PRSCS-Net: Progressive 3D/2D rigid Registration network with the guidance of Single-view Cycle Synthesis.

The 3D/2D registration for 3D pre-operative images (computed tomography, CT) and 2D intra-operative images (X-ray) plays an important role in image-guided spine surgeries. Conventional iterative-based approaches suffer from time-consuming processes. Existing learning-based approaches require high computational costs and face poor performance on large misalignment because of projection-induced losses or ill-posed reconstruction. In this paper, we propose a Progressive 3D/2D rigid Registration network with the guidance of Single-view Cycle Synthesis, named PRSCS-Net. Specifically, we first introduce the differentiable backward/forward projection operator into the single-view cycle synthesis network, which reconstructs corresponding 3D geometry features from two 2D intra-operative view images (one from the input, and the other from the synthesis). In this way, the problem of limited views during reconstruction can be solved. Subsequently, we employ a self-reconstruction path to extract latent representation from pre-operative 3D CT images. The following pose estimation process will be performed in the 3D geometry feature space, which can solve the dimensional gap, greatly reduce the computational complexity, and ensure that the features extracted from pre-operative and intra-operative images are as relevant as possible to pose estimation. Furthermore, to enhance the ability of our model for handling large misalignment, we develop a progressive registration path, including two sub-registration networks, aiming to estimate the pose parameters via two-step warping volume features. Finally, our proposed method has been evaluated on a public dataset CTSpine1k and an in-house dataset C-ArmLSpine for 3D/2D registration. Results demonstrate that PRSCS-Net achieves state-of-the-art registration performance in terms of registration accuracy, robustness, and generalizability compared with existing methods. Thus, PRSCS-Net has potential for clinical spinal disease surgical planning and surgical navigation systems.

Incidence of Acute Cystoid Macular Edema After Starting a Prostaglandin Analog Compared With Other Classes of Glaucoma Medications.

PURPOSE: There is a longstanding belief that prostaglandin analogs (PGAs) may predispose patients with glaucoma to develop acute cystoid macular edema (CME). However, there is little solid evidence supporting this notion. The purpose of this study is to compare CME incidence rates among patients initiating treatment with different glaucoma medication classes. DESIGN: Database study. PARTICIPANTS: 39948 patients who were newly prescribed glaucoma medications METHODS: Using data from 10 health systems contributing data to the Sight Outcomes Research Collaborative (SOURCE) Ophthalmology Data Repository, we identified all adults with glaucoma who had been newly started on a topical glaucoma medication. Patients with pre-existing documentation of macular edema were excluded. We assessed the incidence of CME among patients with glaucoma who were newly started on PGAs, topical beta blockers (BBs), alpha agonists (AAs), and carbonic anhydrase inhibitors (CAIs). Using multivariable logistic regression, and adjusting for sociodemographic factors, we assessed the odds of developing CME among patients prescribed each of the 4 glaucoma medication classes. We also performed a subset regression analysis including lens status as a co-variate. MAIN OUTCOME MEASURES: Incidence of CME within 3 months of initiating therapy with different topical glaucoma medications. RESULTS: Among the 39,948 patients were newly treated with a topical glaucoma medication, 139 (0.35%) developed CME. The incidence of CME was 0.13%, 0.65%, 0.55%, 1.76% for users of PGAs, BBs, alpha agonists (AAs) and carbonic anhydrase inhibitors (CAIs), respectively. After adjusting for sociodemographic factors, users of topical BBs, AAs and CAIs had substantially higher odds of developing CME compared with PGA users (P<0.001 for all comparisons). The subset analysis also showed higher odds ratio of the non-PGA medication classes in association with CME. CONCLUSIONS: Clinicians should reconsider the notion that PGAs carry a higher risk of CME versus other glaucoma medication classes. If additional studies support the findings of these analyses, clinicians may feel more comfortable prescribing PGAs to patients with glaucoma without fear they will predispose patients to CME.

