Investigator Sylvia Sudat, PhD

Dr. Sudat is a Sutter Health Epic data and analytic expert, and an informal content leader for the analytics team at the Sutter Health Center for Health Systems Research (East Campus, currently operating as Sutter's Research Development and Dissemination).

Over her 13-year career at Sutter Health, she has developed methods for accessing, extracting, and analyzing complex health data from multi-source electronic health records (EHRs) for clinical and observational research.

Dr. Sudat provides statistical consultation and support to Sutter researchers, and leads projects using large EHR datasets to address questions and challenges facing healthcare delivery and patient experience.

She has 10 years’ experience in palliative care, and led the evaluation of the Sutter Health Advanced Illness Management® (AIM) program. Using findings from AIM and with EHR data, Dr. Sudat developed an algorithm to prospectively identify patients potentially eligible for palliative care, which has been implemented across Sutter Health.Her other recent work includes risk prediction in palliative care and hospital readmissions, and evaluation of the impact of front-line treatments for sepsis on Sutter patient outcomes.

Dr. Sudat is a co-investigator on projects in migraine and mindfulness, diabetes, and the impact of air pollution on pre-term birth. She leads a project exploring the use of artificial intelligence to improve the identification of sepsis patients in the hospital.

Dr. Sudat completed graduate training in Biostatistics at the University of California at Berkeley, where she focused on risk prediction and semi-parametric methods for estimation in the context of causal inference and observational data.

Sutter Health Research Enterprise
2121 N. California Ave, Suite 310
Walnut Creek, CA, 94596
9252874037
keuters@sutterhealth.org

Primary Research Interests

Research Studies

Developing Clinically-Viable Predictive Readmission Risk Models and Evaluating Clinical Implementation

This project aims to develop an effective hospital readmission model with a focus on operationalization and clinical usability.

Investigator: Sylvia Sudat PhD

Evaluation of a Lifestyle Intervention Adopted for Clinical Practice for Diabetes Prevention (ELEVATE-DP)

This study will identify important barriers to and facilitators of translating an efficacious diabetes prevention intervention (Group Lifestyle Balance, GLB)

Investigators: Kristen M.J. Azar R.N., BSN, MSN/MPH, Investigator, Alice R. Pressman Ph.D., M.S., Robert Romanelli Ph.D., MPH, Associate Scientist, Sylvia Sudat PhD

Hyper-localized Air Pollution Measures and Preterm Birth in the Bay Area

Investigate association between hyperlocal (within city block) measures of air pollution and preterm birth, gestational hypertension, and diabetes in Bay Area.

Investigators: External PI Principal Investigator, Sylvia Sudat PhD

Mindfulness and Migraine: A Randomized Controlled Trial

Conduct a randomized controlled feasibility trial of mindfulness-based stress reduction for patients with moderate-to-severe migraine headache.

Investigators: Alice R. Pressman Ph.D., M.S., Sylvia Sudat PhD

Pilot Project in Applied Artificial Intelligence: Using Machine Learning to Improve the Safety of Hospital Care

Develop and test predictive model identifying emerging sepsis using artificial intelligence, and translate learnings into improved operational criteria.

Investigators: Alice R. Pressman Ph.D., M.S., Sylvia Sudat PhD

Sutter Health’s Advanced Illness Management program

Expand pilot of SH's Advanced Illness Management program across entire Sutter Health system to study quality of care, total care cost, and implementation.

Investigators: External PI Principal Investigator, Sylvia Sudat PhD

Publications

Conducting a pilot randomized controlled trial of community-based mindfulness-based stress reduction versus usual care for moderate-to-severe migraine: protocol for the Mindfulness and Migraine Study (M&M).

This is the first pragmatic trial in U.S. of mindfulness-based stress reduction for migraine using community classes.

Diverse transcriptional programs associated with environmental stress and hormones in the Arabidopsis receptor-like kinase gene family.

Study represents a preliminary, working model of processes and interactions in which the members of the receptor-like kinase gene family may be involved.

Using variable importance measures from causal inference to rank risk factors of schistosomiasis infection in a rural setting in China.

Results support applying analysis approaches that do not require arbitrary model pre-specification in data analysis related to water contact and schistosomiasis

Predicting all-cause risk of 30-day hospital readmission using artificial neural networks.

We demonstrate that neural networks are good candidates to capture complexity and interdependency of various EHR data fields to predict 30-day readmission risk.

Predicting need for advanced illness or palliative care in a primary care population using electronic health record data.

Applied predictive modeling to primary care population and examine the impact of biostatistical choices on model performance--predict need for palliative care.

Causal inference and prediction in health studies: environmental exposures and schistosomiasis, HIV-1 genotypic susceptibility scores and virologic suppression, and risk of hospital readmission for heart failure patients.

In this dissertation, semi-parametric methods to assess variable importance are applied to three real-world health applications.

Impact of home-based, patient-centered support for people with advanced illness in an open health system: a retrospective claims analysis of health expenditures, utilization, and quality of care at end of life.

Advanced Illness Management program has a positive impact on inpatient utilization, cost of care, hospice enrollment, and site of death.

Early weight loss and treatment response: data from a lifestyle change program in clinical practice.

Percentage weight change at 12 weeks from baseline can serve as a single indicator of nonresponse at the completion of the 12-month lifestyle change program.

Longitudinal weight outcomes from a behavioral lifestyle intervention in clinical practice.

A lifestyle change program in clinical practice is associated with modest weight loss, sustained through 24 months, in setting of cardiometabolic risk factors.

Short-term weight trajectories and long-term weight outcomes from a lifestyle intervention in real-world clinical practice.

With relationship between magnitudes of short- and long-term wt change, individual wt trajectories may be useful in identifying non-responders who need alt tx.

We've expanded your view