Real-World Pilot of EndoConnect: A Digital Health Platform for Endometriosis Education, Symptom Management, and Ethical AI-Assisted Triage in Brazilian Primary Care – A Formative Study and Proposal of the NAM-Endora Framework for Bias Mitigation and Health Equity in LMICs (Preprint)

Kelnner Portela Luz, Danilo Lopes Ferreira Lima
2025 · doi:10.2196/preprints.89464 · W4417311924
article OA: gold CC0
🔓 Open OA copy Full text JSON View on OpenAlex View at publisher
⚙ AI-generated summary by claude@2026-06, 2026-06-07 ⓘ

The EndoConnect platform showed excellent usability and engagement, improving pain, adherence, knowledge, and anxiety while reducing diagnostic delays in Brazilian primary care, and a new ethical AI framework was proposed.

One-sentence paraphrase of the abstract; not a substitute for reading it. No clinical advice. How this works

⚙ AI-generated deep summary by claude@2026-06, 2026-06-07 · read from full text ⓘ

This formative pilot study developed and deployed EndoConnect Alpha, an offline-capable digital health platform for endometriosis education, symptom tracking, moderated community support, and privacy-by-design AI-assisted tele-ultrasound triage in Brazilian SUS primary care units in Ceará, enrolling 60 participants (45 women aged 18–45 with suspected/confirmed endometriosis and 15 primary care professionals) over 8 weeks. Using usability (System Usability Scale), acceptability (Technology Acceptance Model), engagement analytics, and pre/post outcomes including pelvic pain VAS, EKES-15 knowledge, GAD-7 anxiety, adherence, and referral rate, the authors found high usability and acceptability (mean SUS 88.9; TAM 91.4%) alongside improvements in pain, knowledge, anxiety, adherence, and referral rates, with the largest benefits in rural and historically underserved subgroups. A key limitation is the formative, quantitative cross-sectional design with a small sample and lack of a clinical trial framework (trial not applicable), limiting causal inference about clinical impacts. This paper is centrally about endometriosis—feasibility and equity impacts of the EndoConnect platform and its NAM-Endora ethical AI governance framework in Brazilian primary care.

Read from the paper's body, not the abstract. Not a substitute for reading the paper. No clinical advice. How this works

Abstract

BACKGROUND Endometriosis affects ≈10% of reproductive-age women worldwide (≈190 million) and is marked by debilitating chronic pain and infertility. In Brazil’s public health system (SUS), diagnostic delays average 7–10 years, disproportionately affecting low-income, rural, Black, and Indigenous women. OBJECTIVE This formative study aimed to (1) develop and deploy EndoConnect Alpha—an offline-capable progressive web app integrating evidence-based education, symptom tracking, moderated community support, and privacy-by-design AI-assisted tele-ultrasound triage—in SUS primary care units in Ceará, Brazil; (2) evaluate usability, acceptability, engagement, and preliminary clinical-psychosocial impact; and (3) propose the NAM-Endora Framework for ethical AI governance in low- and middle-income countries (LMICs). METHODS Applied methodological study with quantitative cross-sectional formative design (January 2024–November 2025). After expert validation and software registration (INPI BR5120250005556-0), 60 participants (45 women aged 18–45 years with suspected/confirmed endometriosis and 15 primary care professionals) were recruited from 10 SUS units (60% rural). Usability (System Usability Scale), acceptability (Technology Acceptance Model), engagement (Firebase Analytics), and pre/post outcomes (pain VAS, EKES-15 knowledge, GAD-7 anxiety, adherence, referral rate) were assessed over 8 weeks. Ethics approval: CAAE 82094924.8.0000.5049. RESULTS Mean SUS score 88.9 ± 9.8 (excellent); TAM 91.4%. Trail completion 79%; mean daily use 17.2 minutes. Significant improvements: pelvic pain −23% (P=.02), adherence +17% (P=.01), knowledge +21% (P<.001), anxiety −14% (P=.04), referrals +15% (P=.04). Largest benefits observed in rural, low-education, Black/Brown/Indigenous subgroups. The NAM-Endora Framework is proposed as the first LMIC-tailored ethical AI governance model. CONCLUSIONS EndoConnect Alpha is feasible and equity-enhancing in SUS primary care. The NAM-Endora Framework provides a novel, replicable model for responsible AI deployment in LMICs, with potential to reduce the global burden of endometriosis. CLINICALTRIAL Not applicable
Full text 3,203 characters · extracted from oa-html · 5 sections · click to expand

Abstract

Background: Endometriosis affects ≈10% of reproductive-age women worldwide (≈190 million) and is marked by debilitating chronic pain and infertility. In Brazil’s public health system (SUS), diagnostic delays average 7–10 years, disproportionately affecting low-income, rural, Black, and Indigenous women.

Objective

This formative study aimed to (1) develop and deploy EndoConnect Alpha—an offline-capable progressive web app integrating evidence-based education, symptom tracking, moderated community support, and privacy-by-design AI-assisted tele-ultrasound triage—in SUS primary care units in Ceará, Brazil; (2) evaluate usability, acceptability, engagement, and preliminary clinical-psychosocial impact; and (3) propose the NAM-Endora Framework for ethical AI governance in low- and middle-income countries (LMICs).

Methods

Applied methodological study with quantitative cross-sectional formative design (January 2024–November 2025). After expert validation and software registration (INPI BR5120250005556-0), 60 participants (45 women aged 18–45 years with suspected/confirmed endometriosis and 15 primary care professionals) were recruited from 10 SUS units (60% rural). Usability (System Usability Scale), acceptability (Technology Acceptance Model), engagement (Firebase Analytics), and pre/post outcomes (pain VAS, EKES-15 knowledge, GAD-7 anxiety, adherence, referral rate) were assessed over 8 weeks. Ethics approval: CAAE 82094924.8.0000.5049.

Results

Mean SUS score 88.9 ± 9.8 (excellent); TAM 91.4%. Trail completion 79%; mean daily use 17.2 minutes. Significant improvements: pelvic pain −23% (P=.02), adherence +17% (P=.01), knowledge +21% (P<.001), anxiety −14% (P=.04), referrals +15% (P=.04). Largest benefits observed in rural, low-education, Black/Brown/Indigenous subgroups. The NAM-Endora Framework is proposed as the first LMIC-tailored ethical AI governance model.

Conclusions

EndoConnect Alpha is feasible and equity-enhancing in SUS primary care. The NAM-Endora Framework provides a novel, replicable model for responsible AI deployment in LMICs, with potential to reduce the global burden of endometriosis. Clinical Trial: Not applicable Citation Request queued. Please wait while the file is being generated. It may take some time. Copyright © The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.

Text is read by the "Ask this paper" AI Q&A widget below. Extraction quality varies by source — PMC NXML preserves structure cleanly, OA-HTML may include some navigation residue, and OA-PDF can have broken hyphenation. The publisher copy (via DOI) is the canonical version.

My notes (saved in your browser only)

⚙ Ask this paper AI returns verbatim quotes from the full text · source: oa-html ⓘ

Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works

Outcome instruments

VAS-pain

Condition tags

endometriosisinfertility

Citation neighborhood (sparse)

Too few in-corpus citations on either side for a chart; here are the lists.

Cites (3)

References (11)

Source provenance

openalex
last seen: 2026-06-10T17:14:06.276822+00:00
License: CC0 · commercial use OK