Zhenhong Hu
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
Research Subjects
Zhenhong Hu has a total of 85 co-authors. Here are the top co-authors by number of shared publications:
- Azra Bihorac
Intelligent Clinical Care Center, University of Florida, Gainesville, Florida
5 shared publications - Mingzhou Ding
J. Crayton Pruitt Family Department of Biomedical Engineering, University of Florida
4 shared publications - Yingbo Ma
Division of Nephrology, Hypertension, and Renal Transplantation, Department of Medicine, College of Medicine, University of Florida, Gainesville, Florida
4 shared publications - Benjamin Shickel
AI for Health Institute, University of Florida, Gainesville, FL, USA, USA
3 shared publications - Immanuel Babu Henry Samuel
J. Crayton Pruitt Family Department of Biomedical Engineering, University of Florida, Gainesville, FL, USA
3 shared publications Jiaqing Yan
College of Electrical and Control Engineering, North China University of Technology, Beijing, China
3 shared publications
Latest Publications
- Open Access
- 6 November 2026
- Published by MDPI AG in Preprints.org
Intelligent Healthcare: A Systematic Review of Digital Twins in Healthcare Systems
Digital twins (DTs) have emerged as a transformative technology across various industries, and their potential in healthcare is garnering significant attention. DTs represent digital replicas of physical objects, systems, processes, and environments, offering unprecedented opportunities for personalized, precision, and intelligent healthcare. This paper systematically reviews the current applications of DTs in healthcare, focusing on how these technologies can enhance healthcare, improve patient and provider experiences, and deliver intelligent and personalized care. By leveraging immersive virtual worlds, healthcare practitioners can simulate complex medical situations, refine treatment strategies, and engage patients in more tailored, interactive ways. However, the integration of DTs into healthcare systems also presents technical, regulatory, and ethical challenges, such as data privacy concerns, the need for standardized protocols, and issues of accessibility. Addressing these challenges is crucial for the successful adoption and implementation of DTs in healthcare. This review aims to provide a comprehensive overview of the transformative potential of DTs in intelligent healthcare, while also highlighting the need for continued research and development in this rapidly evolving field. Through this systematic review, we seek to encourage further innovation and collaboration, paving the way for a future where DTs play a central role in intelligent healthcare delivery.
- 6 November 2026
- Published by MDPI AG in Preprints.org
Open AccessIntelligent Healthcare: A Systematic Review of Digital Twins in Healthcare Systems
Digital twins (DTs) have emerged as a transformative technology across various industries, and their potential in healthcare is garnering significant attention. DTs represent digital replicas of physical objects, systems, processes, and environments, offering unprecedented opportunities for personalized, precision, and intelligent healthcare. This paper systematically reviews the current applications of DTs in healthcare, focusing on how these technologies can enhance healthcare, improve patient and provider experiences, and deliver intelligent and personalized care. By leveraging immersive virtual worlds, healthcare practitioners can simulate complex medical situations, refine treatment strategies, and engage patients in more tailored, interactive ways. However, the integration of DTs into healthcare systems also presents technical, regulatory, and ethical challenges, such as data privacy concerns, the need for standardized protocols, and issues of accessibility. Addressing these challenges is crucial for the successful adoption and implementation of DTs in healthcare. This review aims to provide a comprehensive overview of the transformative potential of DTs in intelligent healthcare, while also highlighting the need for continued research and development in this rapidly evolving field. Through this systematic review, we seek to encourage further innovation and collaboration, paving the way for a future where DTs play a central role in intelligent healthcare delivery.
- Open Access
AI for Equitable Tennis Training: Leveraging AI for Equitable and Accurate Classification of Tennis Skill Levels and Training Phases
Numerous studies have demonstrated the manifold benefits of tennis, such as increasing overall physical and mental health. Unfortunately, many children and youth from low-income families are unable to engage in this sport mainly due to financial constraints such as private lesson expenses as well as logistical concerns to and back from such lessons and clinics. While several tennis self-training systems exist, they are often tailored for professionals and are prohibitively expensive. The present study aims to classify tennis players' skill levels and classify tennis strokes into phases characterized by motion attributes for a future development of an AI-based tennis self-training model for affordable and convenient applications running on devices used in daily life such as an iPhone or an Apple Watch for tennis skill improvement. We collected motion data, including Motion Yaw, Roll and Pitch from inertial measurement units (IMUs) worn by participating junior tennis players. For this pilot study, data from twelve participants were processed using Support Vector Machine (SVM) algorithms. The SVM models demonstrated an overall accuracy of 77% in classifying players as beginners or intermediates, with low rates of false positives and false negatives, effectively distinguishing skill levels. Additionally, the tennis swings were successfully classified into five phases based on the collected motion data. These findings indicate that SVM-based classification can be a reliable foundation for developing an equitable and accessible AI-driven tennis training system.
