Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.
Who will be affected?
Readers: No access to all 28 journals. We recommend accessing our articles via PubMed Central
Authors: No access to the submission form or your user account.
Reviewers: No access to your user account. Please download manuscripts you are reviewing for offline reading before Wednesday, July 01, 2020 at 7:00 PM.
Editors: No access to your user account to assign reviewers or make decisions.
Copyeditors: No access to user account. Please download manuscripts you are copyediting before Wednesday, July 01, 2020 at 7:00 PM.
Identifying Patterns of Clinical Interest in Clinicians’ Treatment Preferences: Hypothesis-free Data Science Approach to Prioritizing Prescribing Outliers for Clinical Review
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
A hypothesis-free data science approach to identifying novel patterns of clinical interest in clinicians' treatment preferences: clusters of high Pericyazine and Promazine use in England
Brian MacKenna;
Helen J Curtis;
Alex J Walker;
Richard Croker;
Orla Macdonald;
Stephen JW Evans;
Peter Inglesby;
Dave Evans;
Jessica Morley;
Sebastian CJ Bacon;
Ben Goldacre
ABSTRACT
Background:
Data analysis can be used to identify signals suggestive of variation in treatment choice or
clinical outcome. Analyses to date have generally focused on an hypothesis-driven
approach.
Objective:
Develop hypothesis-blind data driven approaches to identify outlier prescribing behaviour.
Methods:
Here we report an innovative hypothesis-blind approach (calculating chemical-class
proportions for every chemical substance prescribed in each Clinical Commissioning Group
and ranking chemicals by (a) their kurtosis and (b) a ratio between inter-centile differences)
applied to England’s national prescribing data, and demonstrate how this identified unusual
prescribing of two antipsychotics.
Results:
We identified that, while promazine and pericyazine are barely used by most clinicians, they
make up a substantial proportion of all antipsychotic prescribing in two small geographic
regions in England.
Conclusions:
Data-driven approaches can be effective at identifying unusual clinical choices. More
widespread adoption of such approaches, combined with clinician and decision-maker
engagement could lead to better optimised patient care. Clinical Trial: n/a
Identifying Patterns of Clinical Interest in Clinicians’ Treatment Preferences: Hypothesis-free Data Science Approach to Prioritizing Prescribing Outliers for Clinical Review