Perspectives of family medicine residents on artificial intelligence for survival estimation in patients with serious illness
Bibliographic record
Abstract
As technology for artificial intelligence (AI) in medicine has rapidly proliferated, research is needed on how AI should be used in healthcare. Family physicians could deploy AI to predict survival in serious illness which is a particularly difficult task given the breadth of diseases encountered in primary care. Little research exists to inform whether survival estimation tools are welcome in primary care to manage serious illness prognostication. To address this gap, we elicited the perspectives of family medicine residents on the potential use of AI to help them predict survival (i.e., time expected) for their patients with serious illness. Our qualitative study draws on semi-structured interview data from 18 family medicine residents in Canada. We used a pragmatic framework to conduct our analysis, employing principles of constructivist grounded theory. We identified that family medicine residents were receptive to AI survival estimation for serious illness management, particularly for supporting their delivery of expert advice over a broad range of clinical topics. However, caring for patients with serious illness in primary care involves more than survival estimation, with such a tool having likely only limited applicability to end of life. Summarizing these perspectives, we identified four themes: (1) improving patient care with AI, (2) AI with a grain of salt, (3) patient-driven use of AI, and (4) augmenting, not replacing family physicians. Thus, survival estimation with AI for serious illness has potential clinical value in primary care. In addition to survival, pertinent challenges to address with AI include understanding of expected function, maximizing quality of life, and response to interventions, in addition to quantifying survival time. Future prognostication models should consider use of additional patient-centered outcomes and modifying the outcomes predicted based on prediction timepoints. To successfully deploy these technologies in primary care, additional education and role modelling of technology use is needed.
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 | 0.019 | 0.045 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.013 | 0.012 |
| Scholarly communication | 0.004 | 0.004 |
| Open science | 0.001 | 0.004 |
| Research integrity | 0.003 | 0.006 |
| Insufficient payload (model declined to judge) | 0.003 | 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".