Browsing by Author "Zhang, Qingxue"

Now showing 1 - 10 of 25
  • Thumbnail Image
    Item
    Automated Evaluation of Neurological Disorders Through Electronic Health Record Analysis
    (2024-08) Prince, Md Rakibul Islam; Ben Miled, Zina; El-Sharkawy, Mohamed A.; Zhang, Qingxue
    Neurological disorders present a considerable challenge due to their variety and diagnostic complexity especially for older adults. Early prediction of the onset and ongoing assessment of the severity of these disease conditions can allow timely interventions. Currently, most of the assessment tools are time-consuming, costly, and not suitable for use in primary care. To reduce this burden, the present thesis introduces passive digital markers for different disease conditions that can effectively automate the severity assessment and risk prediction from different modalities of electronic health records (EHR). The focus of the first phase of the present study in on developing passive digital markers for the functional assessment of patients suffering from Bipolar disorder and Schizophrenia. The second phase of the study explores different architectures for passive digital markers that can predict patients at risk for dementia. The functional severity PDM uses only a single EHR modality, namely medical notes in order to assess the severity of the functioning of schizophrenia, bipolar type I, or mixed bipolar patients. In this case, the input of is a single medical note from the electronic medical record of the patient. This note is submitted to a hierarchical BERT model which classifies at-risk patients. A hierarchical attention mechanism is adopted because medical notes can exceed the maximum allowed number of tokens by most language models including BERT. The functional severity PDM follows three steps. First, a sentence-level embedding is produced for each sentence in the note using a token-level attention mechanism. Second, an embedding for the entire note is constructed using a sentence-level attention mechanism. Third, the final embedding is classified using a feed-forward neural network which estimates the impairment level of the patient. When used prior to the onset of the disease, this PDM is able to differentiate between severe and moderate functioning levels with an AUC of 76%. Disease-specific severity assessment PDMs are only applicable after the onset of the disease and have AUCs of nearly 85% for schizophrenia and bipolar patients. The dementia risk prediction PDM considers multiple EHR modalities including socio-demographic data, diagnosis codes and medical notes. Moreover, the observation period and prediction horizon are varied for a better understanding of the practical limitations of the model. This PDM is able to identify patients at risk of dementia with AUCs ranging from 70% to 92% as the observation period approaches the index date. The present study introduces methodologies for the automation of important clinical outcomes such as the assessment of the general functioning of psychiatric patients and the prediction of risk for dementia using only routine care data.
  • Thumbnail Image
    Item
    Big Data Edge on Consumer Devices for Precision Medicine
    (IEEE, 2022) Stauffer, Jake; Zhang, Qingxue; Biomedical Engineering and Informatics, Luddy School of Informatics, Computing, and Engineering
    Consumer electronics like smartphones and wearable computers are furthering precision medicine significantly, through capturing/leveraging big data on the edge towards real-time, interactive healthcare applications. Here we propose a big data edge platform that can, not only capture/manage different biomedical dynamics, but also enable real-time visualization of big data. The big data can also be uploaded to cloud for long-term management. The system has been evaluated on the real-world biomechanical data-based application, and demonstrated its effectiveness on big data management and interactive visualization. This study is expected to greatly advance big data-driven precision medicine applications.
  • Thumbnail Image
    Item
    Deep Brain Dynamics and Images Mining for Tumor Detection and Precision Medicine
    (2023-08) Ramesh, Lakshmi; Zhang, Qingxue; King, Brian; Chen, Yaobin
    Automatic brain tumor segmentation in Magnetic Resonance Imaging scans is essential for the diagnosis, treatment, and surgery of cancerous tumors. However, identifying the hardly detectable tumors poses a considerable challenge, which are usually of different sizes, irregular shapes, and vague invasion areas. Current advancements have not yet fully leveraged the dynamics in the multiple modalities of MRI, since they usually treat multi-modality as multi-channel, and the early channel merging may not fully reveal inter-modal couplings and complementary patterns. In this thesis, we propose a novel deep cross-attention learning algorithm that maximizes the subtle dynamics mining from each of the input modalities and then boosts feature fusion capability. More specifically, we have designed a Multimodal Cross-Attention Module (MM-CAM), equipped with a 3D Multimodal Feature Rectification and Feature Fusion Module. Extensive experiments have shown that the proposed novel deep learning architecture, empowered by the innovative MM-CAM, produces higher-quality segmentation masks of the tumor subregions. Further, we have enhanced the algorithm with image matting refinement techniques. We propose to integrate a Progressive Refinement Module (PRM) and perform Cross-Subregion Refinement (CSR) for the precise identification of tumor boundaries. A Multiscale Dice Loss was also successfully employed to enforce additional supervision for the auxiliary segmentation outputs. This enhancement will facilitate effectively matting-based refinement for medical image segmentation applications. Overall, this thesis, with deep learning, transformer-empowered pattern mining, and sophisticated architecture designs, will greatly advance deep brain dynamics and images mining for tumor detection and precision medicine.
