User Guide Contents
The more specific you make your question, the more likely you are to get a relevant answer.
Consider the following examples:
In a patient with T1DM, with the following labs: pH 7.15, Co2 12, AG 27, Gluc 434, and Serum Osm 321 with ketonuria what is the most appropriate management?
The second prompt includes more context and will yield a more relevant and actionable answer to that specific clinical situation.
Specify the structure and format of the answer you want. There is a difference between asking for a "list" and an "explanation."
In a patient with T1DM, with the following labs: pH 7.15, Co2 12, AG 27, Gluc 434, and Serum Osm 321 with ketonuria what is the most appropriate management? Provide this information as a table organized by importance.
Be clear about the outcome you want. Are you seeking a diagnosis, differential, primary treatment options, alternate treatments? This will help the model focus on relevant information.
What are alternative treatment options for otitis media in a pediatric patient with allergies to PCN, cephalosporins and Macrolides?
Characterize the ATTEST-2 trial, give a summary as well as general appraisal and any notable pitfalls of the study, also include a list of other studies of similar focus.
Asking for different details will yield a different answer and determine how broad or narrow the scope of the answer is.
If you wonder whether OpenEvidence can do something, the best way to find out is to ask! Don't be afraid to try different prompts and explore new functionalities.