ABSTRACT
In recent years, there has been a surge in interest regarding the intricate physiological interplay between the brain and the heart, particularly during emotional processing. This has led to the development of various signal processing techniques aimed at investigating Brain-Heart Interactions (BHI), reflecting a growing appreciation for their bidirectional communication and influence on each other. Our study contributes to this burgeoning field by adopting a network physiology approach, employing time-delay stability as a quantifiable metric to discern and measure the coupling strength between the brain and the heart, specifically during visual emotional elicitation. We extract and transform features from EEG and ECG signals into a 1 Hz format, facilitating the calculation of BHI coupling strength through stability analysis on their maximal cross-correlation. Notably, our investigation sheds light on the critical role played by low-frequency components in EEG, particularly in the δ , θ , and α bands, as essential mediators of information transmission during the complex processing of emotion-related stimuli by the brain. Furthermore, our analysis highlights the pivotal involvement of frontal pole regions, emphasizing the significance of δ - θ coupling in mediating emotional responses. Additionally, we observe significant arousal-dependent changes in the θ frequency band across different emotional states, particularly evident in the prefrontal cortex. By offering novel insights into the synchronized dynamics of cortical and heartbeat activities during emotional elicitation, our research enriches the expanding knowledge base in the field of neurophysiology and emotion research.
Subject(s)
Brain , Electrocardiography , Electroencephalography , Emotions , Heart , Humans , Emotions/physiology , Male , Brain/physiology , Female , Young Adult , Adult , Heart/physiology , Heart Rate/physiology , Algorithms , Nerve Net/physiology , Photic Stimulation , Healthy VolunteersABSTRACT
The identification of slag inclusion defects in welds is of the utmost importance in guaranteeing the integrity, safety, and prolonged service life of welded structures. Most research focuses on different kinds of weld defects, but branch research on categories of slag inclusion material is limited and critical for safeguarding the quality of engineering and the well-being of personnel. To address this issue, we design a simulated method using ultrasonic testing to identify the inclusion of material categories in austenitic stainless steel. It is based on a simulated experiment in a water environment, and six categories of cubic specimens, including four metallic and two non-metallic materials, are selected to simulate the slag materials of the inclusion defects. Variational mode decomposition optimized by particle swarm optimization is employed for ultrasonic signals denoising. Moreover, the phase spectrum of the denoised signal is utilized to extract the phase characteristic of the echo signal from the water-slag specimen interface. The experimental results show that our method has the characteristics of appropriate decomposition and good denoising performance. Compared with famous signal denoising algorithms, the proposed method extracted the lowest number of intrinsic mode functions from the echo signal with the highest signal-to-noise ratio and lowest normalized cross-correlation among all of the comparative algorithms in signal denoising of weld slag inclusion defects. Finally, the phase spectrum can ascertain whether the slag inclusion is a thicker or thinner medium compared with the weld base material based on the half-wave loss existing or not in the echo signal phase.
ABSTRACT
BACKGROUND AND OBJECTIVE: Continuous prediction of late-onset sepsis (LOS) could be helpful for improving clinical outcomes in neonatal intensive care units (NICU). This study aimed to develop an artificial intelligence (AI) model for assisting the bedside clinicians in successfully identifying infants at risk for LOS using non-invasive vital signs monitoring. METHODS: In a retrospective study from the NICU of the Máxima Medical Center in Veldhoven, the Netherlands, a total of 492 preterm infants less than 32 weeks gestation were included between July 2016 and December 2018. Data on heart rate (HR), respiratory rate (RR), and oxygen saturation (SpO2) at 1 Hz were extracted from the patient monitor. We developed multiple AI models using 102 extracted features or raw time series to provide hourly LOS risk prediction. Shapley values were used to explain the model. For the best performing model, the effect of different vital signs and also the input type of signals on model performance was tested. To further assess the performance of applying the best performing model in a real-world clinical setting, we performed a simulation using four different alarm policies on continuous real-time predictions starting from three days after birth. RESULTS: A total of 51 LOS patients and 68 controls were finally included according to the patient inclusion and exclusion criteria. When tested by seven-fold cross-validations, the mean (standard deviation) area under the receiver operating characteristic curve (AUC) six hours before CRASH was 0.875 (0.072) for the best performing model, compared to the other six models with AUC ranging from 0.782 (0.089) to 0.846 (0.083). The best performing model performed only slightly worse than the model learning from raw physiological waveforms (0.886 [0.068]), successfully detecting 96.1 % of LOS patients before CRASH. When setting the expected alarm window to 24 h and using a multi-threshold alarm policy, the sensitivity metric was 71.6 %, while the positive predictive value was 9.9 %, resulting in an average of 1.15 alarms per day per patient. CONCLUSIONS: The proposed AI model, which learns from routinely collected vital signs, has the potential to assist clinicians in the early detection of LOS. Combined with interpretability and clinical alarm management, this model could be better translated into medical practice for future clinical implementation.
