Xiao-Yan 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
Xiao-Yan Hu has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Bin Yi
Department of Anesthesiology, Southwest Hospital, Army Medical University, Chongqing, China
2 shared publications - Yuwen Chen
Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing, China
2 shared publications - Hong-Yu Zhi
Department of Anaesthesiology, Southwest Hospital, The Third Military Medical University (Army Medical University), Chongqing, China
1 shared publication - Jian-Teng Gu
Department of Anesthesiology, Southwest Hospital, Third Military Medical University, Chongqing, China
1 shared publication - Jiao-Lin Ning
Department of Anaesthesiology, Southwest Hospital, The Third Military Medical University (Army Medical University), Chongqing, China
1 shared publication - Ju Zhang
Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Science, Chongqing, China
1 shared publication
Latest Publications
- Open Access
- 4 April 2024
- Published by Springer Nature in Research Square
Automatic Non-Invasive Prediction of Hemoglobin Using a Deep Learning-Assisted Smartphone-Based System
Background The context and purpose of this study is to introduce a novel, compact, and efficient system that leverages deep learning and smartphone technology to estimate hemoglobin levels. Accurate measurement of hemoglobin concentration is essential for various medical scenarios, including preoperative evaluations and determining blood loss. Current models, due to their complex parameters, are not well-suited for mobile medical settings, which limits the ability to conduct frequent and rapid testing. Methods The study employed a smartphone application to capture images of the eye, which were then analyzed by a deep neural network trained using invasive blood test data. For the task of eyelid segmentation, the EGE-Unet model was used. The performance of this model was evaluated using statistical metrics including mean intersection over union (MIOU), F1 Score, accuracy, specificity, and sensitivity. For hemoglobin level prediction, the DHA(C3AE) model was employed. The performance of this model was assessed using mean absolute error (MAE), mean absolute percentage error (MAPE), root mean square error (RMSE), and R^2. Results The EGE-Unet model demonstrated robust performance in eyelid segmentation, achieving a MIOU of 0.78, an F1 Score of 0.87, an accuracy of 0.97, a specificity of 0.98, and a sensitivity of 0.86. The DHA(C3AE) model for hemoglobin level prediction yielded promising outcomes with a MAE of 1.34, a MAPE of 2.85, an RMSE of 1.69, and an R^2 of 0.34. The overall size of the model is modest at 1.08M, with a computational complexity of 0.12 FLOPs (G). Conclusions This groundbreaking approach eliminates the necessity for supplementary devices, providing a cost-effective, swift, and accurate method for healthcare professionals to enhance treatment planning and improve patient care in perioperative environments. The proposed system has the potential to enable frequent and rapid testing of hemoglobin levels, which can be particularly beneficial in mobile medical settings. Trial Registration: The clinical trial was registered on the Chinese Clinical Trial Registry (No. ChiCTR2100044138) on March 11, 2021.
- 4 April 2024
- Published by Springer Nature in Research Square
Open AccessAutomatic Non-Invasive Prediction of Hemoglobin Using a Deep Learning-Assisted Smartphone-Based System
Background The context and purpose of this study is to introduce a novel, compact, and efficient system that leverages deep learning and smartphone technology to estimate hemoglobin levels. Accurate measurement of hemoglobin concentration is essential for various medical scenarios, including preoperative evaluations and determining blood loss. Current models, due to their complex parameters, are not well-suited for mobile medical settings, which limits the ability to conduct frequent and rapid testing. Methods The study employed a smartphone application to capture images of the eye, which were then analyzed by a deep neural network trained using invasive blood test data. For the task of eyelid segmentation, the EGE-Unet model was used. The performance of this model was evaluated using statistical metrics including mean intersection over union (MIOU), F1 Score, accuracy, specificity, and sensitivity. For hemoglobin level prediction, the DHA(C3AE) model was employed. The performance of this model was assessed using mean absolute error (MAE), mean absolute percentage error (MAPE), root mean square error (RMSE), and R^2. Results The EGE-Unet model demonstrated robust performance in eyelid segmentation, achieving a MIOU of 0.78, an F1 Score of 0.87, an accuracy of 0.97, a specificity of 0.98, and a sensitivity of 0.86. The DHA(C3AE) model for hemoglobin level prediction yielded promising outcomes with a MAE of 1.34, a MAPE of 2.85, an RMSE of 1.69, and an R^2 of 0.34. The overall size of the model is modest at 1.08M, with a computational complexity of 0.12 FLOPs (G). Conclusions This groundbreaking approach eliminates the necessity for supplementary devices, providing a cost-effective, swift, and accurate method for healthcare professionals to enhance treatment planning and improve patient care in perioperative environments. The proposed system has the potential to enable frequent and rapid testing of hemoglobin levels, which can be particularly beneficial in mobile medical settings. Trial Registration: The clinical trial was registered on the Chinese Clinical Trial Registry (No. ChiCTR2100044138) on March 11, 2021.