Inhibition of ethanol-induced eNAMPT secretion attenuates liver ferroptosis through BAT-Liver communication.

BACKGROUND & AIMS: Extracellular nicotinamide phosphoribosyltransferase (eNAMPT) has long been recognized as an adipokine. However, the exact role of eNAMPT in alcoholic liver disease (ALD) and its relevance to brown adipose tissue (BAT) remain largely unknown. This study aimed to evaluate the impact of eNAMPT on liver function and the underlying mechanisms involved in BAT-Liver communication. METHODS: Serum eNAMPT levels were detected in the serum of both ALD patients and mice. Chronic and binge ethanol feeding was used to induce alcoholic liver injury in mice. An eNAMPT antibody, a coculture model of brown adipocytes and hepatocytes, and BAT-specific Nampt knockdown mice were used to investigate the role of eNAMPT in ALD. RESULTS: Serum eNAMPT levels are elevated in ALD patients and are significantly positively correlated with the liver injury index. In ALD mice, neutralizing eNAMPT reduced the elevated levels of circulating eNAMPT induced by ethanol and attenuated liver injury. In vitro experiments revealed that eNAMPT induced hepatocyte ferroptosis through the TLR4-dependent mitochondrial ROS-induced ferritinophagy pathway. Furthermore, ethanol stimulated eNAMPT secretion from brown adipocytes but not from other adipocytes. In the coculture model, ethanol-induced release of eNAMPT from brown adipocytes promoted hepatocyte ferroptosis. In BAT-specific Nampt-knockdown mice, ethanol-induced eNAMPT secretion was significantly reduced, and alcoholic liver injury were attenuated. These effects can be reversed by intraperitoneal injection of eNAMPT. CONCLUSION: Inhibition of ethanol-induced eNAMPT secretion from BAT attenuates liver injury and ferroptosis. Our study reveals a previously uncharacterized critical role of eNAMPT-mediated BAT-Liver communication in ALD and highlights its potential as a therapeutic target.

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.

Large Language Models for Social Determinants of Health Information Extraction from Clinical Notes - A Generalizable Approach across Institutions.

The consistent and persuasive evidence illustrating the influence of social determinants on health has prompted a growing realization throughout the health care sector that enhancing health and health equity will likely depend, at least to some extent, on addressing detrimental social determinants. However, detailed social determinants of health (SDoH) information is often buried within clinical narrative text in electronic health records (EHRs), necessitating natural language processing (NLP) methods to automatically extract these details. Most current NLP efforts for SDoH extraction have been limited, investigating on limited types of SDoH elements, deriving data from a single institution, focusing on specific patient cohorts or note types, with reduced focus on generalizability. This study aims to address these issues by creating cross-institutional corpora spanning different note types and healthcare systems, and developing and evaluating the generalizability of classification models, including novel large language models (LLMs), for detecting SDoH factors from diverse types of notes from four institutions: Harris County Psychiatric Center, University of Texas Physician Practice, Beth Israel Deaconess Medical Center, and Mayo Clinic. Four corpora of deidentified clinical notes were annotated with 21 SDoH factors at two levels: level 1 with SDoH factor types only and level 2 with SDoH factors along with associated values. Three traditional classification algorithms (XGBoost, TextCNN, Sentence BERT) and an instruction tuned LLM-based approach (LLaMA) were developed to identify multiple SDoH factors. Substantial variation was noted in SDoH documentation practices and label distributions based on patient cohorts, note types, and hospitals. The LLM achieved top performance with micro-averaged F1 scores over 0.9 on level 1 annotated corpora and an F1 over 0.84 on level 2 annotated corpora. While models performed well when trained and tested on individual datasets, cross-dataset generalization highlighted remaining obstacles. To foster collaboration, access to partial annotated corpora and models trained by merging all annotated datasets will be made available on the PhysioNet repository.

