Data science and pharmacoepidemiology for outcome improvement in severe mental illness (DS-SMI)
Lead Research Organisation:
University College London
Department Name: Division of Psychiatry
Abstract
People with severe mental illness (SMI), including schizophrenia, bipolar disorder and other psychotic illness often only partially respond to drug treatment. They also experience medication adverse effects, and increased morbidity and mortality compared to the general population. There is a desperate need to improve pharmacological treatment of SMI. Two cost effective approaches to addressing this problem are to i) improve response to existing medication via personalisation, and ii) identify drugs already in existence (with different indications) that can be repurposed to treat psychiatric symptoms.
These complimentary translational research streams will harness the power of large routine health registers, electronic health records and mobile phone applications, along with modern statistical and machine learning techniques for prediction modelling and causal inference. Data will come from the United Kingdom, United States, Sweden, Denmark, Hong Kong and Taiwan.
PERSONALISING DRUG TREATMENT
This research stream will advance my current work on prediction of maintenance treatment response in individuals with bipolar disorder using machine learning.
Despite recent progress in the field of treatment personalisation, psychiatry lags behind other medical specialties. Currently, no validated system of tailoring treatment choices is available and matching treatment to specific patients is often a matter of trial and error. Via prediction modelling clinicians could more precisely select treatment for patients' needs and thus improve their outcomes. This research stream will focus on:
i) Identifying predictors of treatment response in patients during their first illness episode
ii) Predicting which individuals will not have their symptoms adequately treated after trials of two medications (treatment resistance)
iii) Predicting adverse effects, including weight gain, restlessness (akathisia) and excess sedation
Clinical features contained in medical records have been shown to be associated with response, treatment resistance and adverse effects, but these have not been combined in a systematic way. The scale and widespread use of electronic health records globally now allows for use of multiple data sets for external validation of generated models.
There may also be important changes early in the course of treatment that can predict long term outcomes. These changes are unlikely to be captured in electronic health records, but may be available via patients mobile phones. Capture of passive data via phone apps is now straightforward and potentially contains markers of changes in mental state, such as sleep, movement and phone usage. Apps also facilitate remote symptom monitoring and performance of cognitive tasks. This information will be used to further enhance prediction models. The models built during the early stage of this fellowship will be tested at scale in clinical populations via implementation science methods.
IDENTIFYING AND TESTING TARGETS FOR DRUG REPURPOSING
This translational research stream builds on my previous work which examined whether a number of drugs identified as having potential for repurposing had effects on psychiatric hospitalisation and self-harm rates in patients with SMI.
There are a number of other drugs which should be examined via similar approaches to validate these signals for potential effectiveness, whilst robustly accounting for potential confounding, these include a range of anti-inflammatory agents. This work will be cross-validated in other international data sets.
The process of pharmacoepidemiological validation optimises the chance of success and provides guidance on which drugs to take forward to randomised controlled trial (RCT). Towards the end of this fellowship I will develop the protocol necessary for a large adaptive RCT and run a pilot to assess feasibility and acceptability.
These complimentary translational research streams will harness the power of large routine health registers, electronic health records and mobile phone applications, along with modern statistical and machine learning techniques for prediction modelling and causal inference. Data will come from the United Kingdom, United States, Sweden, Denmark, Hong Kong and Taiwan.
PERSONALISING DRUG TREATMENT
This research stream will advance my current work on prediction of maintenance treatment response in individuals with bipolar disorder using machine learning.
Despite recent progress in the field of treatment personalisation, psychiatry lags behind other medical specialties. Currently, no validated system of tailoring treatment choices is available and matching treatment to specific patients is often a matter of trial and error. Via prediction modelling clinicians could more precisely select treatment for patients' needs and thus improve their outcomes. This research stream will focus on:
i) Identifying predictors of treatment response in patients during their first illness episode
ii) Predicting which individuals will not have their symptoms adequately treated after trials of two medications (treatment resistance)
iii) Predicting adverse effects, including weight gain, restlessness (akathisia) and excess sedation
Clinical features contained in medical records have been shown to be associated with response, treatment resistance and adverse effects, but these have not been combined in a systematic way. The scale and widespread use of electronic health records globally now allows for use of multiple data sets for external validation of generated models.
