MoodMon

AI-powered digital monitoring for proactive, personalised care in affective disorders.

The challenge

Affective disorders, that is bipolar disorder and recurrent depression, are highly prevalent and place a significant burden on healthcare systems and the economy due to treatment costs and lost productivity. Globally, bipolar disorder affects approximately 40 million people [1], with 5 million cases in Europe [2], while depression impacts around 280 million people worldwide [3], including 21 million in Europe [4]. The COVID-19 pandemic has further exacerbated the situation, leading to a 25% increase in depression cases within a year. [5] These disorders are a leading cause of work absence and suicide, contributing to over 55,000 disability-adjusted life years (DALYs) globally in 2019 – accounting for 44% of the total burden of mental disorders. Individuals with bipolar disorder face a suicide risk 20 to 60 times higher than the general population [6], and in Europe, suicide claims twice as many lives as road accidents [7], [8].

Two major challenges hinder the effective management of affective disorders:

• Lack of objective diagnostic and monitoring tools: Current diagnostic approaches rely on subjective assessments of patient behavior, with patients and families expected to recognise predictive symptoms. This method is inconsistent and unreliable, leading to delays in intervention.
• Limited access to mental healthcare: In the EU, there are only 18 psychiatrists per 100,000 people [9], making timely access to specialised care difficult, especially in remote areas. Patients typically see a psychiatrist every three months, with appointments scheduled in advance rather than based on clinical need, limiting the responsiveness of care.

Addressing these gaps is crucial to improving patient outcomes, reducing suicide risk, and alleviating the strain on healthcare systems across Europe.

The solution

MoodMon is an AI-driven monitoring tool designed to enhance the treatment of patients with chronic affective disorders, that is bipolar disorder and recurrent depression. It provides continuous, objective tracking of mental health symptoms, supporting patients, caregivers, and clinicians in monitoring mood changes and adjusting treatment accordingly.

The AI engine analyses patient behavioral data (voice sample, physical and social activity, and sleep patterns) identifying early signs of mood changes. If a potential shift is detected, alerts are sent to the patient, caregivers, and clinicians, enabling proactive intervention. Clinicians can assess alerts via the web portal, and their feedback helps retrain the AI model, improving predictive accuracy over time.

To improve voice sample collection, MoodMon has integrated a voicebot – developed with support from the Eco-Disruptive competition and a BUPA grant – which automatically records voice sample during simulated phone conversation with a bot, offering a more natural and reliable alternative to manual recording.

MoodMon successfully completed a clinical trial, demonstrating high sensitivity (TPR = 89.5%) and specificity (TNR = 98.83%) in detecting mental state changes. The system is currently undergoing certification as a Class IIa medical device under MDR, positioning it as a transformative tool for personalised and data-driven mental healthcare.

Expected impact

The primary objective of this project is to commercialise MoodMon, with key milestones including:

1. CE certification under MDR by mid-2025.
2. Demonstration of health economic value by the end of 2025.
3. Signing sales contracts by the end of 2025.

MoodMon will deliver significant benefits across multiple levels:

• For patients – It enhances quality of life, provides a greater sense of security and control over their condition, and ensures better continuity of care.
• For healthcare systems – By reducing hospitalisations, as indicated in clinical trials, MoodMon has the potential to generate substantial cost savings, alleviating pressure on resources and improving overall efficiency.
• For clinicians – It supports better patient management, saves time, and enhances treatment effectiveness, ultimately contributing to professional satisfaction and improved care delivery.

Integrating MoodMon into statutory and private health insurance systems can unlock additional benefits, enhancing the sustainability of mental healthcare in Europe. Key advantages include:

• Cost reduction – Digital monitoring minimises unnecessary hospital admissions and emergency visits, reducing overall healthcare expenditure.
• Improved risk assessment and personalisation – AI-driven analysis allows for dynamic pricing models in insurance, fostering transparency and personalised premiums based on individual health metrics.
• Increased patient engagement – Continuous monitoring encourages adherence to treatment plans and healthier lifestyle choices, leading to better long-term outcomes.
• Competitive advantage for insurers – Digital health solutions, including remote monitoring and telehealth integration, position insurers as innovators, attracting a tech-savvy customer base.

By enhancing clinical insights, facilitating early intervention, and optimising resource allocation, MoodMon represents a transformative step toward a more efficient, patient-centered, and economically sustainable mental healthcare system in Europe.

External Partners

• Britenet Med (Lead partner)
• Medigent Lab

References

[1] https://www.who.int/news-room/fact-sheets/detail/mental-disorders

[2] https://www.oecd-ilibrary.org/sites/health_glance_eur-2018-4-en/index.html?itemId=/content/component/health_glance_eur-2018-4-en

[3] https://www.who.int/news-room/fact-sheets/detail/depression

[4] https://www.oecd-ilibrary.org/social-issues-migration-health/health-at-a-glance-europe-2018/promoting-mental-health-in-europe-why-and-how_health_glance_eur-2018-4-en;jsessionid=KodxvvB9J1xVbynhyINT-607hPhhyI68tqubpflI.ip-10-240-5-57

[5] https://www.who.int/news/item/02-03-2022-covid-19-pandemic-triggers-25-increase-in-prevalence-of-anxiety-and-depression-worldwide

[6] Novick, D. M., Swartz, H. A., & Frank, E. (2010). Suicide attempts in bipolar I and bipolar II disorder: a review and meta-analysis of the evidence. Bipolar disorders, 12(1), 1-9.

[7] https://ec.europa.eu/eurostat/statistics-explained/index.php?title=Road_safety_statistics_in_the_EU

[8] https://ec.europa.eu/eurostat/web/products-eurostat-news/w/edn-20240909-1

[9] https://www.socialeurope.eu/a-mental-health-strategy-for-europe