Development of a clinical score to distinguish malignant from benign esophageal disease in an undiagnosed patient population referred to an esophageal diagnostic assessment program
Bibliographic record
Abstract
BACKGROUND: Esophageal cancer is associated with poor prognosis. Diagnosis is often delayed, resulting in presentation with advanced disease. We developed a clinical score to predict the risk of a malignant diagnosis in symptomatic patients prior to any diagnostic tests. METHODS: We analyzed data from patients referred to a regional esophageal diagnostic assessment program between May 2013 and August 2016. Logistic regression was performed to identify predictors of malignancy based on patient characteristics and symptoms. Predicted probabilities were used to develop a score from 0 to 10 which was weighted according to beta coefficients for predictors in the model. Score accuracy was evaluated using a receiver operating characteristic (ROC) curve and internally validated using bootstrapping techniques. Patients were classified into low (0-2 points), medium (3-6 points), and high (7-10 points) risk groups based on their scores. Pathologic tissue diagnosis was used to assess the effectiveness of the developed score in predicting the risk of malignancy in each group. RESULTS: Of 530 patients, 363 (68%) were diagnosed with malignancy. Factors predictive of malignancy included male sex, family history of cancer and esophageal cancer, fatigue, chest/throat/back pain, melena and weight loss. These factors were allocated 1-2 points each for a total of 10 points. Low-risk patients had 70% lower chance of malignancy (RR =0.28, 95% CI: 0.21-0.38), medium-risk had 50% higher chance of malignancy (RR =1.5, 95% CI: 1.26-1.77), and high-risk patients were 8 times more likely to be diagnosed with malignancy (RR =8.2, 95% CI: 2.60-25.86). The area under the ROC curve for malignancy was 0.82 (95% CI: 0.77-0.87). CONCLUSIONS: A simple score using patient characteristics and symptoms reliably distinguished malignant from benign diagnoses in a population of patients with upper gastrointestinal symptoms. This score might be useful in expediting investigations, referrals and eventual diagnosis of malignancy.
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 | 0.005 | 0.016 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| 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 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".