Shu Huang

Ms. Shu Huang

University of Florida, Gainesville, Florida, USA
orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 August 2022 in Journal of Clinical Medicine
Verified
Journal Article
Open access
PDF file
Shu HuangShu Huang
Shu Huang
MLMotomori O. Lewis
Motomori O. Lewis
YBYuhua Bao
Yuhua Bao
PAPrakash Adekkanattu
Prakash Adekkanattu
LALauren E. Adkins
Lauren E. Adkins
WCWei Hsuan Lo Ciganic
Wei Hsuan Lo Ciganic
Suicide is a leading cause of death in the US. Patients with pain conditions have higher suicidal risks. In a systematic review searching observational studies from multiple sources (e.g., MEDLINE) from 1 January 2000–12 September 2020, we evaluated existing suicide prediction models’ (SPMs) performance and identified risk factors and their derived data sources among patients with pain conditions. The suicide-related outcomes included suicidal ideation, suicide attempts, suicide deaths, and suicide behaviors. Among the 87 studies included (with 8 SPM studies), 107 suicide risk factors (grouped into 27 categories) were identified. The most frequently occurring risk factor category was depression and their severity (33%). Approximately 20% of the risk factor categories would require identification from data sources beyond structured data (e.g., clinical notes). For 8 SPM studies (only 2 performing validation), the reported prediction metrics/performance varied: C-statistics (n = 3 studies) ranged 0.67–0.84, overall accuracy(n = 5): 0.78–0.96, sensitivity(n = 2): 0.65–0.91, and positive predictive values(n = 3): 0.01–0.43. Using the modified Quality in Prognosis Studies tool to assess the risk of biases, four SPM studies had moderate-to-high risk of biases. This systematic review identified a comprehensive list of risk factors that may improve predicting suicidal risks for patients with pain conditions. Future studies need to examine reasons for performance variations and SPM’s clinical utility.

20 October 2023 in PLOS ONE
Verified
Journal Article
Open access
PDF file
RZRuben D. Zapata
Ruben D. Zapata
Shu HuangShu Huang
Shu Huang
EMEarl Morris
Earl Morris
CWChang Wang
Chang Wang
CHChristopher Harle
Christopher Harle
FMFrançois Modave
François Modave
Objective: This study aimed to develop and validate predictive models using electronic health records (EHR) data to determine whether hospitalized COVID-19-positive patients would be admitted to alternative medical care or discharged home. Methods: We conducted a retrospective cohort study using deidentified data from the University of Florida Health Integrated Data Repository. The study included 1,578 adult patients (≥18 years) who tested positive for COVID-19 while hospitalized, comprising 960 (60.8%) female patients with a mean (SD) age of 51.86 (18.49) years and 618 (39.2%) male patients with a mean (SD) age of 54.35 (18.48) years. Machine learning (ML) model training involved cross-validation to assess their performance in predicting patient disposition. Results: We developed and validated six supervised ML-based prediction models (logistic regression, Gaussian Naïve Bayes, k-nearest neighbors, decision trees, random forest, and support vector machine classifier) to predict patient discharge status. The models were evaluated based on the area under the receiver operating characteristic curve (ROC-AUC), precision, accuracy, F1 score, and Brier score. The random forest classifier exhibited the highest performance, achieving an accuracy of 0.84 and an AUC of 0.72. Logistic regression (accuracy: 0.85, AUC: 0.71), k-nearest neighbor (accuracy: 0.84, AUC: 0.63), decision tree (accuracy: 0.84, AUC: 0.61), Gaussian Naïve Bayes (accuracy: 0.84, AUC: 0.66), and support vector machine classifier (accuracy: 0.84, AUC: 0.67) also demonstrated valuable predictive capabilities. Significance: This study’s findings are crucial for efficiently allocating healthcare resources during pandemics like COVID-19. By harnessing ML techniques and EHR data, we can create predictive tools to identify patients at greater risk of severe symptoms based on their medical histories. The models developed here serve as a foundation for expanding the toolkit available to healthcare professionals and organizations. Additionally, explainable ML methods, such as Shapley Additive Explanations, aid in uncovering underlying data features that inform healthcare decision-making processes.

