Lund University in Sweden has developed an Artificial Intelligence (AI) tool that could improve mental health care.
Patients are often asked to rate their feelings using a rating scale when describing their mental health; this is one of the current methods for diagnosing depression and anxiety. However, to improve mental health care, Lund University has found that allowing patients to describe their experience using their own words is potentially more precise and preferred by the patients.
The team have developed an AI tool that could help doctors and psychologists to analyse their patients’ answers. The study is published in PLOS ONE.
Using AI to improve mental health care
AI has long shown its key role in accurately measuring emotions in language, as opposed to rating scales. Progress has been made with natural language processing, ensuring that depression and anxiety can now be assessed with high validity based on open-ended questions that are then analysed with AI methods.
“Previously, we were limited to rating scales where patients themselves had to convert their feelings into numbers. Today this is not necessary as this assessment can be done by AI”, explained Sverker Sikström, the psychology researcher who led the study.
Sikström developed an AI product that enables patients to freely describe their mental health in text, which is then interpreted by an AI engine. The results can inform the mental health care recommended by doctors. The AI tool is unique as it asks direct open-ended questions to patients and does not rely on large-scale social media, where much of previous work has been done.
“We have received a lot of interest in this from health care providers, given that we now have the technology to support patients individually, yet in an efficient manner”, added Sverker Sikström.
Enabling doctors to obtain precise data about their patients
The researchers interviewed a group of 150 patients with self-diagnosed depression or anxiety and asked the same questions to a control group of 150 other participants.
Clinics often offer rating scales when diagnosing a patient, using language such as little interest in doing things: not at all, sometimes, often, daily; however, patients prefer free language such as describe your mental health.
The responses indicated that using free language is especially important as it is seen as the natural way for people to communicate their feelings. This allows patients to feel understood. The patients responded that the language gives a more accurate description of their feelings, which is not achievable using rating scales.
The patients noted that the only benefit of rating scales is that they are easier and faster to answer, but they lack the potential for more individualised mental health care.