Mental Health DisorderMSITNCT04299789
Military Service Identification Tool
An observational study of Mental Health Disorder, run by King's College London at 1 site in United Kingdom.
Trial summary
Estimates of the UK's military veteran population, defined by the British Government as those who have served in the military for at least one day, is approximately 2.5 million, equivalent to around 5% of household residents aged 16 years or over in the UK. Read more about this study
- Who is it for?
- Ages 18 years and older
- Conditions the study is for
- Mental Health Disorder
- What is being tested?
- Validating the Military Service Identification Tool
- How many people
- 5,844 participants
- Where
- 1 siteUnited Kingdom
- Study dates
- 1 Sep 2020to 1 Sep 2022
- Phase
- Observational
- Are there results?
- None posted in the registry
Key requirements
Who can take part, as listed by the sponsor. Only the study team can confirm whether you are eligible, so take this list to your doctor.
- Ages 18 years and older
- All sexes
- Adult, Older adult
Study population: Participants have already been identified using the Military Service Identification Tool. In a previous research project, the Tool was run on the records of 150,000 patients extracted from the Clinical Record Interactive Search, which is managed by NIHR Maudsley Biomedical Research Centre (BRC). A copy of the article describing the methodology has recently been accepted for publication in JMIR Medical Informatics (DOI: 10.2196/15852). In total 2,922 probable veterans were identified and matched to 2,922 civilians on age and gender. The dataset has a total sample size of 5,844 individuals. Once approvals are in place, we will identify those who have given consent to be contacted and meet our eligibility criteria (described in other parts of our application).
Only those participants who formed part of our original study will be screened for eligibility. This corresponds to 2,922 probable veterans and 2,922 civilians. The following inclusion criteria will apply:
- Participants are listed as 'Alive' in the SLaM BRC Clinical Record Interactive Search database;
- Participants will be aged 18 years and old;
- Participant has given Consent for Contact;
- Participant has a valid postal or email address or telephone number;
- Participants have capacity to consent and deemed fit to participate in research by a clinician.
- Participants will be able to speak English.
Participants will be excluded if a clinician is required to be notified of the research prior to contact, as this may indicate at risk participants. Further participants who are not fluent in spoken English will be unable to take part in the study due to inability to understand the participant information and consent form. Therefore, non-English speaking participants will not be included in this study.
Trial locations and contacts
1 site in 1 country.
United Kingdom1 site, 1 recruiting
- Recruiting
South London and Maudsley NHS Foundation Trust
London, Greater Londn, SE58AZ
Dr Carol Cooley, 020 7848 0339, slam-ioppn.research@kcl.ac.uk
Dr Sharon AM Stevelink, PhD
About this study
Official title: Validating the Military Service Identification Tool in Its Ability to Correctly Identify Civilians and Those Who Have Served in the Military
Estimates of the UK's military veteran population, defined by the British Government as those who have served in the military for at least one day, is approximately 2.5 million, equivalent to around 5% of household residents aged 16 years or over in the UK. UK military veterans receive healthcare provision from the National Health Service (NHS), with care recorded in local, regional and national EHRs. EHRs - structured and unstructured (i.e. free text) - can be used to evaluate disease prevalence, surveillance, to perform epidemiological analyses and investigate quality of care and to improve clinical decision-making.
There is no national marker in UK EHRs to identify veterans, nor is there a requirement for healthcare professionals to record it, making it difficult to evaluate the unique healthcare needs of those who have served in the UK Armed Forces. This study, funded by Forces in Mind Trust, seeks to validate the Military Service Identification Tool, an open-source computer program that searches through free-text clinical notes to make a prediction on a person's military status. It is in the public interest to know the health of our Armed Forces. The Tool has been validated using manually annotated datasets, but we now need to valid an individual's military status by contacting them via post or telephone and asking, "Have you ever served in the Armed Forces". The research team will work closely with the CRIS Patient Advisory Group and local healthcare professionals.
