Can collaborative filtering be applied to the disease detection?

Question

Browsing through some tutorials on collaborative filtering, I have observed that it is mostly used with movie and book recommendations, with datasets that have users and the items they rate. Definitely, the range for rating per item would be the same (e.g 1-10). But what if I have a dataset that has different ranges. Meaning an entirely different dataset that has nothing to do with how people rate an item but instead, based on medical records of people. I am thinking of using the features in the record like BMI, Weight, Height etc. etc. as the item and the user as the person with that record. Basically at the end of the process, i'd like to determine whether one has a disease or not based from other records that already have pre-determined output. I know that this is usually/can easily be done in Neural Networks. But i just really want to know if this is also possible in collaborative Filtering. Or is it not?

Answer 1

It is not a recommendation problem, this is classical classification, nothing more. Neural Networks are just one of dozens od possible approaches,but once again - it is not collaborative filtering, it is exactly how classification is defined. In collaborative filtering you do not know the correct answer (labels/output) - you simply try to find some common pattern among other. In case of disease detection/forecast you know exactly what should be the output.

Recommender systems could be used here if you have very broad spectrum of possible, correlated diseases, and very small amount of people with it (so it is not possible to actually build training sets for the disseas). Then such "recommendation" which looks for a potential health problem would have sense.In case of labeled, binary output data it is just a classification. Even though, you would probably end up with model: "if you have obessity, then you will probably get a heart attack" etc. So finding correlation between similar diagnoses.