Development of Frail RISC-HIV: a Risk Score for Predicting Frailty Risk in the Short-term for Care of People with HIV
Bibliographic record
Abstract
OBJECTIVE: Frailty is common among people with HIV (PWH), so we developed frail risk in the short-term for care (RISC)-HIV, a frailty prediction risk score for HIV clinical decision-making. DESIGN: We followed PWH for up to 2 years to identify short-term predictors of becoming frail. METHODS: We predicted frailty risk among PWH at seven HIV clinics across the United States. A modified self-reported Fried Phenotype captured frailty, including fatigue, weight loss, inactivity, and poor mobility. PWH without frailty were separated into training and validation sets and followed until becoming frail or 2 years. Bayesian Model Averaging (BMA) and five-fold-cross-validation Lasso regression selected predictors of frailty. Predictors were selected by BMA if they had a greater than 45% probability of being in the best model and by Lasso if they minimized mean squared error. We included age, sex, and variables selected by both BMA and Lasso in Frail RISC-HIV by associating incident frailty with each selected variable in Cox models. Frail RISC-HIV performance was assessed in the validation set by Harrell's C and lift plots. RESULTS: Among 3170 PWH (training set), 7% developed frailty, whereas among 1510 PWH (validation set), 12% developed frailty. BMA and Lasso selected baseline frailty score, prescribed antidepressants, prescribed antiretroviral therapy, depressive symptomology, and current marijuana and illicit opioid use. Discrimination was acceptable in the validation set, with Harrell's C of 0.76 (95% confidence interval: 0.73-0.79) and sensitivity of 80% and specificity of 61% at a 5% frailty risk cutoff. CONCLUSIONS: Frail RISC-HIV is a simple, easily implemented tool to assist in classifying PWH at risk for frailty in clinics.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 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".