Read the detailed description
Currently, there is no military service marker in electronic healthcare records to identify who is a veteran in England and Wales [3]. This makes it difficult to evaluate the unique healthcare needs of those who have served in the UK military. In a previous study, the investigators set out to investigate whether it was feasible to identify veterans who accessed secondary mental healthcare services via their anonymized electronic healthcare records using a manual, text search based, method. To do this, the investigators used the South London and Maudsley (SLaM) Biomedical Research Centre Case Register. This is a novel data resource, derived directly from the routine electronic healthcare records of the SLaM NHS Foundation Trust. SLaM is one of Europe's largest mental health providers, serving over 1.2 million residents in four South London boroughs. This Case Register holds patient's electronic healthcare records for all secondary mental healthcare provisions within SLaM. All these electronic healthcare records have been anonymized and a system has been developed to enable researchers to access and search through these records called the clinical record interactive system (CRIS).
As part of the first study the investigators developed a manual, text search based, method using commonly used terms and phrases found in the free text clinical notes to identify veterans. Running this manual method resulted in the identification of n = 6,039 potential veteran records, of which n = 1,600 were selected to scrutinize in more detail, whilst considering time and manpower restrictions. This resulted in n = 693 veteran records, suggesting an identification rate of 43% when using the manual method. Therefore, it was concluded that it was feasible to identify veterans in electronic healthcare records, but time consuming. Each potential veteran record was manually verified by the research team by reading through each patient's notes. This took on average 11 minutes per record.
To address the time it took to identify veterans and improve sensitivity and reach, he investigators developed the Military Service Identification Tool (MSIT), and it proved to be quicker, more accurate and cheaper than the manual method. The Tool was designed to detect military service, not just veteran status. 1the investigators took a systematic approach to developing and testing the MSIT. Then a different subsets of all the electronic healthcare records available to us, to ensure the MSIT was developed and trained on a different set of electronic healthcare records (named the training dataset). Subsequently the MSIT was verified on another subset of the data (named the gold standard dataset) to ensure it would still be able to identify veterans if a different set of electronic healthcare records would be used.
The investigators managed to identify 2,922 veterans in the electronic healthcare records when applying MSIT to inspect 150,000 individual records. The MSIT took only 20 minutes to go through all these records and had an identification rate of 88% when compared to the manual approach. The investigators also matched these veterans to 2,922 non-veterans based on age and gender to compare their mental health treatment pathways.
Despite the success of our initial developments, the investigators have faced a significant barrier that may prevent the widespread, dissemination, roll-out and implementation of the MSIT. Various academics and stakeholders (e.g. NHS England, Cobseo) are interested in the MSIT. However, it has been highlighted an important limitation, namely it is still unclear whether the veterans identified by the MSIT are 'actual' veterans. MSIT identifies veterans based on the notes provided by the clinician in the electronic healthcare record. It is also important to understand if higher rates of physical and mental health are represented in a veteran population compared to civilians. By including both samples - civilian and veteran - this ensures that fair comparisons are able to be made. This There is currently no opportunity to verify their veteran status. For example, no service number is provided in their medical records.
Therefore, to overcome these limitations and to demonstrate that the MSIT is correctly identifying military service (serving personnel, veterans or civilian) it is important to reach out to those who have been identified to ask about their previous Service.
- Conditions
- Mental Health Disorder
- Being tested
- Validating the Military Service Identification Tool
- Keywords
- mental health, natural language processing
- Medical subject headings
- Mental Disorders, Psychological Well-Being
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
Validating the Military Service Identification ToolOther
This study seeks to validate the Military Service Identification Tool in its ability to accurately determine military service status.
| Study group | Role | What they receive |
|---|---|---|
| Probable Civilian | This cohort represents those in which the Military Service Identification Tool has determined are a civilian and have not served in the Armed Forces. Receives: Other: Validating the Military Service Identification Tool | |
| Probable Veteran | This cohort represents those in which the Military Service Identification Tool has determined are a military veteran and have served in the Armed Forces. Receives: Other: Validating the Military Service Identification Tool |
What is being measured
The primary outcome is the main question the study is designed to answer.
Accuracy of the tool
The primary outcome of this study is to provide descriptive statistics on the accuracy of the Military Service Identification Tool in correctly identifying those who have served in the Armed Forces.