There may also be important changes early in the course of treatment that can predict long term outcomes. These changes are unlikely to be captured in electronic health records, but may be available via patients mobile phones. Capture of passive data via phone apps is now straightforward and potentially contains markers of changes in mental state, such as sleep, movement and phone usage. Apps also facilitate remote symptom monitoring and performance of cognitive tasks. This information will be used to further enhance prediction models. The models built during the early stage of this fellowship will be tested at scale in clinical populations via implementation science methods.
IDENTIFYING AND TESTING TARGETS FOR DRUG REPURPOSING
This translational research stream builds on my previous work which examined whether a number of drugs identified as having potential for repurposing had effects on psychiatric hospitalisation and self-harm rates in patients with SMI.
There are a number of other drugs which should be examined via similar approaches to validate these signals for potential effectiveness, whilst robustly accounting for potential confounding, these include a range of anti-inflammatory agents. This work will be cross-validated in other international data sets.
The process of pharmacoepidemiological validation optimises the chance of success and provides guidance on which drugs to take forward to randomised controlled trial (RCT). Towards the end of this fellowship I will develop the protocol necessary for a large adaptive RCT and run a pilot to assess feasibility and acceptability.
Organisations
- University College London (Fellow, Lead Research Organisation)
- University College London (Collaboration)
- University of Hong Kong (Collaboration)
- Karolinska Institute (Collaboration)
- London School of Hygiene and Tropical Medicine (LSHTM) (Collaboration)
- Statistics Denmark (Collaboration)
- Royal Institute of Technology (Collaboration)
Publications
Launders N
(2022)
The temporal relationship between severe mental illness diagnosis and chronic physical comorbidity: a UK primary care cohort study of disease burden over 10 years.
in The lancet. Psychiatry
Chan VK
(2022)
Mortality-causing mechanisms and healthcare resource utilisation of treatment-resistant depression: A six-year population-based cohort study.
in The Lancet regional health. Western Pacific
Hayes J
(2023)
You Can't Manage What You Do Not Measure - Why Adolescent Mental Health Monitoring Matters.
in The Journal of adolescent health : official publication of the Society for Adolescent Medicine
Jeffery A
(2023)
Association between polypharmacy and depression relapse in individuals with comorbid depression and type 2 diabetes: a UK electronic health record study.
in The British journal of psychiatry : the journal of mental science
Jeffery A
(2023)
Polypharmacy and antidepressant acceptability in comorbid depression and type 2 diabetes: a cohort study using UK primary care data.
in The British journal of general practice : the journal of the Royal College of General Practitioners
Adesanya EI
(2023)
Factors associated with depression, anxiety and severe mental illness among adults with atopic eczema or psoriasis: a systematic review and meta-analysis.
in The British journal of dermatology
Bechman K
(2023)
Electronic screening for mental illness in patients with psoriasis.
in The British journal of dermatology
Shoham N
(2023)
Association between visual impairment and psychosis: A longitudinal study and nested case-control study of adults.
in Schizophrenia research
Launders N
(2022)
Cancer rates and mortality in people with severe mental illness: Further evidence of lack of parity.
in Schizophrenia research
Shoham N
(2022)
Association Between Childhood Visual Acuity and Late Adolescent Psychotic Experiences: A Prospective Birth Cohort Study.
in Schizophrenia bulletin
Ng VWS
(2023)
Association between the pharmacological treatment of bipolar disorder and risk of traumatic injuries: a self-controlled case series study.
in Psychological medicine
Launders N
(2022)
The incidence rate of planned and emergency physical health hospital admissions in people diagnosed with severe mental illness: a cohort study
in Psychological Medicine
Yang JC
(2023)
Antipsychotic polypharmacy and adverse drug reactions among adults in a London mental health service, 2008-2018.
in Psychological medicine
Dykxhoorn J
(2023)
Objective and subjective neighbourhood characteristics and suicidality: a multilevel analysis.
in Psychological medicine
Kandola A
(2022)
Device-measured sedentary behaviour and anxiety symptoms during adolescence: a 6-year prospective cohort study.
