Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
7,642
result(s) for
"Lin, Ke"
Sort by:
Using machine learning methods to predict in-hospital mortality of sepsis patients in the ICU
Background
Early and accurate identification of sepsis patients with high risk of in-hospital death can help physicians in intensive care units (ICUs) make optimal clinical decisions. This study aimed to develop machine learning-based tools to predict the risk of hospital death of patients with sepsis in ICUs.
Methods
The source database used for model development and validation is the medical information mart for intensive care (MIMIC) III. We identified adult sepsis patients using the new sepsis definition Sepsis-3. A total of 86 predictor variables consisting of demographics, laboratory tests and comorbidities were used. We employed the least absolute shrinkage and selection operator (LASSO), random forest (RF), gradient boosting machine (GBM) and the traditional logistic regression (LR) method to develop prediction models. In addition, the prediction performance of the four developed models was evaluated and compared with that of an existent scoring tool – simplified acute physiology score (SAPS) II – using five different performance measures: the area under the receiver operating characteristic curve (AUROC), Brier score, sensitivity, specificity and calibration plot.
Results
The records of 16,688 sepsis patients in MIMIC III were used for model training and test. Amongst them, 2949 (17.7%) patients had in-hospital death. The average AUROCs of the LASSO, RF, GBM, LR and SAPS II models were 0.829, 0.829, 0.845, 0.833 and 0.77, respectively. The Brier scores of the LASSO, RF, GBM, LR and SAPS II models were 0.108, 0.109, 0.104, 0.107 and 0.146, respectively. The calibration plots showed that the GBM, LASSO and LR models had good calibration; the RF model underestimated high-risk patients; and SAPS II had the poorest calibration.
Conclusion
The machine learning-based models developed in this study had good prediction performance. Amongst them, the GBM model showed the best performance in predicting the risk of in-hospital death. It has the potential to assist physicians in the ICU to perform appropriate clinical interventions for critically ill sepsis patients and thus may help improve the prognoses of sepsis patients in the ICU.
Journal Article
General deep learning model for detecting diabetic retinopathy
Background
Doctors can detect symptoms of diabetic retinopathy (DR) early by using retinal ophthalmoscopy, and they can improve diagnostic efficiency with the assistance of deep learning to select treatments and support personnel workflow. Conventionally, most deep learning methods for DR diagnosis categorize retinal ophthalmoscopy images into training and validation data sets according to the 80/20 rule, and they use the synthetic minority oversampling technique (SMOTE) in data processing (e.g., rotating, scaling, and translating training images) to increase the number of training samples. Oversampling training may lead to overfitting of the training model. Therefore, untrained or unverified images can yield erroneous predictions. Although the accuracy of prediction results is 90%–99%, this overfitting of training data may distort training module variables.
Results
This study uses a 2-stage training method to solve the overfitting problem. In the training phase, to build the model, the Learning module 1 used to identify the DR and no-DR. The Learning module 2 on SMOTE synthetic datasets to identify the mild-NPDR, moderate NPDR, severe NPDR and proliferative DR classification. These two modules also used early stopping and data dividing methods to reduce overfitting by oversampling. In the test phase, we use the DIARETDB0, DIARETDB1, eOphtha, MESSIDOR, and DRIVE datasets to evaluate the performance of the training network. The prediction accuracy achieved to 85.38%, 84.27%, 85.75%, 86.73%, and 92.5%.
Conclusions
Based on the experiment, a general deep learning model for detecting DR was developed, and it could be used with all DR databases. We provided a simple method of addressing the imbalance of DR databases, and this method can be used with other medical images.