Measured: Analysis will be conducted within 6 months after data collection.
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted9 Mar 2020
- Study start1 Sep 2020
- Primary completion1 Jun 2022 (estimated)
- Study completion1 Sep 2022 (estimated)
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Publications (1)Papers the sponsor has linked to this study.
- Other trials for Mental Health DisorderStudies of the same condition, open and under way.
- What the trial phases meanHow a treatment moves from first tests in people to approval.
More details
For doctors and researchers: how the study is designed, who runs it, and its registry IDs.
Study design
- Study type
- Observational
- Observational model
- Cohort
- Time perspective
- Retrospective
- Enrolment
- 5,844 participants (estimated)
Sponsor and investigators
- Lead sponsor
- King's College London
- Sponsor type
- University, hospital or other
- Collaborators
- Forces in Mind Trust, Combat Stress
- Responsible party
- Sponsor
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT04299789
- Sponsor's protocol ID
- 278987
- Acronym
- MSIT
- Status last verified
- Aug 2021
- First submitted
- 5 Mar 2020
- Last updated
- 2 Sep 2021
- Results posted
- No
- Data monitoring committee
- No
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- No: We will not be sharing any data collected with other researchers as data will be deleted within 6 months of the study finishing.
Publications
Mark KM, Leightley D, Pernet D, Murphy D, Stevelink SAM, Fear NT. Identifying Veterans Using Electronic Health Records in the United Kingdom: A Feasibility Study. Healthcare (Basel). 2019 Dec 19;8(1):1. doi: 10.3390/healthcare8010001.
PubMed 31861575
Study at a glance
From the registry record, last updated by the sponsor on 2 Sep 2021. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- Validating the Military Service Identification Tool in Its Ability to Correctly Identify Civilians and Those Who Have Served in the Military
- ClinicalTrials.gov ID
- NCT04299789
- Acronym / sponsor ID
- MSIT / 278987
- Conditions
- Mental Health Disorder
- Keywords
- mental health, natural language processing
- Study type
- Observational
- Recruitment status
- Unknown status
- Enrolment
- 5,844 participants (estimated)
- Lead sponsor
- King's College LondonUniversity, hospital or other
- Collaborators
- Forces in Mind Trust, Combat Stress
- Study start
- 1 Sep 2020 (actual)
- Primary completion
- 1 Jun 2022 (estimated)
- Study completion
- 1 Sep 2022 (estimated)
- First posted
- 9 Mar 2020 (actual)
- Results
- Not posted in the source record
Clinical summary
The research question as the sponsor registered it. This describes what the study plans to test, not what it found.
Estimates of the UK's military veteran population, defined by the British Government as those who have served in the military for at least one day, is approximately 2.5 million, equivalent to around 5% of household residents aged 16 years or over in the UK. UK military veterans receive healthcare provision from the National Health Service (NHS), with care recorded in local, regional and national EHRs. EHRs - structured and unstructured (i.e. free text) - can be used to evaluate disease prevalence, surveillance, to perform epidemiological analyses and investigate quality of care and to improve clinical decision-making.
There is no national marker in UK EHRs to identify veterans, nor is there a requirement for healthcare professionals to record it, making it difficult to evaluate the unique healthcare needs of those who have served in the UK Armed Forces. This study, funded by Forces in Mind Trust, seeks to validate the Military Service Identification Tool, an open-source computer program that searches through free-text clinical notes to make a prediction on a person's military status. It is in the public interest to know the health of our Armed Forces. The Tool has been validated using manually annotated datasets, but we now need to valid an individual's military status by contacting them via post or telephone and asking, "Have you ever served in the Armed Forces". The research team will work closely with the CRIS Patient Advisory Group and local healthcare professionals.
