Development of an Electronic Frailty Index for Predicting Mortality and Complications Analysis in Pulmonary Hypertension Using Random Survival Forest Model

Prevalence of frailty among chronic respiratory disease patients

BACKGROUND

Although frailty is one of the aging syndromes, it can occur at a younger age and in individuals with organ diseases. Identifying frailty and pre-frailty in patients with chronic respiratory diseases (CRDs) is an emerging assessment in the field of pulmonary medicine and rehabilitation. The aim of this study was to find out the prevalence of frailty among chronic respiratory disease patients.

METHODS

A single centre cross-sectional survey study with a total population of 381 patients, adults aged 18-90 years presenting to the pulmonology OPD was included based on the inclusion and exclusion criteria. Primary data collected were demographics, medical history, including comorbidities, use of long-term oxygen therapy (LTOT), BiPAP (Bilevel Positive Airway Pressure), previous hospital admissions, medication history and frailty assessment were done using the Fried frailty index.

RESULTS

Univariate analysis showed that sex, ECHO abnormality, patients using LTOT, BiPAP, home nebulizers and patients who did not attend the pulmonary rehabilitation programme had a significant association with frailty. Multivariate analysis showed that female sex, LTOT use and older age were significantly associated with frailty.

CONCLUSION

Frailty is frequent in CRD patients regardless of age. The prevalence of frailty has an association with female sex, patients using LTOT, and home BiPAP.

Machine learning in a real-world PFO study: analysis of data from multi-centers in China

PURPOSE

The association of patent foreman ovale (PFO) and cryptogenic stroke has been studied for years. Although device closure overall decreases the risk for recurrent stroke, treatment effects varied across different studies. In this study, we aimed to detect sub-clusters in post-closure PFO patients and identify potential predictors for adverse outcomes.

METHODS

We analyzed patients with embolic stroke of undetermined sources and PFO from 7 centers in China. Machine learning and Cox regression analysis were used.

RESULTS

Using unsupervised hierarchical clustering on principal components, two main clusters were identified and a total of 196 patients were included. The average age was 42.7 (12.37) years and 64.80% (127/196) were female. During a median follow-up of 739 days, 12 (6.9%) adverse events happened, including 6 (3.45%) recurrent stroke, 5 (2.87%) transient ischemic attack (TIA) and one death (0.6%). Compared to cluster 1 (n = 77, 39.20%), patients in cluster 2 (n = 119, 60.71%) were more likely to be male, had higher systolic and diastolic blood pressure, higher body mass index, lower high-density lipoprotein cholesterol and increased proportion of presence of atrial septal aneurysm. Using random forest survival (RFS) analysis, eight top ranking features were selected and used for prediction model construction. As a result, the RFS model outperformed the traditional Cox regression model (C-index: 0.87 vs. 0.54).

CONCLUSIONS

There were 2 main clusters in post-closure PFO patients. Traditional cardiovascular profiles remain top ranking predictors for future recurrence of stroke or TIA. However, whether maximizing the management of these factors would provide extra benefits warrants further investigations.