Identification of the delivery of cognitive behavioural therapy for psychosis (CBTp) using a cross-sectional sample from electronic health records and open-text information in a large UK-based mental health case register

Just Not Enough: Utilization of Outpatient Psychotherapy Provided by Clinical Psychologists for Patients With Psychosis and Bipolar Disorder in Switzerland

Treatment guidelines state that evidence-based psychotherapy is effective for people with psychosis and bipolar disorder and should be offered during every phase of the treatment process. However, research has indicated a lack of outpatient psychotherapeutic services for this patient group, for example, in the United States or Germany. We extend this finding by presenting survey data from Switzerland. We surveyed 112 inpatients with a diagnosis of a schizophrenia spectrum disorder or bipolar disorder and assessed outpatient treatment over the 5 years prior to their index hospitalization by using retrospective self-reports. The survey focused on psychotherapy provided by clinical psychologists. Results indicate that only 23.2% of participants retrospectively reported having utilized any outpatient psychotherapy within the reporting period and only 8% of participants reported having received a number of outpatient sessions that reaches recommended levels of psychotherapy. Exploratory analyses did not detect a significant association between self-reported utilization of outpatient psychotherapy sessions and most demographic, psychiatric, and psychological attributes, but patients with a bipolar disorder diagnosis (vs schizophrenia spectrum diagnosis) reported having utilized outpatient treatment more often. These findings are preliminary. When replicated they highlight the need for increased access to outpatient psychotherapy and better alignment between guideline recommendations and outpatient supply.

Ethnic differences in receipt of psychological interventions in Early Intervention in Psychosis services in England - a cross-sectional study

There is some evidence of differences in psychosis care provision by ethnicity. We investigated variations in the receipt of Cognitive Behavioural Therapy for psychosis (CBTp) and family intervention across ethnic groups in Early Intervention in Psychosis (EIP) teams throughout England, where national policy mandates offering these interventions to all. We included data on 29,610 service users from the National Clinical Audit of Psychosis (NCAP), collected between 2018 and 2021. We conducted mixed effects logistic regression analyses to examine odds ratios of receiving an intervention (CBTp, family intervention, either intervention) across 17 ethnic groups while accounting for the effect of years and variance between teams and adjusting for individual- (age, gender, occupational status) and team-level covariates (care-coordinator caseload, inequalities strategies). Compared with White British people, every minoritized ethnic group, except those of mixed Asian-White and mixed Black African-White ethnicities, had significantly lower adjusted odds of receiving CBTp. People of Black African, Black Caribbean, non-African/Caribbean Black, non-British/Irish White, and of "any other" ethnicity also experienced significantly lower adjusted odds of receiving family intervention. Pervasive inequalities in receiving CBTp for first episode psychosis exist for almost all minoritized ethnic groups, and family intervention for many groups. Investigating how these inequalities arise should be a research priority.

International rates of receipt of psychological therapy for psychosis and schizophrenia: systematic review and meta-analysis

BACKGROUND

International clinical practice guidelines commonly recommend the provision of psychological therapies for psychosis and schizophrenia as an adjunct to medication. However, access to recommended therapies in routine clinical practice is limited. The aim of this review was to synthesise the available data on the provision of recommended psychological therapies for psychosis and schizophrenia across international mental health systems.

METHODS

Electronic databases (PsychINFO, Pubmed and EMBASE) were searched for audits, service evaluation projects, or surveys, which reported data on rates of offer or receipt of any recommended psychological therapy or therapeutic intervention as part of routine clinical care.

RESULTS

Twenty-two eligible studies from 9 countries were identified (N participants = 79,407). The most commonly recommended therapies in national guidelines were Cognitive-Behavioural Therapy for Psychosis (CBTp) and Family Interventions (FI). The overall pooled prevalence of rate of receipt of CBTp was 24% [95% CI 0.15-0.32] based on 15 studies (N = 42,494), with a higher rate of receipt of therapy found when pooling data from Early Intervention services only (41% [95% CI 0.21-0.60], 6 studies, N = 11,068). The overall pooled prevalence of rate of receipt of FI was 30% [95% CI 0.22-0.37] based on 14 studies (N = 13,863).