TM7SF2-induced lipid reprogramming promotes cell proliferation and migration via CPT1A/Wnt/ß-Catenin axis in cervical cancer cells.

Cervical cancer poses a serious threat to women's health globally. Our previous studies found that upregulation of TM7SF2, which works as an enzyme involved in the process of cholesterol biosynthesis expression, was highly correlated with cervical cancer. However, the mechanistic basis of TM7SF2 promoting cervical cancer progression via lipid metabolism remains poorly understood. Therefore, quantification of fatty acids and lipid droplets were performed in vitro and in vivo. The protein-protein interaction was verified by Co-IP technique. The mechanism and underlying signaling pathway of TM7SF2 via CPT1A associated lipid metabolism in cervical cancer development were explored using Western blotting, IHC, colony formation, transwell assay, and wound healing assay. This study reported that overexpression of TM7SF2 increased fatty acids content and lipid droplets both in vivo and in vitro experiments. While knockout of TM7SF2 obviously attenuated this process. Moreover, TM7SF2 directly bonded with CPT1A, a key enzyme in fatty acid oxidation, and regulated CPT1A protein expression in cervical cancer cells. Notably, the proliferation and metastasis of cervical cancer cells were elevated when their CPT1A expression was upregulated. Then, rescue assay identified that CPT1A overexpressed could enhance the cell viability and migration in TM7SF2-knockout cells. Furthermore, depletion of TM7SF2 significantly inhibited WNT and ß-catenin proteins expression, which was enhanced by CPT1A-overexpressed. The proliferation and migration of cervical cancer cells were reversed in CPT1A-overexpressed cells with the treatment of MSAB, an inhibitor of Wnt/ß-Catenin pathway. This study put forward an idea that TM7SF2-induced lipid reprogramming promotes proliferation and migration via CPT1A/Wnt/ß-Catenin axis in cervical cancer, underlying the progression of cervical cancer.

Identifying Radical Pathways for Cu(I)/Cu(II) Relay Catalyzed Oxygenation via Online Coupled EPR/UV-Vis/Near-IR Monitoring.

Copper-catalyzed C─H oxygenation has drawn considerable attention in mechanistic studies. However, a comprehensive investigation combining radical pathways with a metal-catalytic cycle is challenged by the intricate organic radicals and metallic intermediates. Herein, an online coupled EPR/UV-vis/near-IR detecting method is developed to simultaneously monitor both reactive radical species and copper complex intermediates during the reaction. Focusing on copper-catalyzed phenol oxygenation with cumene hydroperoxide, the short-lived alkylperoxyl radical (EPR signal at g = 2.0143) as well as the unexpected square planar Cu(II)-alkoxyl radical complex (near-IR signal at 833 nm) are unveiled during the reaction, in addition to the observable phenoxyl radical in EPR, quinone product in UV-vis, and Cu(II) center in EPR. With a comprehensive picture of diverse intermediates evolving over the same timeline, a novel Cu(I)/Cu(II) proposed relay-catalyzed sequential radical pathway. In this sequence, Cu(II) activates hydroperoxide through Cu(II)-OOR into the alkylperoxide radical, while the reaction between Cu(I) and hydroperoxide leads to Cu(II)(•OR)OH with high H-atom abstracting activity. These results provide a thorough understanding of the Cu(I)/Cu(II) relay catalysis for phenol oxygenation, setting the stage for mechanistic investigations into intricate radical reactions promoted by metallic complexes.

FedFSA: Hybrid and federated framework for functional status ascertainment across institutions.