ABSTRACT
An epileptic seizure can usually be divided into three stages: interictal, preictal, and ictal. However, the seizure underlying the transition from interictal to ictal activities in the brain involves complex interactions between inhibition and excitation in groups of neurons. To explore this mechanism at the level of a single population, this paper employed a neural mass model, named the complete physiology-based model (cPBM), to reconstruct electroencephalographic (EEG) signals and to infer the changes in excitatory/inhibitory connections related to excitation-inhibition (E-I) balance based on an open dataset recorded for ten epileptic patients. Since epileptic signals display spectral characteristics, spectral dynamic causal modelling (DCM) was applied to quantify these frequency characteristics by maximizing the free energy in the framework of power spectral density (PSD) and estimating the cPBM parameters. In addition, to address the local maximum problem that DCM may suffer from, a hybrid deterministic DCM (H-DCM) approach was proposed, with a deterministic annealing-based scheme applied in two directions. The H-DCM approach adjusts the temperature introduced in the objective function by gradually decreasing the temperature to obtain relatively good initialization and then gradually increasing the temperature to search for a better estimation after each maximization. The results showed that (i) reconstructed EEG signals belonging to the three stages together with their PSDs can be reproduced from the estimated parameters of the cPBM; (ii) compared to DCM, traditional D-DCM and anti D-DCM, the proposed H-DCM shows higher free energies and lower root mean square error (RMSE), and it provides the best performance for all stages (e.g., the RMSEs between the reconstructed PSD computed from the reconstructed EEG signal and the sample PSD obtained from the real EEG signal are 0.33 ± 0.08, 0.67 ± 0.37 and 0.78 ± 0.57 in the interictal, preictal and ictal stages, respectively); and (iii) the transition from interictal to ictal activity can be explained by an increase in the connections between pyramidal cells and excitatory interneurons and between pyramidal cells and fast inhibitory interneurons, as well as a decrease in the self-loop connection of the fast inhibitory interneurons in the cPBM. Moreover, the E-I balance, defined as the ratio between the excitatory connection from pyramidal cells to fast inhibitory interneurons and the inhibitory connection with the self-loop of fast inhibitory interneurons, is also significantly increased during the epileptic seizure transition. Supplementary Information: The online version contains supplementary material available at 10.1007/s11571-023-09976-6.
ABSTRACT
Automatic emotion recognition based on multichannel Electroencephalography (EEG) holds great potential in advancing human-computer interaction. However, several significant challenges persist in existing research on algorithmic emotion recognition. These challenges include the need for a robust model to effectively learn discriminative node attributes over long paths, the exploration of ambiguous topological information in EEG channels and effective frequency bands, and the mapping between intrinsic data qualities and provided labels. To address these challenges, this study introduces the distribution-based uncertainty method to represent spatial dependencies and temporal-spectral relativeness in EEG signals based on Graph Convolutional Network (GCN) architecture that adaptively assigns weights to functional aggregate node features, enabling effective long-path capturing while mitigating over-smoothing phenomena. Moreover, the graph mixup technique is employed to enhance latent connected edges and mitigate noisy label issues. Furthermore, we integrate the uncertainty learning method with deep GCN weights in a one-way learning fashion, termed Connectivity Uncertainty GCN (CU-GCN). We evaluate our approach on two widely used datasets, namely SEED and SEEDIV, for emotion recognition tasks. The experimental results demonstrate the superiority of our methodology over previous methods, yielding positive and significant improvements. Ablation studies confirm the substantial contributions of each component to the overall performance.
