Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Yun Jiang has a total of 144 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Large Language Model-derived Symptom Clusters and Patient Outcomes in Colorectal Cancer from MIMIC-IV Clinical Notes

    by Youran Lee, Ivo Dinov, Xiaosu Hu, Yun Jiang

    Background: Prior research on symptom clusters (SCs) in colorectal cancer (CRC) has relied primarily on patient-reported outcome surveys, which capture symptom experience at discrete assessment points rather than the continuous documentation generated during routine care, leaving open whether SCs derived from electronic health record (EHR) text carry the same clinical meaning and predictive value. To construct and validate patient-level symptom co-occurrence networks from large language model (LLM)-extracted symptom data in CRC patients, and to test whether resulting SCs predict clinical outcomes. Methods: Using a zero-shot LLM extraction pipeline previously benchmarked against a manually annotated ground truth (Macro F1=0.70 for the best-performing model), we extracted 46 symptoms from 2,728 discharge notes of 1,507 CRC patients in MIMIC-IV. Patient-level symptom co-occurrence networks were constructed independently from Gemini 3.5 Flash and Claude Haiku extractions using phi correlation (≥0.10) and Louvain community detection, with sensitivity analyses across correlation thresholds, random seeds, note-aggregation strategy, and bootstrap resampling. Per-cluster symptom burden scores were tested as predictors of in-hospital mortality, 30-day readmission, and 1-year mortality using logistic regression adjusted for age, sex, and (in sensitivity models) metastatic disease. Results: Both LLMs’ networks converged on three clinically coherent SCs — Systemic, Gastrointestinal, and CRC Disease-Specific — across sensitivity analyses (cross-model Adjusted Rand Index=0.727; 100-seed Louvain ARI=0.985; bootstrap ARI=0.733). The Systemic Symptom Cluster was the most consistent predictor of in-hospital mortality (OR=1.33) and 1-year mortality (OR=1.41), while the CRC Disease-Specific Cluster specifically and independently predicted 30-day readmission (OR=1.20); both associations were robust to adjustment for metastatic disease. Conclusion: LLM-extracted symptom data recover clinically coherent, reproducible SCs from unstructured discharge notes that carry independent prognostic value for mortality and readmission, supporting the clinical validity of automated, EHR-derived symptom profiling in CRC. Highlights: LLMs identified Systemic, CRC Disease-Specific, and Gastrointestinal clusters. Three symptom clusters were reproducible across LLMs and sensitivity analyses. Systemic symptom burden predicted in-hospital and 1-year mortality.

  • Open Access

    A tailored maturity model for REDCap-based patient-facing technology: revealing development stages and guiding future evolution

    by Zhengcan Xie, Yuheng Shi, Eric Yang, Yun Jiang, Yang Gong

    Objectives: This integrative review aims to analyze the REDCap-based patient-facing technologies (PFTs) and propose a tailored maturity model to characterize their development stages, challenges, and future evolution toward intelligent, proactive care. Materials and Methods: Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, a focused search of PubMed, Web of Science, and Embase identified relevant studies. Data were analyzed using aggregate and thematic synthesis. Combining literature evidence with pilot case insights, a tailored maturity model was developed to define the distinct stages of REDCap-based PFT development. Results: The proposed model progresses from Data Collection (Tier 1) and System Integration (Tier 2) to Personalized Insights (Tier 3), culminating in a conceptual Intelligence Hub (Tier 4). Analysis of 14 studies (2016-2026) reveals a rapidly evolving field, with a surge in publications since 2021 (n = 12, 86%). Most included studies were US-based (n = 11, 79%), primarily pilot tests (n = 6) and system design studies (n = 5). Most implementations (n = 10, 71%) remain at early maturity stages (Tiers 1 and 2), with only a minority (n = 4, 29%) achieving Personalized Insights (Tier 3). Conclusion: These findings underscore the promise of REDCap-based PFTs but reveal a critical gap between current capabilities and the advanced Intelligence Hub envisioned in the maturity model. Applying the tailored maturity model highlights priorities for advancing research, including rigorous, longitudinal evaluations and strategies to achieve higher levels of integration and optimization.

