Data Research

When you sign up with us, we will collect information about you for three reasons:

1) To inform your individual care

2) The NHS requires that we collect information about our patient care so that they can monitor the quality of the service we provide. This information includes how well patients respond to treatment along with some personal information including statistics around gender, age and ethnicity. (See IAPT Minimum Data Set)

3) To learn from your episode of care, to improve our service, to learn about mental health and how to improve recovery.

We want to understand what works in CBT and further improve treatment and recovery rates.

Much of our research is based on questionnaire scores and responses, in combination with some or all of: number of sessions, age, gender, diagnoses and partial post codes; but we also use machine learning, natural language processing (NLP) and artificial intelligence (AI) on the communications between you and your therapist.

Collecting information from the conversations that happen between patients and therapists help us to build a greater understanding of the causes of mental illness and what makes treatment work. Click here to read more about our data science.

We have processes in place to safeguard your privacy. We make sure that only essential data is collected and that your directly identifiable information e.g. your name and address is kept separate from the data used for our research.

Being able to look at and analyse conversations between patients and therapists provides us with a unique opportunity to learn how therapy works and improve it.

We have treated over 30,000 patients and we use the data from this for research. We are training computer algorithms to find patterns in the therapy process – so we can see what aspects of therapy are most effective. An example of our research using this approach can be seen here: Ewbank et al., 2019.

They might do, very occasionally for deep learning research, but never in connection with your name, location or other clinical details.

To teach the computer algorithms to find patterns we need to give them examples – for the research mentioned in the question above, we had to indicate which type of utterance was a greeting, setting an agenda, setting homework, being empathetic etc to see how the content affected outcomes, to ensure we used the right ingredients in sessions to achieve the best possible recovery rates.

This teaching requires a research scientist to access a limited number of randomly selected therapy sessions, extracted from the database in isolation, without the patient and therapist full names, and detached from the patient health record, or any other personal data information fields, so that they can categorise the content manually.

To teach the models, researchers accessed 0.15% of randomly selected sessions (i.e. about 3 in every 2000). Any future research involving deep learning will likely require a similar process. (Much of our research, however, is actually done on anonymised or deidentified sub sets of the NHS IAPT Minimum Data Set, very little involves researchers accessing conversations between patients and therapists)

Some research may also require deep learning techniques to be applied to the therapist notes (summary) of a session. In this case a researcher will need to tag randomly selected therapist notes, disconnected from the rest of your medical file, in the same way and approximate quantities as described above for tagging the word for word record of your therapy session.

Sometimes, but with strict safeguards. So that we can conduct research to improve treatment, we sometimes partner with researchers outside of Ieso, e.g. university research groups.

When this happens, we remove directly identifiable information (including any names and locations) from the data we share with them, so they will not be able to identify anyone personally.

All partners also sign a legal agreement that any data they have is kept confidential and secure.

Never in a way that could identify you.

In order to increase the number of people who recover with online CBT, it is important to share our findings with the research community. We publish our findings in peer reviewed journals and present them at academic conferences.

However, we only report aggregated statistics, patterns and our conclusions – we don’t include details about individuals’ treatment or condition. You can see a list of all our published research on our Data Science page.

We're very happy to help if you have more questions. To get in touch email mydataresearch@iesohealth.com.

You can choose to stop your confidential patient information being used for research and planning.

Your choice will only apply to the health and care system in England. This does not apply to health or care services accessed in Scotland, Wales or Northern Ireland.

Any choice you make will not impact your individual care.

Make and record your choice.

If you live in Scotland, Wales or Northern Ireland, please email mydataresearch@iesohealth.com and one of our research team will call you to discuss this.