CONCLUSIONS

Overall rates of receipt of recommended psychological therapies for psychosis were low across the 9 countries data were available for in this review. However, there were high rates of heterogeneity across studies, meaning that pooled estimates should be interpreted with caution. Sources of heterogeneity included different service settings (e.g. early intervention vs. non-early intervention services), and varying methods used to collect the data (e.g. audit of electronic health records vs. self-report etc.). There were no available data from the continents of South America, Asia, or Africa, meaning that a truly global picture of provision of psychological therapies for psychosis and schizophrenia is currently lacking.

Recommended practices and ethical considerations for natural language processing-assisted observational research: A scoping review

An increasing number of studies have reported using natural language processing (NLP) to assist observational research by extracting clinical information from electronic health records (EHRs). Currently, no standardized reporting guidelines for NLP-assisted observational studies exist. The absence of detailed reporting guidelines may create ambiguity in the use of NLP-derived content, knowledge gaps in the current research reporting practices, and reproducibility challenges. To address these issues, we conducted a scoping review of NLP-assisted observational clinical studies and examined their reporting practices, focusing on NLP methodology and evaluation. Through our investigation, we discovered a high variation regarding the reporting practices, such as inconsistent use of references for measurement studies, variation in the reporting location (reference, appendix, and manuscript), and different granularity of NLP methodology and evaluation details. To promote the wide adoption and utilization of NLP solutions in clinical research, we outline several perspectives that align with the six principles released by the World Health Organization (WHO) that guide the ethical use of artificial intelligence for health.

Ethnic inequalities in involuntary admission under the Mental Health Act: an exploration of mediation effects of clinical care prior to the first admission

BACKGROUND

Studies show ethnic inequalities in rates of involuntary admission and types of clinical care (such as psychological therapies). However, few studies have investigated if there is a relationship between clinical care practices and ethnic inequalities in involuntary admission.

AIMS

This study investigated the impact of ethnicity and clinical care on involuntary admission and the potential mediation effects of prior clinical care.

METHOD

In this retrospective cohort study, we used data from the electronic records of the South London and Maudsley NHS Foundation Trust and identified patients with a first hospital admission between January 2008 and May 2021. Logistic regression and mediation analyses were used to investigate the association between ethnicity and involuntary admission, and whether clinical care, in the 12 months preceding admission, mediates the association.

RESULTS

Compared with White British people, higher odds of involuntary admission were observed among 10 of 14 minority ethnic groups; with more than twice the odds observed among people of Asian Chinese, of Asian Bangladeshi and of any Black background. There were some ethnic differences in clinical care prior to admission, but these had a minimal impact on the inequalities in involuntary admission. More out-patient appointments and home treatment were associated with higher odds of involuntary admission, whereas psychological therapies and having a care plan were associated with reduced odds of involuntary admission.

CONCLUSIONS

Ethnic inequalities in involuntary admission persist after accounting for potential mediating effects of several types and frequencies of clinical care. Promoting access to psychological therapies and ensuring that care plans are in place may reduce involuntary admissions.

A psychological intervention for engaging dialogically with auditory hallucinations (Talking With Voices): A single-site, randomised controlled feasibility trial

There is growing clinical interest in addressing relationship dynamics between service-users and their voices. The Talking With Voices (TwV) trial aimed to establish feasibility and acceptability of a novel dialogical intervention to reduce distress associated with voices amongst adults diagnosed with schizophrenia spectrum disorders. The single-site, single-blind (rater) randomised controlled trial recruited 50 participants who were allocated 1:1 to treatment as usual (TAU), or TAU plus up to 26 sessions of TwV therapy. Participants were assessed at baseline and again at end of treatment (six-months). The primary outcomes were quantitative and qualitative assessments of feasibility and acceptability. Secondary outcomes involved clinical measures, including targeted instruments for voice-hearing, dissociation, and emotional distress. The trial achieved 100 % of the target sample, 24 of whom were allocated to therapy and 26 to TAU. The trial had high retention (40/50 [80 %] participants at six-months) and high intervention adherence (21/24 [87.5 %] receiving ≥8 sessions). Signals of efficacy were shown in targeted measures of voice-hearing, dissociation, and perceptions of recovery. Analysis on the Positive and Negative Syndrome Scale indicated that there were no differences in means of general psychosis symptom scores in TwV compared to the control group. There were four serious adverse events in the therapy group and eight in TAU, none of which were related to study proceedings. The trial demonstrates the acceptability of the intervention and the feasibility of delivering it under controlled, randomised conditions. An adequately powered definitive trial is necessary to provide robust evidence regarding efficacy evaluation and cost-effectiveness. Trial registration: ISRCTN 45308981.

