Purine metabolite inosine induced by transforming growth factor­ß promotes epithelial­mesenchymal transition in colorectal cancer.

Transforming growth factor-ß (TGF-ß) signaling pathway serves a pivotal role in the pathogenesis of colorectal cancer (CRC). However, the specific molecular mechanisms by which the TGF-ß signaling pathway regulates CRC are still not fully understood. In the present study, metabolomics and transcriptomics were used to screen for key metabolites and regulatory genes most related to the regulation of the TGF-ß signaling pathway in CRC. Additionally, reverse transcription-quantitative PCR, western blotting and Transwell assays were performed to assess the process of epithelial-mesenchymal transition (EMT). Metabolomics analysis indicated that TGF-ß1 has an impact on purine metabolism, leading to an increase in the purine metabolite inosine. The increase of inosine is essential for facilitating EMT and cell migration in CRC cells. Furthermore, the integrated analysis of metabolomics and transcriptomics data revealed that TGF-ß1 induces the expression of laccase domain-containing 1 (LACC1), an enzyme involved in the regulation of inosine. Knockdown of LACC1 resulted in a reduction of TGF-ß1-induced alterations in inosine levels, EMT and cell migration in CRC cells. The results of the present study suggest that the TGF-ß signaling pathway is involved in the regulation of purine metabolism in CRC through the modulation of LACC1 expression. Furthermore, LACC1 appears to influence EMT and cell migration by elevating the levels of the purine metabolite inosine.

Triboelectric-electromagnetic hybrid nanogenerator for harvesting blue energy and creating an ocean wave warning system.

The abundant water wave energy on Earth stands as one of the most promising renewable blue energy sources, as it exhibits minimal dependence on weather, time and temperature. However, the low fluctuation frequency and extremely irregular nature of the wave energy restrict both the methods and efficiency of energy harvesting. In this study, a packed box-like hybrid nanogenerator was designed, comprising two single-electrode triboelectric nanogenerators (TENGs) and two electromagnetic generators (EMGs). The outputs of both the TENG and EMG were demonstrated under different fluctuation frequencies and swing amplitudes, inspiring the development of a wave warning system. The maximum output voltage, current, and transferred charge of the single TENG, as part of hybrid nanogenerator (HG), reach approximately 110 V, 2.3 µA, and 50 nC, respectively. Its peak power reaches 85.3 µW under a resistance load of 20 MΩ at a frequency of 2 Hz. The EMG component produced maximum output voltages and currents of up to 0.45 V and 1.2 mA, respectively. The peak power is approximately 95.6 µW with a resistance load of 200 Ω. The output performances of the TENG and EMG increase linearly with the increase in the swing angle. Most importantly, a packed box-like hybrid nanogenerator can be conveniently packaged for harvesting energy from water waves. A wave energy collection array floating on the sea is proposed for harvesting blue energy and creating a self-powered ocean wave warning system.

Combining Federated Machine Learning and Qualitative Methods to Investigate Novel Pediatric Asthma Subtypes: Protocol for a Mixed Methods Study.

BACKGROUND: Pediatric asthma is a heterogeneous disease; however, current characterizations of its subtypes are limited. Machine learning (ML) methods are well-suited for identifying subtypes. In particular, deep neural networks can learn patient representations by leveraging longitudinal information captured in electronic health records (EHRs) while considering future outcomes. However, the traditional approach for subtype analysis requires large amounts of EHR data, which may contain protected health information causing potential concerns regarding patient privacy. Federated learning is the key technology to address privacy concerns while preserving the accuracy and performance of ML algorithms. Federated learning could enable multisite development and implementation of ML algorithms to facilitate the translation of artificial intelligence into clinical practice. OBJECTIVE: The aim of this study is to develop a research protocol for implementation of federated ML across a large clinical research network to identify and discover pediatric asthma subtypes and their progression over time. METHODS: This mixed methods study uses data and clinicians from the OneFlorida+ clinical research network, which is a large regional network covering linked and longitudinal patient-level real-world data (RWD) of over 20 million patients from Florida, Georgia, and Alabama in the United States. To characterize the subtypes, we will use OneFlorida+ data from 2011 to 2023 and develop a research-grade pediatric asthma computable phenotype and clinical natural language processing pipeline to identify pediatric patients with asthma aged 2-18 years. We will then apply federated learning to characterize pediatric asthma subtypes and their temporal progression. Using the Promoting Action on Research Implementation in Health Services framework, we will conduct focus groups with practicing pediatric asthma clinicians within the OneFlorida+ network to investigate the clinical utility of the subtypes. With a user-centered design, we will create prototypes to visualize the subtypes in the EHR to best assist with the clinical management of children with asthma. RESULTS: OneFlorida+ data from 2011 to 2023 have been collected for 411,628 patients aged 2-18 years along with 11,156,148 clinical notes. We expect to complete the computable phenotyping within the first year of the project, followed by subtyping during the second and third years, and then will perform the focus groups and establish the user-centered design in the fourth and fifth years of the project. CONCLUSIONS: Pediatric asthma subtypes incorporating RWD from diverse populations could improve patient outcomes by moving the field closer to precision pediatric asthma care. Our privacy-preserving federated learning methodology and qualitative implementation work will address several challenges of applying ML to large, multicenter RWD data. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/57981.

