| |
Development of Frail RISC-HIV: a Risk Score for Predicting
Frailty Risk in the Short-term for Care of People with HIV
|
| |
| |
Download the PDF here
The predictor with the largest weight was baseline frailty score, with an HR of 2.9 per additional component of frailty. The next largest weight was illicit opioid use, with a 2.3 times greater risk of frailty. The average predicted risk of frailty in the training set was 8.6% [interquartile range (IQR): 2.0-10.1%].
May 1 2023
Frailty among PWH is commonly attributed to HIV-related factors (e.g. depletion of CD4+ cells and accelerated aging due to chronic inflammation from HIV), non-HIV comorbidities, and greater polypharmacy, including medications for HIV [3-5,9,10,14-21]. These HIV-related factors can add to the aging process that adults without HIVexperience. Earlier initiation of antiretroviral therapy (ART) and improvements in ART medications leading to greater viremic control and reduced inflammation may change the impact of HIV-related factors on frailty development [22]. There remains a gap in the literature addressing early detection despite multiple calls emphasizing the need for a transition from characterizing frailty to focusing on screening and interventions among PWH [1,8,23]. Although some studies have assessed risk factors for frailty, they have often been limited by small size and lack of consideration of risk behaviors that are more common among PWH (e.g. substance use) [4,16,20,24,25]. To overcome these limitations, we developed a clinical care decision-making risk score through modeling factors that predicted development of frailty in the short-term among PWH.
Cohort description
The analytic cohort included 4680 PWH, separated into training (n = 3170) and validation sets (n = 1510). There were not significant differences between PWH who had complete case data and those who did not, with the exception of a lower proportion of Hispanic PWH included and younger average age (43 years vs. 45 among PWH excluded) in the training set (Table 1, Supplemental Digital Content, https://links.lww.com/QAD/C804). Both groups were followed for a mean of 1.6 years (maximum 2 years by definition) and 220 PWH (7%) became frail in the training set, while 186 (12%) became frail in the validation set. Comparisons of the training and validation set for all candidate predictors are presented in Table 1. Among the entire cohort, 14% of PWH were female, 48% were White, 30% were Black, and the average age at baseline was 43 years. There were 140 (3%) PWH aged 65 or older and 1,494 (32%) aged 50 or older.
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.
depressive symptomology was an important predictor in Frail RISC-HIV.
Furthermore, clinical depression, or other reasons such as anxiety, that warrants pharmacological intervention with antidepressants increases polypharmacy burden [17,18]. Despite excluding two items in the depression symptoms assessment, both symptomology and treatment of depression were identified as predictors. This provides further evidence of the association between frailty and depression and underscores need to focus research on understanding and ultimately reducing their co-occurrence.
Conclusions:
Frail RISC-HIV is a simple, easily implemented tool to assist in classifying PWH at risk for frailty in clinics.
|
|
| |
| |
|
|
|
