Arsi Ikäheimonen’s doctoral research: Smartphone data could reveal early signs of depression
Smart devices collect information on movement, sleep, messaging, and even social media use. These digital traces can also reveal changes in mental health.
‘If there are changes in daily mobility or sleep patterns, they may indicate changes in health. The same applies to things like social media activity or nighttime phone use,’ says Arsi Ikäheimonen, who examined the use of digital phenotyping in depression care in his doctoral thesis.
Digital phenotyping combines data science, behavioural science, and medicine. It uses data collected by smart devices in everyday settings to study human behaviour, social interaction, and health.
Insight into patient’s daily life
Mental health disorders are a major global challenge, causing significant human suffering and also economic burden. Their assessment relies largely on clinical interviews and questionnaires.
‘Several weeks or even months may pass between appointments, and healthcare professionals have limited insight into what happens in a patient’s daily life between visits. Digital phenotyping offers a new tool: smart devices collect continuous data in real-world settings.’
The field is still emerging, and progress has been slowed by a lack of shared research practices. Ikäheimonen’s thesis addresses this gap by introducing a standardised software solution and a data-driven workflow for analysing behavioural data.
‘This improves the reproducibility and comparability of studies. Openly available software and concrete guidelines make behavioural analysis clearer, more transparent, and more accessible to new researchers as well.’
Machine learning detects changes
The thesis explored how smartphone data can be used to monitor and predict changes in depressive symptoms. The study was conducted in collaboration with the HUS Psychiatry Center and involved 164 volunteer participants, both outpatients and healthy controls.
‘The results show that machine learning models trained on smartphone data can predict changes in depressive symptoms. We also found that changes within an individual’s behaviour were more informative than differences between individuals. This highlights the importance of personalised models and longitudinal monitoring.’
Ikäheimonen emphasises that digital phenotyping is not meant to replace traditional mental health assessments but to complement them.
‘At its best, it can detect early warning signs of conditions such as depression, allowing for timely intervention.’
Arsi Ikäheimosen defended his doctoral thesis Advancing research methodologies in digital phenotyping for mental health at the School of Science on 13 February 2026.
Read more about the public defence here.
Text: Marjukka Puolakka
Photo: Nita Vera
This article will be published in the Aalto University Magazine issue 38, September 2026.
Read more news
Bachelor's Students Successfully Complete Research Internship
Three bachelor's students have successfully completed their research internships.
From Materials to Smart Textiles: Benjamin Begins a New Chapter at Aalto
Ping-Chun Chen is a researcher from National Tsing Hua University, Taiwan.
The idea of three researchers generated a deep tech company
Sim Analytics Oy relies on strong research expertise. Its story began when three researcher colleagues working in different laboratories at LUT University began to consider how to provide and analyse data in a way that would support industrial companies in making business decisions.