Redcap and custom item banks for Computerized Adaptive Testing (CAT).

Novel methods

Although PROMIS (Patient-Reported Outcomes Measurement Information System) has created several Computerized Adaptive Testing (CAT) systems, at this point, most of them target general conditions. In contrast, the literature has repeatedly demonstrated that condition-specific assessment tools tend to be more sensitive. This characteristic translates into a higher probability of detecting real differences between treatments, as well as smaller sample sizes in clinical trials.

  1. We clean and prepare your dataset. This phase of the project ensures that your dataset is in a format that is ready for analysis. This management involves evaluating and addressing missing data, problems in data quality, variable distribution, among other factors that might violate assumptions of subsequent models.
  2. We use psychometric methods to create your item bank. In this step, we use your dataset to identify the properties of each question. The first property is the item difficulty, or how each item relates to the degree of the concept you are trying to measure. For example, a question might represent a high, medium, or low level of depression. Second, we evaluate how reliably each question measures your concept of interest. After data scientists estimate several other properties, you will have your item bank.
  3. We place your item bank in a secure, private cloud. To connect to your electronic data capture system – Redcap, for example – data scientists will put the item bank on a cloud. We ensure that this is HIPAA (Health Insurance Portability and Accountability Act) compliant, private, and secure.
  4. We provide educational material on how to use your CAT system in your studies. Adding your new CAT system to your research studies is as easy as adding any PROMIS CAT system to a Redcap form.