ObjectivesWe set out to develop, evaluate and implement a novel application using natural language processing to text mine occupations from the free-text of psychiatric clinical notes.DesignDevelopment and validation of a natural language processing application using General Architecture for Text Engineering software to extract occupations from de-identified clinical records.Setting and participantsElectronic health records from a large secondary mental healthcare provider in south London, accessed through the Clinical Record Interactive Search platform. The text mining application was run over the free-text fields in the electronic health records of 341 720 patients (all aged ≥16 years).OutcomesPrecision and recall estimates of the application performance; occupation retrieval using the application compared with structured fields; most common patient occupations; and analysis of key sociodemographic and clinical indicators for occupation recording.ResultsUsing the structured fields alone, only 14% of patients had occupation recorded. By implementing the text mining application in addition to the structured fields, occupations were identified in 57% of patients. The application performed on gold-standard human-annotated clinical text at a precision level of 0.79 and recall level of 0.77. The most common patient occupations recorded were ‘student’ and ‘unemployed’. Patients with more service contact were more likely to have an occupation recorded, as were patients of a male gender, older age and those living in areas of lower deprivation.ConclusionThis is the first time a natural language processing application has been used to successfully derive patient-level occupations from the free-text of electronic mental health records, performing with good levels of precision and recall, and applied at scale. This may be used to inform clinical studies relating to the broader social determinants of health using electronic health records.
Background
Analyzing Twitter posts enables rapid access to how issues and experiences are socially shared and constructed among communities of health service users and providers, in ways that traditional qualitative methods may not.
Objective
To enrich the understanding of mental health crisis care in the United Kingdom, this study explores views on crisis resolution teams (CRTs) expressed on Twitter. We aim to identify the similarities and differences among views expressed on Twitter compared with interviews and focus groups.
Methods
We used Twitter’s advanced search function to retrieve public tweets on CRTs. A thematic analysis was conducted on 500 randomly selected tweets. The principles of refutational synthesis were applied to compare themes with those identified in a multicenter qualitative interview study.
Results
The most popular hashtag identified was #CrisisTeamFail, where posts were principally related to poor quality of care and access, particularly for people given a personality disorder diagnosis. Posts about CRTs giving unhelpful self-management advice were common, as were tweets about resource strains on mental health services. This was not identified in the research interviews. Although each source yielded unique themes, there were some overlaps with themes identified via interviews and focus groups, including the importance of rapid access to care. Views expressed on Twitter were generally more critical than those obtained via face-to-face methods.
Conclusions
Traditional qualitative studies may underrepresent the views of more critical stakeholders by collecting data from participants accessed via mental health services. Research on social media content can complement traditional or face-to-face methods and ensure that a broad spectrum of viewpoints can inform service development and policy.
life, and optimise patients' outcomes and clinical shared decision-making is a priority. Patient Reported Outcome Measures (PROMs) are used in healthcare to understand the impact of symptoms on people's quality of life. Electronic capture of PROM data (e-PROMS) are an efficient way of collecting PROM data and can minimise patients' burden. Aim This study aims to establish the impact of trauma on patients' quality of life and to explore views on using e-PROMs to support clinical care and research. Methods In-depth semi-structured one-to-one interviews were conducted with (i) TBI survivors and family members/carers; (ii) healthcare professionals/researchers working in trauma related clinical areas; and (iii) members from third sector organisations who support trauma patients and their families/ carers. Results Preliminary results from 19 participants show using PROMs contributed to focus clinical consultations on issues deemed important to patients, including memory loss, anxiety, and lack of concentration. E-PROMS were considered flexible and timesaving and a valuable way of evaluating ongoing symptoms and their impact on quality of life when consulting with clinicians. Patients' mental health, type of injury, physical impairments, and changes in personality were considered as key features for inclusion in e-PROMs. Over and underreporting, lack of insight, cognitive and communication problems and lack of internet access, (especially among older patients), were considered barriers to using e-PROMs. Suggested features to facilitate use, included: easy to use, short length, conciseness, and lay language easily understood by trauma patients. Conclusion The electronic capture of PROMs was found to be an acceptable way of reporting patients' symptoms. Particular attention should be paid to the inclusion of specific measures in future e-PROMs system, such as patients' ongoing mental health.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.