ABSTRACT
Rapid identification of pathogens with higher sensitivity and specificity plays a significant role in maintaining public health, environmental monitoring, controlling food quality, and clinical diagnostics. Different methods have been widely used in food testing laboratories, quality control departments in food companies, hospitals, and clinical settings to identify pathogens. Some limitations in current pathogens detection methods are time-consuming, expensive, and laborious sample preparation, making it unsuitable for rapid detection. Microfluidics has emerged as a promising technology for biosensing applications due to its ability to precisely manipulate small volumes of fluids. Microfluidics platforms combined with spectroscopic techniques are capable of developing miniaturized devices that can detect and quantify pathogenic samples. The review focuses on the advancements in microfluidic devices integrated with spectroscopic methods for detecting bacterial microbes over the past five years. The review is based on several spectroscopic techniques, including fluorescence detection, surface-enhanced Raman scattering, and dynamic light scattering methods coupled with microfluidic platforms. The key detection principles of different approaches were discussed and summarized. Finally, the future possible directions and challenges in microfluidic-based spectroscopy for isolating and detecting pathogens using the latest innovations were also discussed.
ABSTRACT
Purpose: In age-related macular degeneration (AMD), choriocapillaris flow deficits (CCFDs) under soft drusen can be measured using established compensation strategies. This study investigated whether CCFDs can be quantified under calcified drusen (CaD). Methods: CCFDs were measured in normal eyes (n = 30) and AMD eyes with soft drusen (n = 30) or CaD (n = 30). CCFD density masks were generated to highlight regions with higher CCFDs. Masks were also generated for soft drusen and CaD based on both structural en face OCT images and corresponding B-scans. Dice similarity coefficients were calculated between the CCFD density masks and both the soft drusen and CaD masks. A phantom experiment was conducted to simulate the impact of light scattering that arises from CaD. Results: Area measurements of CCFDs were highly correlated with those of CaD but not soft drusen, suggesting an association between CaD and underlying CCFDs. However, unlike soft drusen, the detected optical coherence tomography (OCT) signals underlying CaD did not arise from the defined CC layer but were artifacts caused by the multiple scattering property of CaD. Phantom experiments showed that the presence of highly scattering material similar to the contents of CaD caused an artifactual scattering tail that falsely generated a signal in the CC structural layer but the underlying flow could not be detected. Similarly, CaD also caused an artifactual scattering tail and prevented the penetration of light into the choroid, resulting in en face hypotransmission defects and an inability to detect blood flow within the choriocapillaris. Upon resolution of the CaD, the CC perfusion became detectable. Conclusions: The high scattering property of CaD leads to a scattering tail under these drusen that gives the illusion of a quantifiable optical coherence tomography angiography signal, but this signal does not contain the angiographic information required to assess CCFDs. For this reason, CCFDs cannot be reliably measured under CaD, and CaD must be identified and excluded from macular CCFD measurements.