Open AccessAI for Equitable Tennis Training: Leveraging AI for Equitable and Accurate Classification of Tennis Skill Levels and Training Phases
Numerous studies have demonstrated the manifold benefits of tennis, such as increasing overall physical and mental health. Unfortunately, many children and youth from low-income families are unable to engage in this sport mainly due to financial constraints such as private lesson expenses as well as logistical concerns to and back from such lessons and clinics. While several tennis self-training systems exist, they are often tailored for professionals and are prohibitively expensive. The present study aims to classify tennis players' skill levels and classify tennis strokes into phases characterized by motion attributes for a future development of an AI-based tennis self-training model for affordable and convenient applications running on devices used in daily life such as an iPhone or an Apple Watch for tennis skill improvement. We collected motion data, including Motion Yaw, Roll and Pitch from inertial measurement units (IMUs) worn by participating junior tennis players. For this pilot study, data from twelve participants were processed using Support Vector Machine (SVM) algorithms. The SVM models demonstrated an overall accuracy of 77% in classifying players as beginners or intermediates, with low rates of false positives and false negatives, effectively distinguishing skill levels. Additionally, the tennis swings were successfully classified into five phases based on the collected motion data. These findings indicate that SVM-based classification can be a reliable foundation for developing an equitable and accessible AI-driven tennis training system.
- Open Access
Explainable Interfaces for Rapid Gaze-Based Interactions in Mixed Reality
Gaze-based interactions offer a potential way for users to naturally engage with mixed reality (XR) interfaces. Black-box machine learning models enabled higher accuracy for gaze-based interactions. However, due to the black-box nature of the model, users might not be able to understand and effectively adapt their gaze behaviour to achieve high quality interaction. We posit that explainable AI (XAI) techniques can facilitate understanding of and interaction with gaze-based model-driven system in XR. To study this, we built a real-time, multi-level XAI interface for gaze-based interaction using a deep learning model, and evaluated it during a visual search task in XR. A between-subjects study revealed that participants who interacted with XAI made more accurate selections compared to those who did not use the XAI system (i.e., F1 score increase of 10.8%). Additionally, participants who used the XAI system adapted their gaze behavior over time to make more effective selections. These findings suggest that XAI can potentially be used to assist users in more effective collaboration with model-driven interactions in XR.
Open AccessExplainable Interfaces for Rapid Gaze-Based Interactions in Mixed Reality
Gaze-based interactions offer a potential way for users to naturally engage with mixed reality (XR) interfaces. Black-box machine learning models enabled higher accuracy for gaze-based interactions. However, due to the black-box nature of the model, users might not be able to understand and effectively adapt their gaze behaviour to achieve high quality interaction. We posit that explainable AI (XAI) techniques can facilitate understanding of and interaction with gaze-based model-driven system in XR. To study this, we built a real-time, multi-level XAI interface for gaze-based interaction using a deep learning model, and evaluated it during a visual search task in XR. A between-subjects study revealed that participants who interacted with XAI made more accurate selections compared to those who did not use the XAI system (i.e., F1 score increase of 10.8%). Additionally, participants who used the XAI system adapted their gaze behavior over time to make more effective selections. These findings suggest that XAI can potentially be used to assist users in more effective collaboration with model-driven interactions in XR.
