Online Decision Support Tool for Personalized Cancer Symptom Checking in the Community (REACT): Acceptability, Feasibility, and Usability Study
Bibliographic record
Abstract
BACKGROUND: Improving cancer survival in the UK, despite recent significant gains, remains a huge challenge. This can be attributed to, at least in part, patient and diagnostic delays, when patients are unaware they are suffering from a cancerous symptom and therefore do not visit a general practitioner promptly and/or when general practitioners fail to investigate the symptom or refer promptly. To raise awareness of symptoms that may potentially be indicative of underlying cancer among members of the public a symptom-based risk assessment model (developed for medical practitioner use and currently only used by some UK general practitioners) was utilized to develop a risk assessment tool to be offered to the public in community settings. Such a tool could help individuals recognize a symptom, which may potentially indicate cancer, faster and reduce the time taken to visit to their general practitioner. In this paper we report results about the design and development of the REACT (Risk Estimation for Additional Cancer Testing) website, a tool to be used in a community setting allowing users to complete an online questionnaire and obtain personalized cancer symptom-based risk estimation. OBJECTIVE: The objectives of this study are to evaluate (1) the acceptability of REACT among the public and health care practitioners, (2) the usability of the REACT website, (3) the presentation of personalized cancer risk on the website, and (4) potential approaches to adopt REACT into community health care services in the UK. METHODS: Our research consisted of multiple stages involving members of the public (n=39) and health care practitioners (n=20) in the UK. Data were collected between June 2017 and January 2018. User views were collected by (1) the "think-aloud" approach when participants using the website were asked to talk about their perceptions and feelings in relation to the website, and (2) self-reporting of website experiences through open-ended questionnaires. Data collection and data analysis continued simultaneously, allowing for website iterations between different points of data collection. RESULTS: The results demonstrate the need for such a tool. Participants suggest the best way to offer REACT is through a guided approach, with a health care practitioner (eg, pharmacist or National Health Service Health Check nurse) present during the process of risk evaluation. User feedback, which was generally consistent across members of public and health care practitioners, has been used to inform the development of the website. The most important aspects were: simplicity, ability to evaluate multiple cancers, content emphasizing an inviting community "feel," use (when possible) of layperson language in the symptom screening questionnaire, and a robust and positive approach to cancer communication relying on visual risk representation both with affected individuals and the entire population at risk. CONCLUSIONS: This study illustrates the benefits of involving public and stakeholders in developing and implementing a simple cancer symptom check tool within community. It also offers insights and design suggestions for user-friendly interfaces of similar health care Web-based services, especially those involving personalized risk estimation.
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 | 0.002 | 0.000 |
| 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 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".