Develop and validate a computable phenotype for the identification of Alzheimer's disease patients using electronic health record data.

INTRODUCTION: Alzheimer's disease (AD) is often misclassified in electronic health records (EHRs) when relying solely on diagnosis codes. This study aimed to develop a more accurate, computable phenotype (CP) for identifying AD patients using structured and unstructured EHR data. METHODS: We used EHRs from the University of Florida Health (UFHealth) system and created rule-based CPs iteratively through manual chart reviews. The CPs were then validated using data from the University of Texas Health Science Center at Houston (UTHealth) and the University of Minnesota (UMN). RESULTS: Our best-performing CP was "patient has at least 2 AD diagnoses and AD-related keywords in AD encounters," with an F1-score of 0.817 at UF, 0.961 at UTHealth, and 0.623 at UMN, respectively. DISCUSSION: We developed and validated rule-based CPs for AD identification with good performance, which will be crucial for studies that aim to use real-world data like EHRs. Highlights: Developed a computable phenotype (CP) to identify Alzheimer's disease (AD) patients using EHR data.Utilized both structured and unstructured EHR data to enhance CP accuracy.Achieved a high F1-score of 0.817 at UFHealth, and 0.961 and 0.623 at UTHealth and UMN.Validated the CP across different demographics, ensuring robustness and fairness.

Identification of subclusters and prognostic genes based on GLS-associated molecular signature in ulcerative colitis.

Ulcerative colitis (UC) is a chronic and recurrent inflammatory disease that affects the colon and rectum. The response to treatment varies among individuals with UC. Therefore, the aim of this study was to identify and explore potential biomarkers for different subtypes of UC and examine their association with immune cell infiltration. We obtained UC RNA sequencing data from the GEO database, which included the training set GSE92415 and the validation set GSE87473 and GSE72514. UC patients were classified based on GLS and its associated genes using consensus clustering analysis. We identified differentially expressed genes (DEGs) in different UC subtypes through a differential expression analysis of the training cohort. Machine learning algorithms, including Weighted Gene Co-Expression Network Analysis (WGCNA), Least Absolute Shrinkage and Selection Operator (LASSO), and Support Vector Machine Recursive Feature Elimination (SVM-RFE), were utilized to identify marker genes for UC. The CIBERSORT algorithm was used to determine the abundance of various immune cells in UC and their correlation with UC signature genes. Finally, we validated the expression of GLS through in vivo and ex vivo experiments. The expression of GLS was found to be elevated in patients with UC compared to normal patients. GLS and its related genes were able to classify UC patients into two subtypes, C1 and C2. The C1 subtype, as compared to the C2 subtype, showed a higher Mayo score and poorer treatment response. A total of 18 DEGs were identified in both subtypes, including 7 up-regulated and 11 down-regulated genes. Four UC signature genes (CWH43, HEPACAM2, IL24, and PCK1) were identified and their diagnostic value was validated in a separate cohort (AUC > 0.85). Furthermore, we found that UC signature biomarkers were linked to the immune cell infiltration. CWH43, HEPACAM2, IL24, and PCK1 may serve as potential biomarkers for diagnosing different subtypes of UC, which could contribute to the development of targeted molecular therapy and immunotherapy for UC.

Me-LLaMA: Foundation Large Language Models for Medical Applications.