Subject(s)
Choroid , Fluorescein Angiography , Retinal Drusen , Tomography, Optical Coherence , Humans , Tomography, Optical Coherence/methods , Choroid/blood supply , Choroid/diagnostic imaging , Retinal Drusen/diagnostic imaging , Retinal Drusen/diagnosis , Female , Aged , Male , Fluorescein Angiography/methods , Regional Blood Flow/physiology , Calcinosis/diagnostic imaging , Calcinosis/diagnosis , Aged, 80 and over , Macular Degeneration/diagnosis , Macular Degeneration/physiopathology , Macular Degeneration/diagnostic imaging , Middle Aged , Phantoms, Imaging , Fundus OculiABSTRACT
PURPOSE: The association between the total macular burden of hyperreflective foci (HRF) in eyes with intermediate AMD (iAMD) and the onset of persistent choroidal hypertransmission defects (hyperTDs) was studied using swept-source optical coherence tomography (SS-OCT). DESIGN: Post hoc subgroup analysis of a prospective study. METHODS: A retrospective review of iAMD eyes from subjects enrolled in a prospective SS-OCT study was performed. All eyes underwent 6×6 mm SS-OCT angiography (SS-OCTA) imaging at baseline and follow-up visits. En face sub-retinal pigment epithelium (subRPE) slabs with segmentation boundaries positioned 64 to 400 µm beneath Bruch's membrane (BM) were used to identify persistent choroidal hyperTDs. None of the eyes had persistent hyperTDs at baseline. The same subRPE slab was used to identify choroidal hypotransmission defects (hypoTDs) attributable to HRF located either intraretinally (iHRF) or along the RPE (rpeHRF) based on corresponding B-scans. A semiautomated algorithm was used by 2 independent graders to validate and refine the HRF outlines. The HRF area and the drusen volume within a 5 mm fovea-centered circle were measured at each visit. RESULTS: The median follow-up time for the 171 eyes from 121 patients included in this study was 59.1 months (95% CI: 52.0-67.8 months). Of these, 149 eyes (87%) had HRF, and 82 (48%) developed at least one persistent hyperTD during the follow-up. Although univariable Cox regression analyses showed that both drusen volume and total HRF area were associated with the onset of the first persistent hyperTD, multivariable analysis showed that the area of total HRF was the sole significant predictor for the onset of hyperTDs (P < .001). ROC analysis identified an HRF area ≥ 0.07 mm² to predict the onset of persistent hyperTDs within 1 year with an area under the curve (AUC) of 0.661 (0.570-0.753), corresponding to a sensitivity of 55% and a specificity of 74% (P < .001). CONCLUSIONS: The total macular burden of HRF, which includes both the HRF along the RPE and within the retina, is an important predictor of disease progression from iAMD to the onset of persistent hyperTDs and should serve as a key OCT biomarker to select iAMD patients at high risk for disease progression in future clinical trials.
ABSTRACT
An all-solid fiber-tip Fabry-Perot interferometer (FPI) coated with a nickel film is proposed and experimentally verified for magnetic field sensing with high sensitivity. It is fabricated by splicing a segment of a thin-wall capillary tube to a standard single-mode fiber (SMF), then inserting a tiny segment of fiber with a smaller diameter into the capillary tube, and creating an ultra-narrow air-gap at the SMF end to form an FPI. When the device is exposed to magnetic field, the capillary tube is strained due to the magnetostrictive effect of the nickel film coated on its outer surface. In addition, owing to the unique breakpoint sensitivity-enhancement structure of the air-gap FPI, the elongation of the capillary tube whose length is over 100 times longer than the air-gap width is entirely transferred to the cavity length change of the FPI, and the sensor is extremely sensitive to the magnetic field as proved by our experiments, achieving a high sensitivity of up to 2.236 nm/mT for a linear magnetic field range from 40 to 60 mT, as well as a low-temperature cross-sensitivity of 56 µT/°C. The all-solid stable structure, compact size (total length of â¼3.0 mm), and reflective working mode with high magnetic field sensitivity indicate that this sensor has good application prospects.
ABSTRACT
PURPOSE: Swept-source OCT angiography (SS-OCTA) scans of eyes with age-related macular degeneration (AMD) were used to replace color, autofluorescence, infrared reflectance, and dye-based fundus angiographic imaging for the diagnosis and staging of AMD. Through the use of different algorithms with the SS-OCTA scans, both structural and angiographic information can be viewed and assessed using both cross sectional and en face imaging strategies. DESIGN: Presented at the 2022 Charles L. Schepens, MD, Lecture at the American Academy of Ophthalmology Retina Subspecialty Day, Chicago, Illinois, on September 30, 2022. PARTICIPANTS: Patients with AMD. METHODS: Review of published literature and ongoing clinical research using SS-OCTA imaging in AMD. MAIN OUTCOME MEASURES: Swept-source OCT angiography imaging of AMD at different stages of disease progression. RESULTS: Volumetric SS-OCTA dense raster scans were used to diagnose and stage both exudative and nonexudative AMD. In eyes with nonexudative AMD, a single SS-OCTA scan was used to detect and measure structural features in the macula such as the area and volume of both typical soft drusen and calcified drusen, the presence and location of hyperreflective foci, the presence of reticular pseudodrusen, also known as subretinal drusenoid deposits, the thickness of the outer retinal layer, the presence and thickness of basal laminar deposits, the presence and area of persistent choroidal hypertransmission defects, and the presence of treatment-naïve nonexudative macular neovascularization. In eyes with exudative AMD, the same SS-OCTA scan pattern was used to detect and measure the presence of macular fluid, the presence and type of macular neovascularization, and the response of exudation to treatment with vascular endothelial growth factor inhibitors. In addition, the same scan pattern was used to quantitate choriocapillaris (CC) perfusion, CC thickness, choroidal thickness, and the vascularity of the choroid. CONCLUSIONS: Compared with using several different instruments to perform multimodal imaging, a single SS-OCTA scan provides a convenient, comfortable, and comprehensive approach for obtaining qualitative and quantitative anatomic and angiographic information to monitor the onset, progression, and response to therapies in both nonexudative and exudative AMD. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.
