The overall aim of the study is to observe the change of long-term metabolic control in patients with type 2 diabetes who have access to a digital intervention tool as compared with randomized controls during one year. The tool is based on self-affirmation theory and has large emphasis on self-reflection to enable sustainable lifestyle changes. Users get access to expert-written information about relevant health topics and interact with an LLM to promote reflection on the information.

Type-2 diabetes afflicts more than 300 million people worldwide and poses a heavy burden on the healthcare systems everywhere. Recent guidelines from the American Diabetes Association and the European Association for the Study of Diabetes recommend enhanced focus on lifestyle management in addition to glucose-lowering drugs. Individual or group-based diabetes education programs can improve glucose control and quality-of-life, but they are resource-intense and long-term outcomes are variable. Moreover, few individuals with diabetes attend such programs because of practical, medical and financial hurdles to attend sessions.

Consequently, there is a large need for complementary lifestyle support that can meet individual preferences in content and timing and reach many patients at low cost. Digital tools have considerable potential for clinical utility. The investigators have previously shown that the digital Livsstilsverktyget ('Lifestyle tool') developed at the University of Gothenburg leads to improved glycemic controls in patients using it regularly (Dwibedi et al., npj Digital Medicine 2022). To make the intervention more personal the investigators have coupled it with a large language model (LLM) to promote reflection on the expert-written content of the Lifestyle tool. Thus, participants interact with the LLM to explore a current area of interest. They then get recommendations from the LLM on relevant texts from the Lifestyle tool. These texts are written by experts (physicians, researchers). The participants go through the text and are then stimulate by the LLM to reflect on how to use the content in daily life.

Study participants with type 2 diabetes will be randomized to the intervention and the change of long-term blood glucose from baseline to end of follow-up will be compared with participants who are randomized to a control group without access to the intervention.

Blood samples are drawn for analysis of glycated hemoglobin (HbA1c), a measure of glucose control, at baseline, after six months and after twelve months. Blood samples are drawn at their primary care unit. Technical problems are referred to a study coordinator, who also responded to requests to clarify content in a general manner without providing personal advice.

Study participants are managed by their ordinary healthcare providers throughout the study.

Inclusion Criteria:

• Patients with type 2 diabetes
• Diagnosis of diabetes mellitus was based on prior documentation or treatment with anti-hyperglycemic medication
• age at or above 35 years
• access to Internet
• informed consent

Exclusion Criteria:

• Treatment with insulin
• Change of anti-diabetic treatment with three months prior to inclusion
• Participation in other study that may affect the outcomes
• Condition or treatment that in the judgement of the Investigator precludes participation
• Inability to read and write in Swedish
• Work in competing areas

Individual participant data that underlie the results will be shared after deidentification.

Data will be available after publication.

To researchers who provide a methodologically sound proposal in order to achieve the aims of that proposal. Proposals should be directed by email to livsstilsverktyget@gu.se