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.
25 June 2018 in BMC Medical Informatics and Decision Making
Traditional health information systems are generally devised to support clinical data collection at the point of care. However, as the significance of the modern information economy expands in scope and permeates the healthcare domain, there is an increasing urgency for healthcare organisations to offer information systems that address the expectations of clinicians, researchers and the business intelligence community alike. Amongst other emergent requirements, the principal unmet need might be defined as the 3R principle (right data, right place, right time) to address deficiencies in organisational data flow while retaining the strict information governance policies that apply within the UK National Health Service (NHS). Here, we describe our work on creating and deploying a low cost structured and unstructured information retrieval and extraction architecture within King’s College Hospital, the management of governance concerns and the associated use cases and cost saving opportunities that such components present. To date, our CogStack architecture has processed over 300 million lines of clinical data, making it available for internal service improvement projects at King’s College London. On generated data designed to simulate real world clinical text, our de-identification algorithm achieved up to 94% precision and up to 96% recall. We describe a toolkit which we feel is of huge value to the UK (and beyond) healthcare community. It is the only open source, easily deployable solution designed for the UK healthcare environment, in a landscape populated by expensive proprietary systems. Solutions such as these provide a crucial foundation for the genomic revolution in medicine.
Objectives Mood instability is a clinically important phenomenon but has received relatively little research attention. The objective of this study was to assess the impact of mood instability on clinical outcomes in a large sample of people receiving secondary mental healthcare. Design Observational study using an anonymised electronic health record case register. Setting South London and Maudsley NHS Trust (SLaM), a large provider of inpatient and community mental healthcare in the UK. Participants 27 704 adults presenting to SLaM between April 2006 and March 2013 with a psychotic, affective or personality disorder. Exposure The presence of mood instability within 1 month of presentation, identified using natural language processing (NLP). Main outcome measures The number of days spent in hospital, frequency of hospital admission, compulsory hospital admission and prescription of antipsychotics or non-antipsychotic mood stabilisers over a 5-year follow-up period. Results Mood instability was documented in 12.1% of people presenting to mental healthcare services. It was most frequently documented in people with bipolar disorder (22.6%), but was common in people with personality disorder (17.8%) and schizophrenia (15.5%). It was associated with a greater number of days spent in hospital (β coefficient 18.5, 95% CI 12.1 to 24.8), greater frequency of hospitalisation (incidence rate ratio 1.95, 1.75 to 2.17), greater likelihood of compulsory admission (OR 2.73, 2.34 to 3.19) and an increased likelihood of prescription of antipsychotics (2.03, 1.75 to 2.35) or non-antipsychotic mood stabilisers (2.07, 1.77 to 2.41). Conclusions Mood instability occurs in a wide range of mental disorders and is not limited to affective disorders. It is generally associated with relatively poor clinical outcomes. These findings suggest that clinicians should screen for mood instability across all common mental health disorders. The data also suggest that targeted interventions for mood instability may be useful in patients who do not have a formal affective disorder.
Clozapine can cause severe adverse effects yet it is associated with reduced mortality risk. We test the hypothesis this association is due to increased clinical monitoring and investigate risk of premature mortality from natural causes. We identified 14 754 individuals (879 deaths) with serious mental illness (SMI) including schizophrenia, schizoaffective and bipolar disorders aged ≥ 15 years in a large specialist mental healthcare case register linked to national mortality tracing. In this cohort study we modeled the effect of clozapine on mortality over a 5-year period (2007-2011) using Cox regression. Individuals prescribed clozapine had more severe psychopathology and poorer functional status. Many of the exposures associated with clozapine use were themselves risk factors for increased mortality. However, we identified a strong association between being prescribed clozapine and lower mortality which persisted after controlling for a broad range of potential confounders including clinical monitoring and markers of disease severity (adjusted hazard ratio 0.4; 95% CI 0.2-0.7; p = .001). This association remained after restricting the sample to those with a diagnosis of schizophrenia or those taking antipsychotics and after using propensity scores to reduce the impact of confounding by indication. Among individuals with SMI, those prescribed clozapine had a reduced risk of mortality due to both natural and unnatural causes. We found no evidence to indicate that lower mortality associated with clozapine in SMI was due to increased clinical monitoring or confounding factors. This is the first study to report an association between clozapine and reduced risk of mortality from natural causes.
Objectives To identify negative symptoms in the clinical records of a large sample of patients with schizophrenia using natural language processing and assess their relationship with clinical outcomes. Design Observational study using an anonymised electronic health record case register. Setting South London and Maudsley NHS Trust (SLaM), a large provider of inpatient and community mental healthcare in the UK. Participants 7678 patients with schizophrenia receiving care during 2011. Main outcome measures Hospital admission, readmission and duration of admission. Results 10 different negative symptoms were ascertained with precision statistics above 0.80. 41% of patients had 2 or more negative symptoms. Negative symptoms were associated with younger age, male gender and single marital status, and with increased likelihood of hospital admission (OR 1.24, 95% CI 1.10 to 1.39), longer duration of admission (β-coefficient 20.5 days, 7.6–33.5), and increased likelihood of readmission following discharge (OR 1.58, 1.28 to 1.95). Conclusions Negative symptoms were common and associated with adverse clinical outcomes, consistent with evidence that these symptoms account for much of the disability associated with schizophrenia. Natural language processing provides a means of conducting research in large representative samples of patients, using data recorded during routine clinical practice.
Electronic healthcare records (EHRs) are a rich source of information, with huge potential for secondary research use. The aim of this study was to develop an application to identify instances of Adverse Drug Events (ADEs) from free text psychiatric EHRs. We used the GATE Natural Language Processing (NLP) software to mine instances of ADEs from free text content within the Clinical Record Interactive Search (CRIS) system, a de-identified psychiatric case register developed at the South London and Maudsley NHS Foundation Trust, UK. The tool was built around a set of four movement disorders (extrapyramidal side effects [EPSEs]) related to antipsychotic therapy and rules were then generalised such that the tool could be applied to additional ADEs. We report the frequencies of recorded EPSEs in patients diagnosed with a Severe Mental Illness (SMI) and then report performance in identifying eight other unrelated ADEs. The tool identified EPSEs with >0.85 precision and >0.86 recall during testing. Akathisia was found to be the most prevalent EPSE overall and occurred in the Asian ethnic group with a frequency of 8.13%. The tool performed well when applied to most of the non-EPSEs but least well when applied to rare conditions such as myocarditis, a condition that appears frequently in the text as a side effect warning to patients. The developed tool allows us to accurately identify instances of a potential ADE from psychiatric EHRs. As such, we were able to study the prevalence of ADEs within subgroups of patients stratified by SMI diagnosis, gender, age and ethnicity. In addition we demonstrated the generalisability of the application to other ADE types by producing a high precision rate on a non-EPSE related set of ADE containing documents. The application can be found at http://git.brc.iop.kcl.ac.uk/rmallah/dystoniaml.