About

Dr. Kensaku Kawamoto serves as the Chief Health AI Transformation Officer for University of Utah Health and holds the position of Dr. Helmuth F. Orthner Endowed Professor and Vice Chair of Clinical AI and Informatics for the University of Utah Department of Biomedical Informatics. His work focuses on advancing artificial intelligence across the health system to enhance patient care, operational performance, research, and education. He leads efforts such as the University of Utah Health Innovation Lab, the ReImagine EHR Initiative, and the enterprise Value Driven Outcomes framework, all aimed at improving health care through innovative AI and informatics solutions. Dr. Kawamoto's background includes a B.A. in biochemical sciences from Harvard University, an M.D. and Ph.D. in biomedical engineering with a focus on biomedical informatics, and an M.H.S. in clinical research from Duke University. He has been recognized as a Top 25 Innovator in health care by Modern Healthcare and as a University of Utah Presidential Societal Impact Scholar. His contributions extend to national health IT policy, having served on the U.S. Health IT Advisory Committee and co-chaired the Interoperability Standards Priorities Task Force. He is a co-solution architect of the Value Driven Outcomes framework and the founder and director of OpenCDS, a multi-institutional initiative for clinical decision support used nationwide. His research and leadership aim to address the grand challenge of providing high-quality, affordable health care through clinical AI and informatics.

Research topics

• Computer Science
• Medicine
• Artificial Intelligence
• Sociology
• Internal medicine
• Political Science
• Knowledge management
• Business
• Process management
• Family medicine
• Nursing
• Intensive care medicine
• Emergency medicine
• Engineering
• Medical education
• Pathology
• World Wide Web
• Psychology
• Data Mining
• Demography
• Data science
• Public relations
• Statistics
• Endocrinology

Selected publications

• MyLungHealth, a Patient-Facing Education Tool for Lung Cancer Screening: Qualitative User-Centered Design Study

  JMIR Formative Research · 2026-05-21

  articleOpen accessSenior author

  Background: 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.

  PublisherOA PDFDOI

• Reassessing Utility in the MyLungHealth Trial—Reply

  JAMA Oncology · 2026-04-02

  articleSenior author
  PublisherDOI

• Enhancing prediction of inpatient deterioration by combining clinical and nurse concern features, with or without temporal clustering

  JAMIA Open · 2026-05-02

  articleOpen access

  Background: Early warning systems (EWSs) help clinicians identify deteriorating patients using clinical data, such as vital signs. However, standard systems struggle to capture nuanced nursing concerns. The Healthcare Process Model-ExpertSignals (HPM-ExpertSignals) framework describes how nurses' concerns are reflected in their documentation patterns. While a recent trial showed positive outcomes, the predictive gain of combining both data types remains unquantified. Objectives: We evaluated improvements in F-measure by combining HPM-ExpertSignals with clinical data using the k-shape temporal clustering algorithm. Materials and Methods: Six models were compared based on their features and the inclusion of k-shape. Models were trained to predict patient deterioration (cardiac arrest and death) 12 h before the event using a large dataset. The primary outcome was the harmonic mean of precision and recall (F-measure). Results: The F-measure achieved by the model that uses both feature types was 0.25 (±0.01). The clinical features-only model was 0.16 (±0.01), and the HPM-ExpertSignals-only model was 0.19 (±0.02). F-measures for their corresponding k-Shape models were all at 0.06 (±0.0). Discussion: The combined model has the highest F-measure among the clinical-only and HPM-ExpertSignals-only models. The low performance of the k-Shape models suggests that k-Shape is not well suited to capturing the specific temporal patterns present in this problem set. Conclusion: Early warning systems leveraged both clinical data and HPM-ExpertSignals predictors, which may offer clinically significant improvements. Future research should explore alternative temporal pattern algorithms to further refine predictive accuracy.

  PublisherDOI

• Barriers and facilitators to implementing a shared decision-making tool for anticoagulant-related drug–drug interactions: a qualitative study across three academic medical centres in the USA

  BMJ Open · 2026-03-01

  articleOpen access

  OBJECTIVES: To identify barriers and facilitators to implementing an electronic shared decision-making tool for managing anticoagulant-related drug-drug interactions that affect bleeding risk in routine clinical care. DESIGN: Preimplementation qualitative study using semistructured interviews. SETTING: Three academic medical centres in the southeastern and western USA. Interviews were conducted between 27 March and 25 September 2024. PARTICIPANTS: 36 participants, including 19 clinicians involved in prescribing or managing anticoagulants and seventeen patients prescribed anticoagulants, were recruited using purposive and convenience sampling. RESULTS: Participants identified multiple barriers and facilitators to tool implementation. Common barriers included limited visit time, challenges integrating the tool into existing workflows, role and scope-of-practice constraints, and variation in patient digital literacy. Facilitators included clear visualisation of bleeding risk, access to supporting evidence, familiar interface design and perceived potential to support patient engagement and shared decision-making. Several determinants functioned as both barriers and facilitators, depending on clinical context and user role. CONCLUSIONS: This preimplementation qualitative study identified context-specific determinants that influence the adoption of an electronic shared decision-making tool for anticoagulant-related drug-drug interactions. Findings highlight the importance of early attention to workflow integration, role alignment and usability to support uptake in routine care. Addressing these factors during design and implementation may inform strategies to support adoption and future evaluation in real-world clinical settings.

