mHOMR: the acceptability of an automated mortality prediction model for timely identification of patients for palliative care
Bibliographic record
Abstract
Patients with non-cancer serious illnesses are under-recognised and receive palliative care only in the final weeks of life, if at all.1 The modified Hospitalised-patient One-year Mortality Risk (mHOMR) tool is a computer-based mortality prediction tool that accurately identifies patients at risk of 1-year mortality and is a feasible alternative to healthcare provider (HCP)-dependent models.2 Briefly, the tool uses data from the electronic health record to calculate an mHOMR score for each new hospital admission. The alert only notifies the lead physician, suggesting they refer the patient topalliative care and does not provide the actual score.2 In this study, we sought the perspectives of patients, family members, and HCPs to identify acceptability of mHOMR as a mortality risk tool. Together, these two studies represent the feasibility and acceptability components of the implementation outcomes (IO) framework.3 Previously we reported the development and feasibility of mHOMR (see Wegier et al 2 for more details). Alongside the feasibility study2 we collected qualitative data from November 2016 to May 2017 pre-implementation and from June to October 2017 post-implementation at two quaternary hospitals in Toronto, Canada. We used a postpositivist, qualitative content methodology4 and consecutively recruited: (1) English-speaking patients admitted to a medicosurgical ward with an mHOMR score >0.21 (ie, >21% risk of death in 12 months) and (2) HCPs who admitted patients with an mHOMR score >0.21 or were involved in advance care planning or goals of care (GOC) discussions with these patients. Substitute decision makers were recruited if a patient could not consent. In-person interviews with patients and caregivers and phone interviews with HCPs were …
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".