Research Studies
Putting the patient perspective at the forefront of endometriosis research
// background
Endometriosis is a complex, highly individualized condition that remains poorly understood among both society and healthcare providers. In collaboration with Prof. Dr. Sylvia Mechsner at the Endometriosis Center, Charité — Medical University Berlin, we've built one of the largest databases of patient-reported experiences with endometriosis and adenomyosis.
// research focus
- Mapping diagnostic and treatment pathways from first symptom onward
- Identifying causal factors behind diagnostic delays
- Examining socioeconomic and sociopsychological impacts
- Analysing patient-reported outcomes from multi-modal therapies
// what we capture
2,800+ real-world journeys from initial symptoms through to diagnosis, medical consultations, and treatments. Aggregated sociodemographic data across all DACH countries. Subjective experiences, advice patients want to share, and outcomes that trial data doesn't capture.
// eligibility
Adults with a diagnosis of endometriosis or adenomyosis, or currently undergoing diagnostic work-up. Open to patients across Germany, Austria and Switzerland.
// research team
Prof. Dr. Sylvia Mechsner — Principal investigator, Charité
Katrina Holmes — MD, Charité / Tübingen
Ann-Katrin Abeler — Doctoral student, Charité
Zeinab Soleimani — PhD student, HPI
condition
principal investigator
institution
study type
cohort
region
data collected
status
publications
Endometriosis & adenomyosis
Prof. Dr. Sylvia Mechsner
Endometriosis Center, Charité — Medical University Berlin
Observational, patient-reported, longitudinal
2,800+ journeys shared
DACH (Germany, Austria, Switzerland)
Symptoms, consultations, treatments, sociodemographics, subjective experience
Closed
In preparation
OPADE Project: tell your story with major depressive disorder (MDD)
// background
280 million people worldwide live with major depressive disorder (MDD). Although there is a well-populated therapeutic landscape of antidepressants, fewer than 6% of patients fully benefit from their current therapeutic journey. Remission rates remain stubbornly low. OPADE is developing an AI / ML-driven predictive tool to support clinical decision-making in MDD. The project focuses on the gut–brain axis, studying how genetics, epigenetics, microbiome, and inflammatory networks combine to shape treatment response.
// research focus
- Identify patient profiles that predict and optimize antidepressant efficacy, increasing remission and reducing functional impairment
- Map correlations between neuroinflammatory indices — microbiome, metabolomics, immune profile, epigenomic and enzymatic markers — and treatment outcomes
- Evaluate molecular and non-molecular biomarkers as predictors of recurrence
- Improve diagnostic accuracy for primary prevention
- Trace the onset of depressive symptoms retrospectively from adolescence
- Establish how blood biomarkers correlate with other disease-specific biomarkers
// what we capture
Patients share their daily experience through a personalized chatbot — symptoms, medications, therapies, and key events — feeding into the AI / ML predictive tool.
// eligibility
Adults and adolescents aged 14–50 with major depressive disorder. Recruitment across six EU and international countries.
// research team
Here is the list of research partners
Project is funded by the European Union
condition
consortium
study type
cohort
duration
focus area
data collected
status
publications
Major depressive disorder (MDD)
OPADE
Multi-modal clinical, AI / ML predictive
350 patients, ages 14–50
24 months
Gut–brain axis · genetics · epigenetics · microbiome · inflammation
Symptoms, consultations, treatments, sociodemographics, subjective experience (mama health)
Closed
In preparation
Publications
Incretin-based therapies in psychiatry: A landscape analysis of ongoing randomized trials registered on ClinicalTrials.gov
This paper maps 34 ongoing randomized trials exploring incretin-based therapies, including GLP-1 drugs, for psychiatric indications. It highlights growing research interest while emphasizing the need for stronger evidence of lasting clinical benefit.
Conformal Prediction for ECG Interpretation: A Study on Human-AI Collaboration in Clinical Decision Support
Despite the recognized potential of Artificial Intelligence (AI)-based decision support systems for electrocardiogram (ECG) interpretation, the complex interactions between AI-generated advice and its presentation to physicians through user interfaces still need to be comprehensively understood...
From Oracular to Judicial: Enhancing Clinical Decision Making through Contrasting Explanations and a Novel Interaction Protocol
Clinical Decision Support Systems (CDSS) utilizing machine learning (ML) classifiers have demonstrated substantial potential for improving diagnostic accuracy across various medical domains. However, concerns regarding automation bias, diminished sense of agency, and over-reliance on these systems..
Teaching While Asking: Retrieval-Augmented Conversational Nudging Improves First-Session Completion in AI-Led Clinical Interviews: A Quasi-Experimental Pre/Post Evaluation Across Three Disease Areas
A pre/post study of 2,829 patients found that retrieval-augmented educational nudging in an AI clinical interviewer increased first-session completion from 9.0% to 22.3% across three diseases, supporting a “teaching while asking” approach while warranting randomized validation.
Industry Conference Articles
From Clicks to Conversations: AI Interviews Head-to-Head With Online Surveys
In a head-to-head study run by mama health and Cogent Healthcare, AI-moderated interviews were put up against traditional online surveys to see which could uncover more meaningful patient insight. The results reveal where AI conversations go further, capturing the reasoning, emotions, and context that structured surveys can miss.