Detailed description
Currently, there is no military service marker in electronic healthcare records to identify who is a veteran in England and Wales [3]. This makes it difficult to evaluate the unique healthcare needs of those who have served in the UK military. In a previous study, the investigators set out to investigate whether it was feasible to identify veterans who accessed secondary mental healthcare services via their anonymized electronic healthcare records using a manual, text search based, method. To do this, the investigators used the South London and Maudsley (SLaM) Biomedical Research Centre Case Register. This is a novel data resource, derived directly from the routine electronic healthcare records of the SLaM NHS Foundation Trust. SLaM is one of Europe's largest mental health providers, serving over 1.2 million residents in four South London boroughs. This Case Register holds patient's electronic healthcare records for all secondary mental healthcare provisions within SLaM. All these electronic healthcare records have been anonymized and a system has been developed to enable researchers to access and search through these records called the clinical record interactive system (CRIS).
As part of the first study the investigators developed a manual, text search based, method using commonly used terms and phrases found in the free text clinical notes to identify veterans. Running this manual method resulted in the identification of n = 6,039 potential veteran records, of which n = 1,600 were selected to scrutinize in more detail, whilst considering time and manpower restrictions. This resulted in n = 693 veteran records, suggesting an identification rate of 43% when using the manual method. Therefore, it was concluded that it was feasible to identify veterans in electronic healthcare records, but time consuming. Each potential veteran record was manually verified by the research team by reading through each patient's notes. This took on average 11 minutes per record.
To address the time it took to identify veterans and improve sensitivity and reach, he investigators developed the Military Service Identification Tool (MSIT), and it proved to be quicker, more accurate and cheaper than the manual method. The Tool was designed to detect military service, not just veteran status. 1the investigators took a systematic approach to developing and testing the MSIT. Then a different subsets of all the electronic healthcare records available to us, to ensure the MSIT was developed and trained on a different set of electronic healthcare records (named the training dataset). Subsequently the MSIT was verified on another subset of the data (named the gold standard dataset) to ensure it would still be able to identify veterans if a different set of electronic healthcare records would be used.
The investigators managed to identify 2,922 veterans in the electronic healthcare records when applying MSIT to inspect 150,000 individual records. The MSIT took only 20 minutes to go through all these records and had an identification rate of 88% when compared to the manual approach. The investigators also matched these veterans to 2,922 non-veterans based on age and gender to compare their mental health treatment pathways.
Despite the success of our initial developments, the investigators have faced a significant barrier that may prevent the widespread, dissemination, roll-out and implementation of the MSIT. Various academics and stakeholders (e.g. NHS England, Cobseo) are interested in the MSIT. However, it has been highlighted an important limitation, namely it is still unclear whether the veterans identified by the MSIT are 'actual' veterans. MSIT identifies veterans based on the notes provided by the clinician in the electronic healthcare record. It is also important to understand if higher rates of physical and mental health are represented in a veteran population compared to civilians. By including both samples - civilian and veteran - this ensures that fair comparisons are able to be made. This There is currently no opportunity to verify their veteran status. For example, no service number is provided in their medical records.
Therefore, to overcome these limitations and to demonstrate that the MSIT is correctly identifying military service (serving personnel, veterans or civilian) it is important to reach out to those who have been identified to ask about their previous Service.
Study design
- Observational model
- Cohort
- Time perspective
- Retrospective
- Number of arms
- 2
| Arm | Type | Receives |
|---|---|---|
| Probable Civilian | – | Other: Validating the Military Service Identification ToolThis cohort represents those in which the Military Service Identification Tool has determined are a civilian and have not served in the Armed Forces. |
| Probable Veteran | – | Other: Validating the Military Service Identification ToolThis cohort represents those in which the Military Service Identification Tool has determined are a military veteran and have served in the Armed Forces. |
Who may qualify
- Ages
- 18 years and older
- Sex
- All
- Age groups
- Adult, Older adult
- Study population
- Participants have already been identified using the Military Service Identification Tool. In a previous research project, the Tool was run on the records of 150,000 patients extracted from the Clinical Record Interactive Search, which is managed by NIHR Maudsley Biomedical Research Centre (BRC). A copy of the article describing the methodology has recently been accepted for publication in JMIR Medical Informatics (DOI: 10.2196/15852). In total 2,922 probable veterans were identified and matched to 2,922 civilians on age and gender. The dataset has a total sample size of 5,844 individuals. Once approvals are in place, we will identify those who have given consent to be contacted and meet our eligibility criteria (described in other parts of our application).