Ethnic inequalities in clozapine use among people with treatment-resistant schizophrenia: a retrospective cohort study using data from electronic clinical records

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.

Exploring how to improve access to psychological therapies on acute mental health wards from the perspectives of patients, families and mental health staff: qualitative study

BACKGROUND

Psychological therapy is core component of mental healthcare. However, many people with severe mental illnesses do not receive therapy, particularly in acute mental health settings.

AIMS

This study identifies barriers to delivering and accessing psychological therapies in acute mental health settings, and is the first to recommend how services can increase access from the perspectives of different stakeholders (staff, patients and carers).

METHOD

Sixty participants with experiences of acute mental health wards (26 staff, 22 patients and 12 carers) were interviewed about barriers to accessing therapy in in-patient settings and how therapies should be delivered to maximise access.

RESULTS

Four themes were identified: (a) 'Models of care', including the function of in-patient wards, beliefs about the causes of mental health problems and the importance of strong leadership to support psychosocial interventions; (b) 'Integrated care', including the importance of psychologists being ward-based, as well as having strong links with community teams; (c) 'Acute levels of distress', including factors that aggravate or ameliorate the impact of this on engagement in therapy; and (d) 'Enhancing staff capability and motivation', which is influenced by contextual issues.

CONCLUSIONS

It is possible to improve access to therapy through strong leadership (that is supportive of talking treatments), flexible delivery of therapy (that considers short admissions) and a whole-systems approach that promotes ward staff understanding of the psychosocial causes of mental illness and staff well-being. It is essential to ensure continuity between in-patient and community therapy services, and for wards to have physical space to carry out therapy.

SlowMo therapy, a new digital blended therapy for fear of harm from others: An account of therapy personalisation within a targeted intervention

OBJECTIVES

SlowMo therapy is a pioneering blended digital therapy for paranoia, augmenting face-to-face therapy with an interactive 'webapp' and a mobile app. A recent large-scale trial demonstrated small-moderate effects on paranoia alongside improvements in self-esteem, worry, well-being and quality of life. This paper provides a comprehensive account of therapy personalisation within this targeted approach.

DESIGN

Case examples illustrate therapy delivery and descriptive data are presented on personalised thought content.

METHOD

Thought content was extracted from the webapp (n = 140 participants) and coded using newly devised categories: Worries: (1) Persecutory, (2) Negative social evaluation, (3) Negative self-concept, (4) Loss/life stresses, (5) Sensory-perceptual experiences and (6) Health anxieties. Safer thoughts: (1) Safer alternative (specific alternatives to worries), (2) Second-wave (generalised) coping, (3) Positive self-concept, (4) Positive activities and (5) Third-wave (mindfulness-based) coping. Data on therapy fidelity are also presented.

RESULTS

Worries: 'Persecutory' (92.9% of people) and 'Negative social evaluation' (74.3%) were most common. 'General worries/ life stresses' (31.4%) and 'Negative self-concept' (22.1%) were present in a significant minority; 'Health anxieties' (10%) and 'Sensory-perceptual' (10%) were less common. Safer thoughts: 'Second-wave (general) coping' (85%), 'Safer alternatives' (76.4%), 'Positive self-concept' (65.7%) and 'Positive activities' (64.3%) were common with 'Third-wave' (mindfulness) coping observed for 30%. Fidelity: Only three therapy withdrawals were therapy related. Session adherence was excellent (mean = 15.2/16; SD = 0.9). Behavioural work was conducted with 71% of people (119/168).

CONCLUSION

SlowMo therapy delivers a targeted yet personalised approach. Potential mechanisms of action extend beyond reasoning. Implications for cognitive models of paranoia and causal interventionist approaches are discussed.

