Polina V. Kukhareva
· Research Assistant ProfessorVerifiedUniversity of Utah · Biomedical Informatics
Active 2013–2026
About
Polina V. Kukhareva, PhD, MPH, FAMIA, is a Research Assistant Professor at the University of Utah in the Department of Biomedical Informatics. She earned her Ph.D. in Biomedical Informatics at the University of Utah and her M.P.H. in Biostatistics from the University of North Carolina-Chapel Hill. Her research interests include evaluating innovative digital health solutions to enhance healthcare outcomes and reduce costs. Her work, grounded in rigorous evidence-based methods, explores both the clinical benefits of digital health interventions and their impact on health equity. Dr. Kukhareva has extensive expertise in analyzing large-scale real-world electronic health record (EHR) data and has overseen the evaluation of over 20 digital health solutions addressing a broad range of healthcare topics, including lung cancer screening, neonatal bilirubin management, sepsis, diabetes pharmacotherapy, diabetic ketoacidosis, weight management, opioid overuse, telemetry overutilization, and laboratory test ordering. She developed the Evaluation in Life Cycle of Health information Technology (ELICIT) framework to guide the evaluation of digital health interventions. Her contributions highlight the transformative potential of digital health and emphasize the importance of rigorous evaluation in this field.
Research topics
- Computer Science
- Medicine
- Internal medicine
- Intensive care medicine
- Emergency medicine
- Family medicine
- Knowledge management
- Sociology
- Process management
- Political Science
- Business
- Artificial Intelligence
- Statistics
- Engineering
- World Wide Web
- Engineering management
- Medical emergency
- Nursing
- Demography
- Database
- Endocrinology
- Pathology
Selected publications
AIM-AHEAD Year 4 Research Fellowship - Project 2185 Dataset
Zenodo (CERN European Organization for Nuclear Research) · 2026-03-23
datasetOpen access1st authorCorrespondingProject Title: Developing Transformer Models for Smarter Prescribing in Diabetes Care Project Awardee: Polina Kukhareva This dataset is derived from the OCHIN Community Health Database – AIM‑AHEAD Year 4 and implemented as a set of views. It includes adults aged 18 and older with ambulatory or telehealth encounters between 2017 and 2024 who have a diagnosis of diabetes and/or at least one recorded HbA1c measurement, enabling longitudinal modeling of treatment pathways and prescribing patterns. The dataset includes patient demographics (sex, age, race, ethnicity, language, payer, federal poverty level, ZIP/ZCTA, homelessness status, and marital status), visit‑level data, provider and care site characteristics, vital signs, condition diagnoses across cardiometabolic and related comorbidity domains, laboratory results (glycemic, renal, lipid, and metabolic panels), medication exposures, procedures related to diabetes management and preventive care, immunization records, mortality indicators, and structured patient screening data capturing behavioral and contextual health information. If you are interested in learning more about this dataset and understanding access requirements, we recommend you reach out to the named Project Awardee and/or OCHIN at AI‑DataConsult[at]ochin.org.
