis. Toward a strategic framework for AI in endometriosis To fully harness the transformative potential of Artificial Intelligence (AI) in endometriosis care, it is imperative to transition from isolated algorithmic solutions to integrated, adaptive, and ethically governed digital health ecosystems. Based on the current literature and critical gaps identified, we propose a strategic framework composed of five core pillars: Participatory co‑design AI solutions must be co-developed with active engagement of women living with endometriosis, multidisciplinary clini- cians, ethicists, and advocacy groups. Participatory design ensures that innovations are: • Aligned with real-world patient needs and lived experi- ences; • Culturally, socially, and economically sensitive; • Usable, accessible, and empowering across diverse user populations. Continuous involvement of end-users throughout design, testing, and implementation phases is essential to foster relevance, usability, and trust. Real‑world data integration Effective AI solutions require longitudinal, multimodal data- sets encompassing: • Clinical records (diagnoses, imaging, treatments); • Patient-reported outcomes (e.g., pain diaries, quality of life metrics); • Data from symptom-tracking apps and wearable devices. Integrating structured and unstructured real-world data enables dynamic personalization, predictive modeling, and a holistic understanding of disease trajectories. Personalized educational modules AI-powered educational platforms should adapt content delivery according to: • Literacy level; • Cultural background; • Health knowledge; • Emotional readiness of the user. Through behavioral analytics and recommendation systems, content can be dynamically tailored to optimize patient comprehension, self-efficacy, and therapeutic adherence. Virtual psychosocial support Given the significant psychosocial burden of endometriosis, AI solutions must embed mental health support, including: • Conversational agents delivering empathetic responses and evidence-based coping strategies; • Mindfulness exercises and cognitive–behavioral therapy (CBT) modules; • Peer support facilitation within safe, moderated digital communities. Such features can enhance psychologi- cal resilience, reduce isolation, and complement formal healthcare services. Ethical AI design Ethical considerations must be embedded throughout the AI lifecycle, adhering to the frameworks outlined by: Table 1 Comparative analysis of FemTech platforms relevant to endometriosis care *Hypothetical model based on AI-driven symptom-tracking principles Platform/App Primary focus AI integration Specificity to endome- triosis Clinical/regulatory validation Ethical and privacy practices Flo health Menstrual cycle/fertility Yes (machine learning) No No FDA/CE certifica- tion Standard policy; potential sensitive data risks Clue Menstrual health Yes (predictive algo- rithms) Partial (menstrual symptoms) No FDA/CE certifica- tion Good practices; lacks independent audits Sympto Natural contraception No No No clinical validation Unclear Endomind* Endometriosis symp- tom triage Yes (AI-based triage model) Yes (dedicated focus) Conceptual proposal Ethically designed from inception Natural cycles Fertility/contraception Yes (probabilistic models) No FDA approved Rigorous privacy policy Journal of Medical Imaging and Interventional Radiology (2025) 12:15 Page 5 of 7 15 • World Health Organization (WHO); • United Nations Educational, Scientific and Cultural Organization (UNESCO); • European High-Level Expert Group on Artificial Intel- ligence (EU HLEG) [4 , 5, 21]. Core ethical principles include: • Transparency and explainability of AI outputs; • Ongoing bias detection and mitigation; • Informed consent and robust data protection; • Clear accountability mechanisms for adverse outcomes. Building ethical AI is essential not only for compliance but also for establishing societal trust and maximizing long- term impact. Expanded discussion and implications While Artificial Intelligence (AI) offers unprecedented opportunities to improve endometriosis care, its develop - ment, deployment, and evaluation must be critically exam- ined through ethical, regulatory, and sociocultural lenses to ensure that innovations promote health equity rather than exacerbate existing disparities. Ethical priorities for AI in endometriosis Ethical deployment of AI in sensitive health domains like endometriosis demands strict adherence to principles of transparency, justice, beneficence, and respect for patient autonomy. Key ethical imperatives include: • Transparency and Explainability: AI models must pro- duce outputs interpretable by both clinicians and patients. Black box algorithms compromise trust and impede informed decision-making; • Bias Mitigation: AI systems must undergo regular audit- ing to detect and mitigate biases related to race, ethnicity, socioeconomic status, and geography. Without deliber - ate correction, healthcare disparities may be perpetuated [22]; • Informed Consent and Data Governance : Patients must maintain control over their personal data, supported by explicit, clear, and understandable consent processes that specify how data are used, stored, and shared; • Accountability Mechanisms: Clear pathways must exist to assign responsibility for AI-driven decisions and potential adverse outcomes. Oversight structures, exter - nal audits, and real-time monitoring can enhance system accountability. International frameworks, such as the WHO Guidance on Ethics and Governance of AI for Health [5], UNESCO’s Recommendations on the Ethics of AI [4], and the EU HLEG Ethics Guidelines for Trustworthy AI [21], provide essential foundations that must guide all AI innovations in endome - triosis care. Bridging the Digital Divide and Future Directions If not deliberately addressed, digital health innovations risk amplifying existing inequities, particularly among underserved populations. Key strategies to bridge the digital divide include: • Infrastructure Development: Design AI tools that are mobile-compatible, offline-capable, and functional in low- bandwidth environments to ensure broad accessibility; • Cultural and Linguistic Adaptation: Develop multi- lingual, culturally sensitive platforms that resonate with diverse populations. Participatory design