pDenoiser: A Personalized Speech Enhancement Neural Network for Pre-hospital Emergency Medical Services.

Pre-hospital emergency medical service (EMS) tasks often come with complex and diverse noise interferences, posing challenges in implementing ASR-based medical technologies and hindering efficient and accurate telephonic communication. Among the different types of noise distortion, interfering speech is especially annoying. To address these issues, our aim is to develop a technology capable of extracting the intended speech content of the target physician from noisy and mixed audio during EMS tasks. In this work, we propose a monoaural personalized speech enhancement (PSE) method called pDenoiser, which is a real-time neural network that operates in the time domain. By leveraging the prior vocalization cues of emergency physicians, pDenoiser selectively enhances target speech components while suppressing noise and nontarget speech components, thereby improving speech quality and speech recognition accuracy under noisy conditions. We demonstrate the potential value of our approach through evaluations on both public general-domain test sets and our self-collected real-world EMS test sets. The experimental results are promising, as our model effectively promotes both speech quality and ASR performance under various conditions and outperforms related methods across multiple evaluation metrics. Our methodology will hopefully elevate EMS efficiency and fortify security against nontarget speech during EMS tasks.

Bi2Te3-Based Thermoelectric Modules for Efficient and Reliable Low-Grade Heat Recovery.

Bismuth-telluride-based alloy has long been considered as the most promising candidate for low-grade waste heat power generation. However, optimizing the thermoelectric performance of n-type Bi2Te3 is more challenging than that of p-type counterparts due to its greater sensitivity to texture, and thus limits the advancement of thermoelectric modules. Herein, the thermoelectric performance of n-type Bi2Te3 is enhanced by incorporating a small amount of CuGaTe2, resulting in a peak ZT of 1.25 and a distinguished average ZT of 1.02 (300-500 K). The decomposed Cu+ strengthens interlayer interaction, while Ga+ optimizes carrier concentration within an appropriate range. Simultaneously, the emerged numerous defects, such as small-angle grain boundaries, twin boundaries, and dislocations, significantly suppresses the lattice thermal conductivity. Based on the size optimization by finite element modelling, the constructed thermoelectric module yields a high conversion efficiency of 6.9% and output power density of 0.31 W cm-2 under a temperature gradient of 200 K. Even more crucially, the efficiency and output power little loss after subjecting the module to 40 thermal cycles lasting for 6 days. This study demonstrates the efficient and reliable Bi2Te3-based thermoelectric modules for broad applications in low-grade heat harvest.

Harnessing eCIRP by PS-OMe miR130: A promising shield against hemorrhage-induced lung injury.

INTRODUCTION: Hemorrhagic shock (HS) poses a life-threatening condition with the lungs being one of the most susceptible organs to its deleterious effects. Extracellular cold-inducible RNA binding protein (eCIRP) has emerged as a pivotal mediator of inflammation, and its release has been observed as a case of HS-induced tissue injury. Previous studies unveiled a promising engineered microRNA, designated PS-OMe miR130, which inhibits eCIRP, thereby safeguarding vital organs. In this study, we hypothesized that PS-OMe miR130 serves as a protective shield against HS-induced lung injury by curtailing the overzealous inflammatory immune response. METHODS: Hemorrhagic shock was induced in male C57BL6 mice by withdrawing blood via a femoral artery cannula to a mean arterial pressure of 30 mm Hg for 90 min. The mice were resuscitated with twice the shed blood volume with Ringer's Lactate solution. They were then treated intravenously with either PBS (vehicle) or 62.5 nmol PS-OMe miR130. At 4 h later, blood and lungs were harvested. RESULTS: Following PS-OMe miR130 treatment in HS mice, a substantial decrease was observed in serum injury markers including aspartate aminotransferase (AST), alanine aminotransferase (ALT), lactate dehydrogenase (LDH), and blood urea nitrogen (BUN). Serum IL-6 exhibited a similar reduction. In lung tissues, PS-OMe miR130 led to a significant decrease in the mRNA expressions of pro-inflammatory cytokines (IL-6, IL-1ß, and TNF-α), chemokines (KC and MIP-2), and an endothelial injury marker, E-selectin. PS-OMe miR130 also produced substantial inhibition of lung MPO activity and resulted in a marked reduction in lung injury as evidenced by histological evaluation. This was further confirmed by the observation that PS-OMe miR130 significantly reduced the presence of Ly6G-positive neutrophils and TUNEL-positive apoptotic cells. CONCLUSION: PS-OMe miR130 emerges as a potent safeguard against HS-induced lung injury by effectively inhibiting proinflammation and injuries, offering a promising therapeutic strategy in such critical clinical condition.