- Open Access
Transparent AI: Developing an Explainable Interface for Predicting Postoperative Complications
Given the sheer volume of surgical procedures and the significant rate of postoperative fatalities, assessing and managing surgical complications has become a critical public health concern. Existing artificial intelligence (AI) tools for risk surveillance and diagnosis often lack adequate interpretability, fairness, and reproducibility. To address this, we proposed an Explainable AI (XAI) framework designed to answer five critical questions: why, why not, how, what if, and what else, with the goal of enhancing the explainability and transparency of AI models. We incorporated various techniques such as Local Interpretable Model-agnostic Explanations (LIME), SHapley Additive exPlanations (SHAP), counterfactual explanations, model cards, an interactive feature manipulation interface, and the identification of similar patients to address these questions. We showcased an XAI interface prototype that adheres to this framework for predicting major postoperative complications. This initial implementation has provided valuable insights into the vast explanatory potential of our XAI framework and represents an initial step towards its clinical adoption.
Open AccessTransparent AI: Developing an Explainable Interface for Predicting Postoperative Complications
Given the sheer volume of surgical procedures and the significant rate of postoperative fatalities, assessing and managing surgical complications has become a critical public health concern. Existing artificial intelligence (AI) tools for risk surveillance and diagnosis often lack adequate interpretability, fairness, and reproducibility. To address this, we proposed an Explainable AI (XAI) framework designed to answer five critical questions: why, why not, how, what if, and what else, with the goal of enhancing the explainability and transparency of AI models. We incorporated various techniques such as Local Interpretable Model-agnostic Explanations (LIME), SHapley Additive exPlanations (SHAP), counterfactual explanations, model cards, an interactive feature manipulation interface, and the identification of similar patients to address these questions. We showcased an XAI interface prototype that adheres to this framework for predicting major postoperative complications. This initial implementation has provided valuable insights into the vast explanatory potential of our XAI framework and represents an initial step towards its clinical adoption.
- Open Access
Global Contrastive Training for Multimodal Electronic Health Records with Language Supervision
Modern electronic health records (EHRs) hold immense promise in tracking personalized patient health trajectories through sequential deep learning, owing to their extensive breadth, scale, and temporal granularity. Nonetheless, how to effectively leverage multiple modalities from EHRs poses significant challenges, given its complex characteristics such as high dimensionality, multimodality, sparsity, varied recording frequencies, and temporal irregularities. To this end, this paper introduces a novel multimodal contrastive learning framework, specifically focusing on medical time series and clinical notes. To tackle the challenge of sparsity and irregular time intervals in medical time series, the framework integrates temporal cross-attention transformers with a dynamic embedding and tokenization scheme for learning multimodal feature representations. To harness the interconnected relationships between medical time series and clinical notes, the framework equips a global contrastive loss, aligning a patient's multimodal feature representations with the corresponding discharge summaries. Since discharge summaries uniquely pertain to individual patients and represent a holistic view of the patient's hospital stay, machine learning models are led to learn discriminative multimodal features via global contrasting. Extensive experiments with a real-world EHR dataset demonstrated that our framework outperformed state-of-the-art approaches on the exemplar task of predicting the occurrence of nine postoperative complications for more than 120,000 major inpatient surgeries using multimodal data from UF health system split among three hospitals (UF Health Gainesville, UF Health Jacksonville, and UF Health Jacksonville-North).
Open AccessGlobal Contrastive Training for Multimodal Electronic Health Records with Language Supervision
Modern electronic health records (EHRs) hold immense promise in tracking personalized patient health trajectories through sequential deep learning, owing to their extensive breadth, scale, and temporal granularity. Nonetheless, how to effectively leverage multiple modalities from EHRs poses significant challenges, given its complex characteristics such as high dimensionality, multimodality, sparsity, varied recording frequencies, and temporal irregularities. To this end, this paper introduces a novel multimodal contrastive learning framework, specifically focusing on medical time series and clinical notes. To tackle the challenge of sparsity and irregular time intervals in medical time series, the framework integrates temporal cross-attention transformers with a dynamic embedding and tokenization scheme for learning multimodal feature representations. To harness the interconnected relationships between medical time series and clinical notes, the framework equips a global contrastive loss, aligning a patient's multimodal feature representations with the corresponding discharge summaries. Since discharge summaries uniquely pertain to individual patients and represent a holistic view of the patient's hospital stay, machine learning models are led to learn discriminative multimodal features via global contrasting. Extensive experiments with a real-world EHR dataset demonstrated that our framework outperformed state-of-the-art approaches on the exemplar task of predicting the occurrence of nine postoperative complications for more than 120,000 major inpatient surgeries using multimodal data from UF health system split among three hospitals (UF Health Gainesville, UF Health Jacksonville, and UF Health Jacksonville-North).
