MétaCan
Menu
← Back to cohort
Record W4411058017 · doi:10.2196/69115

Personalized Support in Hereditary Breast and Ovarian Cancer After Genetic Counseling by the Chatbot-Based GENIE Mobile App: Proof-of-Concept Wizard of Oz Study

2025· article· en· W4411058017 on OpenAlexvenueno aff
Dominik Wolff, Thomas Kupka, Chiara Reichert, Nils Ammon, Steffen Oeltze‐Jafra, Beate Vajen

Bibliographic record

VenueJMIR Formative Research · 2025
Typearticle
Languageen
FieldPsychology
TopicDigital Mental Health Interventions
Canadian institutionsnot available
Fundersnot available
KeywordsUsabilityChatbotSession (web analytics)WizardGenetic counselingFocus groupPsychologyMobile appsComputer scienceMedical educationMedicineWorld Wide WebHuman–computer interaction

Abstract

fetched live from OpenAlex

Background: The primary aim of genetic counseling at a human genetics center is to empower individuals at risk for hereditary diseases to make informed decisions regarding their health. In Germany, genetic counseling sessions typically last approximately 1 hour and provide highly personalized information by a specialist in human genetics. Despite this, many counselees report a need for additional support following the counseling session. Objective: This study introduces GENIE, a chatbot-based mobile app designed to assist individuals in the postcounseling phase, with a focus on hereditary breast and ovarian cancer. GENIE delivers expert-curated, personalized information tailored to the user's health and family circumstances. The content is presented through predefined dialogs between the user and the mobile assistant, aiming to extend the benefits of genetic counseling beyond the initial session. Methods: A Wizard of Oz study was conducted to evaluate a functional prototype of GENIE. A total of 6 patients with breast cancer, at least 2 years postdiagnosis, participated in the study. Participants were given access to the app for a minimum of 1 week. The evaluation was based on their interaction with GENIE, which was personalized using the details of a fictitious patient. Data collection included semistructured interviews and a 45-item questionnaire to assess usability and content quality. Results: The analysis of the interview and questionnaire data indicated high usability for GENIE, with a mean System Usability Score of 75.33 (SD 4.13). In total, 5 of the 6 participants used the app daily; 3 participants were willing to pay between US $5 and US $45 as a single purchase, while the other 3 participants agreed that the app should be free for the user and the costs should be directly covered by health insurance. Still, opinions on the app's appeal were divided. The layout was seen as moderately professional, a bit crowded, and slightly uninspiring. Nevertheless, participants highlighted the credibility and relevance of the content, noting its alignment with the fictitious patient's scenario. However, areas for improvement were identified, particularly concerning the app's design. All participants would recommend the app to other affected persons. Conclusions: The findings suggest that a mobile app like GENIE can provide valuable support to individuals in the postcounseling phase of genetic services. GENIE offers distinct advantages over large language models, as the information it provides is carefully curated by human experts, minimizing the risk of inaccuracies or hallucinations and significantly enhancing the system's credibility. This study highlights the need to involve the user group as early as possible in the development of a digital health app. Future work will focus on the implementation of a comprehensive personalization engine, redesign of the user interface, and the execution of a large-scale, 2-arm randomized intervention study to validate GENIE's effectiveness.

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 imitation

Not 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.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.005
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Non-randomized trial · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.004
Threshold uncertainty score0.014

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0020.005
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0010.000
Insufficient payload (model declined to judge)0.0040.001

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.

Opus teacher head0.039
GPT teacher head0.450
Teacher spread0.411 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designNon-randomized trial
Domainnot available
GenreEmpirical

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".

Quick stats

Citations2
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueJMIR Formative Research→Same topicDigital Mental Health Interventions→French-language works237,207→