Dataset Information

Identifying Predictors of Suicide in Severe Mental Illness: A Feasibility Study of a Clinical Prediction Rule (Oxford Mental Illness and Suicide Tool or OxMIS).

ABSTRACT: Background:Oxford Mental Illness and Suicide tool (OxMIS) is a brief, scalable, freely available, structured risk assessment tool to assess suicide risk in patients with severe mental illness (schizophrenia-spectrum disorders or bipolar disorder). OxMIS requires further external validation, but a lack of large-scale cohorts with relevant variables makes this challenging. Electronic health records provide possible data sources for external validation of risk prediction tools. However, they contain large amounts of information within free-text that is not readily extractable. In this study, we examined the feasibility of identifying suicide predictors needed to validate OxMIS in routinely collected electronic health records. Methods:In study 1, we manually reviewed electronic health records of 57 patients with severe mental illness to calculate OxMIS risk scores. In study 2, we examined the feasibility of using natural language processing to scale up this process. We used anonymized free-text documents from the Clinical Record Interactive Search database to train a named entity recognition model, a machine learning technique which recognizes concepts in free-text. The model identified eight concepts relevant for suicide risk assessment: medication (antidepressant/antipsychotic treatment), violence, education, self-harm, benefits receipt, drug/alcohol use disorder, suicide, and psychiatric admission. We assessed model performance in terms of precision (similar to positive predictive value), recall (similar to sensitivity) and F1 statistic (an overall performance measure). Results:In study 1, we estimated suicide risk for all patients using the OxMIS calculator, giving a range of 12 month risk estimates from 0.1-3.4%. For 13 out of 17 predictors, there was no missing information in electronic health records. For the remaining 4 predictors missingness ranged from 7-26%; to account for these missing variables, it was possible for OxMIS to estimate suicide risk using a range of scores. In study 2, the named entity recognition model had an overall precision of 0.77, recall of 0.90 and F1 score of 0.83. The concept with the best precision and recall was medication (precision 0.84, recall 0.96) and the weakest were suicide (precision 0.37), and drug/alcohol use disorder (recall 0.61). Conclusions:It is feasible to estimate suicide risk with the OxMIS tool using predictors identified in routine clinical records. Predictors could be extracted using natural language processing. However, electronic health records differ from other data sources, particularly for family history variables, which creates methodological challenges.

SUBMITTER: Senior M

PROVIDER: S-EPMC7175991 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Identifying Predictors of Suicide in Severe Mental Illness: A Feasibility Study of a Clinical Prediction Rule (Oxford Mental Illness and Suicide Tool or OxMIS).

Senior Morwenna M Burghart Matthias M Yu Rongqin R Kormilitzin Andrey A Liu Qiang Q Vaci Nemanja N Nevado-Holgado Alejo A Pandit Smita S Zlodre Jakov J Fazel Seena S

Frontiers in psychiatry 20200415

<h4>Background</h4>Oxford Mental Illness and Suicide tool (OxMIS) is a brief, scalable, freely available, structured risk assessment tool to assess suicide risk in patients with severe mental illness (schizophrenia-spectrum disorders or bipolar disorder). OxMIS requires further external validation, but a lack of large-scale cohorts with relevant variables makes this challenging. Electronic health records provide possible data sources for external validation of risk prediction tools. However, the ...[more]

