YYYunshu Yang

Yunshu Yang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yunshu Yang has a total of 16 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Examining Regulatory Classifications and Social Determinants of Health in Telehealth-Mediated ADHD Prescription Fulfillment Barriers

    by Yunshu Yang, Weijian Qin, Wenyu Zhang, Taiwo Opeyemi Aremu

    Background: Telehealth has expanded remote access to ADHD care, yet a prescription issued remotely must still be filled at a pharmacy—and whether telehealth resolves these downstream fulfillment barriers remains unclear. Federal regulatory distinctions between Schedule II controlled stimulants and non-controlled ADHD pharmacotherapies create structurally divergent procurement experiences, particularly under ongoing nationwide stimulant shortages. This study examined whether prescription fulfillment difficulty differs by medication regulatory classification among adults using telehealth for ADHD care, and identified social determinants of health (SDOH) associated with access difficulty. Methods: Data were drawn from Round 2 of the NCHS Rapid Surveys System (RSS-2; October–November 2023). The analytic sample comprised 141 adults with a current ADHD diagnosis who reported pharmacotherapy use and telehealth utilization for ADHD care, classified as controlled-exposed (n = 95) or non-controlled-exposed (n = 46) by medication regulatory class. Chi-square tests, multivariable logistic regression, and five machine learning algorithms were applied across 19 SDOH variables. Results: Prescription access difficulty was substantially more prevalent among controlled-exposed than non-controlled-exposed participants (75.8% vs. 45.7%, p < 0.001). Multivariable logistic regression identified controlled medication exposure (coefficient = 2.155, p < 0.001), difficulty paying medical bills (coefficient = 1.409, p = 0.034), and income (coefficient = 0.145, p = 0.042) as significant correlates. Random Forest permutation importance ranked controlled medication exposure and having a usual place for care as the two strongest predictors, although these exploratory rankings warrant caution given the small held-out test set (n = 28). Notably, all 13 participants reporting non-prescribed online medication purchases also reported access difficulty through formal channels, a pattern consistent with displacement toward unregulated supply chains. Conclusions: Prescription fulfillment barriers were strongly stratified by medication regulatory classification, with financial strain further compounding access difficulty. As federal telemedicine flexibilities approach their 31 December 2026, expiration, regulatory deliberations should weigh downstream fulfillment constraints—including the Schedule II refill prohibition under shortage conditions—alongside upstream telehealth access.

  • Open Access

    Examining Regulatory Classifications and Social Determinants of Health in Telehealth-Mediated ADHD Prescription Fulfillment Barriers

    by Yunshu Yang, Weijian Qin, Wenyu Zhang, Taiwo Opeyemi Aremu

    Background: Telehealth has expanded remote access to ADHD care, yet a prescription issued remotely must still be filled at a pharmacy—and whether telehealth resolves these downstream fulfillment barriers remains unclear. Federal regulatory distinctions between Schedule II controlled stimulants and non-controlled ADHD pharmacotherapies create structurally divergent procurement experiences, particularly under ongoing nationwide stimulant shortages. This study examined whether prescription fulfillment difficulty differs by medication regulatory classification among adults using telehealth for ADHD care, and identified social determinants of health (SDOH) associated with access difficulty. Methods: Data were drawn from Round 2 of the NCHS Rapid Surveys System (RSS-2; October–November 2023). The analytic sample comprised 141 adults with a current ADHD diagnosis who reported pharmacotherapy use and telehealth utilization for ADHD care, classified as controlled-exposed (n = 95) or non-controlled-exposed (n = 46) by medication regulatory class. Chi-square tests, multivariable logistic regression, and five machine learning algorithms were applied across 19 SDOH variables. Results: Prescription access difficulty was substantially more prevalent among controlled-exposed than non-controlled-exposed participants (75.8% vs. 45.7%, p < 0.001). Multivariable logistic regression identified controlled medication exposure (coefficient = 2.155, p < 0.001), difficulty paying medical bills (coefficient = 1.409, p = 0.034), and income (coefficient = 0.145, p = 0.042) as significant correlates. Random forest permutation importance ranked controlled medication exposure and having a usual place for care as the two strongest predictors. Notably, all 13 participants reporting non-prescribed online medication purchases also reported access difficulty through formal channels, a pattern consistent with displacement toward unregulated supply chains. Conclusions: Prescription fulfillment barriers were strongly stratified by medication regulatory classification, with financial strain further compounding access difficulty. As federal telemedicine flexibilities approach their December 31, 2026, expiration, regulatory deliberations should weigh downstream fulfillment constraints, including the Schedule II refill prohibition under shortage conditions, alongside upstream telehealth access.

