NCT06147687

Machine Learning for Early Diagnosis of Endometriosis(MLEndo)

FEMaLe: The Use of Machine Learning for Early Diagnosis of Endometriosis Based on Patient Self-reported Data - Study Protocol of a Multicenter Trial

• Status: Unknown
• Phase: —
• Study type: Observational
• Enrollment: 10,000 (estimated)
• Sponsor: Semmelweis University · Academic / Other
• Sex: Female
• Age: 14 Years – 45 Years
• Healthy volunteers: Accepted

Summary

The project aims to create a large prospective data bank using the Lucy medical mobile application and collect and analyze patient profiles and structured clinical data with artificial intelligence. In addition, authors will investigate the association of removed or restricted dietary components with quality of life, pain, and central sensitization.

Detailed description

Introduction: Endometriosis is a complex and chronic disease that affects ∼176 million women of reproductive age and remains largely unresolved. It is defined by the presence of endometrium-like tissue outside the uterus and is commonly associated with chronic pelvic pain, infertility, and decreased quality of life. Despite numerous proposed screening and triage methods such as biomarkers, genomic analysis, imaging techniques, and questionnaires to replace invasive diagnostic laparoscopy, none have been widely adopted in clinical practice. . Despite the availability of various screening methods (e.g., biomarkers, genomic analysis, imaging techniques) that are intended to replace the need for invasive diagnostic laparoscopy, the time to diagnosis remains in the range of 4 to 11 years. Aims: The project aims to create a large prospective data bank using the Lucy medical mobile application and collect and analyze patient profiles and structured clinical data with artificial intelligence. In addition, authors will investigate the association of removed or restricted dietary components with quality of life, pain, and central sensitization. Methods: A Baseline and Longitudinal Questionnaire in the Lucy app collects self-reported information on symptoms related to endometriosis, socio-demographics, mental and physical health, nutritional, and other lifestyle factors. 5,000 women with endometriosis and 5,000 women in a control group will be enrolled and followed up for one year. With this information, any connections between symptoms and endometriosis will be analyzed with machine learning. Conclusions: Authors can develop a phenotypic description of women with endometriosis by linking the collected data with existing registry-based information on endometriosis diagnosis, healthcare utilization, and big data approach. This may help to achieve earlier detection of endometriosis with pelvic pain and significantly reduce the current diagnostic delay. Additionally, authors can identify nutritional components that may worsen the quality of life and pain in women with endometriosis; thus, authors can create evidence-based dietary recommendations. Keywords: Endometriosis, Machine learning, Non-invasive diagnosis, Diet

Conditions

• Endometriosis
• Pelvic Pain
• Infertility, Female

Interventions

Type	Name	Description
DIAGNOSTIC_TEST	Self reported data collection	ML assessement of colleceted data

Timeline

• Start date: 2022-01-01
• Primary completion: 2024-12-31
• Completion: 2024-12-31
• First posted: 2023-11-28
• Last updated: 2023-11-28

Locations

2 sites across 1 country: Hungary