A Web Application for Adrenal Incidentaloma Identification, Tracking, and Management Using Machine Learning
Bibliographic record
Abstract
BACKGROUND: Incidental radiographic findings, such as adrenal nodules, are commonly identified in imaging studies and documented in radiology reports. However, patients with such findings frequently do not receive appropriate follow-up, partially due to the lack of tools for the management of such findings and the time required to maintain up-to-date lists. Natural language processing (NLP) is capable of extracting information from free-text clinical documents and could provide the basis for software solutions that do not require changes to clinical workflows. OBJECTIVES: In this manuscript we present (1) a machine learning algorithm we trained to identify radiology reports documenting the presence of a newly discovered adrenal incidentaloma, and (2) the web application and results database we developed to manage these clinical findings. METHODS: adrenal incidentaloma. We trained a convolutional neural network to perform this text classification task. Over the NLP backbone we built a web application that allows users to coordinate clinical management of adrenal incidentalomas in real time. RESULTS: The annotated dataset included 404 positive (9.9%) and 3,686 (90.1%) negative reports. Our model achieved a sensitivity of 92.9% (95% confidence interval: 80.9-97.5%), a positive predictive value of 83.0% (69.9-91.1)%, a specificity of 97.8% (95.8-98.9)%, and an F1 score of 87.6%. We developed a front-end web application based on the model's output. CONCLUSION: Developing an NLP-enabled custom web application for tracking and management of high-risk adrenal incidentalomas is feasible in a resource constrained, safety net hospital. Such applications can be used by an institution's quality department or its primary care providers and can easily be generalized to other types of clinical findings.
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 | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.014 | 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".