- Open Access
Federated learning model for predicting major postoperative complications
Background: The accurate prediction of postoperative complication risk using Electronic Health Records (EHR) and artificial intelligence shows great potential. Training a robust artificial intelligence model typically requires large-scale and diverse datasets. In reality, collecting medical data often encounters challenges surrounding privacy protection. Methods: This retrospective cohort study includes adult patients who were admitted to UFH Gainesville (GNV) (n = 79,850) and Jacksonville (JAX) (n = 28,636) for any type of inpatient surgical procedure. Using perioperative and intraoperative features, we developed federated learning models to predict nine major postoperative complications (i.e., prolonged intensive care unit stay and mechanical ventilation). We compared federated learning models with local learning models trained on a single site and central learning models trained on pooled dataset from two centers. Results: Our federated learning models achieved the area under the receiver operating characteristics curve (AUROC) values ranged from 0.81 for wound complications to 0.92 for prolonged ICU stay at UFH GNV center. At UFH JAX center, these values ranged from 0.73-0.74 for wound complications to 0.92-0.93 for hospital mortality. Federated learning models achieved comparable AUROC performance to central learning models, except for prolonged ICU stay, where the performance of federated learning models was slightly higher than central learning models at UFH GNV center, but slightly lower at UFH JAX center. In addition, our federated learning model obtained comparable performance to the best local learning model at each center, demonstrating strong generalizability. Conclusion: Federated learning is shown to be a useful tool to train robust and generalizable models from large scale data across multiple institutions where data protection barriers are high.
Open AccessFederated learning model for predicting major postoperative complications
Background: The accurate prediction of postoperative complication risk using Electronic Health Records (EHR) and artificial intelligence shows great potential. Training a robust artificial intelligence model typically requires large-scale and diverse datasets. In reality, collecting medical data often encounters challenges surrounding privacy protection. Methods: This retrospective cohort study includes adult patients who were admitted to UFH Gainesville (GNV) (n = 79,850) and Jacksonville (JAX) (n = 28,636) for any type of inpatient surgical procedure. Using perioperative and intraoperative features, we developed federated learning models to predict nine major postoperative complications (i.e., prolonged intensive care unit stay and mechanical ventilation). We compared federated learning models with local learning models trained on a single site and central learning models trained on pooled dataset from two centers. Results: Our federated learning models achieved the area under the receiver operating characteristics curve (AUROC) values ranged from 0.81 for wound complications to 0.92 for prolonged ICU stay at UFH GNV center. At UFH JAX center, these values ranged from 0.73-0.74 for wound complications to 0.92-0.93 for hospital mortality. Federated learning models achieved comparable AUROC performance to central learning models, except for prolonged ICU stay, where the performance of federated learning models was slightly higher than central learning models at UFH GNV center, but slightly lower at UFH JAX center. In addition, our federated learning model obtained comparable performance to the best local learning model at each center, demonstrating strong generalizability. Conclusion: Federated learning is shown to be a useful tool to train robust and generalizable models from large scale data across multiple institutions where data protection barriers are high.
- Open Access
Temporal Cross-Attention for Dynamic Embedding and Tokenization of Multimodal Electronic Health Records
The breadth, scale, and temporal granularity of modern electronic health records (EHR) systems offers great potential for estimating personalized and contextual patient health trajectories using sequential deep learning. However, learning useful representations of EHR data is challenging due to its high dimensionality, sparsity, multimodality, irregular and variable-specific recording frequency, and timestamp duplication when multiple measurements are recorded simultaneously. Although recent efforts to fuse structured EHR and unstructured clinical notes suggest the potential for more accurate prediction of clinical outcomes, less focus has been placed on EHR embedding approaches that directly address temporal EHR challenges by learning time-aware representations from multimodal patient time series. In this paper, we introduce a dynamic embedding and tokenization framework for precise representation of multimodal clinical time series that combines novel methods for encoding time and sequential position with temporal cross-attention. Our embedding and tokenization framework, when integrated into a multitask transformer classifier with sliding window attention, outperformed baseline approaches on the exemplar task of predicting the occurrence of nine postoperative complications of more than 120,000 major inpatient surgeries using multimodal data from three hospitals and two academic health centers in the United States.
