Cognitive technology addressing optimal cancer clinical trial matching and protocol feasibility in a community cancer practice.
Bibliographic record
Abstract
6501 Background: IBM Watson for Clinical Trial Matching (CTM) is a cognitive computing solution that uses natural language processing (NLP) to help increase the efficiency and accuracy of the clinical trial matching process. This solution helps providers locate suitable protocols for their patients by reading the trial criteria and matching it to the structured and unstructured patient characteristics when integrated with the Electronic Medical Record (EMR). It is also designed to determine which sites have the most viable patient population and identify inclusion and exclusion criteria that limit enrollment. Methods: This project was a collaboration among Highlands Oncology Group (HOG), Novartis and IBM Watson Health to explore the use of CTM in a community oncology practice. HOG is in Northeast Arkansas and has 15 physicians and 310 staff members working across 3 sites. During the 16-week pilot period, data from 2,620 visits by lung and breast cancer patients were processed by the CTM system. Using NLP capabilities, CTM read the clinical trial protocols provided by Novartis, and evaluated the patient data against the protocols’ inclusion and exclusion criteria. Watson excluded ineligible patients, determined those that needed further screening, and assisted in that process. Feedback on the user experience was also obtained. Results: In an initial pre-screening test, the HOG clinical trial coordinator (CTC) took 1 hour and 50 minutes to process 90 patients against 3 breast cancer protocols. Conversely, when the CTM screening solution was used, it took 24 minutes. This represents a significant reduction in time of 86 minutes or 78%. Watson excluded 94% of the patients automatically, providing criteria level evidence regarding the reason for exclusion, thus reducing the screening workload dramatically. Conclusions: IBM Watson CTM can help expedite the screening of patient charts for clinical trial eligibility and therefore may also help determine the feasibility of protocols to optimize site selection and enable higher and more efficient trial accruals.
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 | 0.012 | 0.051 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.002 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.003 |
| 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; both teacher heads agree on what is shown here.
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".