ABSTRACT
Objective.Recent studies have shown that integrating inertial measurement unit (IMU) signals with surface electromyographic (sEMG) can greatly improve hand gesture recognition (HGR) performance in applications such as prosthetic control and rehabilitation training. However, current deep learning models for multimodal HGR encounter difficulties in invasive modal fusion, complex feature extraction from heterogeneous signals, and limited inter-subject model generalization. To address these challenges, this study aims to develop an end-to-end and inter-subject transferable model that utilizes non-invasively fused sEMG and acceleration (ACC) data.Approach.The proposed non-invasive modal fusion-transformer (NIMFT) model utilizes 1D-convolutional neural networks-based patch embedding for local information extraction and employs a multi-head cross-attention (MCA) mechanism to non-invasively integrate sEMG and ACC signals, stabilizing the variability induced by sEMG. The proposed architecture undergoes detailed ablation studies after hyperparameter tuning. Transfer learning is employed by fine-tuning a pre-trained model on new subject and a comparative analysis is performed between the fine-tuning and subject-specific model. Additionally, the performance of NIMFT is compared to state-of-the-art fusion models.Main results.The NIMFT model achieved recognition accuracies of 93.91%, 91.02%, and 95.56% on the three action sets in the Ninapro DB2 dataset. The proposed embedding method and MCA outperformed the traditional invasive modal fusion transformer by 2.01% (embedding) and 1.23% (fusion), respectively. In comparison to subject-specific models, the fine-tuning model exhibited the highest average accuracy improvement of 2.26%, achieving a final accuracy of 96.13%. Moreover, the NIMFT model demonstrated superiority in terms of accuracy, recall, precision, and F1-score compared to the latest modal fusion models with similar model scale.Significance.The NIMFT is a novel end-to-end HGR model, utilizes a non-invasive MCA mechanism to integrate long-range intermodal information effectively. Compared to recent modal fusion models, it demonstrates superior performance in inter-subject experiments and offers higher training efficiency and accuracy levels through transfer learning than subject-specific approaches.
Subject(s)
Gestures , Recognition, Psychology , Mental Recall , Electric Power Supplies , Neural Networks, Computer , ElectromyographyABSTRACT
The 12-lead electrocardiogram (ECG) is crucial in assessing patient decisions. However, portable ECG devices capable of acquiring a complete 12-lead ECG are scarce. For the first time, a deep learning-based method is proposed to reconstruct the 12-lead ECG from Frank leads (VX, VY, and VZ) or EASI leads (VES, VAS, and VAI). The innovative ECG reconstruction network called M2Eformer is composed of a 2D-ECGblock and a ProbDecoder module. The 2D-ECGblock module adaptively segments EASI leads into multi-periods based on frequency energy, transforming the 1D time series into a 2D tensor representing within-cycle and between-cycle variations. The ProbDecoder module aims to extract Probsparse self-attention and achieve one-step output for the target leads. Experimental results from comparing recorded and reconstructed 12-lead ECG using Frank leads indicate that M2Eformer outperforms traditional ECG reconstruction methods on a public database. In this study, a self-constructed database (10 healthy individuals + 15 patients) was utilized for the clinical diagnostic validation of ECG reconstructed from EASI leads. Subsequently, both the ECG reconstructed using EASI and the recorded 12-lead ECG were subjected to a double-blind diagnostic experiment conducted by three cardiologists. The overall diagnostic consensus among three cardiology experts, reaching a rate of 96%, indicates the significant utility of EASI-reconstructed 12-lead ECG in facilitating the diagnosis of cardiac conditions.
