Increasing knowledge of mental illness through secondary research of electronic health records: opportunities and challenges

Abstract

Aim/Purpose: The primary use of electronic health records (EHRs) is in the care of the individual patient. Secondary research uses employ information in EHRs for purposes beyond that of care of the individual. Secondary research uses may broadly be divided into studies which focus on improving care and treatment of individuals and those which aim to increase knowledge about disease causes, associations and prevalence at a population level. This paper provides a review of studies that have used EHRs to increase knowledge at a population level. It examines the methods used, types of research conducted, difficulties and challenges faced and implications for future research and mental health research in particular. Method: A review was undertaken based on a search for peer-reviewed and recently (i.e. since 2005) published articles with full-text available online. Findings/Results: The studies which have used EHRs to increase knowledge have predominantly involved; (1) data mining to identify biomarkers and gene-disease associations, (2) epidemiological research using linked/merged health records and (3) surveillance, prediction and alerts for diseases/illnesses. The principal methodological challenges identified were data quality, discrepancies/inconsistencies in data and interoperability of EHRs. Conclusions: Despite the challenges faced in secondary usage of EHRs, significant research has been undertaken and researchers have proposed and tested various approaches to address methodological issues. The study methods employed in other fields of medical research can be extrapolated to study issues of significance to mental health using EHRs.

Can mental health diagnoses in administrative data be used for research? A systematic review of the accuracy of routinely collected diagnoses

“…There has been a long history of using routine data in mental health research, from the earliest studies of asylum records through to the ‘case register’ of the 20th century [ 4 ]. The easy availability of large volumes of data regarding patients with mental health diagnoses from routine clinical practice following the shift to electronic health records can be utilised for research [ 5 , 6 ], and massed electronically produced administrative data has been used by a diverse range of groups, using routinely collected diagnosis to identify cases of mental illness for public health and advocacy [ 7 – 10 ].…”

Enhancing early detection of cognitive impairment in the criminal justice system: feasibility of a proposed method

“…NLP has been transformative (Liao et al 2015). NLP has successfully been used, among other things, to detect warning signs of heart failure, to screen and predict adverse responses to certain drugs, and for genetic research (see Spiranovic et al 2016). Furthermore, the CRIS-CODE project more recently provides some guidance for expanding NLP into mental illness.…”

How data science can advance mental health research

“…60 Using full-text medical records for research with natural language processing can identify specific signs, symptoms, and health trajectories at a large scale. 32,61,62 Studying these data could lead to better phenotypic classifications which predict clinically relevant outcomes. 63,64 For example, the depression can be heterogeneous in prognosis: one study identified five broad trajectories of depression in 3000 patients using electronic health records .…”