Recent advancements in large language models (LLMs) such as ChatGPT and LLaMA have hinted at their potential to revolutionize medical applications, yet their application in clinical settings often reveals limitations due to a lack of specialized training on medical-specific data. In response to this challenge, this study introduces Me-LLaMA, a novel medical LLM family that includes foundation models - Me-LLaMA 13/70B, along with their chat-enhanced versions - Me-LLaMA 13/70B-chat, developed through continual pre-training and instruction tuning of LLaMA2 using large medical datasets. Our methodology leverages a comprehensive domain-specific data suite, including a large-scale, continual pre-training dataset with 129B tokens, an instruction tuning dataset with 214k samples, and a new medical evaluation benchmark (MIBE) across six critical medical tasks with 12 datasets. Our extensive evaluation using the MIBE shows that Me-LLaMA models achieve overall better performance than existing open-source medical LLMs in zero-shot, few-shot and supervised learning abilities. With task-specific instruction tuning, Me-LLaMA models outperform ChatGPT on 7 out of 8 datasets and GPT-4 on 5 out of 8 datasets. In addition, we investigated the catastrophic forgetting problem, and our results show that Me-LLaMA models outperform other open-source medical LLMs in mitigating this issue. Me-LLaMA is one of the largest open-source medical foundation LLMs that use both biomedical and clinical data. It exhibits superior performance across both general and medical tasks compared to other open-source medical LLMs, rendering it an attractive choice for medical AI applications. We release our models, datasets, and evaluation scripts at: https://github.com/BIDS-Xu-Lab/Me-LLaMA.

Radiomics analysis based on CT for predicting lymph node metastasis and prognosis in duodenal papillary carcinoma.

OBJECTIVES: Radiomics has been demonstrated to be strongly associated with TNM stage and patient prognosis. We aimed to develop a model for predicting lymph node metastasis (LNM) and survival. METHODS: For radiomics texture selection, 3D Slicer 5.0.3 software and the least absolute shrinkage and selection operator (LASSO) algorithm were used. Subsequently, the radiomics model, computed tomography (CT) image, and clinical risk model were compared. The performance of the three models was evaluated using receiver operating characteristic (ROC) curves, decision curve analysis (DCA), calibration plots, and clinical impact curves (CICs). RESULTS: For the LNM prediction model, 224 patients with LNM information were used to construct a model that was applied to predict LNM. According to the CT data and clinical characteristics, we constructed a radiomics model, CT imaging model and clinical model. The radiomics model for evaluating LNM status showed excellent calibration and discrimination in the training cohort (AUC = 0.926, 95% CI = 0.869-0.982) and the validation cohort (AUC = 0.872, 95% CI = 0.802-0.941). DeLong's test demonstrated that the difference among the three models was significant. Similarly, DCA and CIC showed that the radiomics model has better clinical utility than the CT imaging model and clinical model. Our model also exhibited good performance in predicting survival-in line with the findings of the model built with clinical risk factors. CONCLUSIONS: CT radiomics models exhibited better predictive performance for LNM than models built based on clinical risk characteristics and CT imaging and had comparative clinical utility for predicting patient prognosis. CRITICAL RELEVANCE STATEMENT: The radiomics model showed excellent performance and discrimination for predicting LNM and survival of duodenal papillary carcinoma (DPC). KEY POINTS: LNM status determines the most appropriate treatment for DPC. Our radiomics model for evaluating the LNM status of DPC performed excellently. The radiomics model had high sensitivity and specificity for predicting survival, exhibiting great clinical value.

A Systematic Review of Natural Language Processing Methods and Applications in Thyroidology.

This study aimed to review the application of natural language processing (NLP) in thyroid-related conditions and to summarize current challenges and potential future directions. We performed a systematic search of databases for studies describing NLP applications in thyroid conditions published in English between January 1, 2012 and November 4, 2022. In addition, we used a snowballing technique to identify studies missed in the initial search or published after our search timeline until April 1, 2023. For included studies, we extracted the NLP method (eg, rule-based, machine learning, deep learning, or hybrid), NLP application (eg, identification, classification, and automation), thyroid condition (eg, thyroid cancer, thyroid nodule, and functional or autoimmune disease), data source (eg, electronic health records, health forums, medical literature databases, or genomic databases), performance metrics, and stages of development. We identified 24 eligible NLP studies focusing on thyroid-related conditions. Deep learning-based methods were the most common (38%), followed by rule-based (21%), and traditional machine learning (21%) methods. Thyroid nodules (54%) and thyroid cancer (29%) were the primary conditions under investigation. Electronic health records were the dominant data source (17/24, 71%), with imaging reports being the most frequently used (15/17, 88%). There is increasing interest in NLP applications for thyroid-related studies, mostly addressing thyroid nodules and using deep learning-based methodologies with limited external validation. However, none of the reviewed NLP applications have reached clinical practice. Several limitations, including inconsistent clinical documentation and model portability, need to be addressed to promote the evaluation and implementation of NLP applications to support patient care in thyroidology.