involving target communities can surface critical contextual factors; • Enhancing Digital Health Literacy: Implement educa- tional initiatives aimed at empowering users to engage meaningfully with AI-driven health tools and interpret outputs accurately; • Community Engagement and Trust Building: Foster collaborations with community leaders, advocacy organi- zations, and patient groups to enhance credibility, trust, and uptake. Future research directions • Hybrid Effectiveness-Implementation Studies: Evalu- ate both clinical efficacy and real-world feasibility of AI interventions across diverse healthcare settings; • Dynamic Consent Models : Innovate patient consent processes to accommodate evolving AI applications and secondary uses of health data; • Global Health Equity Frameworks: Position endome- triosis within broader global digital health equity initia- tives, ensuring that innovations do not reinforce struc- tural exclusions. By proactively addressing these ethical and structural challenges, AI can transition from a promising technol- ogy to a catalyst for meaningful, sustainable, and equitable improvements in endometriosis care. Key recommendations for implementation To ensure that Artificial Intelligence (AI) fulfills its trans- formative potential in endometriosis care while upholding ethical principles and advancing health equity, we propose the following strategic recommendations: Journal of Medical Imaging and Interventional Radiology (2025) 12:15 15 Page 6 of 7 1. Foster Participatory Development • Actively engage women living with endometriosis, multidisciplinary clinicians, developers, and advocacy groups throughout all stages of AI development; • Maintain continuous feedback loops to refine AI tools based on real-world user experiences, ensuring rel- evance, accessibility, and trust. 2. Mandate Algorithm Auditing and Explainability • Require routine bias audits of AI models, particularly regarding training datasets and predictive outputs; • Prioritize the development of interpretable models (e.g., attention-based networks, explainable decision trees) that allow clinicians and patients to understand and question AI recommendations. 3. Ensure Real-World Validation • Conduct prospective, multicenter clinical trials to eval- uate AI system performance under real-world condi- tions; • Integrate implementation science frameworks to assess usability, adoption rates, sustainability, and equity impacts alongside traditional clinical outcomes. 4. Strengthen Regulatory Oversight • Advocate for AI-specific extensions to existing regu- latory frameworks (e.g., FDA, EMA, ANVISA) to address dynamic algorithm updates, transparency requirements, and long-term risk monitoring; • Mandate post-market surveillance and public reporting mechanisms for AI-related adverse events. 5. Design Inclusive, Offline-Capable Platforms • Ensure that AI tools are accessible in low-bandwidth environments and compatible with widely available mobile devices; • Tailor digital interfaces and educational modules to accommodate different literacy levels, cultural back- grounds, and user abilities. By systematically implementing these recommendations, stakeholders can create a responsible and patient-centered AI ecosystem that advances early diagnosis, personalized man- agement, and psychosocial support for women living with endometriosis, while safeguarding against unintended harms.

Artificial Intelligence (AI) holds unprecedented potential to transform the landscape of endometriosis diagnosis, education, and management. Through advanced pattern recognition, predictive analytics, and personalized educa - tional pathways, AI can address longstanding challenges including diagnostic delays, fragmented care pathways, and limited patient empowerment. However, the realization of this potential is not automatic. It requires confronting and overcoming substantial technical, clinical, ethical, and sociocultural barriers. Without deliber- ate attention to inclusivity, transparency, and participatory development, AI innovations risk reinforcing—rather than mitigating—existing inequities in endometriosis care. Global health authorities, policymakers, researchers, and technology developers must recognize endometriosis as a significant public health and equity challenge within the broader landscape of digital health innovation. Strategic investments in ethical governance frameworks, real-world validation studies, culturally adaptive platforms, and inclu- sive digital infrastructures are critical. Future research must prioritize hybrid effective- ness–implementation studies that assess not only clinical efficacy but also usability, sustainability, and impact across diverse settings. Additionally, regulatory bodies must evolve to ensure that AI-driven solutions are accountable, explainable, and responsive to patients' rights and societal expectations. Harnessing the power of AI to revolutionize endometrio- sis care is not merely a technological endeavor; it is a moral imperative. By centering the experiences, needs, and voices of women living with endometriosis, we can transform inno- vation into tangible improvements in health, dignity, and quality of life worldwide. Author contributions Kelnner Portela Luz conceptualized and designed the study, conducted the literature review, performed the com- parative analysis, and drafted the manuscript. The author approved the final version and is accountable for all aspects of the work. Funding This study received no external funding. Availability of data and materials Not applicable. No new datasets were generated or analyzed for this study. Declarations Conflict of interest The author declares no conflicts of interest. Ethics approval and consent to participate Not applicable. This manu- script is a narrative review and does not involve human participants, data, or material requiring ethical approval. Consent for publication Not applicable. Open Access This article is licensed under a Creative Commons Attri- bution 4.0 International License, which permits use, sharing, adapta- tion, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are Journal of Medical Imaging and Interventional Radiology (2025) 12:15 Page 7 of 7 15 included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http:// creat iveco mmons. org/ licen ses/ by/4. 0/.

