Abstract A63: Overcoming challenges in health care with machine learning: Innovation from retinoblastoma
Bibliographic record
Abstract
Abstract Introduction: As retinoblastoma is a rare pediatric cancer (1/17,000 live births) with little evidence to justify treatment choices, we built a cloud-based retinoblastoma-specific electronic health record database for point-of-care data to support clinical and research collaboration and provide a quantitative analysis of prescribed treatments. Methods: Disease-specific Electronic Patient Illustrated Clinical Timeline (DEPICT HEALTH) is online, cloud-based, interactive, with point-of-care timelines and corresponding retinal/tumor drawings, with standardized scoring of tumor number, size, and locations. Results: DEPICT HEALTH records are contributed by the entire care team and used in quantitative treatment analyses. DEPICT HEALTH effectively communicates disease and treatment information to the patients’ circle of care and their parents, independent of language. The Retinoblastoma Activity Index (RAI) quantifies the active tumor (colored yellow) by counting the yellow pixels in the DEPICT HEALTH digital drawings. The drawings represent tumor at every encounter based on the collective opinion of the care team, and the RAI will quantitate tumor response to treatment. Two clinical trials were initiated using DEPICT HEALTH and RAI for eligibility and short- and long-term outcomes. Conclusion: Using RAI to score tumor response provides RECIST (response evaluation criteria in solid tumors) for retinoblastoma research, a standard of measurement that has never before been available. Machine learning methods will ultimately analyze point-of-care data to predict patient outcomes and assist with clinical decision making. DEPICT HEALTH provides an unbiased view of the efficacy of treatments, with potential to allow global point-of-care data to be widely available for research, essentially an “n” of “ALL.” Citation Format: Isabella Janusonis, Tran Truong, Justin Liu, Mei Chen, Brenda Gallie. Overcoming challenges in health care with machine learning: Innovation from retinoblastoma [abstract]. In: Proceedings of the AACR Special Conference on the Advances in Pediatric Cancer Research; 2019 Sep 17-20; Montreal, QC, Canada. Philadelphia (PA): AACR; Cancer Res 2020;80(14 Suppl):Abstract nr A63.
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 | 0.001 | 0.001 |
| 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) | 0.000 | 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".