Causal effects of circulating glutamine on colitis, IBD, and digestive system cancers: a Mendelian randomisation study.

Backgrounds: There is growing evidence linking glutamine levels to the risk of gastrointestinal diseases, yet the presence of a causal relationship remains uncertain. In this study, we employed a Mendelian randomization (MR) approach to investigate potential causal associations between glutamine and colitis, inflammatory bowel disease (IBD), and digestive tumors. Methods: Genetic instrumental variables for glutamine exposure were identified from a genome-wide association study (GWAS) involving 114,751 participants. We pooled statistics from GWAS of gastrointestinal diseases in European populations, encompassing colitis (cases=1193, controls=461,740), IBD (cases=31,665, controls=33,977), Crohn's disease (cases=17,897, controls=33,977), ulcerative colitis (cases=1,239, controls=990), oesophageal cancer (cases=740, controls=372,016), gastric cancer (cases=6,563, controls=195,745), liver cell carcinoma (cases=168, controls=372,016), hepatic bile duct cancer (cases=418, controls=159,201), pancreatic cancer (cases=1,196, controls=475,049), and colon cancer (cases=1,494, controls=461,439). To ensure the validity of our findings, we utilized several analytical approaches including inverse variance weighted, weighted median, weighted mode, MR-Egger, and simple mode method. Results: Using the IVW method, we found that glutamine levels were inversely associated with colon cancer (OR = 0.998; 95% CI: 0.997-1.000; P = 0.027), colitis (OR = 0.998; 95% CI: 0.997-1.000; P = 0.020), and IBD (OR = 0.551; 95% CI: 0.343-0.886; P = 0.014). Subgroup analysis revealed a negative association between glutamine and Crohn's disease (OR = 0.375; 95% CI: 0.253-0.557; P = 1.11E-06), but not with ulcerative colitis (OR = 0.508; 95% CI: 0.163-1.586; P = 0.244). Glutamine levels showed no significant correlation with oesophageal cancer (OR = 1.000; 95% CI: 0.999-1.001; P = 0.566), gastric cancer (OR = 0.966; 95% CI: 0.832-1.121; P = 0.648), liver cell carcinoma (OR = 1.000; 95% CI: 0.999-1.000; P = 0.397), hepatic bile duct cancer (OR = 0.819; 95% CI: 0.499-1.344; P = 0.430), and pancreatic cancer (OR = 1.130; 95% CI: 0.897-1.423; P = 0.301). Sensitivity analyses also supports this finding, affirming the reliability and robustness of our study. Conclusions: This study suggests that blood glutamine levels in European populations may lower the risk of colon cancer, colitis, and IBD, particularly Crohn's disease. Nevertheless, additional research involving a diverse range of ancestries is imperative to corroborate this causal relationship.

Edaravone Alleviates Traumatic Brain Injury by Inhibition of Ferroptosis via FSP1 Pathway.

Traumatic brain injury (TBI) is a highly severe form of trauma with complex series of reactions in brain tissue which ultimately results in neuronal damage. Previous studies proved that neuronal ferroptosis, which was induced by intracranial haemorrhage and other reasons, was one of the most primary causes of neuronal damage following TBI. However, the association between neuronal mechanical injury and ferroptosis in TBI and relevant treatments remain unclear. In the present study, we first demonstrated the occurrence of neuronal ferroptosis in the early stage of TBI and preliminarily elucidated that edaravone (EDA), a cerebroprotective agent that eliminates oxygen radicals, was able to inhibit ferroptosis induced by TBI. A cell scratching model was established in PC12 cells, and it was confirmed that mechanical injury induced ferroptosis in neurons at the early stage of TBI. Ferroptosis suppressor protein 1 (FSP1) plays a significant role in inhibiting ferroptosis, and we found that iFSP, a ferroptosis agonist which is capable to inhibit FSP1 pathway, attenuated the anti-ferroptosis effect of EDA. In conclusion, our results suggested that EDA inhibited neuronal ferroptosis induced by mechanical injury in the early phase of TBI by activating FSP1 pathway, which could provide evidence for future research on prevention and treatment of TBI.

Identification of glutamine metabolism-related gene signature to predict colorectal cancer prognosis.