  • Thumbnail Image
    Item
    Deep Image Processing with Spatial Adaptation and Boosted Efficiency & Supervision for Accurate Human Keypoint Detection and Movement Dynamics Tracking
    (2023-05) Dai, Chao Yang; Zhang, Qingxue; King, Brian S.; Fang, Shiaofen
    This thesis aims to design and develop the spatial adaptation approach through spatial transformers to improve the accuracy of human keypoint recognition models. We have studied different model types and design choices to gain an accuracy increase over models without spatial transformers and analyzed how spatial transformers increase the accuracy of predictions. A neural network called Widenet has been leveraged as a specialized network for providing the parameters for the spatial transformer. Further, we have evaluated methods to reduce the model parameters, as well as the strategy to enhance the learning supervision for further improving the performance of the model. Our experiments and results have shown that the proposed deep learning framework can effectively detect the human key points, compared with the baseline methods. Also, we have reduced the model size without significantly impacting the performance, and the enhanced supervision has improved the performance. This study is expected to greatly advance the deep learning of human key points and movement dynamics.
  • Thumbnail Image
    Item
    Deep Learning of Biomechanical Dynamics With Spatial Variability Mining and Model Sparsifiation
    (2024-08) Liu, Ming; Zhang, Qingxue; King, Brian S.; Ben-Miled, Zina; Xia, Yuni
    Deep learning of biomechanical dynamics is of great promise in smart health and data-driven precision medicine. Biomechanical dynamics are related to the movement patterns and gait characteristics of human people and may provide important insights if mined by deep learning models. However, efficient deep learning of biomechanical dynamics is still challenging, considering that there is a high diversity in the dynamics from different body locations, and the deep learning model may need to be lightweight enough to be able to be deployed in real-time. Targeting these challenges, we have firstly conducted studies on the spatial variability of biomechanical dynamics, aiming to evaluate and determine the optimal body location that is of great promise in robust physical activity type detection. Further, we have developed a framework for deep learning pruning, aiming to determine the optimal pruning schemes while maintaining acceptable performance. More specifically, the proposed approach first evaluates the layer importance of the deep learning model, and then leverages the probabilistic distribution-enabled threshold determination to optimize the pruning rate. The weighted random thresholding method is first investigated to further the understanding of the behavior of the pruning action for each layer. Afterwards, the Gaussian-based thresholding is designed to more effectively optimize the pruning strategies, which can find out the fine-grained pruning schemes with both emphasis and diversity regulation. Even further, we have enhanced and boosted the efficient deep learning framework, to co-optimize the accuracy and the continuity during the pruning process, with the latter metric – continuity meaning that the pruning locations in the weight matrices are encouraged to not cause too many noncontinuous non-pruned locations thereby achieving friendly model implementation. More specifically, the proposed framework leverages the significance scoring and the continuity scoring to quantize the characteristics of each of pruned convolutional filters, then leverages the clustering technique to group the pruned filters for each convolutional stage. Afterwards, the regularized ranking approach is designed to rank the pruned filters, through putting more emphasis on the continuity scores to encourage friendly implementation. In the end, a dual-thresholding strategy is leveraged to increase the diversity in this framework, during significance & continuity co-optimization. Experimental results have demonstrated promising findings, with enhanced understanding of the spatial variability of the biomechanical dynamics and best performance body location selection, with the effective deep learning model pruning framework that can reduce the model size significantly with performance maintained, and further, with the boosted framework that co-optimizes the accuracy and continuity to all consider the friendly implementation during the pruning process. Overall, this research will greatly advance the deep biomechanical mining towards efficient smart health.
