Investigating Data Diversity and Model Robustness of AI Applications in Palliative Care and Hospice: Protocol for Scoping Review
Bibliographic record
Abstract
BACKGROUND: Artificial intelligence (AI) has become a pivotal element in health care, leading to significant advancements across various medical domains, including palliative care and hospice services. These services focus on improving the quality of life for patients with life-limiting illnesses, and AI's ability to process complex datasets can enhance decision-making and personalize care in these sensitive settings. However, incorporating AI into palliative and hospice care requires careful examination to ensure it reflects the multifaceted nature of these settings. OBJECTIVE: This scoping review aims to systematically map the landscape of AI in palliative care and hospice settings, focusing on the data diversity and model robustness. The goal is to understand AI's role, its clinical integration, and the transparency of its development, ultimately providing a foundation for developing AI applications that adhere to established ethical guidelines and principles. METHODS: Our scoping review involves six stages: (1) identifying the research question; (2) identifying relevant studies; (3) study selection; (4) charting the data; (5) collating, summarizing, and reporting the results; and (6) consulting with stakeholders. Searches were conducted across databases including MEDLINE through PubMed, Embase.com, IEEE Xplore, ClinicalTrials.gov, and Web of Science Core Collection, covering studies from the inception of each database up to November 1, 2023. We used a comprehensive set of search terms to capture relevant studies, and non-English records were excluded if their abstracts were not in English. Data extraction will follow a systematic approach, and stakeholder consultations will refine the findings. RESULTS: The electronic database searches conducted in November 2023 resulted in 4614 studies. After removing duplicates, 330 studies were selected for full-text review to determine their eligibility based on predefined criteria. The extracted data will be organized into a table to aid in crafting a narrative summary. The review is expected to be completed by May 2025. CONCLUSIONS: This scoping review will advance the understanding of AI in palliative care and hospice, focusing on data diversity and model robustness. It will identify gaps and guide future research, contributing to the development of ethically responsible and effective AI applications in these settings. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/56353.
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 | 0.141 | 0.210 |
| Meta-epidemiology (narrow) | 0.006 | 0.006 |
| Meta-epidemiology (broad) | 0.015 | 0.019 |
| Bibliometrics | 0.021 | 0.020 |
| Science and technology studies | 0.005 | 0.007 |
| Scholarly communication | 0.011 | 0.009 |
| Open science | 0.006 | 0.008 |
| Research integrity | 0.010 | 0.007 |
| Insufficient payload (model declined to judge) | 0.042 | 0.008 |
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".