The Identification of Clinically Relevant Readmission Risk Factors in Previously Hospitalized Albertan Heart Failure (HF) Patients: A Modified Delphi Process
Bibliographic record
Abstract
Introduction: Heart failure (HF) is a leading national cause of hospitalization. Canadians hospitalized with HF have a 20% 30-day readmission rate. Readmission risk prediction (RRP) helps providers plan follow-up patient care, decreasing readmission risk. Current RRP models have low predictive ability. There is poor consensus on variables to include in RRP models. RRP models often use clinician-derived variables. However, including patient perspectives encourages the integration of sociodemographic and healthcare utilization variables in RRP models. To our knowledge, there are no previously published works on clinician/ non-clinician derived variables for an RRP. The aim was to formulate a list of variables deemed necessary for inclusion in an RRP model by both clinicians and non-clinicians. Methods: An in-depth literature review revealed variables associated with readmission risk in HF patients. A modified Delphi process was used as the consensus-reaching method. A survey was administered to 13 panelists for a total of 3 rounds. Panelists included clinicians who varied in clinical expertise, profession, and years of practice. Also included were patients with HF and their caregivers. Results were summarized using medians, interquartile range (IQR) and narrative synthesis. Results: A total 61 of 99 original variables reached consensus for association with readmission risk in HF patients. Variables were grouped into 6 domains. The domains with the lowest consensus were Clinical Features and Treatment. Comorbidities and Sociodemographic reached high levels of consensus. Within the systematic reviews, of the 19 variables not reaching agreement on association with readmission risk, 10 reached consensus in the Delphi. The five variables that were heavily reported in the literature and reached high % consensus in the Delphi were: “follow-up with a multi-disciplinary team”, “elevated BNP” ,“elevated Creatinine”, “ACE-I” and “ARB” prescriptions upon discharge. Conclusion: The combination of clinicians and non-clinicians using a Delphi method to establish variables associated with readmission risk in HF patients proved to be productive. A final list of 61 variables has been proposed for inclusion in RRP models. These variables may be able to be abstracted from the electronic medical record (EMR) and will be included in an RRP model in the province of Alberta using local EMR systems.
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 | 0.155 | 0.114 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.006 | 0.003 |
| Science and technology studies | 0.005 | 0.005 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.002 | 0.012 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 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".