10 April 2025 in Pain Medicine
Verified
Journal Article
Closed access
Shu HuangShu Huang
Shu Huang
TJTianze Jiao
Tianze Jiao
SGSerena Jingchuan Guo
Serena Jingchuan Guo
JSJill A Star
Jill A Star
JBJiang Bian
Jiang Bian
AGAmie J. Goodin
Amie J. Goodin
Importance: Centers for Disease Control and Prevention guidelines highlight the increased suicide risk associated with abrupt discontinuations of long-term opioid therapy (LTOT). However, evidence on specific dose and duration “thresholds” of LTOT for suicide risk is limited. Objective: We aimed to identify opioid dose trajectories before abrupt LTOT discontinuations and their association with 6-month suicide risk. Design: This retrospective cohort study analyzed 2016-2021 Florida Medicaid claims for adult non-cancer beneficiaries with abrupt LTOT discontinuation, defined as having a > 15-day gap in opioid supply after ≥90 consecutive days of use. We assessed prescription opioid doses as the mean weekly morphine-milligram equivalent (MME) 6 months preceding the first abrupt LTOT discontinuation. Group-based trajectory modeling identified distinct opioid trajectory patterns, and multivariable Cox proportional hazards models examined associations between trajectory groups and a composite outcome of suicidal ideation, non-fatal suicide attempts, and suicide death 6 months following the abrupt LTOT discontinuation. Results: Among 15 680 beneficiaries (mean age: 46.2 ± 11.1 years; 60.8% female), 4 trajectory groups based on weekly MMEs: Low (150: n = 1101, 7.0%) were identified. Compared with the low-dose group, the very-high dose group had a significantly higher risk of suicide-related outcomes [adjusted hazard ratio (aHR): 2.2, 95% confidence interval (95%CI):1.3-3.6], while the moderate and high dose groups had similar risks (moderate: aHR = 1.3, 95%CI: 0.9-1.8, high: aHR = 0.7, 95%CI: 0.4-1.3). Conclusions: Among Florida Medicaid beneficiaries with LTOT, very-high opioid doses (>150 weekly MME) in the 6 months preceding an abrupt LTOT discontinuation were associated with an increased risk of suicide-related outcomes.

29 September 2023 in Journal of Clinical Medicine
Verified
Journal Article
Open access
PDF file
SYSeonkyeong Yang
Seonkyeong Yang
Shu HuangShu Huang
Shu Huang
Juan Manuel Hincapie-CastilloJuan Manuel Hincapie-Castillo
Juan Manuel Hincapie-Castillo
XKXuehua Ke
Xuehua Ke
HDHelen Ding
Helen Ding
WCWei Hsuan Lo Ciganic
Wei Hsuan Lo Ciganic
Among patients with chronic cough (CC) in the 2012–2021 statewide OneFlorida Clinical Research Consortium database, we examined trends in cough medication (CM) prescribing prevalence over time in repeated cross-sectional analyses and identified distinct CM utilization trajectories using group-based trajectory modeling (GBTM) in a retrospective cohort study. Among eligible adults (≥18 years) without cancer/benign respiratory tumor diagnoses, we identified CC patients and non-CC patients with any cough-related diagnosis. In the GBTM analysis, we calculated the number of monthly prescriptions for any CMs (excluding gabapentinoids) during the 12 months from the first qualifying cough event to identify distinct utilization trajectories. From 2012 to 2021, benzonatate (9.6% to 26.1%), dextromethorphan (5.2% to 8.6%), and gabapentinoid (5.3% to 14.4%) use increased among CC patients, while opioid antitussive use increased from 2012 to 2015 and decreased thereafter (8.4% in 2012, 14.7% in 2015, 6.7% in 2021; all p < 0.001). Of 15,566 CC patients and 655,250 non-CC patients identified in the GBTM analysis, CC patients had substantial burdens of respiratory/non-respiratory comorbidities and healthcare service and concomitant medication use compared to non-CC patients. Among CC patients, GBTM identified three distinct CM utilization trajectories: (1) no CM use (n = 11,222; 72.1%); (2) declining CM use (n = 4105; 26.4%); and (3) chronic CM use (n = 239; 1.5%). CC patients in Florida had limited CM use with increasing trends in use of benzonatate, dextromethorphan, and gabapentinoids and a decreasing trend in opioid antitussive use. CC patients, particularly with chronic prescription CM use, experienced substantial disease burden.

