Comparing the Fried frailty phenotype versus the Veterans Affairs frailty index among dialysis dependent patients

Introduction

Frailty in dialysis patients is a modifiable disease state which can increase mortality if left untreated but remains underdiagnosed as frailty evaluations can be arduous or time consuming. We evaluate the agreement between a clinical frailty construct (Fried frailty phenotype, FFP) against and an electronic health record-based Veterans Affairs Frailty Index (VAFI) and their association with mortality.

Methods

A r etrospective cohort analysis of 764 participants from the ACTIVE/ADIPOSE study was performed. Frailty as measured by VAFI and FFP was obtained and Kappa statistic estimating concordance between the two scores were calculated. Differences in mortality risk were analyzed according to presence or absence of frailty.

Findings

When assessing agreement between the VAFI and FFP, the kappa statistic was 0.09 (95% confidence interval [CI] 0.02–0.16) suggesting a low level of agreement. Frailty was independently associated with higher mortality risk (hazards ratio [HR] 1.40–1.42 in fully adjusted models depending upon frailty construct). Discordantly frail patients by construct had a higher risk of mortality though this was not statistically significant after adjustment. However, concordantly frail patients had much higher mortality risk compared to concordantly nonfrail (adjusted HR 2.08, 95% CI 1.44–3.01).

Discussion

Poor agreement between constructs is likely reflective of the multifactorial definition of frailty. While further longitudinal studies are needed to determine if the VAFI would be beneficial in the reassessment of frailty, it may be beneficial as a cue for further frailty testing (e.g., with FFP) with the combination of multiple frail constructs providing improved prognostic information.     

Aspect Level Songs Rating Based Upon Reviews in English

With the advancements in internet facilities, people are more inclined towards the use of online services. The service providers shelve their items for e-users. These users post their feedbacks, reviews, ratings, etc. after the use of the item. The enormous increase in these reviews has raised the need for an automated system to analyze these reviews to rate these items. Sentiment Analysis (SA) is a technique that performs such decision analysis. This research targets the ranking and rating through sentiment analysis of these reviews, on different aspects. As a case study, Songs are opted to design and test the decision model. Different aspects of songs namely music, lyrics, song, voice and video are picked. For the reason, reviews of 20 songs are scraped from YouTube, pre-processed and formed a dataset. Different machine learning algorithms—Naïve Bayes (NB), Gradient Boost Tree, Logistic Regression LR, K-Nearest Neighbors (KNN) and Artificial Neural Network (ANN) are applied. ANN performed the best with 74.99% accuracy. Results are validated using K-Fold.