Web-Based Patient Recommender Systems for Preventive Care: Protocol for Empirical Research Propositions
Bibliographic record
Abstract
BACKGROUND: Preventive care helps patients identify and address medical issues early when they are easy to treat. The internet offers vast information about preventive measures, but the sheer volume of data can be overwhelming for individuals to process. To help individuals navigate this information, recommender systems filter and recommend relevant information to specific users. Despite their popularity in other fields, such as e-commerce, recommender systems have yet to be extensively studied as tools to support the implementation of prevention strategies in health care. This underexplored area presents an opportunity for recommender systems to serve as a complementary tool for medical professionals to enhance patient-centered decision-making and for patients to access health information. Thus, these systems can potentially improve the delivery of preventive care. OBJECTIVE: This study proposes practical, evidence-based propositions. It aims to identify the key factors influencing patients' use of recommender systems and outlines a study design, methods for creating a survey, and techniques for conducting an analysis. METHODS: This study proposes a 6-stage approach to examine user perceptions of the factors that may influence the use of recommender systems for preventive care. First, we formulate 6 research propositions that can be developed later into hypotheses for empirical testing. Second, we will create a survey instrument by collecting items from extant literature and then verify their relevance using expert analysis. This stage will continue with content and face validity testing to ensure the robustness of the selected items. Using Qualtrics (Qualtrics), the survey can be customized and prepared for deployment on Amazon Mechanical Turk. Third, we will obtain institutional review board approval because this is a human subject study. In the fourth stage, we propose using the survey to collect data from approximately 600 participants on Amazon Mechanical Turk and then using R to analyze the research model. This platform will serve as a recruitment tool and the method of obtaining informed consent. In our fifth stage, we will perform principal component analysis, Harman Single Factor test, exploratory factor analysis, and correlational analysis; examine the reliability and convergent validity of individual items; test if multicollinearity exists; and complete a confirmatory factor analysis. RESULTS: Data collection and analysis will begin after institutional review board approval is obtained. CONCLUSIONS: In pursuit of better health outcomes, low costs, and improved patient and provider experiences, the integration of recommender systems with health care services can extend the reach and scale of preventive care. Examining recommender systems for preventive care can be vital in achieving the quadruple aims by advancing the steps toward precision medicine and applying best practices. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/43316.
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 | 0.008 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.003 |
| Science and technology studies | 0.002 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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".