JCO Oncology Practice · 2026-03-17 · 1 citations
articleOpen accessPURPOSE: Over 90% of people with hereditary cancer syndromes in the United States remain unidentified. The Genetic Cancer Risk Detector (GARDE) is an open-source, electronic health record (EHR)-integrated, digital health platform that can facilitate genetic cancer risk assessment and genetic testing. This study evaluates its budget impact on health care institutions. METHODS: A budget impact analysis was performed from the perspective of a US health care provider system over a 3-year horizon. Data from the BRIDGE randomized controlled trial data from the University of Utah Health (UHealth) were used, where eligible primary care patients were screened for genetic cancer risk via GARDE. Costs of GARDE were categorized across planning, implementation, and operational phases. Revenue projections were based on Centers for Medicare & Medicaid Services reimbursement rates. Scenario analyses varied uptake of interventions, surveillance intervals, reimbursement rates, and implementation scale. RESULTS: Of 1,444 patients identified by GARDE at UHealth and enrolled in the BRIDGE trial, 205 completed genetic testing, with 15 found to carry pathogenic variants. The total 3-year implementation cost was $29,217 US dollars (USD). Revenue from guideline-recommended procedures totaled $86,563 USD, yielding a net positive budget impact of $57,347 USD. Most revenue (76.4%) was generated by surgical risk-reduction procedures. Scenario analyses revealed high sensitivity to cancer risk-reducing surgery uptake and implementation scale. Modeling 100% uptake of risk-reducing surgeries increased revenue to $128,102 USD, while 20-fold scaling of the implementation population increased revenue to $1.7 million USD. Commercial insurance reimbursement assumptions further amplified revenue. CONCLUSION: GARDE enables scalable hereditary cancer risk assessment within a health care provider system. Even with modest uptake, it yields a positive financial return, and significantly greater revenue is achievable with broader implementation. These findings support adoption of EHR-integrated tools to enhance clinical outcomes in precision cancer prevention and risk management, in an economically viable manner.
Reassessing Utility in the MyLungHealth Trial—Reply
JAMA Oncology · 2026-04-02
article1st authorCorrespondingAIM-AHEAD Year 4 Research Fellowship - Project 2185 Dataset
Zenodo (CERN European Organization for Nuclear Research) · 2026-03-23
datasetOpen access1st authorCorrespondingProject Title: Developing Transformer Models for Smarter Prescribing in Diabetes Care Project Awardee: Polina Kukhareva This dataset is derived from the OCHIN Community Health Database – AIM‑AHEAD Year 4 and implemented as a set of views. It includes adults aged 18 and older with ambulatory or telehealth encounters between 2017 and 2024 who have a diagnosis of diabetes and/or at least one recorded HbA1c measurement, enabling longitudinal modeling of treatment pathways and prescribing patterns. The dataset includes patient demographics (sex, age, race, ethnicity, language, payer, federal poverty level, ZIP/ZCTA, homelessness status, and marital status), visit‑level data, provider and care site characteristics, vital signs, condition diagnoses across cardiometabolic and related comorbidity domains, laboratory results (glycemic, renal, lipid, and metabolic panels), medication exposures, procedures related to diabetes management and preventive care, immunization records, mortality indicators, and structured patient screening data capturing behavioral and contextual health information. If you are interested in learning more about this dataset and understanding access requirements, we recommend you reach out to the named Project Awardee and/or OCHIN at AI‑DataConsult[at]ochin.org.
JMIR Formative Research · 2026-05-21
articleOpen accessBackground: Lung cancer remains the leading cause of cancer-related mortality worldwide, with low-dose computed tomography screening demonstrating an approximately 20% reduction in mortality among high-risk individuals. Despite this benefit, screening prevalence remains suboptimal, with often less than 20% of eligible individuals reported to be up to date on screening. Shared decision-making is essential for effective lung cancer screening (LCS) implementation, with decision aids shown to enhance patient knowledge and engagement. Objective: The aim of this study is to identify patient preferences, concerns, and design considerations through qualitative evaluation of MyLungHealth, a personalized patient-facing educational tool for LCS integrated with electronic health records, and to describe how these findings informed iterative design modifications. Methods: We employed qualitative research methods through focus groups (n=34) and individual interviews (n=18) with individuals who met screening eligibility criteria. Participants were recruited from the University of Utah Health and New York University Langone Health between May and December 2023. Feedback was analyzed using Braun and Clarke's thematic analysis principles. Results: Six themes were organized into three overarching domains. Domain A included interpretation and impact of personalized risk information: theme 1, difficulties interpreting risk information, and theme 2, varied impacts of risk information on motivation. Domain B included autonomy, privacy, and user interface preferences: theme 3, desire for autonomy and control over personal health data, and theme 4, preference for straightforward language and multiple information formats. Domain C included integration with clinical workflows and patient portal systems: theme 5, expectations for integration with health care provider workflows, and theme 6, mixed experiences with personal health record systems. These insights led to key design modifications, including simplified risk presentation, multimodal content delivery options (video and text), and implementation of electronic health record alerts for clinicians. Conclusions: The user-centered design process for MyLungHealth revealed important considerations for developing effective patient education tools for LCS. The findings highlighted the need for simplified risk presentation, personalized information delivery, and integration with clinical workflows. These findings underscore the importance of balancing comprehensive risk communication with user accessibility.