  • Open Access

    Digital Divide Among U.S. Adults with and without Cancer: Prevalence and Associated Factors

    by Yupawadee Kantabanlang, Shushun Ren, Misun Hwang, Rumei Yang, Abdul-Ghaniyu Alidu, Yun Jiang

    Digital technologies have transformed healthcare, yet disparities persist, particularly among older adults and individuals with cancer. The digital divide encompasses not only access but also challenges in electronic communication and cognitive engagement, affecting health equity. This study examined the prevalence of three digital divide dimensions (Access, E-communication, and Cognitive Gaps) among U.S.adults with and without cancer and assessed their associations with sociodemographic factors, clinical characteristics, and self-rated health. Cross-sectional data from the 2022 Health Information National Trends Survey (HINTS 6; N = 5,808) were analyzed using survey-weighted methods. Generalized linear models examined sociodemographic and clinical predictors of digital gaps, and survey-weighted linear regression assessed associations with self-rated health. The E-communication Gap was most prevalent (36.2%), followed by the Cognitive Gap (13.3%) and Access Gap (4.7%). Older adults had higher prevalence across all gaps. Individuals with cancer showed higher Access and Cognitive Gaps than those without cancer. Older age and lower education were consistent predictors, and comorbidities increased the likelihood of Access Gap among adults with cancer. The Cognitive Gap reflecting low confidence in finding health information online was significantly associated with poorer self-rated health overall (β̂ = −0.18; 95% CI [− 0.30, − 0.06]) and among older adults. The digital divide is multidimensional and disproportionately affects older adults and individuals with cancer. Cognitive-related digital barriers may play an important role in perceived health, highlighting the need for interventions that strengthen digital literacy and support equitable participation in digital health.

  • Open Access

    Stakeholder Perspectives on the Use of Telehealth to Support Deprescribing for Older Patients Transitioning From the Hospital to Home Health Care

    by Jinjiao Wang, Jenny Y. Shen, Fang Yu, Sandra F. Simmons, Amanda S. Mixon, Kobi Nathan, Marian S. Moskow, Judith D. Brasch, Sally A. Norton, Kathi L. Heffner, et al.

    Background: Multimorbidity affects most older adults in home health care (HHC), leading to inappropriate polypharmacy and increased risks for adverse outcomes. While deprescribing can mitigate these risks, fragmented communication during hospital‐to‐home transitions remains a major barrier. This study explored stakeholder perspectives on using telehealth to facilitate deprescribing for older adults with multimorbidity while receiving post‐acute HHC. Methods: We conducted semi‐structured interviews with 44 stakeholders across 12 U.S. states, including 14 HHC patients and 30 clinicians (physicians, nurse practitioners, pharmacists, and HHC nurses). Guided by the socioecological model of deprescribing, interviews explored factors across individual, interpersonal, organizational, and societal levels associated with telehealth use in deprescribing. Analysis followed a phased, iterative approach with independent double‐coding and interprofessional team consensus to ensure credibility. Results: Findings categorized telehealth as a promising tool to align medications with the “4Ms” (Medications, Mentation, Mobility, and What Matters) through goal‐concordant deprescribing. At the individual level, stakeholders noted that telehealth readiness depended on patient cognition and digital literacy. At the interpersonal level, telehealth facilitated real‐time multidisciplinary “virtual huddles” that reduced communication delays but could occasionally overwhelm patients and may be logistically challenging to schedule. Organizational barriers included reimbursement constraints and complex synchronous scheduling. Societal factors include equitable access for rural or low‐income populations, populations who may benefit the most from telehealth‐enabled deprescribing due to challenges in accessing care. Stakeholders emphasized a hybrid approach which pairs virtual prescriber consultation with in‐home support of a clinician to provide context and assist with implementation for patient‐centered deprescribing. Conclusions: Telehealth can support goal‐concordant deprescribing during post‐acute care transitions in HHC. A hybrid model, one that combines remote prescriber consultations with in‐home clinician support, is the preferred approach to bridge coordination gaps. To maximize impact, future efforts are needed to improve reimbursement, infrastructure, and scheduling to integrate telehealth into routine deprescribing workflows.