Association between depressive symptoms and cognitive-behavioural therapy receipt within a psychosis sample: a cross-sectional study

OBJECTIVES

To examine whether depressive symptoms predict receipt of cognitive-behavioural therapy for psychosis (CBTp) in individuals with psychosis.

DESIGN

Retrospective cross-sectional analysis of electronic health records (EHRs) of a clinical cohort.

SETTING

A secondary National Health Service mental healthcare service serving four boroughs of south London, UK.

PARTICIPANTS

20 078 patients diagnosed with an International Classification of Diseases, version 10 (ICD-10) code between F20 and 29 extracted from an EHR database.

PRIMARY AND SECONDARY OUTCOME MEASURES

Primary: Whether recorded depressive symptoms predicted CBTp session receipt, defined as at least one session of CBTp identified from structured EHR fields supplemented by a natural language processing algorithm. Secondary: Whether age, gender, ethnicity, symptom profiles (positive, negative, manic and disorganisation symptoms), a comorbid diagnosis of depression, anxiety or bipolar disorder, general CBT receipt prior to the primary psychosis diagnosis date or type of psychosis diagnosis predicted CBTp receipt.

RESULTS

Of patients with a psychotic disorder, only 8.2% received CBTp. Individuals with at least one depressive symptom recorded, depression symptom severity and 12 out of 15 of the individual depressive symptoms independently predicted CBTp receipt. Female gender, White ethnicity and presence of a comorbid affective disorder or primary schizoaffective diagnosis were independently positively associated with CBTp receipt within the whole sample and the top 25% of mentioned depressive symptoms.

CONCLUSIONS

Individuals with a psychotic disorder who had recorded depressive symptoms were significantly more likely to receive CBTp sessions, aligning with CBTp guidelines of managing depressive symptoms related to a psychotic experience. However, overall receipt of CBTp is low and more common in certain demographic groups, and needs to be increased.

Towards better care for women with schizophrenia-spectrum disorders

Women with a schizophrenia-spectrum disorder (SSD) have a better clinical profile than do men at the start of their illness but progress to the same state within the first few years of living with SSD. There are benefits to be gained across different areas in the care currently offered to women with psychosis. An important point for improvement is the early detection of female-specific signs of a first episode of psychosis, to shorten the duration of untreated psychosis, with prompt access to early intervention services. Special attention should be paid to sexual health, and to any history of childhood trauma. Antipsychotics require dosing and prescription tailored to the female physiology that consider hormonal life phases such as menopause. Switching to prolactin-sparing medications can benefit both mental and somatic health. Finally, hormone replacement therapy should be considered for postmenopausal women. By providing female-specific care, women with schizophrenia-spectrum disorders will have optimal chances to fare well.

Using Natural Language Processing on Electronic Health Records to Enhance Detection and Prediction of Psychosis Risk

BACKGROUND

Using novel data mining methods such as natural language processing (NLP) on electronic health records (EHRs) for screening and detecting individuals at risk for psychosis.

METHOD

The study included all patients receiving a first index diagnosis of nonorganic and nonpsychotic mental disorder within the South London and Maudsley (SLaM) NHS Foundation Trust between January 1, 2008, and July 28, 2018. Least Absolute Shrinkage and Selection Operator (LASSO)-regularized Cox regression was used to refine and externally validate a refined version of a five-item individualized, transdiagnostic, clinically based risk calculator previously developed (Harrell's C = 0.79) and piloted for implementation. The refined version included 14 additional NLP-predictors: tearfulness, poor appetite, weight loss, insomnia, cannabis, cocaine, guilt, irritability, delusions, hopelessness, disturbed sleep, poor insight, agitation, and paranoia.

RESULTS

A total of 92 151 patients with a first index diagnosis of nonorganic and nonpsychotic mental disorder within the SLaM Trust were included in the derivation (n = 28 297) or external validation (n = 63 854) data sets. Mean age was 33.6 years, 50.7% were women, and 67.0% were of white race/ethnicity. Mean follow-up was 1590 days. The overall 6-year risk of psychosis in secondary mental health care was 3.4 (95% CI, 3.3-3.6). External validation indicated strong performance on unseen data (Harrell's C 0.85, 95% CI 0.84-0.86), an increase of 0.06 from the original model.

