2
$\begingroup$

In Ch-14.4 @ Pattern Recognition and Machine Learning by Bishop it is mentioned that tree-based models are more widely used in Medical Diagnosis.

Apart from giving better performance, is there a human-centric reason for this trade off as medical diagnosis is mainly performed by human?

$\endgroup$
  • 1
    $\begingroup$ Well. It's two broad imho. I work in the healthcare domain myself, and we use LSTMs. However, there might be a million problem statements in the domain. So, tough to say which ones Bishop was talking about :) $\endgroup$ – Dawny33 Aug 8 '17 at 10:32
  • $\begingroup$ @Dawny33 any thoughts on how to narrow the scope of this question to be more answerable? $\endgroup$ – DukeZhou Aug 8 '17 at 21:15
  • 1
    $\begingroup$ @DukeZhou Making it pinpointed to a specific domain in health care would help, like for example, neuroimaging, cardio-related, etc. $\endgroup$ – Dawny33 Aug 9 '17 at 1:39
1
$\begingroup$

One possible reason may have something to do with the scrutability of models, as described in the first few paragraphs of this article. It presents a case study of a hospital whose policy was to send asthma sufferers to an intensive care unit; the intensive care meant they were less likely to develop pneumonia and therefore the data showed that people with asthma were less likely to have pneumonia.

Essentially, since machine learning models learn false relationships if the data are in any way flawed, it is beneficial to be able to "debug" them. The processes by which decision trees make their decisions, and the reasons for making them, are more readily visible than in other models - particularly neural networks - which makes errors such as the example given in the article more likely to be picked up and corrected.

$\endgroup$
0
$\begingroup$

I work in medical research, but I (and my colleagues) don't use decision trees at all. I don't think "tree-based models are more widely used in Medical Diagnosis" makes any sense, at least it's application specific.

Ignore the statement and enjoy the mathematics in the book.

$\endgroup$
0
$\begingroup$

I myself working on similar product for Medical Diagnosis. The reason for it is we as ML engineer, generally try to replicate, how human approach any problem into mathematical model and build library on top of it to use it in application.

So, how Doctor approach to any specific decision of diagnosis, based on symptoms. Mainly symptoms are in two form True or False, you have it or not.

Now we just need to replicate doctors approach to make decision, But yes to extract those symptoms from raw data in the form of text, image of sound we need to use other classifier and clustering models.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.