The Extent to Which Artificial Intelligence Can Help Fulfill Metastatic Breast Cancer Patient Healthcare Needs: A Mixed-Methods Study
Bibliographic record
Abstract
The Artificial Intelligence Patient Librarian (AIPL) was designed to meet the psychosocial and supportive care needs of Metastatic Breast Cancer (MBC) patients with HR+/HER2- subtypes. AIPL provides conversational patient education, answers user questions, and offers tailored online resource recommendations. This study, conducted in three phases, assessed AIPL's impact on patients' ability to manage their advanced disease. In Phase 1, educational content was adapted for chatbot delivery, and over 100 credible online resources were annotated using a Convolutional Neural Network (CNN) to drive recommendations. Phase 2 involved 42 participants who completed pre- and post-surveys after using AIPL for two weeks. The surveys measured patient activation using the Patient Activation Measure (PAM) tool and evaluated user experience with the System Usability Scale (SUS). Phase 3 included focus groups to explore user experiences in depth. Of the 42 participants, 36 completed the study, with 10 participating in focus groups. Most participants were aged 40-64. PAM scores showed no significant differences between pre-survey (mean = 59.33, SD = 5.19) and post-survey (mean = 59.22, SD = 6.16), while SUS scores indicated good usability. Thematic analysis revealed four key themes: AIPL offers basic wellness and health guidance, provides limited support for managing relationships, offers limited condition-specific medical information, and is unable to offer hope to patients. Despite showing no impact on the PAM, possibly due to high baseline activation, AIPL demonstrated good usability and met basic information needs, particularly for newly diagnosed MBC patients. Future iterations will incorporate a large language model (LLM) to provide more comprehensive and personalized assistance.
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 | 0.020 | 0.028 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 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".