Use of a Smartphone Self-assessment App for a Tobacco-Induced Disease (COPD, Cardiovascular Diseases, Cancer) Screening Strategy and to Encourage Smoking Cessation: Observational Study
Bibliographic record
Abstract
BACKGROUND: Patient self-assessment via a mobile app detects actionable symptoms and has been shown to detect lung cancer relapses early, thereby lengthening survival. OBJECTIVE: The purpose of this study was to assess the incidence of chief symptoms associated with the main tobacco-induced pathologies in both current and ex-smokers through a self-assessment smartphone app and to evaluate the app's capacity to encourage users to quit smoking or reduce consumption, as well as its impact on early lung cancer stages at the time of diagnosis. METHODS: Current and ex-smokers were recruited through an advertising campaign in Sarthe county (France) proposing the free download of a smartphone app. App users were asked to answer 13 questions related to symptoms associated with tobacco-induced diseases (chronic obstructive pulmonary disease [COPD], cardiovascular diseases, cancer). In the event of any positive answer, a message was displayed recommending the user to consult a physician. In addition, they were asked about smoking cessation intention before and after answering these 13 questions. Finally, incidence of stage 1 or 2 lung cancers diagnosed during the launch period of our application was evaluated by comparing data from various sources to those from the same period during the previous year. RESULTS: Of the 5671 users who were eligible for evaluation, an alert was sent to the majority (4118/5671, 72.6%), with a higher incidence for current smokers (2833/3679, 77.0% vs 1298/1992, 65.2%; P<.001). The most frequent symptoms triggering the notifications were fatigue (2023/5671, 35.7%), cough (1658/5671, 29.2%), dyspnea (1502/5671, 26.5%), and persistent chest pain (1286/5671, 22.7%). Of the current smokers, 14.0% (515/3679) showed symptoms suggesting COPD, 15.5% (571/3679) showed symptoms suggesting stable angina, 12.4% (455/3679) probably had lower extremity artery disease, and 6.8% (249/3679) had possible cancer. Of the users, 36.5% (1343/3679) claimed that they thought about quitting smoking, and 48.7% (1795/3679) had thought about reducing their consumption. Surgery-eligible stage 1 and 2 lung cancer incidence was 24% (14/58) during the study period versus 9% (5/54) during the previous year in Sarthe county (P=.04), whereas it remained unchanged in the neighboring county of Maine-et-Loire. CONCLUSIONS: A majority of current and ex-smokers showed worrying symptoms, and the use of a self-assessment smartphone app may drive a majority of smokers toward the intention of smoking cessation or decreasing consumption. A randomized study should be performed to confirm this intention and to support the potential increase of symptomatic lung cancer detection at early, surgery-accessible stages. TRIAL REGISTRATION: ClinicalTrials.gov NCT04048954; https://www.clinicaltrials.gov/ct2/show/NCT04048954.
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 | 0.002 | 0.005 |
| Meta-epidemiology (narrow) | 0.000 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".