Our Posts

Identifying meaningful questions

No Comments

Sometimes I will know what I want and I will be trying to say, ‘Can we do this? Can we do this this way?

From “Leaders’ perspectives on learning health systems
BMC Health Services Research 2020

Identifying problems with potential to improve care, is the most judgement demanding step in the Learning Health System. It requires a deep understanding of health systems (experience), proficiency in the specific clinical practises (clinical knowledge), and data interrogation skills (data science). To say that these are scarce skills is an understatement, but scarcity adds structural challenges.

None of these skills are easy to come by, to put together a multidisciplinary team in one geographical location is even rarer. For a multidisciplinary team of clinicians and data scientists to meet, the two most unavailable resources in a health system are required: clinicians’ time, and money.  This is not helped by the fact that analytic tools are not fit for purpose in healthcare applications. AI is bad at judgement so is of little help.

Evidentli’s unique solution to this problem is a clinical analytics workbench with powerful collaboration features that adhere to the highest standards of patient privacy. Here, again, we can rely on the specifics of the settings and the data to make a fit for purpose analytic system, powered by a number of specific AI algorithms that support clinically trained users construct observational, case matched, single-cohort and the wide range of other kinds of studies needed to support policy decisions. For example, using a drag and drop interface, a user can provide a selection criteria by demographics, diagnosis and/or treatment, divide it into sub-groups, select outcomes to compare those subgroups by, and produce a report that describes the process in English. Without a single line of code! Not requiring assistance from a data scientist (or similar) saves the clinician time and avoids multiple translation errors. 

Recent Posts

Leave a Reply

Comments, questions or queries? Let us know!"