INTRODUCTION: Patients' functional status assesses their independence in performing activities of daily living, including basic ADLs (bADL), and more complex instrumental activities (iADL). Existing studies have discovered that patients' functional status is a strong predictor of health outcomes, particularly in older adults. Depite their usefulness, much of the functional status information is stored in electronic health records (EHRs) in either semi-structured or free text formats. This indicates the pressing need to leverage computational approaches such as natural language processing (NLP) to accelerate the curation of functional status information. In this study, we introduced FedFSA, a hybrid and federated NLP framework designed to extract functional status information from EHRs across multiple healthcare institutions. METHODS: FedFSA consists of four major components: 1) individual sites (clients) with their private local data, 2) a rule-based information extraction (IE) framework for ADL extraction, 3) a BERT model for functional status impairment classification, and 4) a concept normalizer. The framework was implemented using the OHNLP Backbone for rule-based IE and open-source Flower and PyTorch library for federated BERT components. For gold standard data generation, we carried out corpus annotation to identify functional status-related expressions based on ICF definitions. Four healthcare institutions were included in the study. To assess FedFSA, we evaluated the performance of category- and institution-specific ADL extraction across different experimental designs. RESULTS: ADL extraction performance ranges from an F1-score of 0.907 to 0.986 for bADL and 0.825 to 0.951 for iADL across the four healthcare sites. The performance for ADL extraction with impairment ranges from an F1-score of 0.722 to 0.954 for bADL and 0.674 to 0.813 for iADL across four healthcare sites. For category-specific ADL extraction, laundry and transferring yielded relatively high performance, while dressing, medication, bathing, and continence achieved moderate-high performance. Conversely, food preparation and toileting showed low performance. CONCLUSION: NLP performance varied across ADL categories and healthcare sites. Federated learning using a FedFSA framework performed higher than non-federated learning for impaired ADL extraction at all healthcare sites. Our study demonstrated the potential of the federated learning framework in functional status extraction and impairment classification in EHRs, exemplifying the importance of a large-scale, multi-institutional collaborative development effort.

Is coffee, tea, and red wine consumption beneficial for individuals with hypertension?

OBJECTIVE: To investigate the associations of tea, coffee, and red wine intakes with health risks among individuals with hypertension. METHODS: This prospective cohort study included participants with hypertension from the UK Biobank cohort. Study exposures included self-reported intakes of coffee, tea, and red wine. The primary outcome was all-cause mortality, and the secondary outcomes were cardiovascular mortality and cardiovascular disease. The associations of beverage intake with outcomes were analyzed using Cox regression models. The hazard ratios and 95% confidence intervals were estimated. RESULTS: A total of 187 708 participants with hypertension were included. The median follow-up period was 13.8 years. In individuals with hypertension, drinking one to two cups/day of coffee or three to four cups/day of tea was significantly associated with the lowest risk of all-cause mortality compared with less than one cup/day [hazard ratio for coffee, 0.943 (95% confidence interval, 0.908-0.979); hazard ratio for tea, 0.882 (95% confidence interval, 0.841-0.924)]. Red wine intake was inversely associated with all-cause mortality risk. Dose-response analysis revealed that high coffee intake (approximately greater than or equal to six cups/day) was significantly associated with increased risks of cardiovascular mortality and cardiovascular disease, but high tea and red wine intakes were not. Furthermore, replacing plain water with tea, but not coffee, significantly reduced the risks of all-cause mortality and cardiovascular disease. Replacing other alcoholic beverages with red wine also significantly reduced the risks of all three outcomes. CONCLUSIONS: These findings suggest that tea and red wine, but not coffee, can be part of a healthy diet for the hypertensive population.

Developing deep learning-based strategies to predict the risk of hepatocellular carcinoma among patients with nonalcoholic fatty liver disease from electronic health records.

