Meet Inspiring Speakers and Experts at our 3000+ Global Conference Series Events with over 1000+ Conferences, 1000+ Symposiums
and 1000+ Workshops on Medical, Pharma, Engineering, Science, Technology and Business.

Explore and learn more about Conference Series : World's leading Event Organizer

Back

Shoab Saadat

Shoab Saadat

Shifa International Hospital, Pakistan

Title: What changes the quality of life in a hemodialysis patient - a machine learning approach

Biography

Biography: Shoab Saadat

Abstract

Introduction:

Dialysis patients usually have a long commitment to a certain lifestyle. This, in turn has a significant impact on their quality of life (QOL) irrespective of the modality used (1). Several factors like environmental, social, psychological, financial and physical play an important role in determining the QOL that an individual enjoys (2). Several studies have been carried out worldwide with a purpose of identifying the most significant correlates with a better QOL (3,4). Because, there has been no study specifically aiming at the most important predictors of QOL in Pakistani population in the order of their strength of association using modern machine learning techniques, therefore, the purpose of this study is to produce a classification model for the most significantly associated positive and negative predictors for the QOL in hemodialysis patients in our population. This will be helpful in directing resources to a segment of patients who are at the highest risk of a worsening QOL score.

Methods:

This is a cohort study that will include all the consenting patients (by non-probability convenience sampling) who have received hemodialysis for at least 3 months at the dialysis center of Shifa International Hospital, Pakistan. By the first interim analysis, a total of 78 patients were successfully enrolled. Each patient was administered a proforma containing questions about demographics and the validated Urdu version of WHO BREF questionnaire for the QOL assessment by a MBBS qualified doctor. The same questionnaire was again administered after a month’s period to the same patient by the same investigator. This was to find whether any change in QOL (delta QOL) is associated with another significantly changing variable. Statistical analysis was performed using SPSS version 24, while machine learning algorithms including the classification tree were generated using Orange.

Results:

A total of 78 patients were enrolled and analyzed for the first interim analysis (42 males, 36 females). The mean scores for all the four domains of WHO BREF questionnaire for QOL at the end of the cohort’s observation period of one month were: D1 (Physical) =12.9 (SD=3.7), D2 (Psychological) =15.0 (SD=3.4), D3 (Social) =15.2 (SD=2.75), D4 (Environmental) =16 (SD=2.9) respectively. Initially, a linear regression model (p<0.000) was generated with an R-square of 0.418, which showed monthly income (p<0.000) and serum albumin (p<0.000) to be positively and significantly associated with better quality of life. Later, using machine learning algorithms, two models (classification tree and Naïve Bayes) were generated that would predict an improvement or decrement of 5% in a patient’s BREF QOL score over a period of one month. Classification tree was selected as the most accurate among the two with an area under curve (AUC) of 83.3% for the prediction of 5% increase in QOL and an AUC of 76.2% for the prediction of 5% decrease in QOL over the coming 1 month. The most important variables associated with an increase of QOL by 5% were a positive change in domain 4 (environmental variables), a total QOL score of <65 at the beginning of cohort study, age less than 19 years and higher doses of iron sucrose (>278mg / month) administered. Factors associated with a decrease of 5% in QOL over the following month included a decrease in domains 2, 1 and 3 (psychological, physical and social variables respectively) and a greater than 61 total QOL score at the start of cohort study, in order of their importance.

Conclusion:

There is a significant relationship between a better household income and serum albumin levels with an improved quality of life in patients of hemodialysis. Also, machine learning algorithms can be used to classify patients into those with higher probabilities of having a positive or a negative change of 5% or more in QOL over the coming month. These algorithms also help in identifying the most important factors related with these changes in QOL. This can in turn be used to risk stratify patients and to concentrate on those at high risk to improve the physiological, psychological, social and environmental aspects of their lives.

These results represent an interim analysis into the whole project. The expected duration to complete the study is one year with an expected enrolment of more than 250 patients. A small sample size and patients selected from a single center certainly limit the external validity of this study but with enrolment of more cases, this can be taken care of.