Eligibility is decided by the study team after screening; this overview does not establish that a patient qualifies. Full inclusion and exclusion criteria.
Interventions
| Intervention | Type | Arms |
|---|---|---|
| Validating the Military Service Identification ToolThis study seeks to validate the Military Service Identification Tool in its ability to accurately determine military service status. | Other | Probable Civilian, Probable Veteran |
Primary outcome
Accuracy of the tool
Time frame: Analysis will be conducted within 6 months after data collection.
The primary outcome of this study is to provide descriptive statistics on the accuracy of the Military Service Identification Tool in correctly identifying those who have served in the Armed Forces.
Results and safety
Results are not available in the source record.
Research links
- Official record on ClinicalTrials.govLast updated by the sponsor 2 Sep 2021.
- Background: PubMed 31861575Mark KM, Leightley D, Pernet D, Murphy D, Stevelink SAM, Fear NT. Identifying Veterans Using Electronic Health Records in the United Kingdom: A Feasibility Study. Healthcare (Basel). 2019 Dec 19;8(1):1. doi: 10.3390/healthcare8010001.
- Pre-print of the Military Service Identification Tool.Link provided by the sponsor.
- Individual participant dataSharing planned: No. We will not be sharing any data collected with other researchers as data will be deleted within 6 months of the study finishing.
Related trials for Mental Health Disorder
Not yet recruiting
Reducing Stigma - A Treatment for Early Psychosis to Prevent Suicide
Suicide, Mental Health Stigma
Not yet recruiting
Inflammatory Pathways Modulated by Prenatal Mindfulness: A Route to Improve Maternal Child Emotional Well Being and Whole Person Health
Inflammation, Depression Disorder
Recruiting
Development & Validation of a Life Balance Program for Parents of Preschoolers: A Pilot Study
Parenting Stress, Mental Health
Not yet recruitingObservational study
Community-Based Intensive Treatment (CBIT): Meeting the Complex Needs of Rural Adults With Serious Mental Illness
Severe Mental Illness, Hospitalizations Psychiatric
Active, not recruiting
Improving Maternal Mental Health & SUD Screening and Treatment
Mental Health Issue, Substance Use Disorders
Referral and contact
AzTrials does not enrol participants or take referrals. Contact the study team or a site listed below; they decide who can take part. This study is not recruiting at the moment.
South London and Maudsley NHS Foundation Trust
London, United Kingdom
1 site in 1 country: see every site and its status.
Questions about this trial
What is this clinical trial studying?
An observational study of Mental Health Disorder, run by King's College London at 1 site in United Kingdom.
The full registered description is in the About this study section and the official record.
Who may be eligible to take part?
Eligibility is decided by the study team after screening, so read the full criteria and contact a listed site.
Is this clinical trial currently recruiting?
The record says: status not confirmed, as of the sponsor's last update on 2 Sep 2021. Status can change between updates, so confirm with the study contact before making plans.
Where is the study taking place?
The record lists 1 site in United Kingdom. Whether a site is taking part right now should be confirmed with that site. See every site.
What are the possible benefits and risks?
They depend on the study and the treatment, and no study can promise a benefit. The study team explains the known risks during informed consent, before anyone joins; the record itself does not list them.
Are results available for this study?
Results are not available in the source record.
How can a doctor refer a patient or contact the research team?
Each site lists its own contact: choose the nearest one under Trial locations. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
Accuracy of the tool (time frame: Analysis will be conducted within 6 months after data collection.). It is what the study was designed to measure, not a finding.
Where can I read the original study information?
On the ClinicalTrials.gov record for NCT04299789, which also lists 1 linked publication.
Does a listing mean the treatment is approved or proven to work?
No. A listing means the study is registered. It does not show that the treatment is safe, works, or is approved by a regulator.
How often is this information updated?
AzTrials copies changed records from ClinicalTrials.gov every night and reloads the whole registry every week. The sponsor last updated this record on 2 Sep 2021; AzTrials last refreshed its copy on 29 Oct 2026.