Journal Article
Injectable, Antioxidative, and Tissue‐Adhesive Nanocomposite Hydrogel as a Potential Treatment for Inner Retina Injuries
Reactive oxygen species (ROS) have been recognized as prevalent contributors to the development of inner retinal injuries including optic neuropathies such as glaucoma, non‐arteritic anterior ischemic optic neuropathy, traumatic optic neuropathy, and Leber hereditary optic neuropathy, among others. This underscores the pivotal significance of oxidative stress in the damage inflicted upon retinal tissue. To combat ROS‐related challenges, this study focuses on creating an injectable and tissue‐adhesive hydrogel with tailored antioxidant properties for retinal applications. GelCA, a gelatin‐modified hydrogel with photo‐crosslinkable and injectable properties, is developed. To enhance its antioxidant capabilities, curcumin‐loaded polydopamine nanoparticles (Cur@PDA NPs) are incorporated into the GelCA matrix, resulting in a multifunctional nanocomposite hydrogel referred to as Cur@PDA@GelCA. This hydrogel exhibits excellent biocompatibility in both in vitro and in vivo assessments, along with enhanced tissue adhesion facilitated by NPs in an in vivo model. Importantly, Cur@PDA@GelCA demonstrates the potential to mitigate oxidative stress when administered via intravitreal injection in retinal injury models such as the optic nerve crush model. These findings underscore its promise in advancing retinal tissue engineering and providing an innovative strategy for acute neuroprotection in the context of inner retinal injuries. This study addresses inner retinal injuries, emphasizing the role of reactive oxygen species (ROS). GelCA, a photo‐crosslinkable and injectable hydrogel synthesized by grafting cinnamic acid onto gelatin is developed. Incorporating curcumin‐loaded polydopamine nanoparticles results in Cur@PDA@GelCA, a multifunctional nanocomposite hydrogel. This innovative hydrogel demonstrates excellent biocompatibility, enhanced tissue adhesion, and the potential to mitigate oxidative stress in retinal injury models.
Journal Article
Probe exciplex structure of highly efficient thermally activated delayed fluorescence organic light emitting diodes
The lack of structural information impeded the access of efficient luminescence for the exciplex type thermally activated delayed fluorescence (TADF). We report here the pump-probe Step-Scan Fourier transform infrared spectra of exciplex composed of a carbazole-based electron donor (CN-Cz2) and 1,3,5-triazine-based electron acceptor (PO-T2T) codeposited as the solid film that gives intermolecular charge transfer (CT), TADF, and record-high exciplex type cyan organic light emitting diodes (external quantum efficiency: 16%). The transient infrared spectral assignment to the CT state is unambiguous due to its distinction from the local excited state of either the donor or the acceptor chromophore. Importantly, a broad absorption band centered at ~2060 cm
−1
was observed and assigned to a polaron-pair absorption. Time-resolved kinetics lead us to conclude that CT excited states relax to a ground-state intermediate with a time constant of ~3 µs, followed by a structural relaxation to the original CN-Cz2:PO-T2T configuration within ~14 µs.
The development of exciplex-type hosts for thermally activated delayed fluorescence organic light-emitting diodes is hindered by a lack of structural information for these donor:acceptor blends. Here, the authors report the pump-probe Step-Scan Fourier transform IR spectra for a D:A exciplex host.
Journal Article
Deep Learning-Based Segmentation and Quantification of Cucumber Powdery Mildew Using Convolutional Neural Network
Powdery mildew is a common disease in plants, and it is also one of the main diseases in the middle and final stages of cucumber (
). Powdery mildew on plant leaves affects the photosynthesis, which may reduce the plant yield. Therefore, it is of great significance to automatically identify powdery mildew. Currently, most image-based models commonly regard the powdery mildew identification problem as a dichotomy case, yielding a true or false classification assertion. However, quantitative assessment of disease resistance traits plays an important role in the screening of breeders for plant varieties. Therefore, there is an urgent need to exploit the extent to which leaves are infected which can be obtained by the area of diseases regions. In order to tackle these challenges, we propose a semantic segmentation model based on convolutional neural networks (CNN) to segment the powdery mildew on cucumber leaf images at pixel level, achieving an average pixel accuracy of 96.08%, intersection over union of 72.11% and Dice accuracy of 83.45% on twenty test samples. This outperforms the existing segmentation methods, K-means, Random forest, and GBDT methods. In conclusion, the proposed model is capable of segmenting the powdery mildew on cucumber leaves at pixel level, which makes a valuable tool for cucumber breeders to assess the severity of powdery mildew.