ABSTRACT
Elastic optical network (EON) is a critical transmission infrastructure for emerging new applications due to its spectral efficiency and flexibility. Nowadays, numerous confidential lightpaths (CLPs) are carried over EON to support security-sensitive users. However, they are vulnerable to crosstalk attacks at the optical layer, typically aimed at eavesdropping on the carried data or even disrupting connections. Due to the transparent nature of the optical signals, such attacks are difficult to detect and could last for a long time, resulting in data leakage even spreading throughout the network. This paper presents a novel routing and spectrum allocation (RSA) algorithm to protect CLPs from crosstalk attacks. We investigate intra-channel and inter-channel crosstalk attacks and develop a metric to quantify crosstalk leakage risks (CLRs). We first formulate an ILP model to plan CLPs with a minimum CLR. To solve the same problem for large-scale networks, we also propose a heuristic algorithm, i.e., crosstalk-attack-aware RSA. Results indicate that the proposed algorithm is capable of reducing CLR by 23%.
ABSTRACT
Organic photosensitizers (PSs) with aggregation-induced emission properties have great development potential in the integrated application of multi-mode diagnosis and treatment of photodynamic therapy (PDT) and photothermal therapy (PTT). However, preparing high-quality PSs with both optical and biological properties, high reactive oxygen species (ROS) and photothermal conversion ability are undoubtedly a great challenge. In this work, a series of pyridinium AIE PSs modified with benzophenone have been synthesized. A wide wavelength range of fluorescent materials was obtained by changing the conjugation and donor-acceptor strength. TPAPs5 has a significant advantage over similar compounds, and we have also identified the causes of high ROS generation and high photothermal conversion in terms of natural transition orbitals, excited state energy levels, ground-excited state configuration differences and recombination energy. Interestingly, migration of target sites was also found in biological imaging experiments, which also provided ideas for the design of double-targeted fluorescent probes. Therefore, the present work proposed an effective molecular design strategy for synergistic PDT and PTT therapy.
Subject(s)
Neoplasms , Photochemotherapy , Humans , Photosensitizing Agents/pharmacology , Photochemotherapy/methods , Reactive Oxygen Species , Neoplasms/drug therapyABSTRACT
Deep learning has significantly advanced text-to-speech (TTS) systems. These neural network-based systems have enhanced speech synthesis quality and are increasingly vital in applications like human-computer interaction. However, conventional TTS models still face challenges, as the synthesized speeches often lack naturalness and expressiveness. Additionally, the slow inference speed, reflecting low efficiency, contributes to the reduced voice quality. This paper introduces SynthRhythm-TTS (SR-TTS), an optimized Transformer-based structure designed to enhance synthesized speech. SR-TTS not only improves phonological quality and naturalness but also accelerates the speech generation process, thereby increasing inference efficiency. SR-TTS contains an encoder, a rhythm coordinator, and a decoder. In particular, a pre-duration predictor within the cadence coordinator and a self-attention-based feature predictor work together to enhance the naturalness and articulatory accuracy of speech. In addition, the introduction of causal convolution enhances the consistency of the time series. The cross-linguistic capability of SR-TTS is validated by training it on both English and Chinese corpora. Human evaluation shows that SR-TTS outperforms existing techniques in terms of speech quality and naturalness of expression. This technology is particularly suitable for applications that require high-quality natural speech, such as intelligent assistants, speech synthesized podcasts, and human-computer interaction.