in Psychological medicine
Ng VWS
(2023)
Association between the mood stabilizing treatment of bipolar disorder and risk of suicide attempts: A self-controlled case series study.
in Psychiatry research
Hogstedt C
(2023)
Long-term stability in obsessive thoughts and compulsive behavior in the general population: a longitudinal study in Sweden
in Nordic Journal of Psychiatry
Chan AYL
(2023)
Gabapentinoid consumption in 65 countries and regions from 2008 to 2018: a longitudinal trend study.
in Nature communications
Jauhar S
(2023)
A leaky umbrella has little value: evidence clearly indicates the serotonin system is implicated in depression.
in Molecular psychiatry
Hayes JF
(2022)
Association between quetiapine use and self-harm outcomes among people with recorded personality disorder in UK primary care: A self-controlled case series analysis.
in Journal of psychopharmacology (Oxford, England)
Ye X
(2023)
Association between statins and the risk of suicide attempt, depression, anxiety, and seizure: A population-based, self-controlled case series study.
in Journal of affective disorders
Kandola A
(2022)
Impact on adolescent mental health of replacing screen-use with exercise: A prospective cohort study.
in Journal of affective disorders
Opie E
(2023)
Suicidality in patients with post-traumatic stress disorder and its association with receipt of specific secondary mental healthcare treatments.
in International journal of psychiatry in clinical practice
Bschor T
(2022)
Letter of response to Nabi Z, Stansfeld J, Plöderl M, Wood L, Moncrieff J. Effects of lithium on suicide and suicidal behaviour: a systematic review and meta-analysis of randomised trials. Epidemiol Psychiatr Sci. 2022 Sep 16;31:e65. doi: 10.1017/S204579602200049X.
in Epidemiology and psychiatric sciences
Adesanya E
(2023)
Severe Mental Illness Among Adults with Atopic Eczema or Psoriasis: Population-Based Matched Cohort Studies within UK Primary Care
in Clinical Epidemiology
Matthewman J
(2023)
Anxiety and Depression in People with Eczema or Psoriasis: A Comparison of Associations in UK Biobank and Linked Primary Care Data.
in Clinical epidemiology
Henderson A
(2023)
Common mental health disorders in adults with inflammatory skin conditions: nationwide population-based matched cohort studies in the UK
in BMC Medicine
Shoham N
(2023)
Investigating the association between schizophrenia and distance visual acuity: Mendelian randomisation study.
in BJPsych open
Kandola A
(2023)
Real-time air pollution and bipolar disorder symptoms: remote-monitored cross-sectional study
in BJPsych Open
Bauernfreund Y
(2023)
Incidence and associations of hospital delirium diagnoses in 85,979 people with severe mental illness: A data linkage study.
in Acta psychiatrica Scandinavica
Description | https://www.gov.uk/government/publications/premature-mortality-during-covid-19-in-adults-with-severe-mental-illness/premature-mortality-during-covid-19-in-adults-with-severe-mental-illness |
First Year Of Impact | 2023 |
Sector | Healthcare |
Impact Types | Policy & public services |
Guideline Title | Addressing health inequalities: Developing a better understanding of physical health checks for people with severe mental illness from Black African and Caribbean communities |
Description | Addressing health inequalities: Developing a better understanding of physical health checks for people with severe mental illness from Black African and Caribbean communities |
Geographic Reach | National |
Policy Influence Type | Citation in clinical guidelines |
URL | https://raceequalityfoundation.org.uk/wp-content/uploads/2022/11/REF-SMI-Report-Nov-2022.pdf |
Description | COVID impact on SMI |
Geographic Reach | National |
Policy Influence Type | Contribution to a national consultation/review |
Impact | Increased monitoring in people with SMI |
URL | https://www.gov.uk/government/publications/premature-mortality-during-covid-19-in-adults-with-severe... |
Description | The Severe Mental Illness Profiling tool is part of a suite that make population level data on mental health publicly available, and supports an intelligence driven approach to understanding and meeting need. |
Geographic Reach | National |
Policy Influence Type | Participation in a guidance/advisory committee |