OBJECTIVE: The accuracy of deep learning models for many disease prediction problems is affected by time-varying covariates, rare incidence, covariate imbalance and delayed diagnosis when using structured electronic health records data. The situation is further exasperated when predicting the risk of one disease on condition of another disease, such as the hepatocellular carcinoma risk among patients with nonalcoholic fatty liver disease due to slow, chronic progression, the scarce of data with both disease conditions and the sex bias of the diseases. The goal of this study is to investigate the extent to which the aforementioned issues influence deep learning performance, and then devised strategies to tackle these challenges. These strategies were applied to improve hepatocellular carcinoma risk prediction among patients with nonalcoholic fatty liver disease. METHODS: We evaluated two representative deep learning models in the task of predicting the occurrence of hepatocellular carcinoma in a cohort of patients with nonalcoholic fatty liver disease (n = 220,838) from a national EHR database. The disease prediction task was carefully formulated as a classification problem while taking censorship and the length of follow-up into consideration. RESULTS: We developed a novel backward masking scheme to deal with the issue of delayed diagnosis which is very common in EHR data analysis and evaluate how the length of longitudinal information after the index date affects disease prediction. We observed that modeling time-varying covariates improved the performance of the algorithms and transfer learning mitigated reduced performance caused by the lack of data. In addition, covariate imbalance, such as sex bias in data impaired performance. Deep learning models trained on one sex and evaluated in the other sex showed reduced performance, indicating the importance of assessing covariate imbalance while preparing data for model training. CONCLUSIONS: The strategies developed in this work can significantly improve the performance of hepatocellular carcinoma risk prediction among patients with nonalcoholic fatty liver disease. Furthermore, our novel strategies can be generalized to apply to other disease risk predictions using structured electronic health records, especially for disease risks on condition of another disease.

Application of membrane separation technology in the purification of pharmaceutical components.

Traditional Chinese medicine (TCM) is often composed of a variety of natural medicines. Its composition is complex, and many of its components can not be analyzed and identified. The first step in the rational application of TCM is to successfully separate the effective components which is also a great inspiration for the development of new drugs. Among the many separation technologies of TCM, the traditional heating concentration separation technology has high energy consumption and low efficiency. As a new separation technology, membrane separation technology has the characteristics of simple operation, high efficiency, environment-friendly and so on. The separation effect of high molecular weight difference solution is better. The applications of several main membrane separation technologies such as microfiltration, nanofiltration, ultrafiltration and reverse osmosis are reviewed, the methods of restoring membrane flux after membrane fouling are discussed, and their large-scale industrial applications in the future are prospected and summarized.

Multiomics and blood-based biomarkers of moyamoya disease: protocol of Moyamoya Omics Atlas (MOYAOMICS).

BACKGROUND: Moyamoya disease (MMD) is a rare and complex cerebrovascular disorder characterized by the progressive narrowing of the internal carotid arteries and the formation of compensatory collateral vessels. The etiology of MMD remains enigmatic, making diagnosis and management challenging. The MOYAOMICS project was initiated to investigate the molecular underpinnings of MMD and explore potential diagnostic and therapeutic strategies. METHODS: The MOYAOMICS project employs a multidisciplinary approach, integrating various omics technologies, including genomics, transcriptomics, proteomics, and metabolomics, to comprehensively examine the molecular signatures associated with MMD pathogenesis. Additionally, we will investigate the potential influence of gut microbiota and brain-gut peptides on MMD development, assessing their suitability as targets for therapeutic strategies and dietary interventions. Radiomics, a specialized field in medical imaging, is utilized to analyze neuroimaging data for early detection and characterization of MMD-related brain changes. Deep learning algorithms are employed to differentiate MMD from other conditions, automating the diagnostic process. We also employ single-cellomics and mass cytometry to precisely study cellular heterogeneity in peripheral blood samples from MMD patients. CONCLUSIONS: The MOYAOMICS project represents a significant step toward comprehending MMD's molecular underpinnings. This multidisciplinary approach has the potential to revolutionize early diagnosis, patient stratification, and the development of targeted therapies for MMD. The identification of blood-based biomarkers and the integration of multiple omics data are critical for improving the clinical management of MMD and enhancing patient outcomes for this complex disease.

Expression levels of ADAMTS 5, 9, and 12 in endometrial polyps and their predictive value for the diagnosis and recurrence of endometrial polyps.