Backgrounds: Colorectal cancer (CRC) is a highly malignant gastrointestinal malignancy with a poor prognosis, which imposes a significant burden on patients and healthcare providers globally. Previous studies have established that genes related to glutamine metabolism play a crucial role in the development of CRC. However, no studies have yet explored the prognostic significance of these genes in CRC. Methods: CRC patient data were downloaded from The Cancer Genome Atlas (TCGA), while glutamine metabolism-related genes were obtained from the Molecular Signatures Database (MSigDB) database. Univariate COX regression analysis and LASSO Cox regression were utilized to identify 15 glutamine metabolism-related genes associated with CRC prognosis. The risk scores were calculated and stratified into high-risk and low-risk groups based on the median risk score. The model's efficacy was assessed using Kaplan-Meier survival analysis and receiver operating characteristic (ROC) curve analysis. Cox regression analysis was employed to determine the risk score as an independent prognostic factor for CRC. Differential immune cell infiltration between the high-risk and low-risk groups was assessed using the ssGSEA method. The clinical applicability of the model was validated by constructing nomograms based on age, gender, clinical staging, and risk scores. Immunohistochemistry (IHC) was used to detect the expression levels of core genes. Results: We identified 15 genes related to glutamine metabolism in CRC: NLGN1, RIMKLB, UCN, CALB1, SYT4, WNT3A, NRCAM, LRFN4, PHGDH, GRM1, CBLN1, NRG1, GLYATL1, CBLN2, and VWC2. Compared to the high-risk group, the low-risk group demonstrated longer overall survival (OS) for CRC. Clinical correlation analysis revealed a positive correlation between the risk score and the clinical stage and TNM stage of CRC. Immune correlation analysis indicated a predominance of Th2 cells in the low-risk group. The nomogram exhibited excellent discriminatory ability for OS in CRC. Immunohistochemistry revealed that the core gene CBLN1 was expressed at a lower level in CRC, while GLYATL1 was expressed at a higher level. Conclusions: In summary, we have successfully identified and comprehensively analyzed a gene signature associated with glutamine metabolism in CRC for the first time. This gene signature consistently and reliably predicts the prognosis of CRC patients, indicating its potential as a metabolic target for individuals with CRC.

Evaluation of a miniature mass spectrometer based point-of-care-test method for direct analysis of amlodipine and benazepril in whole blood.

A miniature mass spectrometer (mMS) based point-of-care testing (POCT) method was evaluated for on-site detecting the hypertension drugs, amlodipine and benazepril. The instrument parameters, including voltage, ISO1, ISO2, and CID, were optimized, under which the target compounds could be well detected in MS2. When these two drugs were injected simultaneously, the mutual ionization inhibition and mutual reduction between amlodipine and benazepril were evaluated. This phenomenon was severe on the precursor ions but had a small impact on the product ions, thus making this POCT method suitable for analysis using product ions. Finally, the method was validated and applied. The blood samples from patients were tested one hour after oral administration of the drugs (20 mg), and the benazepril was quantitatively analyzed using a standard curve, with detected concentrations ranging from 190.6 to 210 µg L-1 and a relative standard deviation (RSD) of 8.6 %. In summary, amlodipine has low sensitivity and can only be detected at higher concentrations, while benazepril has high sensitivity, good linearity, and even meets semi-quantitative requirements. The research results of this study are of great clinical significance for monitoring blood drug concentrations during hypertension medication, predicting drug efficacy, and customizing individualized medication plans.

Protective effect of resveratrol on nickel-refining fumes-induced inflammatory damage.

Nickel (Ni), a ductile and hard silver-white transition metal, is commonly found in occupational environments and can harm the human body. Since it is a toxic compound, long-term Ni exposure can cause pneumonia, rhinitis, and other types of respiratory inflammatory diseases. Resveratrol (Res) is a plant antitoxin polyphenol, which also has anti-cancer and anti-inflammatory properties. In this report, the toxicity of Ni-refining fumes on the human lung bronchial epithelial (BEAS-2B) cells, as well as the protective effects of Res were investigated in vitro, and the specific mechanism of its anti-inflammatory effect was explained. The experimental observations of this study revealed that Ni-refining fumes induce BEAS-2B cell damage, increase reactive oxygen species (ROS) content, activate NLRP3 (LRR-, NOD-, and pyrin domain-containing 3) inflammasome, and promote the secretion of the cytokine Interleukin (IL)-1ß, leading to cellular inflammation and reducing cell activity. Resveratrol (20 µmol/L) activated sirtuin 1 (SIRT1) in BEAS-2B cells to increase protein and mRNA expression. SIRT1 was observed to inhibit the transcriptional activity of nuclear factor-kappaB (NF-κB), reduced the expression of NLRP3 protein and mRNA, and inhibited NLRP3 inflammation. The level of inflammasome activation and IL-1ß overexpression could reduce the inflammatory damage caused by the Ni-refining fume particles on the BEAS-2B cells and exert anti-inflammatory protective effects. In vivo experiments further confirmed that resveratrol could effectively alleviate the acute inflammatory injuries caused due to exposure to the Ni-refining fume particles in the lung tissues of the Wistar rats, and verified that resveratrol could exert its anti-inflammatory impact through the SIRT1-NF-κB-NLRP3 pathway. These results provide an important theoretical basis for developing novel protective drugs and investigating the mechanism of action for inflammatory injury in occupational populations caused by exposure to nickel and other heavy metals.