  • Open Access

    Patient-Contributed Data and Medication Safety: A Study on Self-Reporting Behaviors Among Patients with Cancer

    by Xinyue Mao, Serena Chen, Xiayuan Huang, Katie Gahn, Jinjiao Wang, Yang Gong, Yun Jiang

    Understanding cancer patients’ experiences with medication safety events at home is crucial due to their impact on health outcomes. However, patients often face barriers to sharing this information with their clinicians. This study identified key factors influencing cancer patients’ self-reporting behaviors through a mixed-methods approach, analyzing survey and interview data from 41 patients diagnosed with breast, lung, prostate, or colorectal cancer. Logistic regression analysis identified predictors such as beliefs about medication and perceived system usability, achieving an AUC of 0.85. Thematic analysis indicated that patients were more likely to report safety events when medications disrupted their daily routines, with perceived severity as the key trigger. System usability and relationships with clinicians also affected reporting behaviors. Our findings highlight the need for user-friendly reporting systems and supportive communication to improve patient engagement and medication safety, offering valuable insights for designing patient-centered reporting systems to facilitate patient-contributed data.

  • Open Access

    Exploring factors affecting the adoption and use of digital health technologies among older adults with cancer: A qualitative study

    by Misun Hwang, Youmin Cho, Katie Gahn, Heidi Mason, Milisa Manojlovich, Yang Gong, Yun Jiang

    Purpose: Although digital health technologies (DHTs) are promising to improve health outcomes in older adults with cancer, the low adoption and limited use remain significant gaps in their effective digital health care. Little is known about their concerns about adopting and using DHTs in routine life, particularly in the continued use phase. This study aims to explore factors affecting the initial adoption and continued use of DHTs among older adults with cancer. Methods: A secondary analysis of qualitative data was conducted based on interviews with 21 older adults (≥ 65 years) with breast, prostate, lung, or colorectal cancer. The transcripts of interview recordings were analyzed using a thematic analysis. Results: Three major themes and several subthemes were identified as potential factors affecting the (1) initial adoption, (2) continued use, and (3) limited use of DHTs. Digitalized healthcare systems and access to technology influenced the initial adoption of DHTs. Perceived ease of use, perceived usefulness, expected timely care from providers, and increased sense of control emerged as leading factors to the continued use. The limited use of DHTs was influenced by a lack of knowledge and skills, a lack of direct interaction with providers, and concerns about digital communication quality. Conclusions: Ensuring digital access and providing technology-based solutions that meet diverse patient needs is crucial to promoting the adoption and use of DHTs among older adults with cancer. Healthcare providers should address older adults’ low digital literacy and uncertainty to ensure the quality of cancer care provided through DHTs.


  • Open Access

    Association Between Risk Factors and Major Cancers: Explainable Machine Learning Approach

    by Xiayuan Huang, Shushun Ren, Xinyue Mao, Sirui Chen, Elle Chen, Yuqi He, Yun Jiang

