Frailty is often associated with adverse outcomes in older patient populations with COPD. Researchers in China have been studying how to create a practical and convenient risk prediction model for this population.
The study, “Development and Validation of a Clinical Nomogram for Frailty Prediction in Older COPD Patients: a Machine Learning Approach,” was published in BMC Geriatrics.
According to the study, the researchers accessed records of older COPD patients from the China Elderly Comorbidity Medical Database (CECMed) and assessed them using the Fatigue, Resistance, Ambulation, Illnesses, and Loss of Weight (FRAIL) scale. Data gathered included:
- Demographics
- Socioeconomic status
- Medical history
- Medication use
- Vital signs
- Comprehensive geriatric assessment
The researchers employed five machine learning algorithms to construct the prediction models. They used area under the curve (AUC) values to determine the optimal model, then evaluated it through calibration curve analysis and decision curve analysis. The model was presented as a nomogram: a two-dimensional diagram designed to show the approximate graphical computation of a given function.
The model identified six predictors of frailty: age, cranial cervical instability, bronchodilator usage, diastolic blood pressure (DBP), gait speed and grip strength. Those six predictors were used to construct the nomogram, assigning each indicator a point value. The total points were then used to estimate the probability of pre-frailty or frailty.
Of the 860 elderly patients with COPD who were analyzed, 41.5% were pre-frailty and 22.7% were at frailty.
The researchers said the study found the use of bronchodilators, for example, is a protective factor against frailty in older COPD patients. This suggests “that effective medication and management of COPD can lower the risk of frailty in this population,” they wrote.
The study also identified a previously unreported association between low DBP and frailty/pre-frailty in older patients with COPD. They said that this association could be explained by low DBP resulting in myocardial hypoperfusion and injury while also reflecting end-organ perfusion status in the eyes, kidneys and brain. Another possibility is that low DBP could signify the presence of advanced aortic atherosclerosis and a greater burden of cardiovascular disease, implying inferior baseline cardiovascular health. The researchers cautioned that more research is necessary to establish a causal link between low DPB and frailty in older COPD patients.
The researchers concluded that the study found a combined prevalence of frailty and pre-frailty in older COPD patients of 64.19%, with 22.7% meeting frailty criteria. They said the model could be clinically useful in predicting frailty among this population.
“For many relatively healthy COPD patients, early prediction of frailty can move the intervention window forward,” they wrote. “The model’s simplicity and utilization of standard clinical parameters enhance its practicality for swift frailty screening in clinical settings.”