  PublisherOA PDFDOI

• Incomplete Family History and Meeting Algorithmic Criteria for Genetic Evaluation of Hereditary Cancer

  JAMA Network Open · 2025-10-28 · 1 citations

  articleOpen access

  Importance: Incomplete electronic health record (EHR) documentation may limit the effectiveness of clinical decision support (CDS) algorithms designed to identify patients eligible for hereditary cancer genetic evaluation. Objectives: To determine whether a CDS algorithm can identify patients who meet criteria for hereditary cancer genetic evaluation when family history data are incompletely documented in the EHR, and to examine whether data missingness is associated with identification patterns across patient subgroups. Design, Setting, and Participants: This cross-sectional study analyzed EHR data extracted in December 2020 from 2 large US health care systems: University of Utah Health (UHealth) and NYU Langone Health (NYULH). Eligible patients were adults aged 25 to 60 years who visited a primary care clinic within the previous 3 years and had some EHR documentation of cancer family history. Data analysis was conducted in August 2024. Exposures: Patient demographic factors (age, sex, race and ethnicity, and language preference) and cancer family history characteristics (number of cancer history records, number of affected first- and second-degree relatives, relatives with rising mortality cancers, presence of hereditary cancer-related terms in comments, and completeness of documentation). Main Outcomes and Measures: The primary outcome was meeting at least 1 CDS algorithm criterion for genetic evaluation of hereditary cancer risk based on National Comprehensive Cancer Network guidelines. Missing data patterns were assessed using the Little missing completely at random test, with analyses conducted using complete case analysis and multiple imputation. Results: This study included 157 207 patients: 55 918 from UHealth and 101 289 from NYULH. Their mean (SD) age was 43.5 (9.8) years, and most (65.7%) were female. A total of 5607 UHealth patients (10.0%) and 10 375 NYULH patients (10.2%) met CDS criteria for genetic evaluation. At UHealth, data appeared to be missing completely at random (χ239 = 39.09; P = .47), and complete case compared with multiple imputation analyses yielded similar results. At NYULH, data were not missing completely at random (χ255 = 914.89; P < .001). Compared with multiple imputation, complete case analysis produced different association magnitudes for older age and having relatives with rising mortality cancers, suggesting bias when excluding incomplete records. Conclusions and Relevance: In this cross-sectional study, the magnitude of the association between incomplete family history documentation and identification of patients eligible for hereditary cancer genetic evaluation depended on whether data were missing randomly or systematically. These findings suggest that health care organizations implementing CDS algorithms should assess their specific missing data patterns and consider tailored approaches to handling incomplete family history information to ensure equitable identification of all patients who could benefit from genetic evaluation services.

  PublisherOA PDFDOI

• Conceptual framework for prediction models of patient deterioration based on nursing documentation patterns: reproducibility and generalizability with a large number of hospitals across the United States

  Journal of Biomedical Informatics · 2025-07-27 · 2 citations

  articleOpen access
  PublisherOA PDFDOI

• Challenges to Reduce Alert Burden Using Current Decision Support Infrastructure in Two Commercial EHR Systems: Lessons Learned and Path Forward

  Applied Clinical Informatics · 2025-02-28 · 2 citations

  article

  Despite the proven usefulness of appropriate clinical decision support (CDS) alerts, many CDS systems fire excessive, clinically irrelevant alerts that are often ignored by clinicians. We have developed a method to suppress false-positive alerts based on prior drug tolerance but encountered substantial barriers to integrating the method into widely adopted commercial electronic health record (EHR) systems.This study aimed to describe the challenges faced while attempting to integrate our method into the CDS infrastructure of two commercial EHR systems and provide recommendations for future research and CDS design.Using a multifaceted approach, we investigated (1) the use of emergent CDS standards (e.g., CDS Hooks) to create a scalable solution to augment off-the-shelf EHR-based alerts with patient-specific custom alerts, (2) customize CDS rules of commercial medication knowledge bases (MKBs) to reduce false-positive alerts, and (3) manually inactivate allergy documentation in patients with prior drug tolerance.We were unable to implement the standards-based approach because support for CDS Hooks was found to be tailored to specific scenarios that involve the creation of new drug allergy alerts (DAAs) but not the suppression of vendor-supplied DAAs. Likewise, we were unable to suppress alerts imported from MKBs into the EHR systems investigated because these systems do not support discrete clinical documentation changes that drive DAAs. Lastly, we determined that although manually inactivating allergy documentation in patients with prior drug tolerance is possible, doing so requires the impractical solution of creating and maintaining individual rules for each drug at the ingredient level.We describe the barriers that precluded implementation of a novel method to suppress clinically irrelevant CDS alerts in two commercial EHR systems. Overcoming these barriers will require a more flexible CDS infrastructure, as well as collaboration and shared responsibility across diverse stakeholders.