Comparable long­term survival outcomes of endoscopic treatment versus surgical treatment for gastrointestinal stromal tumors with a diameter of 5-10 cm.

Currently, endoscopic treatment for small gastrointestinal stromal tumors (GIST) has been widely accepted. However, for tumors larger than 5 cm, endoscopic treatment has not been recognized by national guidelines as the standard therapy due to concerns about safety and adverse tumor outcomes. Therefore, this study compares the long-term survival outcomes of endoscopic treatment and surgical treatment for GIST in the range of 5-10 cm. We selected patients with GIST from the Surveillance, Epidemiology, and End Results (SEER) database between 2004 and 2015. Kaplan-Meier analysis and the log-rank test were employed to compare the long-term survival outcomes between endoscopic treatment and surgical treatment. A multivariate Cox proportional hazards model was used for analysis to identify risk factors influencing patient prognosis. To balance baseline data, we performed 1:1 propensity score matching (PSM). A total of 1223 GIST patients were included, with 144 patients (11.8%) received endoscopic treatment and 1079 patients (88.2%) received surgical treatment. Before PSM, there was no significant difference in the long-term survival rates between the two groups [5-year OS (86.5% vs. 83.5%, P = 0.42), 10-year OS (70.4% vs. 66.7%, P = 0.42)]. After adjusting for covariates, we found that the overall survival (HR = 1.26, 95% CI 0.89-1.77, P = 0.19) and cancer-specific survival (HR = 1.69, 95% CI 0.99-2.89, P = 0.053) risks were comparable between the endoscopic treatment group and the surgical treatment group. In the analysis after PSM, there was no significant difference between the endoscopic treatment group and the surgical treatment group. Our study found that for GIST patients with tumor sizes between 5 and 10 cm, the long-term OS and CSS outcomes were similar between the endoscopic treatment group and the surgical treatment group.

Identifying social determinants of health from clinical narratives: A study of performance, documentation ratio, and potential bias.

OBJECTIVE: To develop a natural language processing (NLP) package to extract social determinants of health (SDoH) from clinical narratives, examine the bias among race and gender groups, test the generalizability of extracting SDoH for different disease groups, and examine population-level extraction ratio. METHODS: We developed SDoH corpora using clinical notes identified at the University of Florida (UF) Health. We systematically compared 7 transformer-based large language models (LLMs) and developed an open-source package - SODA (i.e., SOcial DeterminAnts) to facilitate SDoH extraction from clinical narratives. We examined the performance and potential bias of SODA for different race and gender groups, tested the generalizability of SODA using two disease domains including cancer and opioid use, and explored strategies for improvement. We applied SODA to extract 19 categories of SDoH from the breast (n = 7,971), lung (n = 11,804), and colorectal cancer (n = 6,240) cohorts to assess patient-level extraction ratio and examine the differences among race and gender groups. RESULTS: We developed an SDoH corpus using 629 clinical notes of cancer patients with annotations of 13,193 SDoH concepts/attributes from 19 categories of SDoH, and another cross-disease validation corpus using 200 notes from opioid use patients with 4,342 SDoH concepts/attributes. We compared 7 transformer models and the GatorTron model achieved the best mean average strict/lenient F1 scores of 0.9122 and 0.9367 for SDoH concept extraction and 0.9584 and 0.9593 for linking attributes to SDoH concepts. There is a small performance gap (∼4%) between Males and Females, but a large performance gap (>16 %) among race groups. The performance dropped when we applied the cancer SDoH model to the opioid cohort; fine-tuning using a smaller opioid SDoH corpus improved the performance. The extraction ratio varied in the three cancer cohorts, in which 10 SDoH could be extracted from over 70 % of cancer patients, but 9 SDoH could be extracted from less than 70 % of cancer patients. Individuals from the White and Black groups have a higher extraction ratio than other minority race groups. CONCLUSIONS: Our SODA package achieved good performance in extracting 19 categories of SDoH from clinical narratives. The SODA package with pre-trained transformer models is available at https://github.com/uf-hobi-informatics-lab/SODA_Docker.