ABSTRACT
BACKGROUND: Early and reliable identification of patients with sepsis who are at high risk of mortality is important to improve clinical outcomes. However, 3 major barriers to artificial intelligence (AI) models, including the lack of interpretability, the difficulty in generalizability, and the risk of automation bias, hinder the widespread adoption of AI models for use in clinical practice. OBJECTIVE: This study aimed to develop and validate (internally and externally) a conformal predictor of sepsis mortality risk in patients who are critically ill, leveraging AI-assisted prediction modeling. The proposed approach enables explaining the model output and assessing its confidence level. METHODS: We retrospectively extracted data on adult patients with sepsis from a database collected in a teaching hospital at Beth Israel Deaconess Medical Center for model training and internal validation. A large multicenter critical care database from the Philips eICU Research Institute was used for external validation. A total of 103 clinical features were extracted from the first day after admission. We developed an AI model using gradient-boosting machines to predict the mortality risk of sepsis and used Mondrian conformal prediction to estimate the prediction uncertainty. The Shapley additive explanation method was used to explain the model. RESULTS: A total of 16,746 (80%) patients from Beth Israel Deaconess Medical Center were used to train the model. When tested on the internal validation population of 4187 (20%) patients, the model achieved an area under the receiver operating characteristic curve of 0.858 (95% CI 0.845-0.871), which was reduced to 0.800 (95% CI 0.789-0.811) when externally validated on 10,362 patients from the Philips eICU database. At a specified confidence level of 90% for the internal validation cohort the percentage of error predictions (n=438) out of all predictions (n=4187) was 10.5%, with 1229 (29.4%) predictions requiring clinician review. In contrast, the AI model without conformal prediction made 1449 (34.6%) errors. When externally validated, more predictions (n=4004, 38.6%) were flagged for clinician review due to interdatabase heterogeneity. Nevertheless, the model still produced significantly lower error rates compared to the point predictions by AI (n=1221, 11.8% vs n=4540, 43.8%). The most important predictors identified in this predictive model were Acute Physiology Score III, age, urine output, vasopressors, and pulmonary infection. Clinically relevant risk factors contributing to a single patient were also examined to show how the risk arose. CONCLUSIONS: By combining model explanation and conformal prediction, AI-based systems can be better translated into medical practice for clinical decision-making.
Subject(s)
Artificial Intelligence , Sepsis , Adult , Humans , Clinical Decision-Making , Hospitals, Teaching , Retrospective Studies , Sepsis/diagnosis , Multicenter Studies as TopicABSTRACT
Early detection of acute kidney injury (AKI) may provide a crucial window of opportunity to prevent further injury, which helps improve clinical outcomes. This study aimed to develop a deep interpretable network for continuously predicting the 24-hour AKI risk in real-time and evaluate its performance internally and externally in critically ill patients. A total of 21,163 patients' electronic health records sourced from Beth Israel Deaconess Medical Center (BIDMC) were first included in building the model. Two external validation populations included 3025 patients from the Philips eICU Research Institute and 2625 patients from Zhongda Hospital Southeast University. A total of 152 intelligently engineered predictors were extracted on an hourly basis. The prediction model referred to as DeepAKI was designed with the basic framework of squeeze-and-excitation networks with dilated causal convolution embedded. The integrated gradients method was utilized to explain the prediction model. When performed on the internal validation set (3175 [15 %] patients from BIDMC) and the two external validation sets, DeepAKI obtained the area under the curve of 0.799 (95 % CI 0.791-0.806), 0.763 (95 % CI 0.755-0.771) and 0.676 (95 % CI 0.668-0.684) for continuousAKI prediction, respectively. For model interpretability, clinically relevant important variables contributing to the model prediction were informed, and individual explanations along the timeline were explored to show how AKI risk arose. The potential threats to generalisability in deep learning-based models when deployed across health systems in real-world settings were analyzed.