  • Thumbnail Image
    Item
    Deep Multimodal Physiological Learning of Cerebral Vasoregulation Dynamics on Stroke Patients Towards Precision Brain Medicine
    (2024-08) Tipparti, Akanksha; Zhang, Qingxue; King, Brain; Yung-Ping Chien, Stanley
    Impaired cerebral vasoregulation is one of the most common post-ischemic stroke effects. Diagnosis and prevention of this condition is often invasive, costly and in-effective. This impairment restricts the cerebral blood vessels to properly regulate blood flow, which is very important for normal brain functioning. Developing accurate, non-invasive and efficient methods to detect this condition aids in better stroke diagnosis and prevention. The aim of this thesis is to develop deep learning techniques for the purpose of detection of cerebral vasoregulation impairments by analyzing physiological signals. This research employs various Deep learning techniques like Convolution Neural Networks (CNN), Mo bileNet, and Long-Short-Term Memory (LSTM) to determine variety of physiological signals from the PhysioNet database like Electrocardio-gram (ECG), Transcranial Doppler (TCD), Electromyogram (EMG), and Blood Pressure(BP) as stroke or non-stroke subjects. The effectiveness of these algorithms is demonstrated by a classification accuracy of 90% for the combination of ECG and EMG signals. Furthermore, this research explores the importance of analyzing dynamic physiologi cal activities in determining the impairment. The dynamic activities include Sit-stand, Sit-stand-balance, Head-up-tilt, and Walk dataset from the PhysioNet website. CNN and MobileNetV3 are employed in classification purposes of these signals, attempting to iden tify cerebral health. The accuracy of the model and robustness of these methods is greatly enhanced when multiple signals are integrated. Overall, this study highlights the potential of deep multimodal physiological learning in the development of precision brain medicine further enhancing stroke diagnosis. The results pave the way for the development of advanced diagnostic tools to determine cerebral health.
  • Thumbnail Image
    Item
    Deep Reinforcement Learning of IoT System Dynamics for Optimal Orchestration and Boosted Efficiency
    (2023-08) Shi, Haowei; Zhang, Qingxue; King, Brian; Fang, Shiaofen
    This thesis targets the orchestration challenge of the Wearable Internet of Things (IoT) systems, for optimal configurations of the system in terms of energy efficiency, computing, and data transmission activities. We have firstly investigated the reinforcement learning on the simulated IoT environments to demonstrate its effectiveness, and afterwards studied the algorithm on the real-world wearable motion data to show the practical promise. More specifically, firstly, challenge arises in the complex massive-device orchestration, meaning that it is essential to configure and manage the massive devices and the gateway/server. The complexity on the massive wearable IoT devices, lies in the diverse energy budget, computing efficiency, etc. On the phone or server side, it lies in how global diversity can be analyzed and how the system configuration can be optimized. We therefore propose a new reinforcement learning architecture, called boosted deep deterministic policy gradient, with enhanced actor-critic co-learning and multi-view state transformation. The proposed actor-critic co-learning allows for enhanced dynamics abstraction through the shared neural network component. Evaluated on a simulated massive-device task, the proposed deep reinforcement learning framework has achieved much more efficient system configurations with enhanced computing capabilities and improved energy efficiency. Secondly, we have leveraged the real-world motion data to demonstrate the potential of leveraging reinforcement learning to optimally configure the motion sensors. We used paradigms in sequential data estimation to obtain estimated data for some sensors, allowing energy savings since these sensors no longer need to be activated to collect data for estimation intervals. We then introduced the Deep Deterministic Policy Gradient algorithm to learn to control the estimation timing. This study will provide a real-world demonstration of maximizing energy efficiency wearable IoT applications while maintaining data accuracy. Overall, this thesis will greatly advance the wearable IoT system orchestration for optimal system configurations.
  • Thumbnail Image
    Item
    Deep Transferable Intelligence for Wearable Big Data Pattern Detection
    (2021-08) Gangadharan, Kiirthanaa; Zhang, Qingxue; King, Brian S.; Chien, Yung-Ping S.
