Ipek Ensari

Early Career Tenure-track Researcher, Icahn School of Medicine at Mount Sinai

1 active project

Female reproductive disorders across diverse patient populations

This project aims to investigate the following primary questions pertaining to disorders of the female reproductive anatomy: 1) Prevalence of menstrual and chronic pelvic pain disorders (e.g., endometriosis, dysmenorrhea) and disease (self-)management techniques among different demographic and socioeconomic segments of…

Scientific Questions Being Studied

This project aims to investigate the following primary questions pertaining to disorders of the female reproductive anatomy:
1) Prevalence of menstrual and chronic pelvic pain disorders (e.g., endometriosis, dysmenorrhea) and disease (self-)management techniques among different demographic and socioeconomic segments of the population documented in the electronic health records (EHRs)
3) Moderators of self-reported vs clinician-documented reproductive health status among sexual and gender minority (SGM) adults
4) Feasibility and performance of different natural language processing (NLP) techniques for detecting under-documented disorders of the female reproductive anatomy from clinical notes within the EHRs.

These questions aim to address the knowledge gaps in the area of women's reproductive health across with respect to their diagnosis, treatment, and definition in clinical records, with a focus on patient populations at increased risk for health disparities and inequities.

Project Purpose(s)

  • Disease Focused Research (female reproductive and related chronic pain disorders )
  • Methods Development
  • Control Set

Scientific Approaches

Data: We will use data from the electronic health records including structured data/codes on diagnosis, medications, treatments, patient-level factors (e.g., insurance, demographics), and unstructured free-text clinician notes, self-reported survey data, and wearable data to answer our research questions.
Methodology: We will implement standard regression-based estimation and prediction models to investigate the clinical questions (#1 and #2). We will implement various NLP methods (e.g., large language models) to study our methodological question (#3). If the language models developed by our team show adequate performance, we will validate the performance of these algorithms on the EHR data available in the All of Us cohort.

Anticipated Findings

We expect to find differences in the documented prevalence and clinical descriptions of these reproductive disorders within the EHRs based on race/ethnicity, socioeconomic factors and insurance status. We similarly expect differences in reported treatment and self-management approaches, and habitual health behaviors across these groups. We expect that patient-reported efficacy outcome for a treatment/management will not differ based on these factors. We anticipate that there will be scarce descriptive information on SGM reproductive health, and moreover that the pre-trained medical language models will not have adequate performance off the shelf. We anticipate that the algorithmic performance will improve with the addition of person-level data. These findings can help identify potential targets of self-management interventions, as well as approaches for how to implement clinical language models when working with less-frequently available terminology within the EHRs.

Demographic Categories of Interest

  • Race / Ethnicity
  • Sex at Birth
  • Gender Identity
  • Sexual Orientation
  • Geography
  • Access to Care
  • Education Level
  • Income Level

Data Set Used

Registered Tier

Research Team

Owner:

  • Ipek Ensari - Early Career Tenure-track Researcher, Icahn School of Medicine at Mount Sinai

Collaborators:

  • Sahiti Kolli - Research Fellow, Icahn School of Medicine at Mount Sinai
1 - 1 of 1
<
>
Request a Review of this Research Project

You can request that the All of Us Resource Access Board (RAB) review a research purpose description if you have concerns that this research project may stigmatize All of Us participants or violate the Data User Code of Conduct in some other way. To request a review, you must fill in a form, which you can access by selecting ‘request a review’ below.