CONCLUSIONS

Using NLP on EHRs can considerably enhance the prognostic accuracy of psychosis risk calculators. This can help identify patients at risk of psychosis who require assessment and specialized care, facilitating earlier detection and potentially improving patient outcomes.

The Potential of Research Drawing on Clinical Free Text to Bring Benefits to Patients in the United Kingdom: A Systematic Review of the Literature

Background: The analysis of clinical free text from patient records for research has potential to contribute to the medical evidence base but access to clinical free text is frequently denied by data custodians who perceive that the privacy risks of data-sharing are too high. Engagement activities with patients and regulators, where views on the sharing of clinical free text data for research have been discussed, have identified that stakeholders would like to understand the potential clinical benefits that could be achieved if access to free text for clinical research were improved. We aimed to systematically review all UK research studies which used clinical free text and report direct or potential benefits to patients, synthesizing possible benefits into an easy to communicate taxonomy for public engagement and policy discussions. Methods: We conducted a systematic search for articles which reported primary research using clinical free text, drawn from UK health record databases, which reported a benefit or potential benefit for patients, actionable in a clinical environment or health service, and not solely methods development or data quality improvement. We screened eligible papers and thematically analyzed information about clinical benefits reported in the paper to create a taxonomy of benefits. Results: We identified 43 papers and derived five themes of benefits: health-care quality or services improvement, observational risk factor-outcome research, drug prescribing safety, case-finding for clinical trials, and development of clinical decision support. Five papers compared study quality with and without free text and found an improvement of accuracy when free text was included in analytical models. Conclusions: Findings will help stakeholders weigh the potential benefits of free text research against perceived risks to patient privacy. The taxonomy can be used to aid public and policy discussions, and identified studies could form a public-facing repository which will help the health-care text analysis research community better communicate the impact of their work.

Who gets evidence-based therapy for psychosis following a psychiatric hospital admission? Follow-up data from an inpatient randomised controlled trial

A major barrier to clinicians referring service users with psychosis for psychological therapies is the belief that they will not engage. We investigated therapy receipt after discharge, in a sample of service users who had already demonstrated willingness to engage in psychological therapy during an inpatient admission. Only one-third of service users (33%; 16/48) received at least 1 session of evidence-based therapy at 6-month follow-up after discharge. Therapy receipt was more common for service users with (i) lower delusional distress at discharge, (ii) Black and Minority Ethnic (BME) background, and (iii) discharged to an Early Intervention (EI) service.

Ethnicity and impact on the receipt of cognitive-behavioural therapy in people with psychosis or bipolar disorder: an English cohort study

OBJECTIVES

(1) To explore the role of ethnicity in receiving cognitive-behavioural therapy (CBT) for people with psychosis or bipolar disorder while adjusting for differences in risk profiles and symptom severity. (2) To assess whether context of treatment (inpatient vs community) impacts on the relationship between ethnicity and access to CBT.

DESIGN

Cohort study of case register data from one catchment area (January 2007-July 2017).

SETTING

A large secondary care provider serving an ethnically diverse population in London.

PARTICIPANTS

Data extracted for 30 497 records of people who had diagnoses of bipolar disorder (International Classification of Diseases (ICD) code F30-1) or psychosis (F20-F29 excluding F21). Exclusion criteria were: <15 years old, missing data and not self-defining as belonging to one of the larger ethnic groups. The sample (n=20 010) comprised the following ethnic groups: white British: n=10 393; Black Caribbean: n=5481; Black African: n=2817; Irish: n=570; and 'South Asian' people (consisting of Indian, Pakistani and Bangladeshi people): n=749.

OUTCOME ASSESSMENTS

ORs for receipt of CBT (single session or full course) as determined via multivariable logistic regression analyses.

RESULTS

In models adjusted for risk and severity variables, in comparison with White British people; Black African people were less likely to receive a single session of CBT (OR 0.73, 95% CI 0.66 to 0.82, p<0.001); Black Caribbean people were less likely to receive a minimum of 16-sessions of CBT (OR 0.83, 95% CI 0.71 to 0.98, p=0.03); Black African and Black Caribbean people were significantly less likely to receive CBT while inpatients (respectively, OR 0.76, 95% CI 0.65 to 0.89, p=0.001; OR 0.83, 95% CI 0.73 to 0.94, p=0.003).