  PublisherDOI

• Enhancement of Patient-Centered Lung Cancer Screening

  JAMA Oncology · 2025-12-26 · 3 citations

  articleOpen accessSenior author

  Importance: 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.

  PublisherOA PDFDOI

• Advancing Digital Access to Physical Therapy via Virtual and Extended Reality Technology: Prototype Development and Usability Evaluation

  JMIR Formative Research · 2025-12-05

  articleOpen access

  Background: The United States faces significant challenges in physical therapy (PT) access due to high demand, a shortage of professionals, and patient-related obstacles, which can adversely affect recovery and function. Limited access to PT may lead to increased dependence on medications for pain management, highlighting the need for nonpharmacologic options to reduce opioid overprescribing. Low back pain, a leading cause of disability and high medical costs, is a common reason for requiring PT following surgery. Studies have shown that virtual reality (VR)-guided movements can improve motor function and reduce pain intensity. Objective: The objective of this study was to design, develop, and evaluate a VR-based prototype for individualized postoperative PT for patients recovering from back surgery to investigate its potential to improve convenience, access, and health outcomes in future research. Methods: Study methods involved participatory design and development of VR software for PT back exercises using the design box method, an inductive, problem-oriented collaborative design approach. A usability evaluation of the resulting prototype was conducted with patients recovering from back surgery using a think-aloud protocol and usability survey. Results: Six participants evaluated the VR prototype and reported usability challenges that included mismatched VR boundaries, limited familiarity with VR, and difficulties with the headset and hand controls. The System Usability Scale resulted in a total usability score of 58.3 out of 100, indicating a below-average score (68 being average). Conclusions: In the design and evaluation of a VR-based PT prototype, we found that while participants were enthusiastic, they faced usability challenges due to insufficient instructions and difficulties operating the VR device, highlighting the need for effective onboarding and extensive prototype testing to improve accessibility and engagement in health care. Future evaluations will investigate disparities among different groups to ensure accessibility and effectiveness for all users.

  PublisherDOI

• Risk of gastrointestinal bleeding by specific SSRIs and SNRIs: A systematic review and meta‐analysis

  British Journal of Clinical Pharmacology · 2025-12-29 · 2 citations

  articleOpen access

  AIM: The purpose of this study is to estimate the risk of gastrointestinal bleeding (GIB) by selective serotonin reuptake inhibitors (SSRIs) and serotonin-norepinephrine reuptake inhibitors (SNRIs) individual agents. METHODS: A systematic review was conducted for each unique antidepressant (i.e. SSRI: citalopram, escitalopram, fluoxetine, fluvoxamine, paroxetine, and sertraline; and SNRIs: desvenlafaxine, venlafaxine, and duloxetine) combined with search terms for GIB in PubMed and EMBASE from inception to October 2025. Articles including results on specific antidepressants and GIB risk were included. RESULTS: From a total of 1218 identified publications, 20 studies were included and analysed using a random-effect meta-analysis. Twelve studies (60%) used a case-control design, three (15%) a cohort study design, one (5%) a case cross-over, one (5%) used both case-control and cross-over designs and three (15%) were randomized control trials (RCTs). Studies sample sizes ranged from 666 235 from a Medicaid population to 1280 from 43 hospitals participating in a RCT. Fluoxetine had the most studies providing evidence (19 studies) and fluvoxamine and duloxetine had the least (five studies). Each antidepressant showed an increased risk of GIB. Venlafaxine had the highest estimated risk (OR 1.50, 95% CI 1.32-1.70), followed by citalopram (OR 1.38, 95% CI 1.17-1.62) and fluoxetine (OR 1.38, 95% CI 1.26-1.51). Paroxetine had the lowest GIB risk (OR 1.31, 95% CI 1.07-1.62). CONCLUSION: GIB is an uncommon adverse event, but this analysis demonstrates that the risk of GIB is elevated for commonly used SSRI/SNRI products, highlighting the relevance for those patients with an increased risk of GIB.

  PublisherOA PDFDOI

Recent grants

• Scalable decision support and shared decision making for lung cancer screening

  NIH · $1.2M · 2019–2022

• NIH Grant K01HG004645

  NIH · $559k · 2011

• Scalable Clinical Decision Support for Individualized Cancer Risk Management

  NIH · $3.7M · 2017–2022

• NIH Grant F37LM008161

  NIH · $140k · 2007

Frequent coauthors

• Guilherme Del Fiol

  University of Utah

  90 shared

• Rachel Hess

  University of Utah

  39 shared

• David F. Lobach

  Electronics for Imaging (United States)

  38 shared

• Polina Kukhareva

  37 shared

• Charlene Weir

  University of Utah

  32 shared

• Kimberly A. Kaphingst

  31 shared

• Michael Flynn

  30 shared

• Richard L. Bradshaw

  University of Utah

  27 shared

Education

• M.D.

  University of Utah

• Ph.D.

  University of Utah

• Other

  University of Utah

Awards & honors

• Fellow of the American College of Medical Informatics
• Fellow of the American Medical Informatics Association
• Top 25 Innovator in health care by Modern Healthcare in 2019
• University of Utah Presidential Societal Impact Scholar in 2…