In our laboratory we conduct research on methods for combining actively-tracked and passively-collected mHealth data to investigate data methods for designing patient-centered mHealth measures, elucidating elucidating phenotypic and endotypic variation in women’s reproductive disorders (e.g., using electronic health records), and designing mHealth intervention tools for chronic symptom management. We are recruiting graduate students and postdoctoral fellows to various new projects on these topics.

Women’s health, participatory mHealth research

A central aim of our groups’ research is to re-tool patient-generated data via mHealth technology to better characterize conditions that are traditionally poorly documented and not well understood. To this end, we collaborate on Citizen Endo and the EVEN initiative led by Professor Noemie Elhadad at Columbia University Department of Biomedical Informatics. Citizen Endo aims to better document, understand, and develop treatment strategies for endometriosis using a citizen science approach through its mHealth research tracking app, Phendo. Endometriosis is an inflammatory, painful disorder in which tissue similar to the tissue that normally lines the inside of your uterus — the endometrium — grows outside the uterus. Surrounding tissue can become irritated, eventually developing scar tissue and adhesions — bands of fibrous tissue that can cause pelvic tissues and organs to stick to each other. Its prevalence is estimated to be ~10%, and takes 7-10 years to diagnose. There is no cure or adequate treatments for endometriosis- even with hysterectomies 2 out of 3 times the pain returns. Pharmacotherapy can be helpful, though has not been found to be efficacious in the long term.

One reason why it is still a clinically misunderstood and poorly managed disease is that this is a cyclical disease where the symptoms fluctuate and the experience of the disease varies from one person to another. As such, we need to first better understand the nature of this variability and possible modifiable factors associated. Direct patient input via self-tracked data could augment electronic health records, which are often the primary source for making many clinical decisions. And this is problematic because EHR can be incomplete, sparse, limited in the amount and type of information they provide and not standardized across different databases. In contrast, self tracked data gives us more individual level details, collected frequently over time, some gives us more context and increases the speed with which the information travels across different components of the medical health system (Ensari et al. 2021)

Digital phenotyping and summarization techniques for mHealth patient data

Our team uses informatics and data-driven approaches to delineate symptom trajectories in diseases with a dynamic course (e.g., endometriosis, multiple sclerosis), and identification of self-management approaches for their effective management. We previously investigated a flexible unsupervised machine learning technique that relies on mixtures of multivariate generalized linear mixed models for digital phenotyping of sleep patterns among heterogeneous samples of Latinx adults (Ensari et al. 2021). I was recently awarded a R01 grant from NIH to investigate functional data methods toward design and evaluation of digital patient reported outcome measures. This project will investigate a functional data analysis framework to design and evaluate mHealth measures of pain, quality of life, and treatment response using patient generated health data with high complexity and temporality. The work is grounded in chronic pelvic pain disorders as the disease model, a complex disorder with high societal burden and impact on quality of life. Novel aspects of the project include: 1) application of Distributed Lag Models (DLMs) in this mHealth context to estimate “critical windows” of tracking analogous to the “window of susceptibility”, and 2) design of outcome measures that consider the entire trajectory of patient symptoms via functional data analysis. These models can handle some of the inherent challenges in complex mobile data that traditional models cannot. Therefore they can facilitate the derivation of ecologically valid and actionable patient reported outcome measures. We are looking to recruit graduate students and postdoctoral fellows for this project.

Symptom self-management and computational methods for patient-generated health data

As a trained kinesiologist, a focus on physical activity and its health outcomes is a central theme across my projects. But why do we do physical activity research? Simply put, because the lack of it can kill you. WHO has declared physical inactivity as an urgent public health priority. It is the 4th leading risk factor for all-cause death and disease. This is not just a developed world problem, it is a global problem. Overall, we are moving less, sitting more, and this is killing us. This is also a missed opportunity because exercise is an important component of effective pain management. Both acute (ie, single bout/session) and chronic (ie, repeated bouts/sessions over time) exercise training can improve numerous pain-related conditions. My recent work (Ensari et al. 2022) investigates the association of daily physical exercise with pain symptoms in endometriosis through an observational, retrospective study conducted using data from the Phendo App. We examined whether an individual’s typical weekly (ie, habitual) exercise frequency influences (ie, moderates) the relationship between their pain symptoms on a given day (day t) and previous-day (day t-1) exercise. Results suggest that regular exercise might influence the day-level (ie, short-term) association of pain symptoms with exercise. These findings can inform exercise recommendations for endometriosis pain management, especially for those who are at greater risk of lack of regular exercise due to acute exacerbation in their pain after exercise. We are looking to recruit students and postdoctoral researchers to join our follow-up project on this, which focuses on tailoring exercise recommendations for symptoms related to women’s reproductive disorders, focusing on comparison of different machine learning models.