A Web-Based Mobile App (INTERACCT App) for Adolescents Undergoing Cancer and Hematopoietic Stem Cell Transplantation Aftercare to Improve the Quality of Medical Information for Clinicians: Observational Study
Bibliographic record
Abstract
BACKGROUND: A growing number of cancer and hematopoietic stem cell transplant (HSCT) survivors require long-term follow-up with optimal communication schemes, and patients' compliance is crucial. Adolescents have various unmet needs. Regarding self-report of symptoms and health status, users of mobile apps showed enhanced compliance. Currently, HSCT aftercare at the HSCT outpatient clinic of the St. Anna Children's Hospital in Vienna, Austria, is based on handwritten diaries, carrying various disadvantages. Recently, we developed the prototype of a web-based, self-monitoring gamified mobile app tailored for adolescents: the INTERACCT (Integrating Entertainment and Reaction Assessment into Child Cancer Therapy) app. OBJECTIVE: This observational, prospective study evaluated the usability of the INTERACCT app for tracking real-time self-reported symptoms and health status data in adolescent HSCT patients and a healthy matched control group. The primary outcome of the study was the quality of the self-reported medical information. We hypothesized that the mobile app would provide superior medical information for the clinicians than would the handwritten diaries. METHODS: Health data were reported via paper diary and mobile app for 5 consecutive days each. The quality of medical information was rated on a 5-point scale independently and blinded by two HSCT clinicians, and the duration of use was evaluated. A total of 52 participant questionnaires were assessed for gaming patterns and device preferences, self-efficacy, users' satisfaction, acceptability, and suggestions for improvement of the mobile app. Interrater reliability was calculated with the intraclass correlation coefficient, based on a two-way mixed model; one-way repeated-measures analysis of variance and t tests were conducted post hoc. Descriptive methods were used for correlation with participants' demographics. For users' satisfaction and acceptability of the mobile app, the median and the IQR were calculated. RESULTS: Data from 42 participants-15 patients and 27 healthy students-with comparable demographics were evaluated. The results of our study indicated a superiority of the quality of self-reported medical data in the INTERACCT app over traditional paper-and-pencil assessment (mobile app: 4.14 points, vs paper-based diary: 3.77 points, P=.02). The mobile app outperformed paper-and-pencil assessments mainly among the patients, in particular among patients with treatment-associated complications (mobile app: 4.43 points, vs paper-based diary: 3.73 points, P=.01). The mobile app was used significantly longer by adolescents (≥14 years: 4.57 days, vs ≤13 years: 3.14 days, P=.03) and females (4.76 days for females vs 2.95 days for males, P=.004). This corresponds with a longer duration of use among impaired patients with comorbidities. User satisfaction and acceptability ratings for the mobile app were high across all groups, but adherence to entering a large amount of data decreased over time. Based on our results, we developed a case vignette of the target group. CONCLUSIONS: Our study was the first to show that the quality of patient-reported medical information submitted via the INTERACCT app embedded in a serious game is superior to that submitted via a handwritten diary. In light of these results, a refinement of the mobile app supported by a machine learning approach is planned within an international research project.
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 | 0.006 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| 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 | 0.000 |
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".