Cl-Pharm-IBS-ML-2026

Machine Learning-Based Phenotyping of IBS Patients Using Multidimensional Patient-Reported Outcomes

The purpose of this study is to identify distinct subgroups (phenotypes) of Irritable Bowel Syndrome (IBS) patients. While traditional IBS classification relies mainly on bowel habits, this research uses a multidimensional questionnaire to capture clinical symptoms, psychological factors, diet triggers, sleep quality, and digital behaviors. By applying advanced machine learning algorithms to these patient-reported outcomes, the study aims to uncover hidden patterns that can help customize future treatments and improve patient care.

Inclusion Criteria:

• Participants aged 18 years or older.
• Formal physician-confirmed diagnosis of Irritable Bowel Syndrome (IBS).
• Ability to access and complete the digital multidimensional questionnaire.
• Willingness to provide digital informed consent.

Exclusion Criteria:

• Presence of organic gastrointestinal diseases (e.g., Inflammatory Bowel Disease, celiac disease, or colorectal cancer).
• Presence of alarm/red flag symptoms (e.g., nocturnal symptoms waking the patient).
• Incomplete or inconsistent questionnaire responses.