Easily identify patient cohorts and collect data to produce real-world evidence for improved patient outcomes.
It all starts with the doctors and nurses. From blood types, to allergies, to vital sign measurements: all of these patient findings are reported by them in the Electronic Health Record (EHR). This wealth of data holds great promise for advancing medical knowledge, but due to its complexity and difficult formatting, it has been a challenge for healthcare organizations to repurpose it for analytics.
More than 70% of all data in the EHR database is stored as text. Details about patients’ histories, conditions and procedures are written down in reports and notes.To produce real-world evidence, it is key that the value of this unstructured data is leveraged. Our solution uses NLP and machine learning to analyze all of the texts and to make their content available for analytics. During this process texts are also pseudonymized, which means that identifiers that can be linked to a patient (e.g. names, addresses, phone numbers) are masked.
Once the texts have been analyzed, it is combined with the structured data (e.g. diagnoses, procedures and appointments) and then cleaned and organized into a logical structure. After this harmonization process, the data is stored into our clinical data warehouse. It is now ready to be searched and collected.
Health care professionals gain direct access to the harmonized data via our self-service analytics solution. It allows users to easily translate their research question into a database query with inclusion- and exclusion criteria and parameters that need to be collected. Users are assisted by smart algorithms for an optimal search experience.
The data journey starts with doctors and nurses, and that is also where it ends. All of the work that has been put into cleaning data and making it accessible for analytics is done with one goal in mind: using real-world evidence to inform best clinical practice.
Our solution has been developed using a privacy by design approach, which means that privacy is our default setting. Before patient data enters our database on the hospital server, it is stripped of all content that can be linked to a patient. Our self-service solution gives users access to a minimal dataset, which means that they only get to see content that is relevant to their research question.
Specialized privacy attorneys from EY have validated our process, paying special attention to the 2016 legislation Bill on Data Breach Notifications (“Meldplicht datalekken”). The use of CTcue complies with the GDPR.