    Background: Cancer is a life-threatening disease and a leading cause of death worldwide, with an estimated 611,000 deaths and over 2 million new cases in the United States in 2024. The rising incidence of major cancers, including among younger individuals, highlights the need for early screening and monitoring of risk factors to manage and decrease cancer risk. Objective: This study aimed to leverage explainable machine learning models to identify and analyze the key risk factors associated with breast, colorectal, lung, and prostate cancers. By uncovering significant associations between risk factors and these major cancer types, we sought to enhance the understanding of cancer diagnosis risk profiles. Our goal was to facilitate more precise screening, early detection, and personalized prevention strategies, ultimately contributing to better patient outcomes and promoting health equity. Methods: Deidentified electronic health record data from Medical Information Mart for Intensive Care (MIMIC)–III was used to identify patients with 4 types of cancer who had longitudinal hospital visits prior to their diagnosis presence. Their records were matched and combined with those of patients without cancer diagnoses using propensity scores based on demographic factors. Three advanced models, penalized logistic regression, random forest, and multilayer perceptron (MLP), were conducted to identify the rank of risk factors for each cancer type, with feature importance analysis for random forest and MLP models. The rank biased overlap was adopted to compare the similarity of ranked risk factors across cancer types. Results: Our framework evaluated the prediction performance of explainable machine learning models, with the MLP model demonstrating the best performance. It achieved an area under the receiver operating characteristic curve of 0.78 for breast cancer (n=58), 0.76 for colorectal cancer (n=140), 0.84 for lung cancer (n=398), and 0.78 for prostate cancer (n=104), outperforming other baseline models (P<.001). In addition to demographic risk factors, the most prominent nontraditional risk factors overlapped across models and cancer types, including hyperlipidemia (odds ratio [OR] 1.14, 95% CI 1.11‐1.17; P<.01), diabetes (OR 1.34, 95% CI 1.29‐1.39; P<.01), depressive disorders (OR 1.11, 95% CI 1.06‐1.16; P<.01), heart diseases (OR 1.42, 95% CI 1.32‐1.52; P<.01), and anemia (OR 1.22, 95% CI 1.14‐1.30; P<.01). The similarity analysis indicated the unique risk factor pattern for lung cancer from other cancer types. Conclusions: The study’s findings demonstrated the effectiveness of explainable ML models in assessing nontraditional risk factors for major cancers and highlighted the importance of considering unique risk profiles for different cancer types. Moreover, this research served as a hypothesis-generating foundation, providing preliminary results for future investigation into cancer diagnosis risk analysis and management. Furthermore, expanding collaboration with clinical experts for external validation would be essential to refine model outputs, integrate findings into practice, and enhance their impact on patient care and cancer prevention efforts.


  • Top Cited Papers
    Open Access

    AI Applications for Chronic Condition Self-Management: Scoping Review

    by Misun Hwang, Yaguang Zheng, Youmin Cho, Yun Jiang

    Background: Artificial intelligence (AI) has potential in promoting and supporting self-management in patients with chronic conditions. However, the development and application of current AI technologies to meet patients’ needs and improve their performance in chronic condition self-management tasks remain poorly understood. It is crucial to gather comprehensive information to guide the development and selection of effective AI solutions tailored for self-management in patients with chronic conditions. Objective: This scoping review aimed to provide a comprehensive overview of AI applications for chronic condition self-management based on 3 essential self-management tasks, medical, behavioral, and emotional self-management, and to identify the current developmental stages and knowledge gaps of AI applications for chronic condition self-management. Methods: A literature review was conducted for studies published in English between January 2011 and October 2024. In total, 4 databases, including PubMed, Web of Science, CINAHL, and PsycINFO, were searched using combined terms related to self-management and AI. The inclusion criteria included studies focused on the adult population with any type of chronic condition and AI technologies supporting self-management. This review was conducted following the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. Results: Of the 1873 articles retrieved from the search, 66 (3.5%) were eligible and included in this review. The most studied chronic condition was diabetes (20/66, 30%). Regarding self-management tasks, most studies aimed to support medical (45/66, 68%) or behavioral self-management (27/66, 41%), and fewer studies focused on emotional self-management (14/66, 21%). Conversational AI (21/66, 32%) and multiple machine learning algorithms (16/66, 24%) were the most used AI technologies. However, most AI technologies remained in the algorithm development (25/66, 38%) or early feasibility testing stages (25/66, 38%). Conclusions: A variety of AI technologies have been developed and applied in chronic condition self-management, primarily for medication, symptoms, and lifestyle self-management. Fewer AI technologies were developed for emotional self-management tasks, and most AIs remained in the early developmental stages. More research is needed to generate evidence for integrating AI into chronic condition self-management to obtain optimal health outcomes.