    Biomechanical Big Data is of great significance to precision health applications, among which we take special interest in Physical Activity Detection (PAD). In this study, we have performed extensive research on deep learning-based PAD from biomechanical big data, focusing on the challenges raised by the need for real-time edge inference. First, considering there are many places we can place the motion sensors, we have thoroughly compared and analyzed the location difference in terms of deep learning-based PAD performance. We have further compared the difference among six sensor channels (3-axis accelerometer and 3-axis gyroscope). Second, we have selected the optimal sensor and the optimal sensor channel, which can not only provide sensor usage suggestions but also enable ultra-lowpower application on the edge. Third, we have investigated innovative methods to minimize the training effort of the deep learning model, leveraging the transfer learning strategy. More specifically, we propose to pre-train a transferable deep learning model using the data from other subjects and then fine-tune the model using limited data from the target-user. In such a way, we have found that, for single-channel case, the transfer learning can effectively increase the deep model performance even when the fine-tuning effort is very small. This research, demonstrated by comprehensive experimental evaluation, has shown the potential of ultra-low-power PAD with minimized sensor stream, and minimized training effort.
  • Thumbnail Image
    Item
    Design Implementation and Evaluation of a Mobile Continuous Blood Oxygen Saturation Monitoring System
    (MDPI, 2020-11) Zhang, Qingxue; Arney, David; Goldman, Julian M.; Isselbacher, Eric M.; Armoundas, Antonis A.; Electrical and Computer Engineering, School of Engineering and Technology
    Objective: In this study, we built a mobile continuous Blood Oxygen Saturation (SpO2) monitor, and for the first time, explored key design principles towards daily applications. Methods: We firstly built a customized wearable computer that can sense two-channel photoplethysmogram (PPG) signals, and transmit the signals wirelessly to smartphone. Afterwards, we explored many SpO2 model building principles, focusing on linear/nonlinear models, different PPG parameter calculation methods, and different finger types. Moreover, we further compared PPG sensor placement principles by comparing different hand configurations and different finger configurations. Finally, a dataset collected from eleven human subjects was used to evaluate the mobile health monitor and explore all of the above design principles. Results: The experimental results show that the root mean square error of the SpO2 estimation is only 1.8, indicating the effectiveness of the system. Conclusion: These results indicate the effectiveness of the customized mobile SpO2 monitor and the selected design principles. Significance: This research is expected to facilitate the continuous SpO2 monitoring of patients with clinical indications.
  • Thumbnail Image
    Item
    Efficient Edge Intelligence in the Era of Big Data
    (2021-08) Wong, Jun Hua; Zhang, Qingxue; King, Brian; Schubert, Peter
    Smart wearables, known as emerging paradigms for vital big data capturing, have been attracting intensive attentions. However, one crucial problem is their power-hungriness, i.e., the continuous data streaming consumes energy dramatically and requires devices to be frequently charged. Targeting this obstacle, we propose to investigate the biodynamic patterns in the data and design a data-driven approach for intelligent data compression. We leverage Deep Learning (DL), more specifically, Convolutional Autoencoder (CAE), to learn a sparse representation of the vital big data. The minimized energy need, even taking into consideration the CAE-induced overhead, is tremendously lower than the original energy need. Further, compared with state-of-the-art wavelet compression-based method, our method can compress the data with a dramatically lower error for a similar energy budget. Our experiments and the validated approach are expected to boost the energy efficiency of wearables, and thus greatly advance ubiquitous big data applications in era of smart health. In recent years, there has also been a growing interest in edge intelligence for emerging instantaneous big data inference. However, the inference algorithms, especially deep learning, usually require heavy computation requirements, thereby greatly limiting their deployment on the edge. We take special interest in the smart health wearable big data mining and inference. Targeting the deep learning’s high computational complexity and large memory and energy requirements, new approaches are urged to make the deep learning algorithms ultra-efficient for wearable big data analysis. We propose to leverage knowledge distillation to achieve an ultra-efficient edge-deployable deep learning model. More specifically, through transferring the knowledge from a teacher model to the on-edge student model, the soft target distribution of the teacher model can be effectively learned by the student model. Besides, we propose to further introduce adversarial robustness to the student model, by stimulating the student model to correctly identify inputs that have adversarial perturbation. Experiments demonstrate that the knowledge distillation student model has comparable performance to the heavy teacher model but owns a substantially smaller model size. With adversarial learning, the student model has effectively preserved its robustness. In such a way, we have demonstrated the framework with knowledge distillation and adversarial learning can, not only advance ultra-efficient edge inference, but also preserve the robustness facing the perturbed input.