CONCLUSIONS

This study highlights disparity in receipt of CBT from a large provider of secondary care in London for Black African and Caribbean people and that the context of therapy (inpatient vs community settings) has a relationship with disparity in access to treatment.

Mindfulness for psychosis groups; description and preliminary evaluation of a novel routine care pathway in Hong Kong

Background

There is no current guidance on where Mindfulness for Psychosis groups should best be situated within care pathways. The objectives of this paper are to (1) describe a novel care pathway tested out in a psychiatric outpatient service in Hong Kong, and (2) to present feasibility outcomes on attendance and drop-out, and routine clinical outcomes.

Methods

A new mindfulness pathway was set up, for service users with psychosis who had first completed a course of Cognitive Behavioural Therapy for psychosis (CBTp). After attending an orientation ‘taster’ session, service users could then attended a 4-session weekly Mindfulness for Psychosis group, followed by optional monthly follow-up sessions.

Results

A high proportion of service users referred into the pathway (19/22; 86%) went on to attend a Mindfulness for Psychosis group after attending an orientation ‘taster’ session. Attendance at group sessions was high, with all participants attending at least 2/4 group sessions, and no drop-outs. Attendance at monthly follow-up groups was also high, with 84% (16/19) attending at least one monthly follow-up. Routine clinical outcome data showed a reduction in negative symptoms of psychosis, and an increase in mindfulness and mindful responding in daily life, from pre- to post group.

Conclusions

Offering service users with psychosis the opportunity to attend a mindfulness for psychosis group after completing a course of CBTp was highly acceptable, as evidenced by high attendance, and low drop-out. Possible benefits in terms of improving negative symptoms may be particularly important in promoting recovery through improved everyday functioning.

Toward the Development of Data Governance Standards for Using Clinical Free-Text Data in Health Research: Position Paper

BACKGROUND

Clinical free-text data (eg, outpatient letters or nursing notes) represent a vast, untapped source of rich information that, if more accessible for research, would clarify and supplement information coded in structured data fields. Data usually need to be deidentified or anonymized before they can be reused for research, but there is a lack of established guidelines to govern effective deidentification and use of free-text information and avoid damaging data utility as a by-product.

OBJECTIVE

This study aimed to develop recommendations for the creation of data governance standards to integrate with existing frameworks for personal data use, to enable free-text data to be used safely for research for patient and public benefit.

METHODS

We outlined data protection legislation and regulations relating to the United Kingdom for context and conducted a rapid literature review and UK-based case studies to explore data governance models used in working with free-text data. We also engaged with stakeholders, including text-mining researchers and the general public, to explore perceived barriers and solutions in working with clinical free-text.

RESULTS

We proposed a set of recommendations, including the need for authoritative guidance on data governance for the reuse of free-text data, to ensure public transparency in data flows and uses, to treat deidentified free-text data as potentially identifiable with use limited to accredited data safe havens, and to commit to a culture of continuous improvement to understand the relationships between the efficacy of deidentification and reidentification risks, so this can be communicated to all stakeholders.

CONCLUSIONS

By drawing together the findings of a combination of activities, we present a position paper to contribute to the development of data governance standards for the reuse of clinical free-text data for secondary purposes. While working in accordance with existing data governance frameworks, there is a need for further work to take forward the recommendations we have proposed, with commitment and investment, to assure and expand the safe reuse of clinical free-text data for public benefit.

'Real time' monitoring of antipsychotic prescribing in patients with dementia: a study using the Clinical Record Interactive Search (CRIS) platform to enhance safer prescribing

BACKGROUND

The use of antipsychotic drugs in dementia has been reported to be associated with increased risk of cerebrovascular events and mortality. There is an international drive to reduce the use of these agents in patients with dementia and to improve the safety of prescribing and monitoring in this area.

OBJECTIVES

The aim of this project was to use enhanced automated regular feedback of information from electronic health records to improve the quality of antipsychotic prescribing and monitoring in people with dementia.