Open AccessTemporal Cross-Attention for Dynamic Embedding and Tokenization of Multimodal Electronic Health Records
The breadth, scale, and temporal granularity of modern electronic health records (EHR) systems offers great potential for estimating personalized and contextual patient health trajectories using sequential deep learning. However, learning useful representations of EHR data is challenging due to its high dimensionality, sparsity, multimodality, irregular and variable-specific recording frequency, and timestamp duplication when multiple measurements are recorded simultaneously. Although recent efforts to fuse structured EHR and unstructured clinical notes suggest the potential for more accurate prediction of clinical outcomes, less focus has been placed on EHR embedding approaches that directly address temporal EHR challenges by learning time-aware representations from multimodal patient time series. In this paper, we introduce a dynamic embedding and tokenization framework for precise representation of multimodal clinical time series that combines novel methods for encoding time and sequential position with temporal cross-attention. Our embedding and tokenization framework, when integrated into a multitask transformer classifier with sliding window attention, outperformed baseline approaches on the exemplar task of predicting the occurrence of nine postoperative complications of more than 120,000 major inpatient surgeries using multimodal data from three hospitals and two academic health centers in the United States.
- Open Access
- 1 January 2022
- Published by Elsevier in SSRN Electronic Journal
Aftereffects of Frontoparietal Theta tACS on Verbal Working Memory: Behavioral and Neurophysiological Analysis
Verbal working memory is supported by left-lateralized frontoparietal theta oscillations (4 to 8 Hz). We tested whether stimulating the left frontoparietal network at theta frequency during verbal working memory can produce observable effects in behavior and neurophysiology following stimulation. Weak theta-band alternating electric currents were delivered via two 4×1 HD electrode arrays centered at F3 and P3. Three stimulation configurations, including in-phase, anti-phase, or sham, were tested on three different days in a cross-over (within-subject) design. On each test day, the subject underwent three experimental sessions: pre-, during- and post-stimulation sessions. In all sessions, the subject performed a Sternberg verbal working memory task with three levels of memory load (load 2, 4 and 6), imposing three levels of cognitive demand. Analyzing behavioral and EEG data from the post-stimulation session, we report two main observations. First, in-phase stimulation improved task performance in subjects with higher working memory capacity (WMC) and under higher memory load (load 6). Second, in-phase stimulation enhanced frontoparietal theta synchrony during working memory retention in subjects with higher WMC under higher memory loads (load 4 and load 6), and the enhanced frontoparietal theta synchronization is mainly driven by enhanced frontal --> parietal theta Granger causality. These observations suggest that in-phase theta transcranial alternating current stimulation (tACS) during verbal working memory can result in observable behavioral and neurophysiological consequences post stimulation and the short-term plasticity effects are state and individual dependent. Funding Information: This work was supported by the National Institute of Health grants MH112206 and MH117991. Declaration of Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest. Ethics Approval Statement: The experimental protocol was approved by the University of Florida Institutional Review Board. Volunteers gave written informed consent and participated in the study.
- 1 January 2022
- Published by Elsevier in SSRN Electronic Journal
Open AccessAftereffects of Frontoparietal Theta tACS on Verbal Working Memory: Behavioral and Neurophysiological Analysis
Verbal working memory is supported by left-lateralized frontoparietal theta oscillations (4 to 8 Hz). We tested whether stimulating the left frontoparietal network at theta frequency during verbal working memory can produce observable effects in behavior and neurophysiology following stimulation. Weak theta-band alternating electric currents were delivered via two 4×1 HD electrode arrays centered at F3 and P3. Three stimulation configurations, including in-phase, anti-phase, or sham, were tested on three different days in a cross-over (within-subject) design. On each test day, the subject underwent three experimental sessions: pre-, during- and post-stimulation sessions. In all sessions, the subject performed a Sternberg verbal working memory task with three levels of memory load (load 2, 4 and 6), imposing three levels of cognitive demand. Analyzing behavioral and EEG data from the post-stimulation session, we report two main observations. First, in-phase stimulation improved task performance in subjects with higher working memory capacity (WMC) and under higher memory load (load 6). Second, in-phase stimulation enhanced frontoparietal theta synchrony during working memory retention in subjects with higher WMC under higher memory loads (load 4 and load 6), and the enhanced frontoparietal theta synchronization is mainly driven by enhanced frontal --> parietal theta Granger causality. These observations suggest that in-phase theta transcranial alternating current stimulation (tACS) during verbal working memory can result in observable behavioral and neurophysiological consequences post stimulation and the short-term plasticity effects are state and individual dependent. Funding Information: This work was supported by the National Institute of Health grants MH112206 and MH117991. Declaration of Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest. Ethics Approval Statement: The experimental protocol was approved by the University of Florida Institutional Review Board. Volunteers gave written informed consent and participated in the study.
