Moodmon is a

n

clinically tested

innovative

AI-based

system that improves the life of mentally disordered patients and their families as well as supports psychiatrists in the process of treatment.

What is Moodmon?

Moodmon is an AI based system supporting therapy of affective disorders.

Monitoring

Currently, Moodmon supports the monitoring of the present state of patients diagnosed with bipolar disorder or depression.

Predictions

Our individual and generic AI models predict possibly dangerous mood changes on the basis of data collected from mobile phones and digital wristbands.

Alerts

Moodmon alerts the patient, the psychiatrist and authorised relatives. The alerts grant faster reaction and better treatment results.

How it works?

Moodmon uses data collected from wearables (mobile phone and wristband) as well as data retrieved from a web app used by the physician to feed AI models predicting possible behaviour changes.
Major advantage of Moodmon is the usage of individual AI models per patient and continuous re-training of models to account for changes not related to the disease.

Moodmon addresses most significant problems faced by different stakeholder groups

A sense of lack of control over their lives due to constant dependence on mood changes. Frequent and irritating questions about their mental state.

Limited access to psychiatrists and difficulties in relating objectively all the past events to be reported to the doctor.

Remembering appointment dates and medication times. Monitoring their condition and informing relatives about their well-being.

Stress, which relatives try to relieve by constant analysis of behaviour and being overprotective.

Deterioration of relationships with the disordered relative caused by disbelief about their declared mental state and being overburdened with responsibility.

The difficulties in patient monitoring forces relatives to allocate more time and financial resources in the treatment process than is actually necessary.

Uncertainty of the diagnosis and medication results due to subjective information provided by patients.

Difficulties to timely adjust medication between regular appointments.

Insufficient and sporadic contact with patients.

How do we help?

Over 10% of the global population suffers from chronic affective disorders. During remission periods patients are valuable members of the society, but relapses destroy their lives both on the professional and personal level. Up to 15% of victims commit successfull suicide. Early prevention of the relapse development allows the patient to avoid hospitalisation and minimises adverse impact on every aspect of life. However, early detection is possible only by close monitoring of the patient and this is what Moodmon offers to patients and their care-takers. We make life easier to endure and save lives threatened by desperation.

Other advantages

Additional communication channel between the patient and the doctor

Notifications for the patient about upcoming visits

Reminders about medication times and dosis

Continuous data gathering for the psychiatrists to improve therapy efficiency and diagnosis accuracy

Data presentation for the patient

Valuable database for scientific investigation in the area of psychiatry and behavioural sciences

The system is characterised by

Objectivity
and reliability

Analysis of behavioural and physiological data, clinically tested, used under medical supervision

Ease of use and accessibility

Cell phone, Internet, data gathered without patient involvement

Flexibility and personalization

Continuous re-training, individual AI models

Privacy

Anonymization, without content analysis

Medical & social proof

The system is being used by clinical trial participants. The clinical trial is both a test with users and a market study.

Clinical trial participation

The assembly of 100 patients willing to participate in the trial is an indication that the system is desired and expected by this community. The very low percentage of patients leaving (only 7%) indicates that Moodmon meets their expectations.

Technical quality

Patients do not report issues with the mobile application.The technical help line does not receive calls with complaints. Physicians who use the web app express satisfaction with the accessibility, transparency and efficiency of the system.

Prediction accuracy

The preliminary evaluation of effectiveness based on the alerts sent so far is over 70%. This result is approved by physicians and very well regarded. The effectiveness rating based on the test set exceeds 80%.

Growth Plan

The idea started in 2015 and originated in the environment of relatives of bipolar patients. With support from a business angel (Britenet company) and European funding, the first POC was launched in 2017.

2021-2023

* Design and development
* Clinical testing of the monitoring system

2024

* Commercial implementation of monitoring system for bipolar and recurrent depression patients

2024

Commercial implementation of monitoring system for bipolar

2025

* Postnatal and seasonal depression – symptoms detection and monitoring

2024

Commercial implementation of monitoring system for bipolar

2026

* Insomnia – monitoring of the treatment effectiveness
* Addictions – patient observation and early reaction

2024

Commercial implementation of monitoring system for bipolar

2029

* Application to monitoring of the treatment effectiveness and detection of exacerbations in Post-Traumatic Stress Disorder (PTSD), Obsessive Compulsive Disorder (OCD) and anxiety.
* Alzheimer's disease and senile dementia – early detection of symptoms

2024

Commercial implementation of monitoring system for bipolar

2030

* Attention Deficit Hyperactivity Disorder (ADHD) - monitoring of the treatment effectiveness and monitoring of drug holidays
* Asperger's syndrome – monitoring of anxiety and psychotic episodes

2024

Commercial implementation of monitoring system for bipolar

Goal

Psychiatry global technology partner

Founders

Małgorzata Sochacka
Iwona Furman
Tomasz Krajewski

Business Dev

Martyna Przewoźnik

Experts

prof. Łukasz Święcicki
Psychatrist
prof. Olgierd Hryniewicz
Data Processing
prof. Bogumił Kamiński
Machine Learning