Scientists in London have developed new AI technology inspired by video games to transform the way we diagnose and monitor depression. The platform, called Thymia, is currently being trialled by patients and clinicians with the objective of making depression and other mental health conditions as measurable as physical illnesses.
The brainchild of neuroscientist Dr Emilia Molimpakis and theoretical physicist Dr Stefano Goria, Thymia will remove the subjectivity from mental health assessments. Instead of answering questionnaires, patients will play specially designed video games on the platform which uses neuropsychology, linguistics, and machine learning to detect signs of depression, as well as monitor whether patients are responding to treatment.
It is currently being trialled by thousands of patients - including at UCL and King’s College London - to train the AI algorithm and finetune the user experience.
The scientists behind the technology hope it will empower clinicians to make faster and more accurate clinical decisions, by making mental illness as objectively measurable as physical health conditions.
Thymia recently raised $1.1 million in investment to help expand their clinical trials and bring the platform to patients across the UK.
Thymia was created after a close friend of Dr Emilia Molimpakis’ developed depression. Traditional depression assessment methods failed to convey the severity of her distress to her clinicians, ultimately culminating in a suicide attempt. This experience led Dr Molimpakis to leverage her understanding of linguistics, cognitive neuroscience, and experimental psychology to build a platform which could supplement and eventually replace the highly subjective questionnaire-based approach to depression diagnoses.
Thymia provides clinicians with a faster and more accurate tool for assessing and monitoring major depression.
Dr Emilia Molimpakis and Dr Stefano Goria - who is an expert in explainable, multi-modal AI - have created smart video game-style activities for patients to interact with, which test for several depressive cues. The games include verbally describing animated scenes and memorising moving objects like bees. Whilst users complete the games, the Thymia software anonymously analyses three key data streams:
- Voice: both how someone speaks and what they are saying (to pick up acoustic and linguistic depressive cues)
- Video: micro-expressions and eye-gaze (which can help track current mood)
- Behavioural measures, including reaction times, memory, and error rates (which can help detect depression severity).
The software identifies data patterns indicative of depression to help pinpoint a diagnosis more quickly and accurately. It will show if any treatments (whether therapies or medications) are working over time.
The platform enables clinicians to continuously and remotely monitor patients at home in the weeks between in-person appointments. This will help doctors and patients build an in-depth understanding of their condition over time.
Thymia is gathering data from thousands of subjects with major depressive disorder and a normative control group to ethically and inclusively train its AI. It is removing the racial, gender and age biases typically associated with AI models to make their assessments as accurate and objective as possible.
Thymia has established collaborations and partnerships with several research institutes, including UCL and King’s College London, to help scale use of the technology to other cognitive disorders. Scientists are already looking to apply the technology to conditions including Alzheimer’s Disease, Lewy Body Dementia, Parkinson’s Disease, Anxiety, ADHD and Autism.
Dr Emilia Molimpakis, CEO and co-founder of Thymia, says: “Thymia was born when a close friend of mine tried to take her own life. Her friends and doctors missed the signs that she was so seriously unwell, not least because the process of accessing the right treatment was based on out-dated methodologies not fit for the complexities and nuances of an illness like depression.
“Depression is a massive, constantly growing societal and economic problem; it is a leading cause of disability and suicides and costs the UK economy billions annually in lost productivity. COVID-19 has further compounded the issue, unleashing a mental illness “tsunami” due to a lack of in-person appointments, but also its harsh societal effects - social isolation, employment loss, bereavement, and grief. From January to March 2021, the ONS found 21% of UK adults reported depressive symptoms, double that observed pre-pandemic.
“Despite this, GPs and psychiatrists are using the same diagnostic questionnaires that have been around since the 1960’s. Rating how sad you feel on a scale of 0 to 3 simply is not enough to capture the subtle nuances of early signs of depression nor track the complexities of ongoing mental illness, but our clinicians have not been given a better option. This means too many cases go undiagnosed or are misdiagnosed, and too many patients wait years before the right treatment is found. We want to empower clinicians and patients themselves with better tools.
“Thymia is bringing psychiatry into the 21st Century, with an AI-enabled platform for accurate and continuous patient monitoring. It’s the first objective psychiatric assessment system, combining multiple layers of rich physiological data to assess depression and distinguish between similarly presenting disorders. Our technology will empower clinicians to assess and treat depression sooner, whilst allowing patients to develop a deeper understanding of their own condition. In time our aim is to become the gold standard of assessment for all mental health disorders and show that mental illness is as real and objectively measurable as physical illness, thereby also helping eradicate the stigma associated with it.”