GCN-Based Risk Prediction for Necrosis Slide of Hepatocellular Carcinoma.

Hepatocellular carcinoma (HCC) is one of the most common cancers in the world which ranks fourth in cancer deaths. Primary pathological necrosis is an effective prognostic indicator for hepatocellular carcinoma. We propose a GCN-based approach that mimics the pathologist's perspective for global assessment of necrosis tissue distribution to analyze patient survival. Specifically, we introduced a graph convolutional neural network to construct a spatial map with necrotic tissue and tumor tissue as graph nodes, aiming to mine the contextual information between necrotic tissue in pathological sections. We used 1381 slides from 303 patients from the First Affiliated Hospital of Zhejiang University School to train the model and used TCGA-LIHC for external validation. The C-index of our method outperforms the baseline by about 4.45%, which proves that the information about the spatial distribution of necrosis learned by GCN is meaningful for guiding patient prognosis.

A NOVEL OLIGONUCLEOTIDE MRNA MIMIC ATTENUATES HEMORRHAGE-INDUCED ACUTE LUNG INJURY.

ABSTRACT: Hemorrhagic shock (HS) is accompanied by a pronounced activation of the inflammatory response in which acute lung injury (ALI) is one of the most frequent consequences. Among the pivotal orchestrators of this inflammatory cascade, extracellular cold-inducible RNA-binding protein (eCIRP) emerges as a noteworthy focal point, rendering it as a promising target for the management of inflammation and tissue injury. Recently, we have reported that oligonucleotide poly(A) mRNA mimic termed A 12 selectively binds to the RNA binding region of eCIRP and inhibits eCIRP binding to its receptor TLR4. Furthermore, in vivo administration of eCIRP induces lung injury in healthy mice and that mouse deficient in CIRP showed protection from inflammation-associated lung injury. We hypothesize that A 12 inhibits systemic inflammation and ALI in HS. To test the impacts of A 12 on systemic and lung inflammation, extent of inflammatory cellular infiltration and resultant lung damage were evaluated in a mouse model of HS. Male mice were subjected to controlled hemorrhage with a mean arterial pressure of 30 mm Hg for 90 min and then resuscitated with Ringer's lactate solution containing phosphate-buffered saline (vehicle) or A 12 at a dose of 4 nmol/g body weight (treatment). The infusion volume was twice that of the shed blood. At 4 h after resuscitation, mice were euthanized, and blood and lung tissues were harvested. Blood and tissue markers of inflammation and injury were evaluated. Serum markers of injury (lactate dehydrogenase, alanine transaminase, and blood urea nitrogen) and inflammation (TNF-α, IL-6) were increased after HS and A 12 treatment significantly decreased their levels. A 12 treatment also decreased lung levels of TNF-α, MIP-2, and KC mRNA expressions. Lung histological injury score, neutrophil infiltration (Ly6G staining and myeloperoxidase activity), and lung apoptosis were significantly attenuated after A 12 treatment. Our study suggests that the capacity of A 12 in attenuating HS-induced ALI and may provide novel perspectives in developing efficacious pharmaceutics for improving hemorrhage prognosis.

Gestational diabetes and risk of perinatal depression in low- and middle-income countries: a meta-analysis.

Background: The relationship between gestational diabetes (GDM) and the risk of depression has been thoroughly investigated in high-income countries on their financial basis, while it is largely unexplored in low- and middle- income countries. This meta-analysis aims to assess how GDM influences the risk of perinatal depression by searching multiple electronic databases for studies measuring the odds ratios between them in low- and middle-income countries. Methods: Two independent reviewers searched multiple electronic databases for studies that investigated GDM and perinatal mental disorders on August 31, 2023. Pooled odds ratios (ORs) and confidence intervals (CIs) were calculated using the random effect model. Subgroup analyses were further conducted based on the type of study design and country income level. Results: In total, 16 observational studies met the inclusion criteria. Only the number of studies on depression (n=10) satisfied the conditions to conduct a meta-analysis, showing the relationship between mental illness and GDM has been overlooked in low- and middle-income countries. Evidence shows an elevated risk of perinatal depression in women with GDM (pooled OR 1.92; 95% CI 1.24, 2.97; 10 studies). The increased risk of perinatal depression in patients with GDM was not significantly different between cross-sectional and prospective design. Country income level is a significant factor that adversely influences the risk of perinatal depression in GDM patients. Conclusion: Our findings suggested that women with GDM are vulnerable to perinatal depressive symptoms, and a deeper understanding of potential risk factors and mechanisms may help inform strategies aimed at prevention of exposure to these complications during pregnancy.

A Noise-Induced Hearing Loss Prediction Model Based on Asymmetric Convolution for Workers Exposed to Complex Industrial Noise.

OBJECTIVES: Current approaches for evaluating noise-induced hearing loss (NIHL), such as the International Standards Organization 1999 (ISO) 1999 prediction model, rely mainly on noise energy and exposure time, thus ignoring the intricate time-frequency characteristics of noise, which also play an important role in NIHL evaluation. In this study, an innovative NIHL prediction model based on temporal and spectral feature extraction using an asymmetric convolution algorithm is proposed. DESIGN: Personal data and individual occupational noise records from 2214 workers across 23 factories in Zhejiang Province, China, were used in this study. In addition to traditional metrics like noise energy and exposure duration, the importance of time-frequency features in NIHL assessment was also emphasized. To capture these features, operations such as random sampling, windowing, short-time Fourier transform, and splicing were performed to create time-frequency spectrograms from noise recordings. Two asymmetric convolution kernels then were used to extract these critical features. These features, combined with personal information (e.g., age, length of service) in various configurations, were used as model inputs. The optimal network structure was selected based on the area under the curve (AUC) from 10-fold cross-validation, alongside the Wilcoxon signed ranks test. The proposed model was compared with the support vector machine (SVM) and ISO 1999 models, and the superiority of the new approach was verified by ablation experiments. RESULTS: The proposed model had an AUC of 0.7768 ± 0.0223 (mean ± SD), outperforming both the SVM model (AUC: 0.7504 ± 0.0273) and the ISO 1999 model (AUC: 0.5094 ± 0.0071). Wilcoxon signed ranks tests confirmed the significant improvement of the proposed model ( p = 0.0025 compared with ISO 1999, and p = 0.00142 compared with SVM). CONCLUSIONS: This study introduced a new NIHL prediction method that provides deeper insights into industrial noise exposure data. The results demonstrated the superior performance of the new model over ISO 1999 and SVM models. By combining time-frequency features and personal information, the proposed approach bridged the gap between conventional noise assessment and machine learning-based methods, effectively improving the ability to protect workers' hearing.

A Personal Healthcare Knowledge Graph Framework for Diagnosis of Pelvic Masses Diseases.

A Personal Health Knowledge Graph (PHKG) facilitates the efficient integration of potential diagnostic clues from patients' electronic health records with medical knowledge, establishing diagnostic reasoning paths and ensuring accurate, individually interpretable results in the diagnosis of pelvic masses.

Design of Household Cognitive Level Assessment System Based on Grip Force and Finger Force Distribution.

In this paper we designed a household cognitive level assessment system based on finger force distribution. The system evaluates the user's current cognitive level according to the degree of matching between the characteristics of user's grip force and finger force distribution data and the characteristics in the database. The system based on finger force distribution will greatly reduce the space and economic cost of household cognitive level assessment.

Design and Application of Multi-Center Clinical Research Platform for Phenotyping of Voriconazole Hepatotoxicity.

We introduce a phenotyping pipeline for voriconazole hepatotoxicity based on a multi-center clinical research platform. Using the platform's queue construction, feature generation, and feature screening functions, 52 features were obtained for model training. The prediction model of voriconazole hepatotoxicity was obtained by using the model training and evaluation functions of the platform. Important risk factors and protection factors of the model were listed.

Does a Digital Health Application Could Be the Supplement to the Influenza Surveillance System?

Epidemics of seasonal influenza is a major public health concern in china. Historical percentage of influenza-like illness (ILI%) from CDC and health enquiry data from a health-related application were collected, when combining the real-time ILI-related search queries with one-week ago's ILI%, it was able to predict the trend of ILI correctly and timely. Digital health application is potentializing a supplement to the traditional influenza surveillance systems in China.

A Post-Marketing Drug Evaluation Framework Based on Real-World Electronic Health Records Data.

Real-world data (RWD) could be a new way to evaluate the safety and efficacy of post-marketing drugs, while there is no common method for how to use RWD for drug evaluation. In this paper, we present a framework for real-world drug evaluation based on electronic medical record (EHR) data. We designed a data model customized for post-marketing drug evaluation and a unified post-marketing drug evaluation pipeline. The proposed framework can be applied to drug evaluations with different study paradigms for different purposes by flexible use of the proposed data model and pipeline. A prototype system has been developed according to the framework. Real-world EHRs in a tertiary hospital in China between 2010 and 2020 were converted to the proposed data model, and as a test case, we conducted a research on the risk of allergic reactions to cefodizime and ceftriaxone using the prototype system.

Temporal Phenotyping for End-Stage Renal Disease Using Longitudinal Electronic Health Records.

End Stage Renal Disease (ESRD) is a highly heterogeneous disease with significant differences in prevalence, mortality, complications, and treatment modalities across age, sex, race, and ethnicity. An improved knowledge of disease characteristics results from the use of a data-driven phenotypic classification strategy to identify patients of different subtypes and expose the clinical traits of different subtypes. This study used topic models and process mining techniques to perform subtyping of ESRD patients on hemodialysis based on real-world longitudinal electronic health record data. The mined subtypes are interpretable and clinically significant, and they can reflect differences in the progression of the disease state and clinical outcomes.

Construction of a Prediction Model for Voriconazole-Induced Hepatotoxicity Based on Mixed-Effects Random Forest.

Voriconazole is a second-generation triazole antifungal agent with strong antifungal activity against a variety of clinically significant pathogens. Controlling blood concentrations within guideline limits through blood concentration monitoring can reduce the probability of hepatotoxicity in patients with voriconazole. However, statistical analysis based on real-world data found that there were still several patients who had blood concentration monitoring developed voriconazole induced hepatotoxicity. Therefore, it has important clinical significance to predict whether hepatotoxicity will occur in patients who meet the guidelines for voriconazole plasma concentration requirements. In this study, based on real-world data, the mixed-effects random forest was used to analyze the electronic medical record data of patients who met the guidelines for voriconazole blood concentration requirements during hospitalization, and a predictive model was constructed to predict whether patients would develop hepatotoxicity within 30 days after using voriconazole.

A Hemodialysis Mortality Prediction Model Based on Active Contrastive Learning.

Hemodialysis (HD) is the main treatment for end-stage renal disease with high mortality and heavy economic burdens. Predicting the mortality risk in patients undergoing maintenance HD and identifying high-risk patients are critical to enable early intervention and improve quality of life. In this study, we proposed a two-stage protocol based on electronic health record (EHR) data to predict mortality risk of maintenance HD patients. First, we developed a multilayer perceptron (MLP) model to predict mortality risk. Second, an Active Contrastive Learning (ACL) method was proposed to select sample pairs and optimize the representation space to improve the prediction performance of the MLP model. Our ACL method outperforms other methods and has an average F1-score of 0.820 and an average area under the receiver operating characteristic curve of 0.853. This work is generalizable to analyses of cross-sectional EHR data, while this two-stage approach can be applied to other diseases as well.

Physician-Centered EHR Data Utilization: A Pilot Study.

The utilization of vast amounts of EHR data is crucial to the studies in medical informatics. Physicians are medical participants who directly record clinical data into EHR with their personal expertise, making their roles essential in follow-up data utilization, which current studies have yet to recognize. This paper proposes a physician-centered perspective for EHR data utilization and emphasizes the feasibility and potentiality of digging into physicians' latent decision patterns in EHR. To support our proposal, we design a physician-centered CDS approach named PhyC and test it on a real-world EHR dataset. Experiments show that PhyC performs significantly better in the auxiliary diagnosis of multiple diseases than globally learned models. Discussions on experimental results suggest that physician-centered data utilization can help to derive more objective CDS models, while more means for utilization need further exploration.

Graph Neural Network Based Multi-Label Hierarchical Classification for Disease Predictions in General Practice.

General practitioners are supposed to be better diagnostics to detect patients with serious diseases earlier, and conduct early interventions and appropriate referrals of patients. However, in the current general practice, primary general practitioners lack sufficient clinical experiences, and the correct rate of general disease diagnosis is low. To assist general practitioners in diagnosis, this paper proposes a multi-label hierarchical classification method based on graph neural network, which integrates medical knowledge and electronic health record (EHR) data to build a disease prediction model. The experimental results based on data consist of 231,783 visits from EHR show that the proposed model outperforms all baseline models in the general disease prediction task with a top-3 recall of 0.865. The interpretable results of the model can effectively help clinicians understand the basis of the model's decision-making.

Personalized Prediction of Parkinson's Disease Progression Based on Deep Gaussian Processes.

Parkinson's disease is a chronic progressive neurodegenerative disease with highly heterogeneous symptoms and progression. It is helpful for patient management to establish a personalized model that integrates heterogeneous interpretation methods to predict disease progression. In the study, we propose a novel approach based on a multi-task learning framework to divide Parkinson's disease progression modeling into an unsupervised clustering task and a disease progression prediction task. On the one hand, the method can cluster patients with different progression trajectories and discover new progression patterns of Parkinson's disease. On the other hand, the discovery of new progression patterns helps to predict the future progression of Parkinson's disease markers more accurately through parameter sharing among multiple tasks. We discovered three different Parkinson's disease progression patterns and achieved better prediction performance (MAE=5.015, RMSE=7.284, r2=0.727) than previously proposed methods on Parkinson's Progression Markers Initiative datasets, which is a longitudinal cohort study with newly diagnosed Parkinson's disease.

A Multi-Resolution Denoising Method for Low-Dose CT Based on the Reconstruction of Wavelet High-Frequency Channel.

Computed tomography (CT) is widely applied in contemporary clinic. Due to the radiation risks carried by X-rays, the imaging and post-processing methods of low-dose CT (LDCT) become popular topics in academia and industrial community. Generally, LDCT presents strong noise and artifacts, while existing algorithms cannot completely overcome the blurring effects and meantime reduce the noise. The proposed method enables CT extend to independent frequency channels by wavelet transformation, then two separate networks are established for low-frequency denoising and high-frequency reconstruction. The clean signals from high-frequency channel are reconstructed through channel translation, which is essentially effective in preserving detailed structures. The public dataset from Mayo Clinic was used for model training and testing. The experiments showed that the proposed method achieves a better quantitative result (PSNR: 37.42dB, SSIM: 0.8990) and details recovery visually, which demonstrates our framework can better restore the detailed features while significantly suppressing the noise.

Hierarchical Label Distribution Learning for Disease Prediction.

The prediction of disease can facilitate early intervention, comprehensive diagnosis and treatment, thereby benefiting healthcare and reducing medical costs. While single class and multi-class learning methods have been applied for disease prediction, they are inadequate in distinguishing between primary and secondary diagnoses, which is crucial for treatments. In this paper, label distribution is suggested to describe the diagnosis, which assigns the description degree to quantify the diagnosis. Additionally, a novel hierarchical label distribution learning (HLDL) model is proposed to make fine-grained predictions based on the hierarchical classification of diseases, taking into account the relationship among diseases. The experimental results on real-world datasets demonstrate that the HLDL model outperforms the baselines with statistical significance.