Overview
Menostik is developing an AI-based diagnostic platform for the early detection of perimenopause. The goal is to create a tool that can detect the onset of perimenopause earlier and more precisely than current methods. Instead of relying only on symptoms or invasive hormone tests, our platform analyzes everyday data from wearable sensors (such as body temperature, heart rate variability, or sleep quality) together with voice recordings and clinical values. This makes diagnostics non-invasive, continuous, and much more accessible.
Research Context
Today, menopause is usually diagnosed too late: most methods are retrospective (for example, only after menstruation has stopped for 12 months) or rely on subjective symptom reports. As a result, women often struggle with years of undiagnosed symptoms such as sleep problems, mood changes, or hot flashes. Misdiagnoses are common, and treatment is often delayed. Menostik takes a different approach. By combining wearable data, speech signals, and hormone measurements with AI methods, we aim to identify digital biomarkers of perimenopause. This means finding patterns in data that can signal hormonal changes early on. The project brings together expertise from health informatics, endocrinology, and human-computer interaction. For students, this context provides hands-on experience in how to process biomedical data, design AI pipelines, and translate technical solutions into meaningful medical applications.
Student Tasks
Depending on the student’s background and interests, tasks may include:
• Data Science & AI: Preprocessing, cleaning and annotating wearable and speech data, exploring digital biomarkers, developing or testing machine learning models
• Biomedical Engineering: supporting study design, testing wearable technologies, validating data acquisition protocols
• Human-Computer Interaction: designing and evaluating visualization methods for patient and clinician dashboards
• Clinical Data Analysis: assisting with integration of symptom reports and hormone assays into the research database
Expected Outcomes
By the end of the project, students are expected to:
• contribute to a submodule of the Menostik platform (e.g., data pipeline, biomarker analysis, model evaluation, or dashboard prototype)
• present their results in a final presentation to the research group
• gain practical experience in interdisciplinary digital health research
• develop skills in medical AI, wearable technology, and explainable machine learning