- Open Access
- 16 February 2021
- Published by Oxford University Press (OUP) in Cerebral Cortex
- Vol. 31  (6) , 3047-3063
Decoding Neural Representations of Affective Scenes in Retinotopic Visual Cortex
The perception of opportunities and threats in complex visual scenes represents one of the main functions of the human visual system. The underlying neurophysiology is often studied by having observers view pictures varying in affective content. It has been shown that viewing emotionally engaging, compared with neutral, pictures (1) heightens blood flow in limbic, frontoparietal, and anterior visual structures and (2) enhances the late positive event-related potential (LPP). The role of retinotopic visual cortex in this process has, however, been contentious, with competing theories predicting the presence versus absence of emotion-specific signals in retinotopic visual areas. Recording simultaneous electroencephalography–functional magnetic resonance imaging while observers viewed pleasant, unpleasant, and neutral affective pictures, and applying multivariate pattern analysis, we found that (1) unpleasant versus neutral and pleasant versus neutral decoding accuracy were well above chance level in retinotopic visual areas, (2) decoding accuracy in ventral visual cortex (VVC), but not in early or dorsal visual cortex, was correlated with LPP, and (3) effective connectivity from amygdala to VVC predicted unpleasant versus neutral decoding accuracy, whereas effective connectivity from ventral frontal cortex to VVC predicted pleasant versus neutral decoding accuracy. These results suggest that affective scenes evoke valence-specific neural representations in retinotopic visual cortex and that these representations are influenced by reentry signals from anterior brain regions.
- 16 February 2021
- Published by Oxford University Press (OUP) in Cerebral Cortex
- Vol. 31  (6) , 3047-3063
Open AccessDecoding Neural Representations of Affective Scenes in Retinotopic Visual Cortex
The perception of opportunities and threats in complex visual scenes represents one of the main functions of the human visual system. The underlying neurophysiology is often studied by having observers view pictures varying in affective content. It has been shown that viewing emotionally engaging, compared with neutral, pictures (1) heightens blood flow in limbic, frontoparietal, and anterior visual structures and (2) enhances the late positive event-related potential (LPP). The role of retinotopic visual cortex in this process has, however, been contentious, with competing theories predicting the presence versus absence of emotion-specific signals in retinotopic visual areas. Recording simultaneous electroencephalography–functional magnetic resonance imaging while observers viewed pleasant, unpleasant, and neutral affective pictures, and applying multivariate pattern analysis, we found that (1) unpleasant versus neutral and pleasant versus neutral decoding accuracy were well above chance level in retinotopic visual areas, (2) decoding accuracy in ventral visual cortex (VVC), but not in early or dorsal visual cortex, was correlated with LPP, and (3) effective connectivity from amygdala to VVC predicted unpleasant versus neutral decoding accuracy, whereas effective connectivity from ventral frontal cortex to VVC predicted pleasant versus neutral decoding accuracy. These results suggest that affective scenes evoke valence-specific neural representations in retinotopic visual cortex and that these representations are influenced by reentry signals from anterior brain regions.
- 1 January 2021
- Published by Elsevier in Epilepsy & Behavior
- Vol. 114, 107598
An association between resting state EEG parameters and the severity of topiramate-related cognitive impairment
- 1 January 2021
- Published by Elsevier in Epilepsy & Behavior
- Vol. 114, 107598
An association between resting state EEG parameters and the severity of topiramate-related cognitive impairment