- Open Access
- 23 April 2022
- Published by Springer Nature in BMC Anesthesiology
- Vol. 22 (1) , 1-11
Learning to predict in-hospital mortality risk in the intensive care unit with attention-based temporal convolution network
Background: Dynamic prediction of patient mortality risk in the ICU with time series data is limited due to high dimensionality, uncertainty in sampling intervals, and other issues. A new deep learning method, temporal convolution network (TCN), makes it possible to deal with complex clinical time series data in ICU. We aimed to develop and validate it to predict mortality risk using time series data from MIMIC III dataset.Methods: A total of 21,139 records of ICU stays were analysed and 17 physiological variables from the MIMIC III dataset were used to predict mortality risk. Then we compared the model performance of the attention-based TCN with that of traditional artificial intelligence (AI) methods.Results: The area under receiver operating characteristic (AUCROC) and area under precision-recall curve (AUC-PR) of attention-based TCN for predicting the mortality risk 48 h after ICU admission were 0.837 (0.824 -0.850) and 0.454, respectively. The sensitivity and specificity of attention-based TCN were 67.1% and 82.6%, respectively, compared to the traditional AI method, which had a low sensitivity (< 50%).Conclusions: The attention-based TCN model achieved better performance in the prediction of mortality risk with time series data than traditional AI methods and conventional score-based models. The attention-based TCN mortality risk model has the potential for helping decision-making for critical patients.Trial registration: Data used for the prediction of mortality risk were extracted from the freely accessible MIMIC III dataset. The project was approved by the Institutional Review Boards of Beth Israel Deaconess Medical Center (Boston, MA) and the Massachusetts Institute of Technology (Cambridge, MA). Requirement for individual patient consent was waived because the project did not impact clinical care and all protected health information was deidentified. The data were accessed via a data use agreement between PhysioNet, a National Institutes of Health–supported data repository (https://www.physionet.org/), and one of us (Yu-wen Chen, Certification Number: 28341490). All methods were carried out in accordance with the institutional guidelines and regulations.
- 23 April 2022
- Published by Springer Nature in BMC Anesthesiology
- Vol. 22 (1) , 1-11
Open AccessLearning to predict in-hospital mortality risk in the intensive care unit with attention-based temporal convolution network
Background: Dynamic prediction of patient mortality risk in the ICU with time series data is limited due to high dimensionality, uncertainty in sampling intervals, and other issues. A new deep learning method, temporal convolution network (TCN), makes it possible to deal with complex clinical time series data in ICU. We aimed to develop and validate it to predict mortality risk using time series data from MIMIC III dataset.Methods: A total of 21,139 records of ICU stays were analysed and 17 physiological variables from the MIMIC III dataset were used to predict mortality risk. Then we compared the model performance of the attention-based TCN with that of traditional artificial intelligence (AI) methods.Results: The area under receiver operating characteristic (AUCROC) and area under precision-recall curve (AUC-PR) of attention-based TCN for predicting the mortality risk 48 h after ICU admission were 0.837 (0.824 -0.850) and 0.454, respectively. The sensitivity and specificity of attention-based TCN were 67.1% and 82.6%, respectively, compared to the traditional AI method, which had a low sensitivity (< 50%).Conclusions: The attention-based TCN model achieved better performance in the prediction of mortality risk with time series data than traditional AI methods and conventional score-based models. The attention-based TCN mortality risk model has the potential for helping decision-making for critical patients.Trial registration: Data used for the prediction of mortality risk were extracted from the freely accessible MIMIC III dataset. The project was approved by the Institutional Review Boards of Beth Israel Deaconess Medical Center (Boston, MA) and the Massachusetts Institute of Technology (Cambridge, MA). Requirement for individual patient consent was waived because the project did not impact clinical care and all protected health information was deidentified. The data were accessed via a data use agreement between PhysioNet, a National Institutes of Health–supported data repository (https://www.physionet.org/), and one of us (Yu-wen Chen, Certification Number: 28341490). All methods were carried out in accordance with the institutional guidelines and regulations.