Real-time clinician text feeds from electronic health records

Teo, J. T.; Dinu, V.; Bernal, W.; Davidson, P.; Oliynik, V.; Breen, C.; Barker, R. D.; Dobson, R.

Introduction: Analyses of search engine and social media feeds have been attempted for infectious disease outbreaks1, but have been found to be susceptible to artefactual distortions from health scares or keyword spamming in social media or the public internet. Method: We describe an approach using real-time aggregation of keywords and phrases of free text from real-time clinician-generated documentation in electronic health records Results: We show that this text feed of clinical text records is able to produce a customisable real-time Covid viral pneumonia signal providing up to 2 days warning for secondary care capacity planning. This signal is media-sensitive and also works for detecting seasonal influenza. Conclusion: This low-cost approach is open-source, is locally customisable, is not dependent on any specific electronic health record system and can be deployed at multiple organisational scales.