4 June 2024 in The Joint Commission Journal on Quality and Patient Safety
Verified
Journal Article
Closed access
JMJill A. Marsteller
Jill A. Marsteller
MRMichael A. Rosen
Michael A. Rosen
RWRhonda Wyskiel
Rhonda Wyskiel
BCBickey H. Chang
Bickey H. Chang
YHYea-Jen Hsu
Yea-Jen Hsu
AGAyse P. Gurses
Ayse P. Gurses

10 December 2025 in Journal of Medical Internet Research
Verified
Journal Article
Open access
Shu HuangShu Huang
Shu Huang
TJTianze Jiao
Tianze Jiao
JGJingchuan Guo
Jingchuan Guo
JFJill Fairless
Jill Fairless
Jie XuJie Xu
Jie Xu
AGAmie J. Goodin
Amie J. Goodin
Background: Health care providers must carefully monitor patients receiving long-term opioid therapy (LTOT) to minimize risks and maximize benefits. Yet, algorithms to support intervention during patient encounters are lacking, with accurate LTOT identification in routine care being the essential first step. Objective: This study aims to develop and validate an LTOT identification algorithm using electronic health record (EHR) data. Methods: In this cross-sectional study, we used 2016-2021 OneFlorida+ EHR data linked with Florida Medicaid claims to identify patients aged ≥18 years who received opioid prescriptions. The main outcome was the first LTOT episode in the algorithm development (2016-2018) and validation (2019-2021) periods. A Medicaid claims-based LTOT algorithm served as the reference standard, defined as ≥90 days of continuous opioid use with ≤15-day gaps. Given strong correlations among covariates, an elastic net regression model was applied to identify LTOT episodes in EHR data using patient characteristics, clinically relevant features, and medication use, and to evaluate the model’s classification performance. We randomly split the 2016-2018 cohort into development and internal validation datasets (2:1 ratio), stratified by LTOT incidence. External validation was performed using 2019-2021 data. Results: Among 64,206 eligible patients identified in 2016-2018 (mean age 35.7, SD 12.3 years; 51,421/64,206, 80.1% female), a total of 8899 (13.9%) had LTOT. Among 50,009 eligible patients identified in 2019-2021 (mean age 37.3, SD 12.5 years; 39,866/50,009, 79.7% female), a total of 6000 (12%) had LTOT. The model selected 29 out of 131 candidate features. Among 2967 individuals with LTOT in the 2016-2018 OneFlorida+ internal validation dataset, a total of 2176 (73.3%) individuals were identified in the top 3 deciles of risk scores. The model achieved a C-statistic of 0.83 (95% CI 0.82-0.84), with 73.4% (95% CI 71.8%-75%) sensitivity, 76.8% (95% CI 76.2%-77.4%) specificity, 33.8% (95% CI 33.1%-34.6%) precision, 76.3% (95% CI 75.8%-76.9%) accuracy, and an F1-score of 0.46. In the 2019-2021 OneFlorida+ external validation dataset, a total of 75.5% (4527/6000) individuals were correctly captured in the top 3 risk subgroups. The model achieved a C-statistic of 0.83 (95% CI 0.83-0.84), with 78.8% (95% CI 77.8%-79.9%) sensitivity, 73.3% (95% CI 72.9%-73.7%) specificity, 28.7% (95% CI 28.3%-29.1%) precision, 73.9% (73.6%-74.3%) accuracy, and an F1-score of 0.42. Conclusions: The EHR-based LTOT algorithm showed comparable accuracy to the claims-based reference and may support risk stratification and inform decision-making during clinical encounters.