Endometriosis Pain Index: development of a model to predict poor pain-related quality of life after endometriosis surgery through machine learning analysis of registry data

Dwayne Tucker; Brie Dungate; Derek S. Chiu; Heather L Noga; Caroline Lee; Mohamed A Bedaiwy; Christina Williams; Catherine Allaire; Aline Talhouk; Paul J. Yong

doi:10.1097/j.pain.0000000000003915

Endometriosis Pain Index: development of a model to predict poor pain-related quality of life after endometriosis surgery through machine learning analysis of registry data

Dwayne Tucker, Brie Dungate, Derek S. Chiu, Heather L Noga, Caroline Lee, Mohamed A Bedaiwy, Christina Williams, Catherine Allaire, Aline Talhouk, Paul J. Yong

Pain · 2026 · vol. 167(5) , pp. 1026–1039 · doi:10.1097/j.pain.0000000000003915 · PMID:41746699

other OA: hybrid CC-BY-NC-ND-4.0

🔓 Open OA copy Full text JSON View on PubMed View at publisher

⚙ AI-generated summary by claude@2026-06, 2026-06-09 ⓘ

This study developed and validated a machine learning model using registry data that predicts poor pain-related quality of life after endometriosis surgery based on 10 preoperative factors.

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, 2026-06-09 · read from full text ⓘ

This study developed and internally validated a machine learning clinical prediction model (the Endometriosis Pain Index) to forecast poor pain-related quality of life 1–2 years after endometriosis surgery. Using registry data from a prospective longitudinal tertiary cohort (EPPIC; 2013–2020), 650 participants completed the EHP-30 pain subscale at baseline and follow-up, and poor outcome was defined as pain subscale scores above the North American 75th percentile; 32 preoperative candidate predictors were reduced to the 10 most important for the best-performing random forest model, which showed similar discrimination in training and held-out test cohorts (AUC ~0.768 vs ~0.766). The paper reports internal validation via bootstrapping and a test split but does not claim external validation, and it also uses registry data from a single tertiary referral setting. This paper is centrally about endometriosis — it creates and validates the Endometriosis Pain Index to predict poor postoperative pain-related quality of life after endometriosis surgery.

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

Abstract

Predictive tools are lacking for pain-related outcomes after endometriosis surgery. The objective of this study was to develop and validate a machine learning-based clinical model to predict poor pain-related quality of life after endometriosis surgery. Registry data from a prospective longitudinal cohort at a tertiary referral center (2013-2020) was used for model development and validation. Participants underwent an index endometriosis surgery, and completed the pain subscale of the Endometriosis Health Profile-30 (EHP-30) at baseline and 1-2-year follow-up. The outcome was poor pain-related quality of life defined as EHP-30 pain subscale above the 75th percentile for North America, at 1 to 2 years postsurgery. Thirty-two preoperative factors were evaluated, with final models retaining the top 10 most important predictors. Elastic net logistic regression, random forest (RF) and multilayer perceptron neural network models were developed. Internal validation was performed using 500 bootstrap samples, and a held-out test cohort. The study included 650 participants: 488 in the training cohort and 162 in a held-out test cohort. The RF model exhibited the most consistent discrimination, measured by the area under the receiver operating characteristic curve, between the training cohort (0.768; 95% CI: 0.690-0.837) and test cohort (0.766; 95% CI: 0.676-0.863, Δ = -0.002). The RF model also demonstrated the best integrated calibration index (0.029) and highest net benefit. Final preoperative predictors for the RF model included baseline EHP-30 score, surgery type (conservative fertility-sparing vs hysterectomy), anxiety scores, depression scores, pain catastrophizing scale scores, abdominal wall pain, pelvic floor myalgia, smoking status, back pain, and race/ethnicity. We present the RF model as the Endometriosis Pain Index to aid preoperative counselling for endometriosis surgery.

Full text 43,220 characters · extracted from oa-html · 2 sections · click to expand

Acknowledgements

Author contributions: D.R.T. and P.J.Y. had access to all the data in the study and take responsibility for the integrity of the data and the accuracy of the data analysis. Concept and design: P.J.Y., A.T., D.R.T., M.A.B., C.A., C.W. Acquisition, analysis, or interpretation of data: All authors. Drafting of manuscript: D.R.T., P.J.Y. Critical review of the manuscript for important content: All authors. Statistical analysis: D.R.T., A.T., D.S.C., B.D. Funding: P.J.Y., M.A.B., C.A., A.T. Administrative, technical, or material support: H.N., P.J.Y., M.A.B., C.A., C.L., C.W., D.R.T. Supervision: A.T., P.J.Y. All authors were involved in reviewing, editing, and final approval of the manuscript; and agree to be accountable for all aspects of the work. This study was funded by Canadian Institutes of Health Research (CIHR) project grant (PGT-183713 and PJT-156084). P.J.Y. was supported by a Health Professional Investigator award from the Michael Smith Health Research BC, Canada, and is supported a Canada Research Chair (Tier 2) in Endometriosis and Pelvic Pain (this research was undertaken, in part, thanks to funding from the Canada Research Chairs Program). D.R.T. was supported by a Graduate Award in Women's Health from the BC Women's Health Research Institute/BC Women's Health Foundation. Role of the funder/sponsor: The sponsors did not play any role in the study design; in the collection, analysis, and interpretation of data; in the writing of the report; and in the decision to submit the article for publication. Additional contributions: The authors thank the participants for their contribution to this work and the clinical staff at the BC Women's Hospital and Health Centre and the BC Centre for Pelvic Pain and Endometriosis. Permission for use of the EHP-30 pain subscale was obtained from Oxford University Innovation.

References

Endometriosis; Clinical modelling; Pelvic pain; Surgery; Machine learning; Quality of life

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

EHP-30

Condition tags

endometriosis

MeSH descriptors

Endometriosis Endometriosis Endometriosis Endometriosis Endometriosis Endometriosis Endometriosis Endometriosis Endometriosis Endometriosis Endometriosis Machine Learning Machine Learning Machine Learning Machine Learning Machine Learning Machine Learning Machine Learning Machine Learning Pain Measurement

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2026) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.

Source provenance

europepmc: last seen: 2026-06-11T06:19:48.454388+00:00
pubmed: last seen: 2026-05-18T00:30:19.791150+00:00
unpaywall: last seen: 2026-05-11T08:34:28.763810+00:00

License: CC-BY-NC-ND-4.0 · commercial use OK · attribution required
Courtesy of the U.S. National Library of Medicine