PMID: 32351413

Similar Datasets

Project description:BackgroundCurrent approaches to stratify patients with psychiatric disorders into groups on the basis of violence risk are limited by inconsistency, variable accuracy, and unscalability. To address the need for a scalable and valid tool to assess violence risk in patients with schizophrenia spectrum or bipolar disorder, we describe the derivation of a score based on routinely collected factors and present findings from external validation.MethodsOn the basis of a national cohort of 75 158 Swedish individuals aged 15-65 years with a diagnosis of severe mental illness (schizophrenia spectrum or bipolar disorder) with 574 018 patient episodes between Jan 1, 2001, and Dec 31, 2008, we developed predictive models for violent offending (primary outcome) within 1 year of hospital discharge for inpatients or clinical contact with psychiatric services for outpatients (patient episode) through linkage of population-based registers. We developed a derivation model to determine the relative influence of prespecified criminal history and sociodemographic and clinical risk factors, which are mostly routinely collected, and then tested it in an external validation. We measured discrimination and calibration for prediction of violent offending at 1 year using specified risk cutoffs.FindingsOf the cohort of 75 158 patients with schizophrenia spectrum or bipolar disorder, we assigned 58 771 (78%) to the derivation sample and 16 387 (22%) to the validation sample. In the derivation sample, 830 (1%) individuals committed a violent offence within 12 months of their patient episode. We developed a 16-item model. The strongest predictors of violent offending within 12 months were conviction for previous violent crime (adjusted odds ratio 5·03 [95% CI 4·23-5·98]; p<0·0001), male sex (2·32 [1·91-2·81]; p<0·0001), and age (0·63 per 10 years of age [0·58-0·67]; p<0·0001). In external validation, the model showed good measures of discrimination (c-index 0·89 [0·85-0·93]) and calibration. For risk of violent offending at 1 year, with a 5% cutoff, sensitivity was 62% (95% CI 55-68) and specificity was 94% (93-94). The positive predictive value was 11% and the negative predictive value was more than 99%. We used the model to generate a simple web-based risk calculator (Oxford Mental Illness and Violence tool [OxMIV]).InterpretationWe have developed a prediction score in a national cohort of patients with schizophrenia spectrum or bipolar disorder, which can be used as an adjunct to decision making in clinical practice by identifying those who are at low risk of violent offending. The low positive predictive value suggests that further clinical assessment in individuals at high risk of violent offending is required to establish who might benefit from additional risk management. Further validation in other countries is needed.FundingWellcome Trust and Swedish Research Council.

Project description:BackgroundTwo OxRisk risk assessment tools, the Oxford Mental Illness and Suicide (OxMIS) and the Oxford Mental Illness and Violence (OxMIV), were developed and validated using national linked registries in Sweden, to assess suicide and violence risk in individuals with severe mental illness (schizophrenia-spectrum disorders and bipolar disorders). In this study, we aim to examine the feasibility and acceptability of the tools in three different clinical services.MethodWe employed a two-step mixed-methods approach, by combining quantitative analyses of risk scores of 147 individual patients, and thematic analyses of qualitative data. First, 38 clinicians were asked to use OxMIS and OxMIV when conducting their routine risk assessments in patients with severe mental illness. The risk scores for each patient (which provide a probability of the outcome over 12 months) were then compared to the unstructured clinical risk assessment made by the treating clinician. Second, we carried out semi-structured interviews with the clinicians on the acceptability and utility of the tools. Thematic analysis was conducted on the qualitative data to identify common themes, in terms of the utility, accuracy, and acceptability of the tools. The investigations were undertaken in three general adult psychiatric clinics located in the cities of Barcelona and Sevilla (Spain), and Changsha (China).ResultsMedian risk probabilities over 12 months for OxMIS were 1.0% in the Spanish patient sample and 1.9% in the Chinese sample. For OxMIV, they were 0.7% (Spanish) and 0.8% (Chinese). In the thematic analysis, clinicians described the tools as easy to use, and thought that the risk score improved risk management. Potential additions to predictors were suggested, including family history and the patient's support network. Concordance rates of risk estimates between the tools and clinicians was high for violence (94.4%; 68/72) and moderate for suicide (50.0%; 36/72).ConclusionBoth OxMIS and OxMIV are feasible and practical in different general adult psychiatric settings. Clinicians interviewed found that both tools provide a useful structured approach to estimate the risk of suicide and violence. Risk scores from OxMIS and OxMIV can also be used to assist clinical decision-making for future management.

