Development and Validation of Clinical Prediction Models for Surgical Success in Patients With Endometriosis: Protocol for a Mixed Methods Study
Bibliographic record
Abstract
BACKGROUND: Endometriosis is a chronic inflammatory condition affecting 6%-10% of women of reproductive age and is defined by the presence of endometrial-like tissue outside the uterus (lesions), commonly affecting the pelvis and ovaries. It is associated with debilitating pelvic pain, infertility, and fatigue and often has devastating effects on the quality of life (QoL). Although it is as common as back pain, it is poorly understood, and treatment and diagnosis are often delayed, leading to unnecessary suffering. Endometriosis has no cure. Surgery is one of several management options. Quantifying the probability of successful surgery is important for guiding clinical decisions and treatment strategies. Factors predicting success through pain reduction after endometriosis surgery have not yet been adequately identified. OBJECTIVE: This study aims to determine which women with confirmed endometriosis benefit from surgical improvement in pain and QoL and whether these women could be identified from clinical symptoms measured before laparoscopy. METHODS: First, we will carry out a systematic search and review and, if appropriate, meta-analysis of observational cohort and case-control studies reporting one or more risk factors for endometriosis and postsurgical treatment success. We will search PubMed, Embase, and Cochrane databases from inception without language restrictions and supplement the reference lists by manual searches. Second, we will develop separate clinical prediction models for women with confirmed and suspected diagnoses of endometriosis. A total of three suitable databases have been identified for development and external validation (the MEDAL [ISRCTN13028601] and LUNA [ISRCTN41196151] studies, and the BSGE database), and access has been guaranteed. The models will be developed using a linear regression approach that links candidate factors to outcomes. Third, we will hold 2 stakeholder co-design workshops involving eight clinicians and eight women with endometriosis separately and then bring all 16 participants together. Participants will discuss the implementation, delivery, usefulness, and sustainability of the prediction models. Clinicians will also focus on the ease of use and access to clinical prediction tools. RESULTS: This project was funded in March 2018 and approved by the Institutional Research Ethics Board in December 2019. At the time of writing, this study was in the data analysis phase, and the results are expected to be available in April 2021. CONCLUSIONS: This study is the first to aim to predict who will benefit most from laparoscopic surgery through the reduction of pain or increased QoL. The models will provide clinicians with robustly developed and externally validated support tools, improving decision making in the diagnosis and treatment of women. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/20986.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.094 | 0.133 |
| Meta-epidemiology (narrow) | 0.004 | 0.003 |
| Meta-epidemiology (broad) | 0.011 | 0.024 |
| Bibliometrics | 0.005 | 0.006 |
| Science and technology studies | 0.003 | 0.003 |
| Scholarly communication | 0.004 | 0.004 |
| Open science | 0.004 | 0.003 |
| Research integrity | 0.006 | 0.005 |
| Insufficient payload (model declined to judge) | 0.052 | 0.007 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".