Journal Article
Halogen hydrogen-bonded organic framework (XHOF) constructed by singlet open-shell diradical for efficient photoreduction of U(VI)
Synthesis of framework materials possessing specific spatial structures or containing functional ligands has attracted tremendous attention. Herein, a halogen hydrogen-bonded organic framework (XHOF) is fabricated by using Cl
−
ions as central connection nodes to connect organic ligands, 7,7,8,8-tetraaminoquinodimethane (TAQ), by forming a Cl
−
···H
3
hydrogen bond structure. Unlike metallic node-linked MOFs, covalent bond-linked COFs, and intermolecular hydrogen bond-linked HOFs, XHOFs represent a different kind of crystalline framework. The electron-withdrawing effect of Cl
−
combined with the electron-rich property of the organic ligand TAQ strengthens the hydrogen bonds and endows XHOF-TAQ with high stability. Due to the production of excited electrons by TAQ under light irradiation, XHOF-TAQ can efficiently catalyze the reduction of soluble U(VI) to insoluble U(IV) with a capacity of 1708 mg-U g
−1
-material. This study fabricates a material for uranium immobilization for the sustainability of the environment and opens up a new direction for synthesizing crystalline framework materials.
While hydrogen bonded organic frameworks are well covered in the scientific literature, halogen hydrogen-bonded organic framework (XHOF) remain less explored. Here, the authors demonstrate a highly stable diradical-based XHOF and demonstrate photoreduction of uranyl ions and high capacity of uranyl immobilization.
Journal Article
Foundations and Innovations in Data Fusion and Ensemble Learning for Effective Consensus
Ensemble learning and data fusion techniques play a crucial role in modern machine learning, enhancing predictive performance, robustness, and generalization. This paper provides a comprehensive survey of ensemble methods, covering foundational techniques such as bagging, boosting, and random forests, as well as advanced topics including multiclass classification, multiview learning, multiple kernel learning, and the Dempster–Shafer theory of evidence. We present a comparative analysis of ensemble learning and deep learning, highlighting their respective strengths, limitations, and synergies. Additionally, we examine the theoretical foundations of ensemble methods, including bias–variance trade-offs, margin theory, and optimization-based frameworks, while analyzing computational trade-offs related to training complexity, inference efficiency, and storage requirements. To enhance accessibility, we provide a structured comparative summary of key ensemble techniques. Furthermore, we discuss emerging research directions, such as adaptive ensemble methods, hybrid deep learning approaches, and multimodal data fusion, as well as challenges related to interpretability, model selection, and handling noisy data in high-stakes applications. By integrating theoretical insights with practical considerations, this survey serves as a valuable resource for researchers and practitioners seeking to understand the evolving landscape of ensemble learning and its future prospects.
Journal Article
Coherent control of an ultrabright single spin in hexagonal boron nitride at room temperature
Hexagonal boron nitride (hBN) is a remarkable two-dimensional (2D) material that hosts solid-state spins and has great potential to be used in quantum information applications, including quantum networks. However, in this application, both the optical and spin properties are crucial for single spins but have not yet been discovered simultaneously for hBN spins. Here, we realize an efficient method for arraying and isolating the single defects of hBN and use this method to discover a new spin defect with a high probability of 85%. This single defect exhibits outstanding optical properties and an optically controllable spin, as indicated by the observed significant Rabi oscillation and Hahn echo experiments at room temperature. First principles calculations indicate that complexes of carbon and oxygen dopants may be the origin of the single spin defects. This provides a possibility for further addressing spins that can be optically controlled.
Optically active defects in hBN are promising for quantum sensing and information applications, however, coherent control of a single defect has not been achieved so far. By using an efficient method to produce arrays of defects in hBN, Guo et al. isolate a new carbon-related defect and show its coherent control.
Journal Article
Perceptron: Learning, Generalization, Model Selection, Fault Tolerance, and Role in the Deep Learning Era
The single-layer perceptron, introduced by Rosenblatt in 1958, is one of the earliest and simplest neural network models. However, it is incapable of classifying linearly inseparable patterns. A new era of neural network research started in 1986, when the backpropagation (BP) algorithm was rediscovered for training the multilayer perceptron (MLP) model. An MLP with a large number of hidden nodes can function as a universal approximator. To date, the MLP model is the most fundamental and important neural network model. It is also the most investigated neural network model. Even in this AI or deep learning era, the MLP is still among the few most investigated and used neural network models. Numerous new results have been obtained in the past three decades. This survey paper gives a comprehensive and state-of-the-art introduction to the perceptron model, with emphasis on learning, generalization, model selection and fault tolerance. The role of the perceptron model in the deep learning era is also described. This paper provides a concluding survey of perceptron learning, and it covers all the major achievements in the past seven decades. It also serves a tutorial for perceptron learning.
Journal Article