Impact | Monitoring of morbidity and mortality in people with severe mental illness has led to changes in screening and QOF measures for addressing these inequalities. |
URL | https://fingertips.phe.org.uk/profile-group/mental-health/profile/severe-mental-illness |
Description | NIHR School for Primary Care Research |
Amount | £61,066 (GBP) |
Organisation | National Institute for Health Research |
Sector | Public |
Country | United Kingdom |
Start | 01/2023 |
End | 01/2024 |
Description | Hong Kong University data science |
Organisation | University of Hong Kong |
Country | Hong Kong |
Sector | Academic/University |
PI Contribution | Methodological input |
Collaborator Contribution | Data input |
Impact | Ye X, Blais JE, Ng VW, Castle D, Hayes JF, Wei Y, Kang W, Gao L, Yan VK, Wong IC, Chan EW. Association between statins and the risk of suicide attempt, depression, anxiety, and seizure: A population-based, self-controlled case series study. Journal of affective disorders. 2023 Jan 1;320:421-7. Wei Y, Yan VK, Kang W, Wong I, Castle DJ, Gao L, Chui CS, Man K, Hayes JF, Chang WC, Chan EW. Disease relapse, healthcare utilization and adverse events associated with the use of long-acting injectable antipsychotics versus oral antipsychotics in people with schizophrenia: A self-controlled case series study. InPHARMACOEPIDEMIOLOGY AND DRUG SAFETY 2022 Sep 1 (Vol. 31, pp. 344-344). 111 RIVER ST, HOBOKEN 07030-5774, NJ USA: WILEY. Wei Y, Yan VK, Kang W, Wong IC, Castle DJ, Gao L, Chui CS, Man KK, Hayes JF, Chang WC, Chan EW. Association of Long-Acting Injectable Antipsychotics and Oral Antipsychotics With Disease Relapse, Health Care Use, and Adverse Events Among People With Schizophrenia. JAMA Network Open. 2022 Jul 1;5(7):e2224163-. Ng VW, Gao L, Chan EW, Lee HM, Hayes JF, Osborn DP, Rainer TH, Man KK, Wong IC. Association between the pharmacological treatment of bipolar disorder and risk of traumatic injuries: a self-controlled case series study. Psychological medicine. 2022 Jul 1:1-9. Ng VW, Man KK, Gao L, Chan EW, Lee EH, Hayes JF, Wong IC. Bipolar disorder prevalence and psychotropic medication utilisation in Hong Kong and the United Kingdom. Pharmacoepidemiology and drug safety. 2021 Nov;30(11):1588-600.\ Ng VW, Man KK, Gao L, Chan EW, Hayes JF, Wong IC. Association between the use of mood stabilizers and risk of trauma among patients with bipolar disorder. InPHARMACOEPIDEMIOLOGY AND DRUG SAFETY 2021 Aug 1 (Vol. 30, pp. 150-151). 111 RIVER ST, HOBOKEN 07030-5774, NJ USA: WILEY. |
Start Year | 2019 |
Description | KABRIS |
Organisation | Karolinska Institute |
Country | Sweden |
Sector | Academic/University |
PI Contribution | Study design, data analysis, manuscript drafting |
Collaborator Contribution | Data provision, data management |
Impact | n/a |
Start Year | 2016 |
Description | LSHTM |
Organisation | London School of Hygiene and Tropical Medicine (LSHTM) |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | Data provision, study design, drafting manuscript |
Collaborator Contribution | Data provision, study design, data analysis, drafting manuscript |
Impact | Conference presentations. |
Start Year | 2015 |
Description | MSc supervisor and dissertation collaborator |
Organisation | London School of Hygiene and Tropical Medicine (LSHTM) |
Department | Faculty of Epidemiology and Population Health |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | Data extraction and analysis for MSc dissertation |
Collaborator Contribution | Supervision |
Impact | N/A |
Start Year | 2013 |
Description | Statistics Denmark |
Organisation | Statistics Denmark |
Country | Denmark |
Sector | Public |
PI Contribution | Analysis of Danish register data. |
Collaborator Contribution | Data and space provision. |
Impact | n/a |
Start Year | 2022 |
Description | UCL KTH/KI machine learning collaboration |
Organisation | Royal Institute of Technology |
Country | Sweden |
Sector | Academic/University |
PI Contribution | Machine learning models: technical and clinical knowledge |
Collaborator Contribution | Machine learning models: advanced technical knowledge |
Impact | Hayes JF, Osborn DP, Francis E, Ambler G, Tomlinson LA, Boman M, Wong IC, Geddes JR, Dalman C, Lewis G. Prediction of individuals at high risk of chronic kidney disease during treatment with lithium for bipolar disorder. BMC medicine. 2021 Dec;19:1-6. |
