Using Machine Learning to Recognize CRS in Patients

Session Number

Project ID: CMPS 05

Advisor(s)

Dr. Claus-Peter Richter, Northwestern University, Feinberg School of Medicine

Discipline

Computer Science

Start Date

20-4-2022 8:50 AM

End Date

20-4-2022 9:05 AM

Abstract

Chronic Rhinosinusitis (CRS) is a nasal disease characterized by the inflammation of the mucosa and paranasal sinuses with a duration of at least 12 consecutive weeks. So, to diagnose CRS, one needs to keep a record of their symptoms for ~12 weeks before they are recommended to get a tomography which will allow physicians to classify them as a patient with CRS or without. This is a timely and costly process; thus, machine learning should be used to speed the process up. This project explores using Python and different machine learning algorithms to classify individuals as with or without CRS based on the way they speak. Files of individuals with and without CRS saying different words were recorded and converted to the frequency domain. These values were then analyzed by machine learning algorithms to classify whether the speaker had CRS or not. Each algorithm is evaluated based on the time it took to run, as well as how accurate its predictions were.

Share

COinS
 
Apr 20th, 8:50 AM Apr 20th, 9:05 AM

Using Machine Learning to Recognize CRS in Patients

Chronic Rhinosinusitis (CRS) is a nasal disease characterized by the inflammation of the mucosa and paranasal sinuses with a duration of at least 12 consecutive weeks. So, to diagnose CRS, one needs to keep a record of their symptoms for ~12 weeks before they are recommended to get a tomography which will allow physicians to classify them as a patient with CRS or without. This is a timely and costly process; thus, machine learning should be used to speed the process up. This project explores using Python and different machine learning algorithms to classify individuals as with or without CRS based on the way they speak. Files of individuals with and without CRS saying different words were recorded and converted to the frequency domain. These values were then analyzed by machine learning algorithms to classify whether the speaker had CRS or not. Each algorithm is evaluated based on the time it took to run, as well as how accurate its predictions were.