  • Open Access

    Exploring the Association Between Social Determinants of Health and Telehealth Utilization for Attention-Deficit/Hyperactivity Disorder Among Adults Using Machine Learning: A Cross-Sectional Study

    by Weijian Qin, Yunshu Yang, Shiqin Tong, Dongze Li, Hang Liu, Zongbo Li, Hawking Yam, Jin Huang, Jose Florez-Arango

    Background: Attention-Deficit/Hyperactivity Disorder (ADHD) affects an estimated 6% of adults in the United States and contributes to a significant economic burden. Telehealth has emerged as a vital tool in the management of ADHD, offering improved access to care, especially for individuals in underserved communities. Despite its growing role, there remain critical gaps in understanding how social determinants of health (SDOH) are associated with disparities in telehealth utilization for ADHD treatment. Objectives and Methods: This study analyzed data from the National Center for Health Statistics (NCHS) Rapid Surveys System (RSS) Round 2: ADHD (October–November 2023), a nationally fielded survey of U.S. adults. Respondents were classified into three groups: never diagnosed, previously diagnosed, and currently diagnosed with ADHD. The study aimed to (1) compare the distribution of SDOH across ADHD status groups and the general adult population to identify factors associated with ADHD diagnosis; (2) assess the homogeneity of SDOH distributions across ADHD groups; (3) evaluate telehealth utilization among adults currently diagnosed with ADHD; and (4) examine the relationship between SDOH and telehealth use for ADHD treatment. Multivariable logistic regression (MVLR) served as a benchmark model, while machine learning (ML) models—including regularized linear regression, support vector machine (SVM), random forest (RF), LightGBM, multilayer perceptron (MLP), and Few-Shot Learning (FSL)—were trained to identify key predictors. Results: A total of 7009 survey responses were analyzed: 124 had a past diagnosis, 444 were currently diagnosed, and the remainder had never been diagnosed with ADHD, corresponding to a current ADHD prevalence of 6.3%. Adults with current ADHD were more likely to be male, single, younger, white, non-homeowners, and frequent users of online health resources. They also reported lower education, income, and financial security. About 70% used telehealth for counseling and prescriptions; insurance covered telehealth visits for 82.32% of users, yet 38.76% reported no coverage of ADHD-related diagnostic or treatment costs. Nineteen SDOH elements across four domains—demographic, socioeconomic, neighborhood/built environment, and healthcare access—were identified as predictors. ML models outperformed MVLR, with SVM and FSL achieving the highest F1 (both 0.63), and FSL the highest recall (0.69). Age, race, marital status, difficulty paying bills, home ownership, education, and household size were the most consistently important variables. Limitations: This study is limited by a cross-sectional design, reliance on self-reported ADHD diagnoses, and a lack of genetic or family-history measures. Additionally, the omission of complex sampling weights limits the national representativeness of these findings. Finally, the small effective sample size poses risks of model overfitting, and the generalizability of the models could not be externally validated due to the unavailability of comparable independent datasets. Conclusions: Despite widespread internet access, disparities in telehealth use for ADHD persist. Among 19 SDOH predictors, age (aOR = 0.56), difficulty paying medical bills (aOR = 2.52), and race (aOR = 1.37) were significantly associated with telehealth use, and all ML models outperformed the MVLR benchmark, though bootstrap CIs overlapped. Future research should incorporate inclusive data collection and stratified modeling to better represent disadvantaged populations and inform equitable access strategies.


  • Open Access

    Exploring the Association Between Social Determinants of Health and Telehealth Utilization for ADHD Among Adults Using Machine Learning: A Cross-Sectional Study (Preprint)

    by Weijian Qin, Yunshu Yang, Shiqin Tong, Dongze Li, Hang Liu, Zongbo Li, Hawking Yam, Jin Huang, Jose Florez Arango

    BACKGROUND Attention-Deficit/Hyperactivity Disorder (ADHD) affects an estimated 6% of adults in the United States and contributes to a significant economic burden. Telehealth has emerged as a vital tool in the management of ADHD, offering improved access to care, especially for individuals in underserved communities. Despite its growing role, there remain critical gaps in understanding how social determinants of health (SDOH) influence disparities in tele- health utilization for ADHD treatment. OBJECTIVE This study analyzed data from the National Center for Health Statistics (NCHS) Rapid Surveys System (RSS) Round 2: ADHD (October–November 2023). Adults were classified into three groups: never diagnosed, previously diagnosed, and currently diagnosed with ADHD. The study aimed to: (1) compare the distribu- tion of SDOH across ADHD status groups and the general adult population to identify factors associated with ADHD diagnosis; (2) assess the homogeneity of SDOH distributions across ADHD groups; (3) evaluate telehealth utiliza- tion among adults currently diagnosed with ADHD; and (4) examine the relationship between SDOH and telehealth use for ADHD treatment. METHODS Multivariable logistic regression (MVLR) served as a benchmark model, while machine learning (ML) models—including regularized linear regression, support vector machine (SVM), random forest (RF), LightGBM, multilayer perceptron (MLP), and Few-Shot Learning (FSL)—were trained to identify key predictors. RESULTS A total of 7,009 survey responses were analyzed: 124 had a past diagnosis, and 444 were currently diagnosed, the remaining do not have an ADHD diagnosis, resulting in an ADHD prevalence of 6.3%. Adults with current ADHD were more likely to be male, single, younger, white, non-homeowners, and frequent users of online health resources. They also reported lower education, income, and financial security. About 70% used telehealth for counseling and prescriptions, but only one-quarter received insurance reimbursement. Nineteen SDOH elements across four domains were identified as predictors. ML models outperformed MVLR, with RF achieving the highest recall (0.73) and strong F1 (0.62). Affordability, coverage, and household resources were key predictors. CONCLUSIONS Despite widespread internet access, disparities in telehealth use for ADHD persist. ML models captured complex patterns and outperformed traditional approaches. Future research should incorporate inclusive data collec- tion and stratified modeling to better represent disadvantaged populations and inform equitable access strategies.