1
$\begingroup$

What are the best machine learning techniques to classify responders to a medicine if I have:

  1. Clinical data with ~200 features (age, education, marital status etc.)
  2. Gene data with around 250K features (genom data (snips) taken from the patient (DNA analysis))
  3. Number of obs. ~ 4K (the data is taken from a study on 4000 patients).

Please advise.

$\endgroup$
  • 1
    $\begingroup$ please describe your data a bit more. $\endgroup$ – Rahul Aedula Oct 10 '17 at 5:54
  • $\begingroup$ @RahulAedula please review again. $\endgroup$ – Steves Oct 10 '17 at 6:05
1
$\begingroup$

Typically you need a much more exact phrasing (in more mathematical terms) of the question to ask.

Will a patient respond to medicine X? What is the likelihood? To what amount will patient repond to medicine X? Is patient in the group that is expected to respond to medicine X? Are slightly diffent questions that may impact choice of technique.

Furthermore, your data plays an important role. Are you missing data? Have you normalized already? Do you expect 'Marital status' or 'Education level' to have an impact on medicine efficiency? (It might if certain groups take medicine at home, but it may be less likely when taking under doctor supervision)

A priori you determine how to measure or quantize the success of a model (typically prediction accuracy).

Then typically you try a few machine learning techniques, and make a model from the most successful one.

|improve this answer|||||
$\endgroup$

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.