Using Text Messages and Fotonovelas to Increase Return of Home-Mailed Colorectal Cancer Screening Tests: Mixed Methods Evaluation
Bibliographic record
Abstract
BACKGROUND: Colorectal cancer (CRC) is currently the second leading cause of cancer-related deaths in the United States; however, it is mostly preventable with appropriate screening and is often treatable when detected at early stages. Many patients enrolled in an urban Federally Qualified Health Center (FQHC) clinic were found to be past due for CRC screening. OBJECTIVE: This study described a quality improvement (QI) project to improve CRC screening rates. This project used bidirectional texting with fotonovela comics and natural language understanding (NLU) to encourage patients to mail fecal immunochemical test (FIT) kits back to the FQHC. METHODS: The FQHC mailed FIT kits to 11,000 unscreened patients in July 2021. Consistent with the usual care, all patients received 2 text messages and a patient navigator call within the first month of mailing. As part of a QI project, 5241 patients who did not return their FIT kit within 3 months, aged 50-75 years, and spoke either English or Spanish were randomized to either usual care (no further intervention) or intervention (4-week texting campaign with a fotonovela comic and remailing kits if requested) groups. The fotonovela was developed to address known barriers to CRC screening. The texting campaign used NLU to respond to patients' texts. A mixed methods evaluation used data from SMS text messages and electronic medical records to understand the impact of the QI project on CRC screening rates. Open-ended text messages were analyzed for themes, and interviews were completed with a convenience sample of patients to understand barriers to screening and impact of the fotonovela. RESULTS: =19.0; P<.001). Of the 1026 participants who engaged bidirectionally, 318 (31%) clicked on the fotonovela. Furthermore, 54% (32/59) of the patients clicked on the fotonovela and responded that they loved it, and 36% (21/59) of patients responded that they liked it. The intervention group was more likely to get screened (487/2597, 18.75%) than those in usual care (308/2644, 11.65%; P<.001), and this pattern held, regardless of demographic subgroup (sex, age, screening history, preferred language, and payer type). Interview data (n=16) indicated that the text messages, navigator calls, and fotonovelas were well received and not unduly invasive. Interviewees noted several important barriers to CRC screening and offered suggestions for reducing barriers and increasing screening. CONCLUSIONS: Texting using NLU and fotonovela is valuable in increasing CRC screening as observed by the FIT return rate for patients in the intervention group. There were patterns in which patients did not engage bidirectionally; future work should investigate how to ensure that populations are not left out of screening campaigns.
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 | 0.048 | 0.069 |
| Meta-epidemiology (narrow) | 0.003 | 0.001 |
| Meta-epidemiology (broad) | 0.003 | 0.006 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.006 | 0.001 |
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".