Generative large language models are all-purpose text analytics engines: text-to-text learning is all your need.

OBJECTIVE: To solve major clinical natural language processing (NLP) tasks using a unified text-to-text learning architecture based on a generative large language model (LLM) via prompt tuning. METHODS: We formulated 7 key clinical NLP tasks as text-to-text learning and solved them using one unified generative clinical LLM, GatorTronGPT, developed using GPT-3 architecture and trained with up to 20 billion parameters. We adopted soft prompts (ie, trainable vectors) with frozen LLM, where the LLM parameters were not updated (ie, frozen) and only the vectors of soft prompts were updated, known as prompt tuning. We added additional soft prompts as a prefix to the input layer, which were optimized during the prompt tuning. We evaluated the proposed method using 7 clinical NLP tasks and compared them with previous task-specific solutions based on Transformer models. RESULTS AND CONCLUSION: The proposed approach achieved state-of-the-art performance for 5 out of 7 major clinical NLP tasks using one unified generative LLM. Our approach outperformed previous task-specific transformer models by ∼3% for concept extraction and 7% for relation extraction applied to social determinants of health, 3.4% for clinical concept normalization, 3.4%-10% for clinical abbreviation disambiguation, and 5.5%-9% for natural language inference. Our approach also outperformed a previously developed prompt-based machine reading comprehension (MRC) model, GatorTron-MRC, for clinical concept and relation extraction. The proposed approach can deliver the "one model for all" promise from training to deployment using a unified generative LLM.

Detection of Personal and Family History of Suicidal Thoughts and Behaviors using Deep Learning and Natural Language Processing: A Multi-Site Study.

Objective: Personal and family history of suicidal thoughts and behaviors (PSH and FSH, respectively) are significant risk factors associated with future suicide events. These are often captured in narrative clinical notes in electronic health records (EHRs). Collaboratively, Weill Cornell Medicine (WCM), Northwestern Medicine (NM), and the University of Florida (UF) developed and validated deep learning (DL)-based natural language processing (NLP) tools to detect PSH and FSH from such notes. The tool's performance was further benchmarked against a method relying exclusively on ICD-9/10 diagnosis codes. Materials and Methods: We developed DL-based NLP tools utilizing pre-trained transformer models Bio_ClinicalBERT and GatorTron, and compared them with expert-informed, rule-based methods. The tools were initially developed and validated using manually annotated clinical notes at WCM. Their portability and performance were further evaluated using clinical notes at NM and UF. Results: The DL tools outperformed the rule-based NLP tool in identifying PSH and FHS. For detecting PSH, the rule-based system obtained an F1-score of 0.75 ± 0.07, while the Bio_ClinicalBERT and GatorTron DL tools scored 0.83 ± 0.09 and 0.84 ± 0.07, respectively. For detecting FSH, the rule-based NLP tool's F1-score was 0.69 ± 0.11, compared to 0.89 ± 0.10 for Bio_ClinicalBERT and 0.92 ± 0.07 for GatorTron. For the gold standard corpora across the three sites, only 2.2% (WCM), 9.3% (NM), and 7.8% (UF) of patients reported to have an ICD-9/10 diagnosis code for suicidal thoughts and behaviors prior to the clinical notes report date. The best performing GatorTron DL tool identified 93.0% (WCM), 80.4% (NM), and 89.0% (UF) of patients with documented PSH, and 85.0%(WCM), 89.5%(NM), and 100%(UF) of patients with documented FSH in their notes. Discussion: While PSH and FSH are significant risk factors for future suicide events, little effort has been made previously to identify individuals with these history. To address this, we developed a transformer based DL method and compared with conventional rule-based NLP approach. The varying effectiveness of the rule-based tools across sites suggests a need for improvement in its dictionary-based approach. In contrast, the performances of the DL tools were higher and comparable across sites. Furthermore, DL tools were fine-tuned using only small number of annotated notes at each site, underscores its greater adaptability to local documentation practices and lexical variations. Conclusion: Variations in local documentation practices across health care systems pose challenges to rule-based NLP tools. In contrast, the developed DL tools can effectively extract PSH and FSH information from unstructured clinical notes. These tools will provide clinicians with crucial information for assessing and treating patients at elevated risk for suicide who are rarely been diagnosed.

Recent Advances of CeO2-Based Composite Materials for Photocatalytic Applications.

