• Corpus ID: 53213190

Phenotyping Endometriosis through Mixed Membership Models of Self-Tracking Data

  title={Phenotyping Endometriosis through Mixed Membership Models of Self-Tracking Data},
  author={I{\~n}igo Urteaga and Mollie M. McKillop and Sharon Lipsky Gorman and No{\'e}mie Elhadad},
We investigate the use of self-tracking data and unsupervised mixed-membership models to phenotype endometriosis. Endometriosis is a systemic, chronic condition of women in reproductive age and, at the same time, a highly enigmatic condition with no known biomarkers to monitor its progression and no established staging. We leverage data collected through a self-tracking app in an observational research study of over 2,800 women with endometriosis tracking their condition over a year and a half… 
Learning endometriosis phenotypes from patient-generated data
The promise of unsupervised learning of endometriosis subtypes from self-tracked data is shown, as learned phenotypes align well with what is already known about the disease, but also suggest new clinically actionable findings.
A generative, predictive model for menstrual cycle lengths that accounts for potential self-tracking artifacts in mobile health data
This work proposes and evaluates a hierarchical, generative model for predicting next cycle length based on previously-tracked cycle lengths that accounts explicitly for the possibility of users skipping tracking their period, and yields state-of-the-art performance against neural network-based and summary statistic-based baselines.
Characterizing physiological and symptomatic variation in menstrual cycles using self-tracked mobile-health data
It is uncovered that women located at different ends of the menstrual variability spectrum, based on the consistency of their cycle length statistics, exhibit statistically significant differences in their cycle characteristics and symptom tracking patterns.
The real-world applications of the symptom tracking functionality available to menstrual health tracking apps
Whether the fields available in iOS mobile phone apps for recording menstrual cycle symptoms are able to be harmonized across platforms for potential use in research, such as aggregated data analysis is evaluated.
Practice Note: ‘If Only All Women Menstruated Exactly Two Weeks Ago’: Interdisciplinary Challenges and Experiences of Capturing Hormonal Variation Across the Menstrual Cycle
How interdisciplinary efforts across anthropology, public health, and data science can leverage the advances in mobile menstrual tracking and hormone measurement to better characterize the menstrual cycle at the population level is shown.
Divided We Stand
The enigmatic nature of endometriosis necessitates complementary approaches from human-centered computing and artificial intelligence, and thus opens a number of future research avenues to support patients and providers in their care work.
„Self-tracking” jako zjawisko kulturowe wspierające procesy samopoznania
The article analyses the popularity of self-tracking as one cultural phenomenon. The practice of tracking one’s activity and controlling life parameters is not new, but nowadays it has been


Learning probabilistic phenotypes from heterogeneous EHR data
Characterizing the clinical relevance of digital phenotyping data quality with applications to a cohort with schizophrenia
The relationship between data quality and future symptom-related survey responses in 16 patients with schizophrenia was examined and it was found that smartphone sensor data as well as phone-use metrics related to the completion of symptom- related surveys were significantly associated with survey results, highlighting the clinical relevance of this approach.
Designing in the Dark: Eliciting Self-tracking Dimensions for Understanding Enigmatic Disease
The process of identifying design requirements for self-tracking endometriosis, a highly enigmatic and prevalent disease, is outlined through interviews, focus groups, surveys, and content analysis of an online endometiosis community and suggestions for overcoming tensions inherent in designing self- tracking tools for individual use and population analysis are discussed.
The mPower study, Parkinson disease mobile data collected using ResearchKit
The study interrogated aspects of this movement disorder through surveys and frequent sensor-based recordings from participants with and without Parkinson disease, and hopes that releasing data contributed by engaged research participants will seed a new community of analysts working collaboratively on understanding mobile health data to advance human health.
Endometriosis: a high-risk population for major chronic diseases?
Increasing evidence suggests that endometriosis patients are at higher risk of several chronic diseases, including ovarian and breast cancers, cutaneous melanoma, asthma, and some autoimmune, cardiovascular and atopic diseases, and at decreased risk of cervical cancer.
The Asthma Mobile Health Study, a large-scale clinical observational study using ResearchKit
Initial findings from the Asthma Mobile Health Study are reported, a research study, including recruitment, consent, and enrollment, conducted entirely remotely by smartphone, that detected increased reporting of asthma symptoms in regions affected by heat, pollen, and wildfires.
The epidemiology of endometriosis.
It is proposed that the genetics of endometriosis may consist of early menarche, short cycles, painful periods, subfertility, and possibly tall stature that could be explained by genetic factors that predispose to poor endowment of germ cells and canalization defects of the cervix.
Association Between Endometriosis and Hypercholesterolemia or Hypertension
In this large cohort study, laparoscopically confirmed endometriosis was prospectively associated with increased risk of hypercholesterolemia and hypertension.
Gastrointestinal symptoms among endometriosis patients—A case-cohort study
A poor association between symptoms and lesion localization was found, indicating existing comorbidity between endometriosis and irritable bowel syndrome (IBS).