A258 SHAPLEY VALUE ANALYSIS OF FACTORS AFFECTING WILLINGNESS TO RETURN TO COLON CANCER SCREENING.
Bibliographic record
Abstract
In 2016 colorectal cancer (CRC) was the second and third most common cause of death for Canadian men and women, respectively. Colon cancer screening can reduce the incidence and mortality of CRC. The British Columbia Cancer Agency’s Colon Screening Program (BCCSP) uses the Fecal Immunochemical Test (FIT) for screening average risk participants aged 50–74. Participants with positive FITs are referred on for colonoscopy. The benefits of colon cancer screening programs are gained by initiation and repeat periodic screening if testing is negative. Participant satisfaction is an important quality indicator in colonoscopy, but there is limited data on how components of colon cancer screening drive dissatisfaction, willingness to refer the program to others, and willingness to return for repeat screening. Marketing companies have used a calculation called the Shapley Value as a tool to answer these questions. We present a novel method to analyze components of participant dissatisfaction in colon cancer screening by using a statistical tool called the Shapley Value. Two surveys were issued randomly to individuals in the BCCSP in 2016. One set were participants who underwent FIT screening and had a negative result. The other group had positive FITs and underwent colonoscopy. Data was collected from surveys where by participants answered responses in Likert-type scale with five possible responses ranging from with “Strongly Agree” to “Strongly Disagree”. The Shapley value was calculated for collections of factors to determine which components of colon cancer screening determined dissatisfaction, willingness to refer the program to others, and willingness to return for repeat screening. In the FIT negative survey, an important factor in determining dissatisfaction was the information provided by the doctor about colon cancer screening. The result letter was important in terms of determining willingness to return and willingness to recommend colon cancer screening. In those participants who were surveyed after a colonoscopy, an important factor in determining satisfaction was the doctor who did their colonoscopy. An important factor in determining willingness to recommend colon cancer screening was whether participants felt their doctor had adequate knowledge of their medical history. The Shapely value identified factors influencing colon screening participant’s likelihood of returning for screening and of referring others for screening. It is important to distinguish drivers for returning to screening versus dissatisfaction, as some survey items reporting dissatisfaction were not associated with an unwillingness to return to screening or recommend screening to others. Future studies can assess whether the Shapley value results were associated with screening retention. None
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 | 0.011 | 0.033 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.010 | 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".