ObjectiveThis paper evaluates the application of a natural language processing (NLP) model for extracting clinical text referring to interpersonal violence using electronic health records (EHRs) from a large mental healthcare provider.DesignA multidisciplinary team iteratively developed guidelines for annotating clinical text referring to violence. Keywords were used to generate a dataset which was annotated (ie, classified as affirmed, negated or irrelevant) for: presence of violence, patient status (ie, as perpetrator, witness and/or victim of violence) and violence type (domestic, physical and/or sexual). An NLP approach using a pretrained transformer model, BioBERT (Bidirectional Encoder Representations from Transformers for Biomedical Text Mining) was fine-tuned on the annotated dataset and evaluated using 10-fold cross-validation.SettingWe used the Clinical Records Interactive Search (CRIS) database, comprising over 500 000 de-identified EHRs of patients within the South London and Maudsley NHS Foundation Trust, a specialist mental healthcare provider serving an urban catchment area.ParticipantsSearches of CRIS were carried out based on 17 predefined keywords. Randomly selected text fragments were taken from the results for each keyword, amounting to 3771 text fragments from the records of 2832 patients.Outcome measuresWe estimated precision, recall and F1 score for each NLP model. We examined sociodemographic and clinical variables in patients giving rise to the text data, and frequencies for each annotated violence characteristic.ResultsBinary classification models were developed for six labels (violence presence, perpetrator, victim, domestic, physical and sexual). Among annotations affirmed for the presence of any violence, 78% (1724) referred to physical violence, 61% (1350) referred to patients as perpetrator and 33% (731) to domestic violence. NLP models’ precision ranged from 89% (perpetrator) to 98% (sexual); recall ranged from 89% (victim, perpetrator) to 97% (sexual).ConclusionsState of the art NLP models can extract and classify clinical text on violence from EHRs at acceptable levels of scale, efficiency and accuracy.

Background: A proportion of people with treatment-resistant schizophrenia fail to show improvement on clozapine treatment. Knowledge of the sociodemographic and clinical factors predicting clozapine response may be useful in developing personalised approaches to treatment. Methods: This retrospective cohort study used data from the electronic health records of the South London and Maudsley (SLaM) hospital between 2007 and 2011. Using the Least Absolute Shrinkage and Selection Operator (LASSO) regression statistical learning approach, we examined 35 sociodemographic and clinical factors’ predictive ability of response to clozapine at 3 months of treatment. Response was assessed by the level of change in the severity of the symptoms using the Clinical Global Impression (CGI) scale. Results: We identified 242 service-users with a treatment-resistant psychotic disorder who had their first trial of clozapine and continued the treatment for at least 3 months. The LASSO regression identified three predictors of response to clozapine: higher severity of illness at baseline, female gender and having a comorbid mood disorder. These factors are estimated to explain 18% of the variance in clozapine response. The model’s optimism-corrected calibration slope was 1.37, suggesting that the model will underfit when applied to new data. Conclusions: These findings suggest that women, people with a comorbid mood disorder and those who are most ill at baseline respond better to clozapine. However, the accuracy of the internally validated and recalibrated model was low. Therefore, future research should indicate whether a prediction model developed by including routinely collected data, in combination with biological information, presents adequate predictive ability to be applied in clinical settings.

No abstract

Purpose Clozapine is the most effective intervention for treatment-resistant schizophrenia (TRS). Several studies report ethnic disparities in clozapine treatment. However, few studies restrict analyses to TRS cohorts alone or address confounding by benign ethnic neutropenia. This study investigates ethnic equity in access to clozapine treatment for people with treatment-resistant schizophrenia spectrum disorder. Methods A retrospective cohort study, using information from 11 years of clinical records (2007–2017) from the South London and Maudsley NHS Trust. We identified a cohort of service-users with TRS using a validated algorithm. We investigated associations between ethnicity and clozapine treatment, adjusting for sociodemographic factors, psychiatric multi-morbidity, substance misuse, neutropenia, and service-use. Results Among 2239 cases of TRS, Black service-users were less likely to be receive clozapine compared with White British service-users after adjusting for confounders (Black African aOR = 0.49, 95% CI [0.33, 0.74], p = 0.001; Black Caribbean aOR = 0.64, 95% CI [0.43, 0.93], p = 0.019; Black British aOR = 0.61, 95% CI [0.41, 0.91], p = 0.016). It was additionally observed that neutropenia was not related to treatment with clozapine. Also, a detention under the Mental Health Act was negatively associated clozapine receipt, suggesting people with TRS who were detained are less likely to be treated with clozapine. Conclusion Black service-users with TRS were less likely to receive clozapine than White British service-users. Considering the protective effect of treatment with clozapine, these inequities may place Black service-users at higher risk for hospital admissions and mortality.

Objectives To develop a prognostic tool of treatment resistant schizophrenia (TRS) in a large and diverse clinical cohort, with comprehensive coverage of patients using mental health services in four London boroughs. Methods We used the Least Absolute Shrinkage and Selection Operator (LASSO) for time-to-event data, to develop a risk prediction model from the first antipsychotic prescription to the development of TRS, using data from electronic health records. Results We reviewed the clinical records of 1,515 patients with a schizophrenia spectrum disorder and observed that 253 (17%) developed TRS. The Cox LASSO survival model produced an internally validated Harrel’s C index of 0.60. A Kaplan-Meier curve indicated that the hazard of developing TRS remained constant over the observation period. Predictors of TRS were: having more inpatient days in the three months before and after the first antipsychotic, more community face-to-face clinical contact in the three months before the first antipsychotic, minor cognitive problems, and younger age at the time of the first antipsychotic. Conclusions Routinely collected information, readily available at the start of treatment, gives some indication of TRS but is unlikely to be adequate alone. These results provide further evidence that earlier onset is a risk factor for TRS.