CHOIR: Why Not Just Use [Insert favorite EMR]?

A frequent question we are asked is, why produce a new system? Why not just use [insert favorite EMR]?

Computational Complexity of Modern Patient Reported Outcomes (PRO)

It is true that a straight-forward translation of paper questionnaires into simple web forms is a doable approach. However, electronic forms enable much more sophisticated and much more efficient patient-reported outcomes based on item-response theory (IRT) widely used in the field of educational abilities testing. This enables dynamic assessments where the questions asked are based on the subject’s performance in the test up to that point. This is done in, for example, the GRE tests.

The NIH PROMIS effort leverages IRT and enables the efficient assessment of various psychometric domains, such as Depression, Anxiety, Anger, Pain Interference, Pain Behavior, Fatgiue, Physical Function, and so on.

In collaboration with the NIH PROMIS and Northwestern University, we have integrated the PROMIS psychometric measures into CHOIR. We went one step further and developed our own integrated CAT engine, called CHOIR CAT. CHOIR CAT contains several novel features of CAT that employ state-of-the-art CAT techniques from the field of Education. These techniques, including multiple objectives and constrained optimization, are not simple static web forms. They require substantial computational resources. Indeed the computational complexity and demands of modern patient reported outcomes (PROs) are beyond what can be provided by traditional EMR.

Next: Future Directions of CHOIR.