Enhancement of Patient-Centered Lung Cancer Screening
JAMA Oncology · 2025-12-26 · 3 citations
articleOpen access1st authorCorrespondingImportance: Lung cancer screening (LCS) with low-dose computed tomography (CT) remains underused in the US, partly because of incomplete smoking history documentation in electronic health records (EHRs) and limited time for shared decision-making in primary care. Objective: To determine whether a patient-facing, EHR-integrated tool combined with clinician-facing clinical decision support improves the identification of LCS-eligible patients and the ordering of low-dose CT compared with clinician-facing tools alone. Design, Setting, and Participants: This pragmatic, unstratified, randomized clinical trial with parallel groups was conducted from March 29, 2024, to March 28, 2025, at primary care clinics at University of Utah Health and New York University Langone Health. Adults aged 50 to 79 years with a documented smoking history, an active patient portal account, and a primary care visit in the preceding year were included. Study 1 enrolled patients with uncertain LCS eligibility (10 to 19 pack-years, unknown pack-years, or missing quit date); study 2 enrolled patients with documented eligibility (20 or more pack-years and currently smoking or quit smoking within 15 years). Interventions: The control included the clinician-facing Decision Precision+ tool (preventive care reminders and a shared decision-making tool). The intervention included the Decision Precision+ tool as well as the MyLungHealth tool, which collected detailed smoking history (study 1) and delivered personalized education and risk/benefit information (studies 1 and 2) via the patient portal in English and Spanish. Main Outcomes and Measures: The primary outcomes were the proportion of patients newly identified as eligible for LCS (study 1) and low-dose CT ordering rates (study 2) over 12 months. Analyses used intention-to-treat mixed-effects logistic regression. Results: There were 31 303 randomized participants, including 26 729 in study 1 (13 144 [49.2%] female; 13 580 [50.8%] male; median [IQR] age, 62 [55-69] years) and 4574 in study 2 (2230 [48.8%] female; 2344 [51.2%] male; median [IQR] age, 63 [56-69] years). In study 1, the MyLungHealth tool increased new LCS eligibility identification (635 of 13 412 [4.7%] vs 308 of 13 317 [2.3%]; adjusted odds ratio, 2.19; 95% CI, 1.99-2.42; P < .001). In study 2, low-dose CT ordering was higher in the intervention arm (474 of 2312 [20.5%] vs 434 of 2262 [19.2%]; adjusted odds ratio, 1.16; 95% CI, 1.04-1.30; P = .008). Conclusions and Relevance: In this randomized clinical trial, integrating a patient-centered tool into primary care EHR workflows increased the identification of patients eligible for LCS and the ordering of low-dose CTs. The relative increases in these primary outcomes were substantial, but absolute increases were more modest. Research on more intensive interventions is warranted to evaluate their ability to further improve LCS screening. Trial Registration: ClinicalTrials.gov Identifier: NCT06338592.