PURPOSE: Endometrial polyps (EPs) are common gynecological disorders for which no clear etiology has been found. ADAMTS have been associated with a variety of diseases. This study aimed to investigate the potential correlation between serologic levels of ADAMTS 5, 9, and 12 in patients with EPs. METHODS: A total of 88 patients were categorized into two groups: the EPs group, consisting of recurrent EPs and first occurrence EPs, and a control group. The study compared the general information and serum levels of ADAMTS 5, 9, and 12 between the groups. RESULTS: Regarding the general data, a statistically significant age difference (p < 0.05) was observed, while no significant differences were found in the other variables. After considering age as a confounding factor, the previously observed statistical significance in the differences of ADAMTS5 and 9 between the groups diminished. However, it was found that the concentrations of ADAMTS12 in both the EPs group and the recurrent EPs group were significantly higher compared to the control group and the first occurrence EPs group (p < 0.05). ROC curves were generated to determine the critical values of ADAMTS12 for predicting EPs and recurrent EPs, which were found to be 0.6962 ng/ml (sensitivity: 100 %, specificity: 39.5 %) and 0.8768 ng/ml (sensitivity: 75.0 %, specificity: 76.3 %), respectively. CONCLUSION: Our findings revealed elevated serologic levels of ADAMTS12 in the EPs group, particularly in the recurrent EPs group. Furthermore, ADAMTS-12 was identified as a valuable biomarker for assisting in the diagnosis and prediction of EPs recurrence.

Dietary Niacin Intake and Mortality Among Individuals With Nonalcoholic Fatty Liver Disease.

Importance: Evidence regarding the effect of dietary niacin intake on the risk of mortality among patients with nonalcoholic fatty liver disease (NAFLD) is scarce. Objective: To examine the association of dietary niacin intake with all-cause mortality and cardiovascular disease (CVD) mortality among individuals with NAFLD. Design, Setting, and Participants: This cohort study used data from the National Health and Nutrition Examination Survey (2003-2018). In total, 4315 adults aged 20 years or older with NAFLD were included, with NAFLD defined using the United States Fatty Liver Index. Exposure: Dietary niacin intake levels. Main Outcomes and Measures: Weighted Cox proportional hazards models and restricted cubic splines were used to estimate hazard ratios and 95% CIs for all-cause and CVD mortality. Data were analyzed March 1 to September 1, 2023. Results: This cohort study included data from 4315 participants in the analysis (mean [SD] age, 52.5 [16.2] years; 1670 participants ≥60 years [weighted, 30.9%]; 2351 men [weighted, 55.0%]). During a median (IQR) follow-up of 8.8 (4.6-11.8) years, 566 deaths were recorded, of which 197 were attributed to CVD. Compared with participants with a niacin intake of 18.4 mg or lower (the lowest tertile), the multivariable-adjusted hazard ratios for participants with a niacin intake of 26.7 mg or higher (the highest tertile) were 0.70 (95% CI, 0.50-0.96) for all-cause mortality (P = .03 for trend) and 0.65 (95% CI, 0.35-1.20) for CVD mortality (P = .16 for trend). Conclusions and Relevance: Findings from this cohort study suggest that higher dietary niacin intake may be associated with lower risk of all-cause mortality among individuals with NAFLD. There was no evident inverse association between dietary niacin intake and the risk of CVD mortality.

Oxygenation of Phenols with Water as the Oxygen Source and Oxoammonium Salt as the Oxidant.

Aromatic C-H oxygenation is important in both industrial production and organic synthesis. Here we report a metal-free approach for phenol oxygenation with water as the oxygen source using oxoammonium salts as the renewable oxidant. Employing this protocol, various alkyl-substituted phenols were converted into benzoquinones in yields of 59-98%. On the basis of 18O-labeling and kinetic studies, the hydroxy-oxoammonium adduct was proposed to attack the aromatic ring similarly to electrophilic aromatic substitution. We suppose that the findings described here not only provide an efficient and highly selective protocol for aromatic C-H oxygenation but also may encourage further developments of possible transition-metal-free catalytic methods.