Subject(s)
Acute Kidney Injury , Critical Illness , Humans , Risk Assessment , Risk Factors , Patients , Acute Kidney Injury/diagnosis , Acute Kidney Injury/etiologyABSTRACT
Conductive additives are of great importance for the adequate utilization of active materials in all-solid-state lithium batteries by establishing conductive networks in the composite cathode. However, it usually causes severe interfacial side reactions with solid electrolytes, especially sulfide electrolytes, leading to sluggish ion transportation and accelerated performance degradation. Herein, a simple hydrogen thermal reduction process is proposed on a commonly used conductive additive Superâ P, which effectively removes the surface oxygen functional groups and weakens the interfacial side reactions with sulfide. With a small amount of 1â wt % reduced Superâ P, ASSLBs demonstrates a competitive capacity of 180.2â mAh g-1, which is much higher than the 130.8â mAh g-1 of untreated Superâ P. Impressively, reduced Superâ P based ASSLBs also exhibit a higher capacity retention of 81.8 % than 64.6 % of untreated Superâ P. The cathode interfacial chemical evolutions reveal that reduced Superâ P could effectively alleviate the side reactions of sulfide. Reduced Superâ P shows better reversible capacity compared to reduced carbon nanofiber with almost no loss of capacity retention, due to its more complete conductive network. Our results highlight the importance of oxygen-containing functional groups for conductive additives, lightening the prospect of low-cost 0D conductive additives for practical ASSLBs.
ABSTRACT
According to numerous reports, Trichinella spiralis (T. spiralis) and its antigens can reduce intestinal inflammation by modulating regulatory immunological responses in the host to maintain immune homeostasis. Galectin has been identified as a protein that is produced by T. spiralis, and its characterization revealed this protein has possible immune regulatory activity. However, whether recombinant T. spiralis galectin (rTs-gal) can cure dextran sulfate sodium (DSS)-induced colitis remains unknown. Here, the ability of rTs-gal to ameliorate experimental colitis in mice with inflammatory bowel disease (IBD) as well as the potential underlying mechanism were investigated. The disease activity index (DAI), colon shortening, inflammatory cell infiltration, and histological damage were used as indicators to monitor clinical symptoms of colitis. The results revealed that the administration of rTs-gal ameliorated these symptoms. According to Western blotting and ELISA results, rTs-gal may suppress the excessive inflammatory response-mediated induction of TLR4, MyD88, and NF-κB expression in the colon. Mice with colitis exhibit disruptions in the gut flora, including an increase in gram-negative bacteria, which in turn can result in increased lipopolysaccharide (LPS) production. However, injection of rTs-gal may inhibit changes in the gut microbiota, for example, by reducing the prevalence of Helicobacter and Bacteroides, which produce LPS. The findings of the present study revealed that rTs-gal may inhibit signalling pathways that involve enteric bacteria-derived LPS, TLR4, and NF-κB in mice with DSS-induced colitis and attenuate DSS-induced colitis in animals by modulating the gut microbiota. These findings shed additional light on the immunological processes underlying the beneficial effects of helminth-derived proteins in medicine.
Subject(s)
Colitis , Gastrointestinal Microbiome , Trichinella spiralis , Animals , Mice , Colitis/chemically induced , Colitis/pathology , Colitis/veterinary , Colon , Disease Models, Animal , Galectins/metabolism , Lipopolysaccharides/pharmacology , Mice, Inbred C57BL , NF-kappa B/metabolism , Toll-Like Receptor 4/metabolismABSTRACT
Noisy labels are often encountered in datasets, but learning with them is challenging. Although natural discrepancies between clean and mislabeled samples in a noisy category exist, most techniques in this field still gather them indiscriminately, which leads to their performances being partially robust. In this paper, we reveal both empirically and theoretically that the learning robustness can be improved by assuming deep features with the same labels follow a student distribution, resulting in a more intuitive method called student loss. By embedding the student distribution and exploiting the sharpness of its curve, our method is naturally data-selective and can offer extra strength to resist mislabeled samples. This ability makes clean samples aggregate tightly in the center, while mislabeled samples scatter, even if they share the same label. Additionally, we employ the metric learning strategy and develop a large-margin student (LT) loss for better capability. It should be noted that our approach is the first work that adopts the prior probability assumption in feature representation to decrease the contributions of mislabeled samples. This strategy can enhance various losses to join the student loss family, even if they have been robust losses. Experiments demonstrate that our approach is more effective in inaccurate supervision. Enhanced LT losses significantly outperform various state-of-the-art methods in most cases. Even huge improvements of over 50% can be obtained under some conditions.