Medicine & Science in Sports & Exercise · 2025-09-16
articlePURPOSE: MAINTAIN PRIME promotes weight maintenance for primary care patients with recent intentional weight loss ≥5%. Previous research shows strong association between higher physical activity (PA) levels and weight management success. This analysis investigates the relationship between objective PA and baseline weight loss. METHODS: ActiGraph GT3X-BT accelerometer was worn on the dominant hip during waking hours for 14 days. We included sedentary time, light activity, average daily steps, MVPA, and peak 1-minute cadence in our analyses. Descriptive statistics, rate ratios (RR) of % weight loss with 95% confidence intervals (CI) were calculated for each PA metric. Adjusted relative risk values controlled for gender, weight loss medications, and education. RESULTS: Baseline PA was assessed in 110 out of 268 randomized participants (41%) with at least 4 days of accelerometer data. There were no significant differences in gender, ethnicity, education level, or BMI between individuals with missing and non-missing accelerometer data. Participants spent an average of 433 (SD = 142) minutes daily in sedentary behavior, 327 (SD = 103) minutes in light activity, and 34 (SD = 27) minutes of daily MVPA. Participants averaged 5,485 (SD = 2878) steps/day with a peak 1-minute cadence of 121 (20), indicating most participants were performing moderate activity. MVPA emerged as the only activity significantly associated with baseline weight loss percentage after adjusting for confounders (Table 1). The RR for MVPA was 1.004 (95% CI: 1.001-1.008, p = 0.03) in Model 2 and 1.004 (95% CI: 1.001-1.008, p = 0.03) in Model 3, indicating a small but statistically significant increase in baseline weight loss percentage with each incremental increase in MVPA. CONCLUSIONS: Our findings highlight MVPA as a key factor in primary care patients with recent intentional weight loss, emphasizing its role in long-term weight management strategies. Supported by: NIH R18DK123372
Diabetes · 2025-06-13
article1st authorCorrespondingIntroduction and Objective: GLP-1 receptor agonists (GLP-1 RAs) have revolutionized type 2 diabetes (T2D) and obesity management but are costly, raising equity concerns. This study examines prescribing disparities for GLP-1 RAs among White, Black, and Hispanic patients using a national EHR database. Methods: This retrospective study analyzed adults with uncomplicated T2D (ICD-10: E11.9) from the TriNetX national EHR repository. Prescription trends were summarized from 2019 to 2023. Adjusted odds ratios (aOR) for semaglutide and tirzepatide prescriptions in 2022-2023 were calculated by race/ethnicity, adjusting for age, sex, and Charlson Comorbidity Index. Results: The study included 14,196 White, 13,982 Black, and 11,974 Hispanic patients. Semaglutide, tirzepatide, and dulaglutide were the most frequently prescribed GLP-1 RAs. In 2022-2023, compared to White patients, Black patients had an aOR of 0.7 (95% CI: 0.6-0.9) for tirzepatide and 0.8 (95% CI: 0.7-0.9) for semaglutide. Hispanic patients had an aOR of 0.4 (95% CI: 0.3-0.5) for tirzepatide and 0.6 (95% CI: 0.6-0.7) for semaglutide. Conclusion: EHR databases are effective tools for monitoring prescribing trends and identifying disparities. White patients are being prescribed the latest-generation GLP-1 RAs (semaglutide and tirzepatide) more frequently than Black and Hispanic patients, highlighting the need for equitable access to GLP-1 RA therapies. Disclosure P. Kukhareva: None. K. Kawamoto: Consultant; Pfizer Inc. Other Relationship; Beckman Coulter.
