Week 2: Learning about the Barriers

Mar 11, 2019

Hello everyone,

This week I looked into research papers done on Obstructive Sleep Apnea and read about experiments, both successful and unsuccessful, that implemented machine learning to diagnose OSA. Previously, I envisioned creating a project that could study existing patterns in the sleep statistics of those already diagnosed and make a diagnosis on a new patient. However, as my internal advisor, Mr. Hansen, brought up, only doctors are allowed to make a valid diagnosis (a diagnosis that is deemed legitimate by an outside entity such as an insurance company). A doctor can order a polysomnography, or a sleep test, to determine whether a patient has OSA. This brings the question, how can my project be useful if sleep tests already exist and my project can’t make a valid diagnosis? Well, instead of providing a diagnosis, I now intend to make this tool indicate whether or not someone should confront their doctor about potentially having OSA. It’s a work in progress…

Additionally, I’ve been continuing with my ML course, learning Octave/Matlab. My external advisor has been busy but he’s been able to give me some solid advice. Transitioning into next week, I want to start looking more at the science behind OSA so the data makes more sense.

Thanks for tuning in!


One Reply to “Week 2: Learning about the Barriers”

  1. Sahil J. says:

    That’s a great point. However, I wouldn’t let “not being able to formally diagnose someone” be a setback to your project. Indicating that they should confront a doctor is equally as important and relevant.

    I hope you’re making progress with the course. Do you plan to use either Octave/MATLAB in your final project as well? Are you considering using Python – which seems to also have great support for resources like Tensorflow and packages such as numpy?

Leave a Reply

Your email address will not be published. Required fields are marked *