Abstract 4974: Development of an ovarian cancer diagnosis score using electronic health records
Bibliographic record
Abstract
Abstract Background: Diagnosis of invasive epithelial ovarian, fallopian tube, and primary peritoneal cancers (hereafter referred to as ovarian cancer) is often delayed, worsening both survival and quality of life for ovarian cancer patients. Diagnosis is delayed in ovarian cancer both because there is no effective screening method and because the symptoms commonly associated with ovarian cancer (i.e., abdominal/pelvic pain, bloating, loss of appetite, urinary symptoms) are non-specific to the disease. It would be beneficial to develop a flag in the electronic health record (EHR) when a patient’s healthcare utilization indicates further investigation for possible ovarian cancer is warranted. Thus, we used EHR data to develop a diagnosis score that identifies people who should be further assessed for potential ovarian cancer. Methods: EHR data from 211,123 female patients, including 135 ovarian cancer patients, at the University of Michigan Medical System during 2012-2023 were analyzed. Time-varying Cox proportional hazard models were fit to identify the association between ovarian cancer and the diagnostic codes recorded for healthcare visits in the EHR, including the temporal sequence of the diagnostic codes. The beta coefficients for the diagnosis codes from the Cox models were summed to create a weighted diagnosis score for each patient. The weighted diagnosis score was tested for association with ovarian cancer in the same population. Results: A total of 79 diagnostic codes were statistically significantly associated with ovarian cancer after applying a Bonferroni correction (p<9x10-5). The temporal sequence of the diagnoses was not associated with ovarian cancer. There were 11 pairs of diagnosis codes that were correlated (correlation coefficient >0.25); the diagnosis code with the higher p-value was excluded from further consideration. The remaining 68 codes were used to construct the diagnosis score. There was a statistically significant trend of increasing rate of ovarian cancer per quartile of the diagnosis score (hazard ratio=3.75, 95% confidence interval 3.50-4.03). Conclusion: A score for ovarian cancer diagnosis was developed based on 68 diagnostic codes in the EHR. The next step is to validate the diagnosis score in an external dataset. This validation is underway using administrative data from British Columbia, Canada. Citation Format: Minh Tung Phung, Karen McLean, Gillian E. Hanley, Celeste Leigh Pearce. Development of an ovarian cancer diagnosis score using electronic health records [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 4974.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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 teacher head, 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".