Develop and Validate a Computable Phenotype for the Identification of Alzheimer's Disease Patients Using Electronic Health Record Data.

INTRODUCTION: Alzheimer's Disease (AD) are often misclassified in electronic health records (EHRs) when relying solely on diagnostic codes. This study aims to develop a more accurate, computable phenotype (CP) for identifying AD patients by using both structured and unstructured EHR data. METHODS: We used EHRs from the University of Florida Health (UF Health) 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 (UT Health) and the University of Minnesota (UMN). RESULTS: Our best-performing CP is " patient has at least 2 AD diagnoses and AD-related keywords " with an F1-score of 0.817 at UF, and 0.961 and 0.623 at UT Health and UMN, respectively. DISCUSSION: We developed and validated rule-based CPs for AD identification with good performance, crucial for studies that aim to use real-world data like EHRs.

Histone lactylation inhibits RARγ expression in macrophages to promote colorectal tumorigenesis through activation of TRAF6-IL-6-STAT3 signaling.

Macrophages are phenotypically and functionally diverse in the tumor microenvironment (TME). However, how to remodel macrophages with a protumor phenotype and how to manipulate them for therapeutic purposes remain to be explored. Here, we show that in the TME, RARγ is downregulated in macrophages, and its expression correlates with poor prognosis in patients with colorectal cancer (CRC). In macrophages, RARγ interacts with tumor necrosis factor receptor-associated factor 6 (TRAF6), which prevents TRAF6 oligomerization and autoubiquitination, leading to inhibition of nuclear factor κB signaling. However, tumor-derived lactate fuels H3K18 lactylation to prohibit RARγ gene transcription in macrophages, consequently enhancing interleukin-6 (IL-6) levels in the TME and endowing macrophages with tumor-promoting functions via activation of signal transducer and activator of transcription 3 (STAT3) signaling in CRC cells. We identified that nordihydroguaiaretic acid (NDGA) exerts effective antitumor action by directly binding to RARγ to inhibit TRAF6-IL-6-STAT3 signaling. This study unravels lactate-driven macrophage function remodeling by inhibition of RARγ expression and highlights NDGA as a candidate compound for treating CRC.

Improving large language models for clinical named entity recognition via prompt engineering.

IMPORTANCE: The study highlights the potential of large language models, specifically GPT-3.5 and GPT-4, in processing complex clinical data and extracting meaningful information with minimal training data. By developing and refining prompt-based strategies, we can significantly enhance the models' performance, making them viable tools for clinical NER tasks and possibly reducing the reliance on extensive annotated datasets. OBJECTIVES: This study quantifies the capabilities of GPT-3.5 and GPT-4 for clinical named entity recognition (NER) tasks and proposes task-specific prompts to improve their performance. MATERIALS AND METHODS: We evaluated these models on 2 clinical NER tasks: (1) to extract medical problems, treatments, and tests from clinical notes in the MTSamples corpus, following the 2010 i2b2 concept extraction shared task, and (2) to identify nervous system disorder-related adverse events from safety reports in the vaccine adverse event reporting system (VAERS). To improve the GPT models' performance, we developed a clinical task-specific prompt framework that includes (1) baseline prompts with task description and format specification, (2) annotation guideline-based prompts, (3) error analysis-based instructions, and (4) annotated samples for few-shot learning. We assessed each prompt's effectiveness and compared the models to BioClinicalBERT. RESULTS: Using baseline prompts, GPT-3.5 and GPT-4 achieved relaxed F1 scores of 0.634, 0.804 for MTSamples and 0.301, 0.593 for VAERS. Additional prompt components consistently improved model performance. When all 4 components were used, GPT-3.5 and GPT-4 achieved relaxed F1 socres of 0.794, 0.861 for MTSamples and 0.676, 0.736 for VAERS, demonstrating the effectiveness of our prompt framework. Although these results trail BioClinicalBERT (F1 of 0.901 for the MTSamples dataset and 0.802 for the VAERS), it is very promising considering few training samples are needed. DISCUSSION: The study's findings suggest a promising direction in leveraging LLMs for clinical NER tasks. However, while the performance of GPT models improved with task-specific prompts, there's a need for further development and refinement. LLMs like GPT-4 show potential in achieving close performance to state-of-the-art models like BioClinicalBERT, but they still require careful prompt engineering and understanding of task-specific knowledge. The study also underscores the importance of evaluation schemas that accurately reflect the capabilities and performance of LLMs in clinical settings. CONCLUSION: While direct application of GPT models to clinical NER tasks falls short of optimal performance, our task-specific prompt framework, incorporating medical knowledge and training samples, significantly enhances GPT models' feasibility for potential clinical applications.