METHODS

The South London and Maudsley NHS Foundation Trust (SLaM) incorporated antipsychotic monitoring forms into its electronic health records. The SLaM Clinical Record Interactive Search (CRIS) platform provides researcher access to de-identified health records, and natural language processing is used in CRIS to derive structured data from unstructured free text, including recorded diagnoses and medication. Algorithms were thus developed to ascertain patients with dementia receiving antipsychotic treatment and to determine whether monitoring forms had been completed. We used two improvement plan-do-study-act cycles to improve the accuracy of the algorithm for automated evaluation and provided monthly feedback on team performance.

RESULTS

A steady increase in antipsychotic monitoring form completion was observed across the study period. The percentage of our sample with a completed antipsychotic monitoring form more than doubled from October 2017 (22%) to January 2019 (58%).

CONCLUSION

'Real time' monitoring and regular feedback to teams offer a time-effective approach, complementary to standard audit methods, to enhance the safer prescribing of high risk drugs.

Predicting high-cost care in a mental health setting

BACKGROUND

The density of information in digital health records offers new potential opportunities for automated prediction of cost-relevant outcomes.

AIMS

We investigated the extent to which routinely recorded data held in the electronic health record (EHR) predict priority service outcomes and whether natural language processing tools enhance the predictions. We evaluated three high priority outcomes: in-patient duration, readmission following in-patient care and high service cost after first presentation.

METHOD

We used data obtained from a clinical database derived from the EHR of a large mental healthcare provider within the UK. We combined structured data with text-derived data relating to diagnosis statements, medication and psychiatric symptomatology. Predictors of the three different clinical outcomes were modelled using logistic regression with performance evaluated against a validation set to derive areas under receiver operating characteristic curves.

RESULTS

In validation samples, the full models (using all available data) achieved areas under receiver operating characteristic curves between 0.59 and 0.85 (in-patient duration 0.63, readmission 0.59, high service use 0.85). Adding natural language processing-derived data to the models increased the variance explained across all clinical scenarios (observed increase in r2 = 12-46%).

CONCLUSIONS

EHR data offer the potential to improve routine clinical predictions by utilising previously inaccessible data. Of our scenarios, prediction of high service use after initial presentation achieved the highest performance.

Use of Natural Language Processing to identify Obsessive Compulsive Symptoms in patients with schizophrenia, schizoaffective disorder or bipolar disorder

Obsessive and Compulsive Symptoms (OCS) or Obsessive Compulsive Disorder (OCD) in the context of schizophrenia or related disorders are of clinical importance as these are associated with a range of adverse outcomes. Natural Language Processing (NLP) applied to Electronic Health Records (EHRs) presents an opportunity to create large datasets to facilitate research in this area. This is a challenging endeavour however, because of the wide range of ways in which these symptoms are recorded, and the overlap of terms used to describe OCS with those used to describe other conditions. We developed an NLP algorithm to extract OCS information from a large mental healthcare EHR data resource at the South London and Maudsley NHS Foundation Trust using its Clinical Record Interactive Search (CRIS) facility. We extracted documents from individuals who had received a diagnosis of schizophrenia, schizoaffective disorder, or bipolar disorder. These text documents, annotated by human coders, were used for developing and refining the NLP algorithm (600 documents) with an additional set reserved for final validation (300 documents). The developed NLP algorithm utilized a rules-based approach to identify each of symptoms associated with OCS, and then combined them to determine the overall number of instances of OCS. After its implementation, the algorithm was shown to identify OCS with a precision and recall (with 95% confidence intervals) of 0.77 (0.65-0.86) and 0.67 (0.55-0.77) respectively. The development of this application demonstrated the potential to extract complex symptomatic data from mental healthcare EHRs using NLP to facilitate further analyses of these clinical symptoms and their relevance for prognosis and intervention response.

Stepped Care as an Implementation and Service Delivery Model for Cognitive Behavioral Therapy for Psychosis

Cognitive behavioral therapy for schizophrenia spectrum disorders is an evidence-based treatment that is recommended by United States schizophrenia treatment guidelines. Based on recent estimates, only 0.3% of individuals with a primary psychotic disorder are able to access this treatment in the United States. Stepped care interventions have shown promise as an applied treatment delivery model in other settings and for other psychotherapeutic interventions. The current paper describes how the stepped care model can be applied to CBT for psychosis in the US to increase access to the intervention in community mental health settings by leveraging the multidisciplinary team.

