Singapore’s SoundKeepers Project Tackles Depression in Seniors with AI

The landscape of mental health diagnosis and treatment in Singapore is set to evolve with the introduction of SoundKeepers, an innovative three-year research and pilot programme that aims to identify early signs of depression in seniors through voice analysis. This AI-powered initiative, developed by a consortium of healthcare, academic, and philanthropic organizations, seeks to address the challenge of undiagnosed subsyndromal depression (SSD) in elderly populations.

The Challenge of Subsyndromal Depression (SSD)

Subsyndromal depression refers to the early stage of depression where symptoms emerge but are not severe enough to meet the diagnostic criteria for major depression. Despite its subtlety, SSD presents significant risks. Seniors with SSD are five times more likely to develop clinical depression within a year and are 12 times more likely to suffer from dementia. Given that depression affects 13.4% of seniors in Singapore, the true impact may be underestimated due to reliance on self-reported data.

How SoundKeepers Works

At the heart of SoundKeepers is a novel AI tool that collects and analyzes voice recordings to detect early signs of depression. By studying voice biomarkers such as pitch, tone, and rhythm, researchers aim to identify physiological changes linked to mental health deterioration. These changes often manifest in the muscles used in voice production, such as those in the throat and jaw, which are affected by stress, anxiety, and depression.

The programme will gather voice samples from over 600 seniors aged 55 and above in Hougang and Woodlands, who will participate in casual conversations or read aloud passages. The AI will analyze these samples, focusing on acoustic properties like timbre, jitter, shimmer, and harmonics-to-noise ratio, to detect subtle variations that could indicate early depression.

Community-Based Intervention

Once seniors are identified as being at risk of SSD, they will be referred to a 24-week community intervention programme. This programme, co-developed by the Institute of Mental Health (IMH) and social service agencies such as Fei Yue Community Services and Club HEAL, includes psychoeducation, social activities, and befriending initiatives. These interventions aim to improve emotional resilience and social connections, providing seniors with coping strategies to manage their mental health.

A Holistic Approach to Mental Health

SoundKeepers is not designed to replace existing mental health screenings but to complement them. Traditionally, mental health assessments rely heavily on self-reported data, which can be influenced by patients’ reluctance to share their true feelings. The AI-driven voice tool provides an objective measure, enabling healthcare professionals to make more accurate diagnoses without relying solely on questionnaires.

As Dr. Mythily Subramaniam, Assistant Chair of the IMH Medical Board for Research, noted, “SSD is not actively diagnosed or treated in the community setting. However, with the focus on early detection and treatment emphasized by national mental health strategies, SoundKeepers is well-positioned to fill this gap”.

A National Vision for Mental Health

SoundKeepers represents a significant leap forward in the integration of AI and mental health care. Once validated, the programme could be expanded to more clinics and participant profiles, potentially becoming a core component of Singapore’s mental health ecosystem through existing initiatives like CREST and COMIT.

This project, funded by the Lien Foundation with $5.6 million in support, reflects Singapore’s broader commitment to improving mental health services for its aging population. As Lien Foundation CEO Lee Poh Wah emphasized, “We need new ways to listen to our seniors. While they may not express their worries through words, we can now try to hear it through their voices”.

SoundKeepers is not just a technological innovation; it is a compassionate approach to addressing one of the most pressing mental health issues among seniors. Through the integration of AI and community support, it aims to make early detection of depression more accessible and less stigmatized, paving the way for more effective and holistic care.

The seven partners in the project include Nanyang Technological University, Singapore’s (NTU Singapore) Lee Kong Chian School of Medicine (LKCMedicine) and College of Computing and Data Science (CCDS); two healthcare institutions of the National Healthcare Group, National Healthcare Group Polyclinics and Institute of Mental Health; two Social Service Agencies, Fei Yue Community Services and Club HEAL; and philanthropic house Lien Foundation. 20 GP clinics in Hougang and Woodlands will also play a supporting role.