Start Year | 2019 |
Description | UCL School of Pharmacy |
Organisation | University College London |
Department | School of Pharmacy |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | Meeting to plan research strategy for BRC. I will lead on two projects: 1. use of large data sets - initially to look at serious mental illness patients and side effects to extend/replicate some of the earlier work in new data sets. 2. using large data sets to look at new things - e.g. effects of lithium on incident dementia and to conduct the definitive attempt to identify potential re-purposed agents for delaying dementia onset through case records. |
Collaborator Contribution | Additional plan for collaboration including new drug delivery methods. |
Impact | none yet |
Start Year | 2017 |
Title | METHODS AND SYSTEMS FOR GENERATING PERSONALIZED RECOMMENDATIONS AND PREDICTIONS OF A LEVEL OF EFFECTIVENESS OF THE PERSONALIZED RECOMMENDATIONS FOR A TYPE OF USER |
Description | Although conventional systems for tracking health issues and generating health recommendations for users exist, such systems do not conventionally provide customized recommendations for users based both on users' health-related data inputs or measures of wellbeing (including, e.g., levels of energy and emotional state), and based on a likelihood the user will effectively implement the recommendations. There is a need for identifying personalized improvement strategies and behavioral chances for users with complex chronic health conditions, often occurring in combinations, optimized by learning personal preferences of users, identified by accessing many data sources and improved by learning from a user base. This is in contrast to conventional solutions, which typically focus only on one condition instead of combinations of conditions, present generic strategies instead of personalized strategies, and/or do not typically integrate data from electronic health records (e.g., EHR / FHIR data). |
IP Reference | US-20220223241-A1 |
Protection | Patent / Patent application |
Year Protection Granted | 2022 |
Licensed | No |
Impact | Workable solution currently undergoing randomised controlled trials. |
Title | juli |
Description | VC funding for behavioural intervention to manage chronic health problems. |
Type | Preventative Intervention - Behavioural risk modification |
Current Stage Of Development | Early clinical assessment |
Year Development Stage Completed | 2022 |
Development Status | Actively seeking support |
Clinical Trial? | Yes |
Impact | n/a |
URL | http://www.juli.co |
Company Name | juli |
Description | Behavioural modification and health tracking app |
Year Established | 2020 |
Impact | currently completing a RCT of the app. |
Website | http://www.juli.co |
Description | OHID expert reference group |
Form Of Engagement Activity | A formal working group, expert panel or dialogue |
Part Of Official Scheme? | No |
Geographic Reach | National |
Primary Audience | Policymakers/politicians |
Results and Impact | Expert refernce groups for OHI SMI work - guiding policy for NHS England |
Year(s) Of Engagement Activity | 2022,2023 |
Description | Scientific American article |
Form Of Engagement Activity | A magazine, newsletter or online publication |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Public/other audiences |
Results and Impact | Scientific American lay summary of possible future for antidepressant drug treatments. |
Year(s) Of Engagement Activity | 2021 |
URL | https://www.scientificamerican.com/article/novel-drug-therapies-could-tackle-treatment-resistant-dep... |
Description | USA Today - discussing air pollution and mental health |
Form Of Engagement Activity | A press release, press conference or response to a media enquiry/interview |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Public/other audiences |
Results and Impact | Discussion about my research into air pollution and mental health and commenting on new research |
Year(s) Of Engagement Activity | 2023 |
URL | https://eu.usatoday.com/story/news/health/2023/02/06/air-pollution-linked-anxiety-depression-study/1... |