Neural network in predicting medical condition

I would like to apply AI in predicting Sick Building Syndrome (SBS) with Indoor Air Quality parameters. I applied neuralnet package to establish parsimonious model.

Input (Numerical-Indoor Air Quality parameters)
Air movement
Carbon dioxide
Respirable particles
Bacterial count
Fungal count

Output (categorical 0=No-SBS, 1=SBS)

I have difficulty in checking the accuracy, specificity, and sensitivity of the model. Can help me share the related link for codes can be applied. Thank you.

Hi @logansalv,

Assuming you can get class predictions from your model (or probabilities that you can use to create hard class assignments), you may consider using some of the metrics available in the {yardstick} package, such as for accuracy(), sensitivity(), and specificity(). Hope this helps.

Yardstick: Function reference • yardstick

Thank you so much sir.

This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.

If you have a query related to it or one of the replies, start a new topic and refer back with a link.