Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2017 Jan 17;7(1):e012012.
doi: 10.1136/bmjopen-2016-012012.

Natural language processing to extract symptoms of severe mental illness from clinical text: the Clinical Record Interactive Search Comprehensive Data Extraction (CRIS-CODE) project

Richard G Jackson  1 , Rashmi Patel  1 , Nishamali Jayatilleke  1 , Anna Kolliakou  1 , Michael Ball  1 , Genevieve Gorrell  2 , Angus Roberts  2 , Richard J Dobson  1 , Robert Stewart  1
Affiliations

Natural language processing to extract symptoms of severe mental illness from clinical text: the Clinical Record Interactive Search Comprehensive Data Extraction (CRIS-CODE) project

Richard G Jackson et al. BMJ Open. .

Abstract

Objectives: We sought to use natural language processing to develop a suite of language models to capture key symptoms of severe mental illness (SMI) from clinical text, to facilitate the secondary use of mental healthcare data in research.

Design: Development and validation of information extraction applications for ascertaining symptoms of SMI in routine mental health records using the Clinical Record Interactive Search (CRIS) data resource; description of their distribution in a corpus of discharge summaries.

Setting: Electronic records from a large mental healthcare provider serving a geographic catchment of 1.2 million residents in four boroughs of south London, UK.

Participants: The distribution of derived symptoms was described in 23 128 discharge summaries from 7962 patients who had received an SMI diagnosis, and 13 496 discharge summaries from 7575 patients who had received a non-SMI diagnosis.

Outcome measures: Fifty SMI symptoms were identified by a team of psychiatrists for extraction based on salience and linguistic consistency in records, broadly categorised under positive, negative, disorganisation, manic and catatonic subgroups. Text models for each symptom were generated using the TextHunter tool and the CRIS database.

Results: We extracted data for 46 symptoms with a median F1 score of 0.88. Four symptom models performed poorly and were excluded. From the corpus of discharge summaries, it was possible to extract symptomatology in 87% of patients with SMI and 60% of patients with non-SMI diagnosis.

Conclusions: This work demonstrates the possibility of automatically extracting a broad range of SMI symptoms from English text discharge summaries for patients with an SMI diagnosis. Descriptive data also indicated that most symptoms cut across diagnoses, rather than being restricted to particular groups.

Keywords: MENTAL HEALTH; Natural Language Processing; Serious Mental Illness; Symptomatology; clinical informatics.

PubMed Disclaimer

Conflict of interest statement

RJ, HS and RS have received research funding from Roche, Pfizer, J&J and Lundbeck.

Figures

Figure 1
Figure 1
Distribution of symptoms by SMI ICD diagnosis. ICD, International Classification of Diseases; SMI, severe mental illness.
Figure 2
Figure 2
Distribution of symptoms by symptom classes.
See this image and copyright information in PMC

References

    1. Jensen PB, Jensen LJ, Brunak S. Mining electronic health records: towards better research applications and clinical care. Nat Rev Genet 2012;13:395–405. 10.1038/nrg3208 - DOI - PubMed
    1. Lin J, Jiao T, Biskupiak JE et al. Application of electronic medical record data for health outcomes research: a review of recent literature. Expert Rev Pharmacoecon Outcomes Res 2013;13:191–200. 10.1586/erp.13.7 - DOI - PubMed
    1. Shivade C, Raghavan P, Fosler-Lussier E et al. A review of approaches to identifying patient phenotype cohorts using electronic health records. J Am Med Inform Assoc 2014;21:221–30. 10.1136/amiajnl-2013-001935 - DOI - PMC - PubMed
    1. Tao C, Jiang G, Oniki TA et al. A semantic-web oriented representation of the clinical element model for secondary use of electronic health records data. J Am Med Inform Assoc 2013;20:554–62. 10.1136/amiajnl-2012-001326 - DOI - PMC - PubMed
    1. Rusanov A, Weiskopf NG, Wang S et al. Hidden in plain sight: bias towards sick patients when sampling patients with sufficient electronic health record data for research. BMC Med Inform Decis Mak 2014;14:51 10.1186/1472-6947-14-51 - DOI - PMC - PubMed

Publication types