Close
Feasibility study of ‘MiADE’ point of care natural language processing
What is MiADE?
When MiADE is activated for your Epic account, you can use it to analyse the text of clinical notes that you create. MiADE will find mentions of problems, medications and allergies and code them to a terminology such as SNOMED CT. The coded entries will be displayed alongside the clinical note, and you will be able to check and save them to the patient’s record with a few clicks.
What is the aim of this study?
This study aims to find out how well MiADE works, and what other factors are important to enable clinicians to easily record more complete structured information in clinical notes.
Why is this study important?
Recording key information about patients such as problems, medications and allergies in a structured way makes it easier for clinicians to find the information in future consultations, and makes it easier to use the information for audit, service evaluation and research. Audits at UCLH have found that problem lists are often incomplete, which could be a risk for patient safety.
One of the reasons why clinicians do not enter structured data is that it can be difficult and time consuming to do. MiADE aims to make this process easier.
What will the study involve for me?
As a clinician participant in this study you will be asked to undergo training in order to be given access to the MiADE system. You will be asked to fill in a survey before and after being given access to MiADE.
A sample of clinicians will be invited to have interviews with a researcher. If you are invited to have an interview this will take place after you have been using the MiADE system for a few weeks. The interview will be face to face or by telephone, will last up to half an hour, and will be audio recorded. Interview recordings will be transcribed by an approved external company. Recordings will be deleted once the transcriptions are complete and have been verified.
You may also be invited to have a sample of your outpatient consultations observed by a researcher, before and after you have been given access to the MiADE system. The researcher will seek consent from the patients and will observe your interaction with the electronic health record during the consultation. The researcher may ask you questions at the end of the clinic to clarify their observations.
Researchers will also analyse anonymised information about the patients you have seen before and after the MiADE system is activated for you. Researchers will analyse the amount of structured information you have recorded for patients in order to evaluate the system.
What are the risks?
This is a low risk project overall. However, there is a risk that some clinical notes may be ambiguous or difficult to analyse, and MiADE may return incorrect suggestions. You should verify all entries suggested by MiADE before saving them in the patient record.
Do I have to take part?
No, it is entirely up to you if you want to take part. Whether or not you take part in the study will not affect your employment, training or appraisal. After you have signed up to the study you are free to withdraw at any time. Please contact a member of the study team if you wish to do so.
How will you use information about me?
We will need to use information from you, such as your contact details and Epic login details, for this research project. We will keep all information about you safe and secure, and write our reports in a way that does not identify individuals.
What are my choices about how my information is used?
You can stop being part of the study at any time, without giving a reason, but we will keep information about you that we already have.
We need to manage your records in specific ways for the research to be reliable. This means that we won’t be able to let you see or change the data we hold about you.
Where can I find out more about how my information is used?
You can find out more about how we use your information on our study website: https://www.ucl.ac.uk/health-informatics/research/medical-information-ai-data-extractor-miade
You can also ask one of the research team by sending an email to uclh.miade@nhs.net. If you have any concerns about how the MiADE project is using and protecting personal information, you can contact the UCL Data Protection Officer at data-protection@ucl.ac.uk.
Who is running the study?
The study is being led from the UCLH Clinical and Research informatics Unit https://www.uclhospitals.brc.nihr.ac.uk/clinical-research-informatics-unit, a collaboration between the hospital (UCLH) and university (UCL). The Principal Investigator is Dr Anoop D. Shah.