1. Zondervan KT, Becker CM, Missmer SA (2020) Endometriosis. N Engl J Med 382(13):1244–1256 2. Dunselman GAJ, Vermeulen N, Becker C et al (2014) ESHRE guideline: management of women with endometriosis. Hum Reprod 29(3):400–412 3. Pereira RM, Motta F (2022) Diagnostic barriers in endometriosis: a narrative review. Rev Bras Ginecol Obstet 44(1):56–63 4. United Nations Educational, Scientific and Cultural Organization (UNESCO) (2022) Recommendation on the Ethics of Artificial Intelligence. UNESCO, Paris 5. World Health Organization (WHO) (2021) Ethics and Govern- ance of Artificial Intelligence for Health: WHO Guidance. WHO, Geneva 6. Esteva A, Robicquet A, Ramsundar B et al (2019) A guide to deep learning in healthcare. Nat Med 25(1):24–29 7. Topol EJ (2019) High-performance medicine: the convergence of human and artificial intelligence. Nat Med 25(1):44–56 8. He H, Zhang Y, Zhang R et al (2023) Application of artificial intelligence in the diagnosis and prediction of endometriosis. Front Med (Lausanne) 10:1172845 9. Ferroni P, Zanzotto FM, Scatena R et al (2019) Artificial intel- ligence for cancer diagnosis and prognosis: a systematic review. J Clin Med 8(8):1015 10. Kaur A, Saini A, Saggar K (2022) Artificial intelligence in obstetrics and gynecology: Friend or foe? Obstet Gynecol Sci 65(3):207–217 11. Chen R, Lu X, Zhang Y (2020) Mining clinical narratives for patient-reported symptoms of endometriosis using natural lan- guage processing. J Biomed Inform 108:103499 12. Sittig DF, Singh H (2010) A new sociotechnical model for study- ing health information technology in complex adaptive healthcare systems. Qual Saf Health Care 19(Suppl 3):i68-74 13. Thiers FA, Gaspar J, Oliveira R et al (2022) Deep learning for detection of endometriotic lesions in MRI: a preliminary study. Comput Biol Med 146:105589 14. Obermeyer Z, Emanuel EJ (2016) Predicting the future—big data, machine learning, and clinical medicine. N Engl J Med 375(13):1216–1219 15. Goodman KW (2015) Ethics, medicine, and information technol- ogy: intelligent machines and the transformation of health care. Cambridge University Press, Cambridge 16. Fiske A, Henningsen P, Buyx A (2019) Your robot therapist will see you now: ethical implications of embodied artificial intelli- gence in mental health care. J Med Internet Res 21(5):e13216 17. Morley J, Luciano F (2021) A framework for the ethical impact assessment of artificial intelligence. Nat Mach Intell 3(2):89–94 18. Fjeld J, Achten N, Hilligoss H et al (2020) Principled artificial intelligence: mapping consensus in ethical and rights-based approaches. Berkman Klein Center Research Publication, Cambridge 19. Khullar D (2019) Building a smarter health care system with arti- ficial intelligence. JAMA 321(22):2151–2152 20. Mittelstadt BD, Floridi L (2016) The ethics of big data: current and foreseeable issues in biomedical contexts. Sci Eng Ethics 22(2):303–341 21. European Commission (2019) Ethics guidelines for trustworthy AI. High-level expert group on artificial intelligence. European Commission, Brussels 22. Serra MF (2021) Descomplicando a perícia psiquiátrica no con- texto trabalhista: uma proposta de sistematização na análise do nexo. Perspect Med Legal Perícias Méd 6:e210814 23. U.S. Food and Drug Administration (FDA) (2021) Artificial Intel- ligence and Machine Learning in Software as a Medical Device 24. Brasil. Lei Geral de Proteção de Dados Pessoais – LGPD. Lei nº 13.709, de 14 de agosto de 2018 25. European Union. General Data Protection Regulation (GDPR). Regulation (EU) 2016/679 26. Mehedintu C, Plotogea MN, Ionescu S et al (2014) Endometriosis still a challenge. J Med Life 7(3):349–357 27. MyEndometriosisTeam. Available from: https:// www. myend ometr iosis team. com/ Publisher's Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.