Dynamic Prognosis Prediction for Patients on DAPT After Drug-Eluting Stent Implantation: Model Development and Validation.

BACKGROUND: The rapid evolution of artificial intelligence (AI) in conjunction with recent updates in dual antiplatelet therapy (DAPT) management guidelines emphasizes the necessity for innovative models to predict ischemic or bleeding events after drug-eluting stent implantation. Leveraging AI for dynamic prediction has the potential to revolutionize risk stratification and provide personalized decision support for DAPT management. METHODS AND RESULTS: We developed and validated a new AI-based pipeline using retrospective data of drug-eluting stent-treated patients, sourced from the Cerner Health Facts data set (n=98 236) and Optum's de-identified Clinformatics Data Mart Database (n=9978). The 36 months following drug-eluting stent implantation were designated as our primary forecasting interval, further segmented into 6 sequential prediction windows. We evaluated 5 distinct AI algorithms for their precision in predicting ischemic and bleeding risks. Model discriminative accuracy was assessed using the area under the receiver operating characteristic curve, among other metrics. The weighted light gradient boosting machine stood out as the preeminent model, thus earning its place as our AI-DAPT model. The AI-DAPT demonstrated peak accuracy in the 30 to 36 months window, charting an area under the receiver operating characteristic curve of 90% [95% CI, 88%-92%] for ischemia and 84% [95% CI, 82%-87%] for bleeding predictions. CONCLUSIONS: Our AI-DAPT excels in formulating iterative, refined dynamic predictions by assimilating ongoing updates from patients' clinical profiles, holding value as a novel smart clinical tool to facilitate optimal DAPT duration management with high accuracy and adaptability.

A novel machine learning-derived four-gene signature predicts STEMI and post-STEMI heart failure.

High mortality and morbidity rates associated with ST-elevation myocardial infarction (STEMI) and post-STEMI heart failure (HF) necessitate proper risk stratification for coronary artery disease (CAD). A prediction model that combines specificity and convenience is highly required. This study aimed to design a monocyte-based gene assay for predicting STEMI and post-STEMI HF. A total of 1,956 monocyte expression profiles and corresponding clinical data were integrated from multiple sources. Meta-results were obtained through the weighted gene co-expression network analysis (WGCNA) and differential analysis to identify characteristic genes for STEMI. Machine learning models based on the decision tree (DT), support vector machine (SVM), and random forest (RF) algorithms were trained and validated. Five genes overlapped and were subjected to the model proposal. The discriminative performance of the DT model outperformed the other two methods. The established four-gene panel (HLA-J, CFP, STX11, and NFYC) could discriminate STEMI and HF with an area under the curve (AUC) of 0.86 or above. In the gene set enrichment analysis (GSEA), several cardiac pathogenesis pathways and cardiovascular disorder signatures showed statistically significant, concordant differences between subjects with high and low expression levels of the four-gene panel, affirming the validity of the established model. In conclusion, we have developed and validated a model that offers the hope for accurately predicting the risk of STEMI and HF, leading to optimal risk stratification and personalized management of CAD, thereby improving individual outcomes.