Supervised Machine Learning Analysis of Food-Related Quality of Life Impact in Olfactory Dysfunction

Area of Science:

• Otolaryngology
• Psychometrics
• Data Science

Background:

• Olfactory dysfunction (OD) affects a significant portion of the population, leading to reduced quality of life (QoL).
• Understanding the key drivers of OD-related QoL impairment is crucial for developing targeted interventions.
• Previous research has explored various factors, but a data-driven approach to identify the most influential elements is needed.

Purpose of the Study:

• To assess the impact of olfactory dysfunction on quality of life.
• To identify key factors influencing quality of life in patients with olfactory dysfunction using supervised machine learning.
• To investigate the relationship between specific olfactory dysfunction symptoms and overall quality of life.

Main Methods:

• Retrospective, cross-sectional study of 260 patients with olfactory dysfunction.
• Olfactory function assessed using the TDI-Sniffin' Sticks test.
• Quality of life measured by the Questionnaire of Olfactory Dysfunction Negative Statements (QOD-NS); a random forest model was employed.

Main Results:

• Food-related statements on the QOD-NS were most influential in predicting QoL impairment.
• Statement 7 ('The changes in my sense of smell annoy me when I eat') was the most significant predictor.
• Patients with COVID-19-associated OD showed better TDI scores compared to other causes.

Conclusions:

• Food-related difficulties are the primary contributors to reduced quality of life in individuals with olfactory dysfunction.
• The subjective perception of smell changes plays a critical role in assessing quality of life.
• These findings underscore the importance of addressing food-related concerns in managing olfactory dysfunction.