Documentation of social determinants of health for patients with type 2 diabetes in Epic Cosmos
JAMIA Open · 2025-08-08 · 3 citations
articleOpen access1st authorCorrespondingObjectives: Type 2 diabetes (T2D) is a growing public health burden with persistent racial and ethnic disparities. . This study assessed the completeness of social determinants of health (SdoH) data for patients with T2D in Epic Cosmos, a nationwide, cross-institutional electronic health recors (EHR) database. Materials and Methods: The study included adults with T2D (ICD-10: E11.*) with encounters between 2022 and 2024. We analyzed 11 individual-level SDoH data elements across 5 domains-financial strain, food insecurity, housing instability, intimate partner violence, and transportation needs-and 4 components of the Social Vulnerability Index (SVI), representing neighborhood-level SDoH. Data completeness for each data element (ie, the proportion of individuals with non-missing values) was evaluated using generalized linear models, adjusting for source healthcare organization, sex, and age. Results: Among 12 031 927 individuals with T2D, adjusted completeness for individual-level SDoH data elements ranged from 11.2% to 31.5%, varying by data element and racial/ethnic group. American Indian or Alaska Native, Asian, Hispanic, and Native Hawaiian or Other Pacific Islander individuals had lower completeness for all individual-level SDoH compared to White individuals. In contrast, SVI data elements were available for nearly all patients since they are derived from patient addresses routinely collected in EHRs. Discussion: While SVI data elements were widely available, individual-level SDoH data elements had significant missingness, limiting their usability for secondary analyses. Racial/ethnic disparities in SDoH completeness further complicate their use. Conclusion: Standardized, equitable SDoH collection is critical to close documentation gaps, reduce disparities, and enable accurate, bias-resistant analyses in T2D care.
Circulation · 2025-03-11
articleIntroduction: Caloric intake and diet quality are important for weight management. This study leverages data from the MAINTAIN PRIME weight maintenance trial, which recruited participants with recent, intentional weight loss ≥ 5%. We analyzed the association between diet quality and percentage weight loss at study enrollment. Methods: We assessed diet quality with the Mediterranean Diet Score (MDS), a validated 14-item survey, and examined individual components, each with 2 or 3 categorical levels. The association between percentage weight loss and MDS components was analyzed using gamma regression with log link across three models: Model 1 controlled for gender, Model 2 for gender and weight loss medication use, and Model 3 for gender, medication use, and education. Rate ratios (RR) and 95% confidence intervals (CI) were calculated for each MDS component. Results: Baseline weight and Mediterranean Diet Score (MDS) data were collected from 262 participants. Adjusted RR values for each component of the MDS are found in Table 1. Key findings include: Commercial pastries (cookies, cakes, etc.) The RR of 0.89 across all models (p <0.01), suggests a clear association between consuming more commercial pastries and less weight loss. Those who consume more are likely to experience about 11% less weight loss compared to those who consume less or none. Carbonated or sugar-sweetened beverages (CSSB): The RR of 0.90 across all three models (p ≤ 0.01) suggests that individuals who consume more CSSB experience 10% less weight loss compared to those who consume fewer or no CSSB. Nuts: The RR of 0.89–0.90 across all models (p = 0.01) indicates that a higher intake of nuts per week is associated with less weight loss. Red meat: Across the models, a higher red meat consumption was associated with less weight loss. While the association is not statistically significant in Model 1 (p = 0.11), it becomes significant in Model 2 (p = 0.03) and Model 3 (p = 0.02). Therefore, adjusting for additional variables strengthens the observed association. In Model 3, the RR of 0.91 indicates 9% less weight loss compared to those with lower or no red meat intake. Conclusions: A higher consumption of commercial pastries, carbonated or sugar-sweetened beverages, nuts, and red meat was negatively associated with less weight loss, highlighting their potential role in hindering weight loss efforts. Our findings highlight the importance of diet quality management.
Frequent coauthors
- 37 shared
Kensaku Kawamoto
University of Utah
- 19 shared
Michael Flynn
- 13 shared
Phillip B. Warner
University of Utah
- 13 shared
Jorie Butler
University of Utah
- 12 shared
Tanner Caverly
- 12 shared
Charlene Weir
University of Utah
- 11 shared
Teresa Taft
University of Utah
- 10 shared
Guilherme Del Fiol
University of Utah
Education
Ph.D., Biomedical Informatics
University of Utah
Other, Biostatistics
University of North Carolina-Chapel Hill
- Resume-aware match score
- Save to shortlist
- AI-drafted outreach
See your match with Polina V. Kukhareva
PhdFit ranks faculty by your research interests, methods, and publications — grounded in their actual work, not templates.
- Free to start
- No credit card
- 30-second signup