Project description:Interventions: We are assessing the impact of the National Bowel Cancer Screening Program (NBCSP) by comparing participation rates of people with and without Severe Mental Illness (SMI) and looking at health outcomes. We will be using data collected from Aug 2006 - latest available. We are linking data using Commonwealth data (NBCSP, Medicare Benefits Schedule, Pharmaceutical Benefits Scheme, Australian Cancer Database & the National Death Index) to compare bowel cancer screening participation in people with SMI to those from the general population. We will additionally link these to the NSW cancer registry and hospital data to examine care pathways from diagnosis through treatment and end-of-life care. We will also conduct a consultation with people with experience of SMI and Colorectal cancer and people with SMI in peer support roles who can provide their perspective on the barriers faced by people with SMI to gaining timely screening, diagnosis and optimal care. These participants will be recruited from New South Wales consumer organisations and organisations with a strong focus on provision of peer support and advocacy. We will use a semi structured group interview schedule to facilitate discussion of a single focus group of 15 people. The group will consist of both people with lived experience who have direct experience of bowel cancer (n=10), as well as other people with lived experience who have supported people in this situation – as peer support workers or in other consumer advocacy/support roles (n=5). We will use this qualitative arm of the study to further develop our understanding of the quantitative findings. The consultation will also develop ideas on how to improve access to care. Primary outcome(s): Participation rates in the National Bowel Cancer Screening Program assessed using data from the NBCSP.[Person-years will be calculated from entry into the study (2006) (the date of commencement of the NBCSP) or from the year that people become eligible for screening (i.e. age 50), whichever occurs later.. This is a retrospective cohort study, so all of the outcomes have already occurred and were recorded in the administrative data. This will be assessed when we receive the data.];Colonoscopy rates assessed using data from the NBCSP [Person-years will be calculated from entry into the study (2006 the date of commencement of the NBCSP), or from the year that people become eligible for screening (i.e. age 50), whichever occurs later, until colonoscopy. This is a retrospective cohort study, so all of the outcomes have already occurred and have been recorded in the administrative data.];Cancer diagnosis using data from the Australian Cancer Database[Person-years will be calculated from entry into the study (2006 the date of commencement of the NBCSP), or from the year that people become eligible for screening (i.e. age 50), whichever occurs later, until cancer diagnosis. This is a retrospective cohort study, so all of the outcomes have already occurred and have been recorded in the administrative data.] Study Design: Purpose: Screening;Duration: Longitudinal;Selection: Case control;Timing: Both

Project description:BACKGROUND:An advance directive is a document specifying a person's preferences for treatment, should he or she lose capacity to make such decisions in the future. They have been used in end-of-life settings to direct care but should be well suited to the mental health setting. OBJECTIVES:To examine the effects of advance treatment directives for people with severe mental illness. SEARCH STRATEGY:We searched the Cochrane Schizophrenia Group's Register (February 2008), the Cochrane Library (Issue 1 2008), BIOSIS (1985 to February 2008), CINAHL (1982 to February 2008), EMBASE (1980 to February 2008), MEDLINE (1966 to February 2008), PsycINFO (1872 to February 2008), as well as SCISEARCH and Google - Internet search engine (February 2008). We inspected relevant references and contacted first authors of included studies. SELECTION CRITERIA:We included all randomised controlled trials (RCTs), involving adults with severe mental illness, comparing any form of advance directive with standard care for health service and clinical outcomes. DATA COLLECTION AND ANALYSIS:We extracted data independently. For homogenous dichotomous data we calculated fixed-effect relative risk (RR) and 95% confidence intervals (CI) on an intention-to-treat basis. For continuous data, we calculated weighted mean differences (WMD) and their 95% confidence interval again using a fixed-effect model. MAIN RESULTS:We were able to include two trials involving 321 people with severe mental illnesses. There was no significant difference in hospital admission (n=160, 1 RCT, RR 0.69 0.5 to 1.0), or number of psychiatric outpatient attendances between participants given advanced treatment directives or usual care. Similarly, no significant differences were found for compliance with treatment, self harm or number of arrests. Participants given advanced treatment directives needed less use of social workers time (n=160, 1 RCT, WMD -106.00 CI -156.2 to -55.8) than the usual care group, and violent acts were also lower in the advanced directives group (n=160, 1 RCT, RR 0.27 CI 0.1 to 0.9, NNT 8 CI 6 to 92). The number of people leaving the study early were not different between groups (n=321, 2 RCTs, RR 0.92 CI 0.6 to 1.6). AUTHORS' CONCLUSIONS:There are too few data available to make definitive recommendations. More intensive forms of advance directive appear to show promise, but currently practice must be guided by evidence other than that derived from randomised trials. More trials are indicated to determine whether higher intensity interventions, such as joint crisis planning, have an effect on outcomes of clinical relevance.

Dataset Information

Identifying Predictors of Suicide in Severe Mental Illness: A Feasibility Study of a Clinical Prediction Rule (Oxford Mental Illness and Suicide Tool or OxMIS).

Publications

Identifying Predictors of Suicide in Severe Mental Illness: A Feasibility Study of a Clinical Prediction Rule (Oxford Mental Illness and Suicide Tool or OxMIS).

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets