Discrimination Between Glioblastoma and Solitary Brain Metastasis Using Conventional MRI and Diffusion-Weighted Imaging Based on a Deep Learning Algorithm.

This study aims to develop and validate a deep learning (DL) model to differentiate glioblastoma from single brain metastasis (BM) using conventional MRI combined with diffusion-weighted imaging (DWI). Preoperative conventional MRI and DWI of 202 patients with solitary brain tumor (104 glioblastoma and 98 BM) were retrospectively obtained between February 2016 and September 2022. The data were divided into training and validation sets in a 7:3 ratio. An additional 32 patients (19 glioblastoma and 13 BM) from a different hospital were considered testing set. Single-MRI-sequence DL models were developed using the 3D residual network-18 architecture in tumoral (T model) and tumoral + peritumoral regions (T&P model). Furthermore, the combination model based on conventional MRI and DWI was developed. The area under the receiver operating characteristic curve (AUC) was used to assess the classification performance. The attention area of the model was visualized as a heatmap by gradient-weighted class activation mapping technique. For the single-MRI-sequence DL model, the T2WI sequence achieved the highest AUC in the validation set with either T models (0.889) or T&P models (0.934). In the combination models of the T&P model, the model of DWI combined with T2WI and contrast-enhanced T1WI showed increased AUC of 0.949 and 0.930 compared with that of single-MRI sequences in the validation set, respectively. And the highest AUC (0.956) was achieved by combined contrast-enhanced T1WI, T2WI, and DWI. In the heatmap, the central region of the tumoral was hotter and received more attention than other areas and was more important for differentiating glioblastoma from BM. A conventional MRI-based DL model could differentiate glioblastoma from solitary BM, and the combination models improved classification performance.

Chalcone derivatives ameliorate lipopolysaccharide-induced acute lung injury and inflammation by targeting MD2.

Acute lung injury (ALI) and its severe form acute respiratory distress syndrome (ARDS) are known as the common causes of respiratory failure in critically ill patients. Myeloid differentiation 2 (MD2), a co-receptor of toll like receptor 4 (TLR4), plays an important role in LPS-induced ALI in mice. Since MD2 inhibition by pharmacological inhibitors or gene knockout significantly attenuates ALI in animal models, MD2 has become an attractive target for the treatment of ALI. In this study we identified two chalcone-derived compounds, 7w and 7x, as new MD2 inhibitors, and investigated the therapeutic effects of 7x and 7w in LPS-induced ALI mouse model. In molecular docking analysis we found that 7w and 7x, formed pi-pi stacking interactions with Phe151 residue of the MD2 protein. The direct binding was confirmed by surface plasmon resonance analysis (with KD value of 96.2 and 31.2 µM, respectively) and by bis-ANS displacement assay. 7w and 7x (2.5, 10 µM) also dose-dependently inhibited the interaction between lipopolysaccharide (LPS) and rhMD2 and LPS-MD2-TLR4 complex formation. In mouse peritoneal macrophages, 7w and 7x (1.25-10 µM) dose-dependently inhibited LPS-induced inflammatory responses, MAPKs (JNK, ERK and P38) phosphorylation as well as NF-κB activation. Finally, oral administration of 7w or 7x (10 mg ·kg-1 per day, for 7 days prior LPS challenge) in ALI mouse model significantly alleviated LPS-induced lung injury, pulmonary edema, lung permeability, inflammatory cells infiltration, inflammatory cytokines expression and MD2/TLR4 complex formation. In summary, we identify 7w and 7x as new MD2 inhibitors to inhibit inflammatory response both in vitro and in vivo, proving the therapeutic potential of 7w and 7x for ALI and inflammatory diseases.

Multienzyme detection and in-situ monitoring of enzyme activity by bending CE using quantum dots-based polypeptide substrate.

Multienzyme detection and monitoring enzyme activity in situ are significant for the disease to diagnose. This study aims to develop a quantum dots (QDs)-based nanoprobe Cyanine5-DDDLEVLFQFPGLVPRGSGGHHHHHH-QDs (Cy5-LEVLVP-QD), which is able to detect two enzymes inside a bent capillary using CE. Cy5-LEVLVP and QDs were allowed to bind with each other through metal affinity interaction and then injected the Cy5-LEVLVP-QD complex into a capillary with different bends, followed by related enzyme that can cleave the Cy5-LEVLVP peptide. The fluorescence of Cy5 was excited by QDs due to Förster resonance energy transfer. By monitoring the peaks produced by the original Cy5-LEVLVP-QD complex and a significant fluorescence change, sensitive analysis of two different enzymes was conducted. Therefore, the novel approach of using capillaries with semicircular bends could prove particularly useful for enzyme investigating in disease.

Inhibition of MyD88 by LM8 Attenuates Obesity-Induced Cardiac Injury.

Obesity-induced cardiomyopathy involves chronic and sustained inflammation. The toll-like receptor 4 (TLR4) signaling pathway can associate innate immunity with obesity. Myeloid differentiation primary response 88 (MyD88), an indispensable downstream adaptor molecule of TLR4, has been reported to mediate obesity complications. However, whether inhibition of MyD88 can mitigate obesity-induced heart injury remains unclear. LM8, a new MyD88 inhibitor, exhibits prominent anti-inflammatory activity in lipopolysaccharide-treated macrophages. In this study, the protective effects of LM8 on a high-fat diet (HFD)-induced heart injury were assessed in a mouse model of obesity. As suggested from the achieved results, LM8 treatment alleviated HFD-induced pathological and functional damages of the heart in mice. Meantime, the treatment of mice with LM8 could significantly inhibit myocardial hypertrophy, fibrosis, inflammatory cytokines expression, and inflammatory cell infiltration induced by HFD. Besides, LM8 administration inhibited the formation of MyD88/TLR4 complex, phosphorylation of ERK, and activation of nuclear factor-κB induced by HFD. According to the achieved results, MyD88 inhibitor LM8 ameliorated obesity-induced heart injury by inhibiting MyD88-ERK/nuclear factor-κB dependent cardiac inflammatory pathways. Furthermore, targeting MyD88 might be a candidate of a therapeutic method to treat obesity-induced heart injury.

L6H9 attenuates LPS-induced acute lung injury in rats through targeting MD2.

Acute lung injury (ALI) is a clinical syndrome characterized by respiratory failure and acute inflammatory response. Myeloid differentiation protein 2 (MD2) has been reported to play a pivotal role in the recognition of LPS and LPS-mediates inflammatory response. There have been no clinically effective therapeutic drugs for ALI. L6H9, an inhibitor of MD2, showed anti-inflammatory effects and cardiac protective activity. However, its effect on ALI has not been elucidated. In this study, intratracheal instillation of LPS was employed to induce ALI in rats. L6H9 pretreatment attenuates LPS-induced pathological variations in lung tissue and pulmonary edema. LPS instillation enhanced lung microvascular permeability, thereby causing inflammatory cells flow into bronchoalveolar lavage fluid (BALF). However, L6H9 inhibited the LPS-induced upregulation of total protein concentration and the number of inflammatory cells in BALF. In the meantime, macrophages infiltration in lung tissue induced by LPS was also mitigated by L6H9 treatment. Furthermore, L6H9 suppressed LPS-induced inflammatory cytokines expression in BALF, serum, and lung tissue. It is noteworthy that LPS-induced MD2/TLR4 complex formation was inhibited by L6H9 in lung tissue. On the whole, these results show that L6H9 can attenuate LPS-induced ALI in vivo by targeting MD2. Our study provide new candidate for the treatment of ALI.

Resolving quantum dots and peptide assembly and disassembly using bending capillary electrophoresis.

Despite the numerous techniques developed for the studying nanoparticle and peptide interaction nowadays, sensitive and convenient assay in the process of flow, especially to simulate the self-assembly of quantum dots (QDs) and peptide inflow in blood vessels, still remains big challenges. Here, we report a novel assay for studying the self-assembly of QDs and peptide, based on CE using a bending capillary. We demonstrate that the semicircles numbers of the bending capillary affect the self-assembly kinetics of CdSe/ZnS QDs and ATTO-D3 LVPRGSGP9 G2 H6 peptide. Moreover, benefitting from this novel assay, the effect of the position on the self-assembly has also been realized. More importantly, we also demonstrate that this novel assay can be used for studying the stability of the QDs-peptide complex inflow. We believe that our novel assay proposed in this work could be further used as a general strategy for the studying nanoparticle-biomolecule interaction or biomolecule-biomolecule interaction.

Deep Learning Techniques for Medical Image Segmentation: Achievements and Challenges.

Deep learning-based image segmentation is by now firmly established as a robust tool in image segmentation. It has been widely used to separate homogeneous areas as the first and critical component of diagnosis and treatment pipeline. In this article, we present a critical appraisal of popular methods that have employed deep-learning techniques for medical image segmentation. Moreover, we summarize the most common challenges incurred and suggest possible solutions.

Myeloid Differentiation Protein 2 Mediates Angiotensin II-Induced Liver Inflammation and Fibrosis in Mice.

Angiotensin II (Ang II) participates in the pathogenesis of liver injury. Our previous publications reported that myeloid differentiation protein 2 (MD2) mediates Ang II-induced cardiac and kidney inflammation by directly binding to Ang II. Thus, we hypothesize that MD2 is critical to Ang II-induced liver injury. Subcutaneous injections of Ang II for 8 weeks were adopted to build the liver injury model. With a specific MD2 inhibitor L6H21 and MD2 knockout mice, we reported that MD2 inhibition and knockout significantly mitigate liver inflammation and fibrosis in mice injected with Ang II. To be more specific, the functional and pathological damages induced by Ang II were mitigated by L6H21 or MD2 knockout. MD2 knockout or L6H21 administration inhibited the Ang II-induced upregulation of fibrosis markers, inflammatory cytokines, and adhesion molecules in gene or protein levels. The activation of NF-κB and Extracellular signal-regulated kinases (ERK) induced by Ang II was also reversed by L6H21 treatment or MD2 deficiency. Note that the co-immunoprecipitation study showed that L6H21 downregulated the ANG II-induced toll-like receptor 4 (TLR4)/MD2 complex in liver tissues while having no effects on MD2 expression. Our results reported the critical role of MD2 in the progress of liver injury and suggested that MD2 is a potential therapeutic target for liver injury.

Clinical and Molecular Features of Thiazide-Induced Hyponatremia.

PURPOSE OF REVIEW: Hypertension affects more than 30% of the world's adult population and thiazide (and thiazide-like) diuretics are amongst the most widely used, effective, and least costly treatments available, with all-cause mortality benefits equivalent to angiotensin-converting enzyme inhibitors or calcium channel antagonists. A minority of patients develop thiazide-induced hyponatremia (TIH) and this is largely unpredictable at the point of thiazide prescription. In some cases, TIH can cause debilitating symptoms and require hospital admission. Although TIH affects only a minority of patients exposed to thiazides, the high prevalence of hypertension leads to TIH being the most common cause of drug-induced hyponatremia requiring hospital admission in the UK. This review examines current clinical and scientific understanding of TIH. Consideration is given to demographic associations, limitations of current electrolyte monitoring regimens, clinical presentation, the phenotype evident on routine clinical blood and urine tests as well as more extensive analyses of blood and urine in research settings, recent genetic associations with TIH, and thoughts on management of the condition. RECENT FINDINGS: Recent genetic and phenotyping analysis has suggested that prostaglandin E2 pathways in the collecting duct may have a role in the development of TIH in a subgroup of patients. Greater understanding of the molecular pathophysiology of TIH raises the prospect of pre-prescription TIH risk profiling and may offer novel insights into how TIH may be avoided, prevented and treated. The rising prevalence of hypertension and the widespread use of thiazides mean that further understanding of TIH will continue to be a pressing issue for patients, physicians, and scientists alike for the foreseeable future.

Agent-based modeling of oxygen-responsive transcription factors in Escherichia coli.

In the presence of oxygen (O2) the model bacterium Escherichia coli is able to conserve energy by aerobic respiration. Two major terminal oxidases are involved in this process - Cyo has a relatively low affinity for O2 but is able to pump protons and hence is energetically efficient; Cyd has a high affinity for O2 but does not pump protons. When E. coli encounters environments with different O2 availabilities, the expression of the genes encoding the alternative terminal oxidases, the cydAB and cyoABCDE operons, are regulated by two O2-responsive transcription factors, ArcA (an indirect O2 sensor) and FNR (a direct O2 sensor). It has been suggested that O2-consumption by the terminal oxidases located at the cytoplasmic membrane significantly affects the activities of ArcA and FNR in the bacterial nucleoid. In this study, an agent-based modeling approach has been taken to spatially simulate the uptake and consumption of O2 by E. coli and the consequent modulation of ArcA and FNR activities based on experimental data obtained from highly controlled chemostat cultures. The molecules of O2, transcription factors and terminal oxidases are treated as individual agents and their behaviors and interactions are imitated in a simulated 3-D E. coli cell. The model implies that there are two barriers that dampen the response of FNR to O2, i.e. consumption of O2 at the membrane by the terminal oxidases and reaction of O2 with cytoplasmic FNR. Analysis of FNR variants suggested that the monomer-dimer transition is the key step in FNR-mediated repression of gene expression.

Estimation of the benchmark dose of urinary cadmium as the reference level for renal dysfunction: a large sample study in five cadmium polluted areas in China.

BACKGROUND: Itai-itai disease primarily results from cadmium (Cd) exposure and is known as one of the four major pollution diseases in Japan. Cd pollution is more serious in several areas of China than in Japan. However, there is still a lack of information regarding the threshold level of Cd exposure for the adverse health effects in the general Chinese population. This study aims to evaluate the reference value of urinary Cd (UCd) for renal dysfunction in a Chinese population as the benchmark dose lower confidence limit (BMDL) based on a large sample survey. METHODS: A total of 6103 participants who lived in five Cd polluted areas of China participated in this study. We analyzed UCd levels as a biomarker of exposure and urinary ß2-microglobulin (Uß2-MG) levels as a renal tubular effect biomarker. The BMD studies were performed using BMD software. The benchmark response (BMR) was defined as a 10% additional risk above the background. RESULTS: There was a positive correlation between the UCd levels and the prevalence of Uß2-MG. The BMD of UCd for Uß2-MG was estimated for each province. The findings showed that the BMD levels were related to the participants' geographic region, which may be partially due to the large differences in Cd exposure level, ethnic group, lifestyle and diet of the sample population in these study areas. The reference level of UCd for the renal effects was further evaluated by combining the five sets of data from all 6103 subjects. The overall BMDLs of UCd for Uß2-MG with an excess risk of 10% were 2.00 µg/g creatinine (µg/g cr) in males and 1.69 µg/g cr in females, which were significantly lower than the World Health Organization (WHO) threshold level of 5 µg/g cr for Cd-related renal effects. CONCLUSIONS: The selection of the sample population and geographic region affected the BMDL evaluation. Based on the findings of this survey of a large sample population, the UCd BMDLs for Uß2-MG in males with BMRs at 10% were 2.00 µg/g cr. The BMD was slightly lower in females, which indicated that females may be relatively more sensitive to Cd exposure than males.

1D structure of Y2O3:Eu nanorods: controllable synthesis, growth mechanisms and luminescence properties.

Y2O3O:Eu nanorods were successfully synthesized by a facile and effective hydrothermal method in the presence of P123 (EO106PO70EO106) as the surfactant followed by a subsequent heat treatment process. The scanning electron microscopy (SEM) and transmission electron microscopy (TEM) images indicate that the as-prepared samples consist of nanorods with diameters ranging from 80 nm to 100 nm and grow along the (100) direction. The growth mechanism of the as-obtained Y2O3:Eu nanorods was proposed on the basis of pH-dependent experiments. It is found that the pH is a crucial factor in determining the phase, morphology and luminescence properties of Y2O3:Eu nanorods. The luminescent spectra of Y2O3:Eu nanorods show the strong characteristic dominant emission of the Eu3+ ions at 613 nm.

Synthesis, phase structure and up-conversion luminescence of NaYF4:Yb3+, Er3+/Tm3+ nanorods.

Upconversion luminescent NaYF4:Yb3+, Er3+/Tm3+ nanocrystals were successfully synthesized via a facile and one-pot solvothermal method using oleic acid/oleylamine (OA/OM) as surfactants. The effects of synthetic parameters including rare earth ion doping concentrations and temperatures on the crystal phase structure, size and shape of NaYF4:Yb3+, Er3+/Tm3+ nanocrystals were systematically investigated. By modulating the synthetic parameters, the shape of NaYF4:Yb3+, Er3+/Tm3+ nanocrystals were controlled in forms of nanorods and nanowires. The reaction temperature has large effects on the phase structure of NaYF4:Yb3+, Er+/Tm3+ nanorods, exhibiting a phase transformation from cubic phase (alpha-) in low temperatures to hexagonal phase (beta-) in high temperatures. Moreover, the upconversion luminescence of NaYF4:Yb3+, Er3+/Tm3+ nanocrystals was found to be dependent on the rare earth ion doping concentrations and temperatures.

Deep local-to-global feature learning for medical image super-resolution.

Medical images play a vital role in medical analysis by providing crucial information about patients' pathological conditions. However, the quality of these images can be compromised by many factors, such as limited resolution of the instruments, artifacts caused by movements, and the complexity of the scanned areas. As a result, low-resolution (LR) images cannot provide sufficient information for diagnosis. To address this issue, researchers have attempted to apply image super-resolution (SR) techniques to restore the high-resolution (HR) images from their LR counterparts. However, these techniques are designed for generic images, and thus suffer from many challenges unique to medical images. An obvious one is the diversity of the scanned objects; for example, the organs, tissues, and vessels typically appear in different sizes and shapes, and are thus hard to restore with standard convolution neural networks (CNNs). In this paper, we develop a dynamic-local learning framework to capture the details of these diverse areas, consisting of deformable convolutions with adjustable kernel shapes. Moreover, the global information between the tissues and organs is vital for medical diagnosis. To preserve global information, we propose pixel-pixel and patch-patch global learning using a non-local mechanism and a vision transformer (ViT), respectively. The result is a novel CNN-ViT neural network with Local-to-Global feature learning for medical image SR, referred to as LGSR, which can accurately restore both local details and global information. We evaluate our method on six public datasets and one large-scale private dataset, which include five different types of medical images (i.e., Ultrasound, OCT, Endoscope, CT, and MRI images). Experiments show that the proposed method achieves superior PSNR/SSIM and visual performance than the state of the arts with competitive computational costs, measured in network parameters, runtime, and FLOPs. What is more, the experiment conducted on OCT image segmentation for the downstream task demonstrates a significantly positive performance effect of LGSR.

Synthesis of Monodisperse Mesoporous Carbon Spheres/EPDM Rubber Composites and Their Enhancement Mechanical Properties.

Monodisperse mesoporous carbon spheres (MCS) were synthesized and their potential applications in ethylene propylene diene monomer (EPDM) foam were evaluated. The obtained MCS exhibited a high specific surface area ranging from 621-to 735 m2/g along with large pore sizes. It was observed that the incorporation of MCS into EPDM foam rubber significantly enhances its mechanical properties. The prepared MCS-40 rubber composites exhibit the highest tear strength of 210 N/m and tensile strength of 132.72 kPa, surpassing those of other samples. The enhancement mechanism was further investigated by employing computer simulation technology. The pores within the MCS allowed for the infiltration of EPDM molecular chains, thereby strengthening the interaction forces between the filler and matrix. Moreover, a higher specific surface area resulted in greater adsorption of molecular chains onto the surface of these carbon spheres. This research offers novel insights for understanding the enhancement mechanism of monodisperse mesoporous particles/polymer composites (MCS/EPDM) and highlights their potential application in high-performance rubber composites.

Inhibition of p38 MAPK/NF-κB p65 signaling pathway activity by rare ginsenosides ameliorates cyclophosphamide-induced premature ovarian failure and KGN cell injury.

ETHNOPHARMACOLOGICAL RELEVANCE: Panax ginseng C. A. Mey., one of the most used herbs in the world, shows effective treatment in reproductive injury. Recent studies have proven that the processed product, red ginseng, which is more active than ginseng itself. Therefore, it is speculated that its main functional component, rare ginsenosides (heat-transformed saponin, HTS), may be effective in treating premature ovarian failure (POF), but its efficacy has not yet been experimentally confirmed. AIM OF THE STUDY: To evaluate whether HTS could attenuate cyclophosphamide-induced inflammation and oxidative damage in POF model rats and the human granulosa-like KGN cell line and protect granulosa cell proliferation. MATERIAL AND METHODS: HTS were isolated from ginsenosides and high performance liquid chromatography (HPLC) analysis was used to analyze the HTS components. Cyclophosphamide (CP) was used to establish a POF rat model and KGN cell injury model. Reactive oxygen species (ROS) and antioxidant enzyme production was determined using specific assays, while inflammatory cytokine secretion was measured by enzyme-linked immunosorbent assay (ELISA). The proliferative function of granulosa cells was assessed using high-content screening and immunohistochemistry to determine the Ki67 protein level. Protein expression in ovarian tissues and KGN cells was analyzed by Western blotting, quantitative real-time PCR (qRT-PCR) was used to determine the transcriptional changes in ovarian tissues and KGN cells. RESULTS: In CP-treated POF model rats, HTS significantly decreased malondialdehyde (MDA), interleukin-6 (IL-6), and tumor necrosis factor-α (TNF-α) levels, increased glutathione oxidase (GSH) levels, and upregulated Ki67 expression in ovarian granulosa cells. In addition, HTS significantly increased cell survival and Ki67 expression levels in CP-treated cells, and superoxide dismutase (SOD) levels were significantly increased. HTS significantly downregulated IL-6, TNF-α, and interleukin-1ß (IL-1ß) mRNA expression and significantly inhibited nuclear factor kappa-B p65 (NF-κB p65) and p38 mitogen activated protein kinase (p38 MAPK) phosphorylation in POF model rats and KGN cells. Moreover, NF-κB p65 and p38 MAPK levels were significantly increased in ovarian granulosa cells. p65 and p38 protein and gene expression was significantly downregulated. CONCLUSION: HTS ameliorated CP-induced POF and human granulosa cell injury, possibly by inhibiting inflammation and oxidative damage mediated by the p38 MAPK/NF-κB p65 signaling pathway.

Association of the systemic immuno-inflammation index, neutrophil-to-lymphocyte ratio, and platelet-to-lymphocyte ratio with diabetic microvascular complications.

Background: The systemic immuno-inflammation index (SII), neutrophil-to-lymphocyte ratio (NLR), and platelet-to-lymphocyte ratio (PLR) are widely used and have been shown to be predictive indicators of various diseases. Diabetic nephropathy (DN), retinopathy (DR), and peripheral neuropathy (DPN) are the most prominent and common microvascular complications, which have seriously negative impacts on patients, families, and society. Exploring the associations with these three indicators and diabetic microvascular complications are the main purpose. Methods: There were 1058 individuals with type 2 diabetes mellitus (T2DM) in this retrospective cross-sectional study. SII, NLR, and PLR were calculated. The diseases were diagnosed by endocrinologists. Logistic regression and subgroup analysis were applied to evaluate the association between SII, NLP, and PLR and diabetic microvascular complications. Results: SII, NLR, and PLR were significantly associated with the risk of DN [odds ratios (ORs): 1.52, 1.71, and 1.60, respectively] and DR [ORs: 1.57, 1.79, and 1.55, respectively] by multivariate logistic regression. When NLR ≥2.66, the OR was significantly higher for the risk of DPN (OR: 1.985, 95% confidence interval: 1.29-3.05). Subgroup analysis showed no significant positive associations across different demographics and comorbidities, including sex, age, hypertension, HbA1c (glycated hemoglobin), and dyslipidemia. Conclusion: This study found a positive relationship between NLR and DN, DR, and DPN. In contrast, SII and PLR were found to be only associated with DN and DR. Therefore, for the diagnosis of diabetic microvascular complications, SII, NLR and PLR are highly valuable.

Deep Learning Radiomics Model of Contrast-Enhanced CT for Differentiating the Primary Source of Liver Metastases.

RATIONALE AND OBJECTIVES: To develop and validate a deep learning radiomics (DLR) model based on contrast-enhanced computed tomography (CT) to identify the primary source of liver metastases. MATERIALS AND METHODS: In total, 657 liver metastatic lesions, including breast cancer (BC), lung cancer (LC), colorectal cancer (CRC), gastric cancer (GC), and pancreatic cancer (PC), from 428 patients were collected at three clinical centers from January 2018 to October 2023 series. The lesions were randomly assigned to the training and validation sets in a 7:3 ratio. An additional 112 lesions from 61 patients at another clinical center served as an external test set. A DLR model based on contrast-enhanced CT of the liver was developed to distinguish the five pathological types of liver metastases. Stepwise classification was performed to improve the classification efficiency of the model. Lesions were first classified as digestive tract cancer (DTC) and non-digestive tract cancer (non-DTC). DTCs were divided into CRC, GC, and PC and non-DTCs were divided into LC and BC. To verify the feasibility of the DLR model, we trained classical machine learning (ML) models as comparison models. Model performance was evaluated using accuracy (ACC) and area under the receiver operating characteristic curve (AUC). RESULTS: The classification model constructed by the DLR algorithm showed excellent performance in the classification task compared to ML models. Among the five categories task, highest ACC and average AUC were achieved at 0.563 and 0.796 in the validation set, respectively. In the DTC and non-DTC and the LC and BC classification tasks, AUC was achieved at 0.907 and 0.809 and ACC was achieved at 0.843 and 0.772, respectively. In the CRC, GC, and PC classification task, ACC and average AUC were the highest, at 0.714 and 0.811, respectively. CONCLUSION: The DLR model is an effective method for identifying the primary source of liver metastases.

Automatic quantitative stroke severity assessment based on Chinese clinical named entity recognition with domain-adaptive pre-trained large language model.

BACKGROUND: Stroke is a prevalent disease with a significant global impact. Effective assessment of stroke severity is vital for an accurate diagnosis, appropriate treatment, and optimal clinical outcomes. The National Institutes of Health Stroke Scale (NIHSS) is a widely used scale for quantitatively assessing stroke severity. However, the current manual scoring of NIHSS is labor-intensive, time-consuming, and sometimes unreliable. Applying artificial intelligence (AI) techniques to automate the quantitative assessment of stroke on vast amounts of electronic health records (EHRs) has attracted much interest. OBJECTIVE: This study aims to develop an automatic, quantitative stroke severity assessment framework through automating the entire NIHSS scoring process on Chinese clinical EHRs. METHODS: Our approach consists of two major parts: Chinese clinical named entity recognition (CNER) with a domain-adaptive pre-trained large language model (LLM) and automated NIHSS scoring. To build a high-performing CNER model, we first construct a stroke-specific, densely annotated dataset "Chinese Stroke Clinical Records" (CSCR) from EHRs provided by our partner hospital, based on a stroke ontology that defines semantically related entities for stroke assessment. We then pre-train a Chinese clinical LLM coined "CliRoberta" through domain-adaptive transfer learning and construct a deep learning-based CNER model that can accurately extract entities directly from Chinese EHRs. Finally, an automated, end-to-end NIHSS scoring pipeline is proposed by mapping the extracted entities to relevant NIHSS items and values, to quantitatively assess the stroke severity. RESULTS: Results obtained on a benchmark dataset CCKS2019 and our newly created CSCR dataset demonstrate the superior performance of our domain-adaptive pre-trained LLM and the CNER model, compared with the existing benchmark LLMs and CNER models. The high F1 score of 0.990 ensures the reliability of our model in accurately extracting the entities for the subsequent automatic NIHSS scoring. Subsequently, our automated, end-to-end NIHSS scoring approach achieved excellent inter-rater agreement (0.823) and intraclass consistency (0.986) with the ground truth and significantly reduced the processing time from minutes to a few seconds. CONCLUSION: Our proposed automatic and quantitative framework for assessing stroke severity demonstrates exceptional performance and reliability through directly scoring the NIHSS from diagnostic notes in Chinese clinical EHRs. Moreover, this study also contributes a new clinical dataset, a pre-trained clinical LLM, and an effective deep learning-based CNER model. The deployment of these advanced algorithms can improve the accuracy and efficiency of clinical assessment, and help improve the quality, affordability and productivity of healthcare services.

Extract of Silphium perfoliatum L. improve lipid accumulation in NAFLD mice by regulating AMPK/FXR signaling pathway.

ETHNOPHARMACOLOGICAL RELEVANCE: Globally, the incidence rate and number of patients with nonalcoholic fatty liver disease are increasing, which has become one of the greatest threats to human health. However, there is still no effective therapy and medicine so far. Silphium perfoliatum L. is a perennial herb native to North America, which is used to improve physical fitness and treat liver and spleen related diseases in the traditional medicinal herbs of Indian tribes. This herb is rich in chlorogenic acids, which have the functions of reducing blood lipids, losing weight and protecting liver. However, the effect of these compounds on nonalcoholic fatty liver disease remains unclear. AIM OF THE STUDY: Clarify the therapeutic effects and mechanism of the extract (CY-10) rich in chlorogenic acid and its analogues from Silphium perfoliatum L. on non-alcoholic fatty liver disease, and to determine the active compounds. MATERIALS AND METHODS: A free fatty acid-induced steatosis model of HepG2 cells was established to evaluate the in vitro activity of CY-10 in promoting lipid metabolism. Further, a high-fat diet-induced NAFLD model in C57BL/6 mice was established to detect the effects of CY-10 on various physiological and biochemical indexes in mice, and to elucidate the in vivo effects of the extract on regulating lipid metabolism, anti-inflammation and hepatoprotection, and nontarget lipid metabolomics was performed to analyze differential metabolites of fatty acids in the liver. Subsequently, western blotting and immunohistochemistry were used to analyze the target of the extract and elucidate its mechanism of action. Finally, the active compounds in CY-10 were elucidated through in vitro activity screening. RESULTS: The results indicated that CY-10 significantly attenuated lipid droplet deposition in HepG2 cells. The results of in vivo experiments showed that CY-10 significantly reduce HFD-induced mouse body weight and organ index, improve biochemical indexes, oxidation levels and inflammatory responses in the liver and serum, thereby protecting the liver tissue. It can promote the metabolism of unsaturated fatty acids in the liver and reduce the generation of saturated fatty acids. Furthermore, it is clarified that CY-10 can promote lipid metabolism balance by regulating AMPK/FXR/SREPB-1c/PPAR-γ signal pathway. Ultimately, the main active compound was proved to be cryptochlorogenic acid, which has a strong promoting effect on the metabolism of fatty acids in cells. Impressively, the activities of CY-10 and cryptochlorogenic acid were stronger than simvastatin in vitro and in vivo. CONCLUSION: For the first time, it is clarified that the extract rich in chlorogenic acids and its analogues in Silphium perfoliatum L. have good therapeutic effects on non-alcoholic fatty liver disease. It is confirmed that cryptochlorogenic acid is the main active compound and has good potential for medicine.