One of the most important steps in integrating Brellium is developing good questions. Clients often find disconnects between how our models answer the questions you ask and the way that you would answer those questions yourself. Below are a few tips and tricks to improve the questions which will ultimately make a massive difference in the answers you receive.

Verbiage

Wording your questions can have massive impact on the way they are interpreted by the model.

First, let’s look at some examples of questions that are NOT conducive to good results:

  1. Was there medical necessity?
  2. Is the CPT code right?
  3. Is the session note filled out?

We find when talking with customers that usually these questions are extremely answerable but they just need to be worded a little differently for the model to fully understand them. The name of the game is specificity. Here are a few ways that the above questions could be improved:

  1. Was there medical necessity? →
    1. Did the treatment plan specifically address the patient’s chief complaint and presenting problem?
    2. Was there a documented reason for each lab or test ordered?
    3. Was the diagnosis and corresponding treatment plan sufficiently justified by the symptoms described?
  2. Is the CPT code right? →
    1. Is the face-to-face time listed in the session note congruent with the CPT code billed?
    2. Does the level of MDM in the session note line up with the CPT code billed?
  3. Is the session note filled out? →
    1. Are the date and time of the visit listed in the report?
    2. Are the treatment goals present and documented specifically?
    3. Is there a documented safety and risk plan?

Complex Questions

For questions that are the most important to you, oftentimes only your clinicians or internal auditors know how to answer them. For these questions, it is important to specify WHERE in the note to find the answer so that our model knows where to look; we like to call this context.

Here are some examples of how to leverage context when asking more complex questions:

  1. Is the treatment plan relevant and specific? →
    1. Was the treatment plan documented in the Treatment Recommendations specific and relevant to the symptoms found in the History of Present Illness?
  2. Does the prescription match the diagnosis? →
    1. Did the prescription listed in New Medications match the diagnosis listed in the Current Diagnosis section?