Photocatalysis has the advantages of practical, sustainable and environmental protection, so it plays a significant role in energy transformation and environmental utilization. CeO2 has attracted widespread attention for its unique 4 f electrons, rich defect structures, high oxygen storage capacity and great chemical stability. In this paper, we review the structure of CeO2 and the common methods for the preparation of CeO2-based composites in the first part. In particular, we highlight the co-precipitation method, template method, and sol-gel method methods. Then, in the second part, we introduce the application of CeO2-based composites in photocatalysis, including photocatalytic CO2 reduction, hydrogen production, degradation, selective organic reaction, and photocatalytic nitrogen fixation. In addition, we discuss several modification techniques to improve the photocatalytic performance of CeO2-based composites, such as elemental doping, defect engineering, constructing heterojunction and morphology regulation. Finally, the challenges faced by CeO2-based composites are analyzed and their development prospects are prospected. This review provides a systematic summary of the recent advance of CeO2-based composites in the field of photocatalysis, which can provide useful references for the rational design of efficient CeO2-based composite photocatalysts for sustainable development.

Single-cell RNA sequencing reveals epithelial cells driving brain metastasis in lung adenocarcinoma.

Brain metastases (BM) of lung adenocarcinoma (LUAD) are the most common intracranial malignancy leading to death. However, the cellular origins and drivers of BM from LUAD have not been clarified. Cellular composition was characterized by single-cell sequencing analysis of primary lung adenocarcinoma (pLUAD), BM and lymph node metastasis (LNM) samples in GSE131907. Our study briefly analyzed the tumor microenvironment (TME), focusing on the role of epithelial cells (ECs) in BM. We have discovered a population of brain metastasis-associated epithelial cells (BMAECs) expressing SPP1, SAA1, and CDKN2A, and it has been observed that this population is mainly composed of aneuploid cells from pLUAD, playing a crucial role in brain metastasis. Our study concluded that both LNM and BM in LUAD originated from pLUAD lesions, but there is currently insufficient evidence to prove a direct association between BM lesions and LNM lesions, which provides inspiration for further investigation of the TME in BM.

Acanthopanax senticosus improves cognitive impairment in Alzheimer's disease by promoting the phosphorylation of the MAPK signaling pathway.

Background: Acanthopanax senticosus (AS) can improve sleep, enhance memory, and reduce fatigue and is considered as an effective drug for Alzheimer's disease (AD). The therapeutic effect and mechanism need to be further investigated. Methods: To confirm the AS play efficacy in alleviating memory impairment in mice, 5×FAD transgenic mice were subjected to an open-field experiment and a novelty recognition experiment. Network pharmacology technique was used to analyze the information of key compounds and potential key targets of AS for the treatment of AD, molecular docking technique was applied to predict the binding ability of targets and compounds, and Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) analyses were also performed on the targets to derive the possible metabolic processes and pathway mechanisms of AS in treating AD. Quantitative real-time PCR (qRT-PCR) and western blot technique were carried out to validate the candidate genes and pathways. Results: In the open-field experiment, compared with the wild-type (WT) group, the number of times the mice in the AD group crossed the central zone was significantly reduced (P< 0.01). Compared with the AD group, the number of times the mice in the AS group crossed the central zone was significantly increased (P< 0.001). In the new object recognition experiment, compared with the WT group, the percentage of times the AD group explored new objects was significantly reduced (P< 0.05). Compared with the AD group, the AS group had an increase in the percentage of time spent exploring new things and the number of times it was explored (P< 0.05). At the same time, the donepezil group had a significantly higher percentage of times exploring new things (P< 0.01). By using network pharmacology technology, 395 common targets of AS and AD were retrieved. The Cytoscape software was used to construct the protein-protein interaction (PPI) network of common targets. Using the algorithm, nine key targets were retrieved: APP, NTRK1, ESR1, CFTR, CSNK2A1, EGFR, ESR2, GSK3B, and PAK1. The results of molecular docking indicate that 11 pairs of compounds and their corresponding targets have a significant binding ability, as the molecular binding energies were less than -7.0. In comparison to the AD group, the mRNA expression of the key target genes was significantly decreased in the AS treatment group (P< 0.001). The KEGG analysis showed that the MAPK signaling pathway was significantly enriched, and Western blot confirmed that the TRAF6 protein decreased significantly (P< 0.0001). Meanwhile, the levels of MAP3K7 and P38 phosphorylation increased, and there was also an increase in the expression of HSP27 proteins. Conclusion: Our study indicates that the multi-component and multi-target properties of AS play an important role in the alleviation of anxiety and memory impairment caused by AD, and the mechanism is involved in the phosphorylation and activation of the MAPK signaling pathway. The results of this study could provide a novel perspective for the clinical treatment of AD.