Improving Access to psychological therapies for people with severe mental illness (IAPT-SMI): Lessons from the South London and Maudsley psychosis demonstration site

Implementation of evidence-based cognitive behavioural therapy for psychosis (CBTp) remains low in routine services. The United Kingdom Improving Access to Psychological Therapies for people with Severe Mental Illness (IAPT-SMI) initiative aimed to address this issue. The project evaluated whether existing services could improve access to CBTp and demonstrate effectiveness using a systematic approach to therapy provision and outcome monitoring (in a similar way to the Improving Access to Psychological Therapies (IAPT) model for people with anxiety and depression). We report the clinical outcomes and key learning points from the South London and Maudsley NHS Foundation Trust IAPT-SMI demonstration site for psychosis. Additional funding enabled increased therapist capacity within existing secondary care community mental health services. Self-reported wellbeing and psychotic symptom outcomes were assessed, alongside service use and social/occupational functioning. Accepted referrals/year increased by 89% (2011/12: n = 106/year; 2012-2015: n = 200/year); 90% engaged (attended ≥5 sessions) irrespective of ethnicity, age and gender. The assessment protocol proved feasible, and pre-post outcomes (n = 280) showed clinical improvements and reduced service use, with medium effects. We conclude that, with appropriate service structure, investment allocated specifically for competent therapy provision leads to increased and effective delivery of CBTp. Our framework is replicable in other settings and can inform the wider implementation of psychological therapies for psychosis.

How Inclusive, User-Centered Design Research Can Improve Psychological Therapies for Psychosis: Development of SlowMo

BACKGROUND

Real-world implementation of psychological interventions for psychosis is poor. Barriers include therapy being insufficiently usable and useful for a diverse range of people. User-centered, inclusive design approaches could improve the usability of therapy, which may increase uptake, adherence, and effectiveness.

OBJECTIVE

This study aimed to optimize the usability of an existing psychological intervention, Thinking Well, which targets reasoning processes in paranoia using a basic digital interface.

METHODS

We conducted inclusive, user-centered design research characterized by purposive sampling of extreme users from the margins of groups, ethnographic investigation of the problem context, and iterative prototyping of solutions. The UK Design Council's double diamond method was used. This consisted of 4 phases: discover, including a case series of Thinking Well, stakeholder interviews, desk research, user profiling, system mapping, and a mood board; define, consisting of workshops to synthesize findings and generate the design brief; develop, involving concept workshops and prototype testing; and deliver, in which the final minimal viable product was storyboarded and iteratively coded.

RESULTS

Consistent with our previous work, the Thinking Well case series showed medium to large effects on paranoia and well-being and small effects on reasoning. These were maintained at follow-up despite some participants reporting difficulties with the therapy interface. Insights from the discover phase confirmed that usability was challenged by information complexity and poor accessibility. Participants were generally positive about the potential of technology to be enjoyable, help manage paranoia, and provide tailored interpersonal support from therapists and peers, although they reported privacy and security concerns. The define phase highlighted that the therapy redesign should support monitoring, simplify information processing, enhance enjoyment and trust, promote personalization and normalization, and offer flexible interpersonal support. During the develop phase over 60 concepts were created, with 2 key concepts of thoughts visualized as bubbles and therapy as a journey selected for storyboarding. The output of the deliver phase was a minimal viable product of an innovative digital therapy, SlowMo. SlowMo works by helping people to notice their worries and fast thinking habits, and encourages them to slow down for a moment to find ways of feeling safer. A Web app supports the delivery of 8 face-to-face sessions, which are synchronized to a native mobile app.

CONCLUSIONS

SlowMo makes use of personalization, ambient information, and visual metaphors to tailor the appeal, engagement, and memorability of therapy to a diversity of needs. Feasibility testing has been promising, and the efficacy of SlowMo therapy is now being tested in a multicentered randomized controlled trial. The study demonstrates that developments in psychological theory and techniques can be enhanced by improving the usability of the therapy interface to optimize its impact in daily life.