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.

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.

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.

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.

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.

Large language models as decision aids in neuro-oncology: a review of shared decision-making applications.

Shared decision-making (SDM) is crucial in neuro-oncology, fostering collaborations between patients and healthcare professionals to navigate treatment options. However, the complexity of neuro-oncological conditions and the cognitive and emotional burdens on patients present significant barriers to achieving effective SDM. This discussion explores the potential of large language models (LLMs) such as OpenAI's ChatGPT and Google's Bard to overcome these barriers, offering a means to enhance patient understanding and engagement in their care. LLMs, by providing accessible, personalized information, could support but not supplant the critical insights of healthcare professionals. The hypothesis suggests that patients, better informed through LLMs, may participate more actively in their treatment choices. Integrating LLMs into neuro-oncology requires navigating ethical considerations, including safeguarding patient data and ensuring informed consent, alongside the judicious use of AI technologies. Future efforts should focus on establishing ethical guidelines, adapting healthcare workflows, promoting patient-oriented research, and developing training programs for clinicians on the use of LLMs. Continuous evaluation of LLM applications will be vital to maintain their effectiveness and alignment with patient needs. Ultimately, this exploration contends that the thoughtful integration of LLMs into SDM processes could significantly enhance patient involvement and strengthen the patient-physician relationship in neuro-oncology care.

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.

Study on chitosan/gelatin hydrogels containing ceria nanoparticles for promoting the healing of diabetic wound.

Chronic inflammation at diabetic wound sites results in the uncontrolled accumulation of pro-inflammatory factors and reactive oxygen species (ROS), which impedes cell proliferation and delays wound healing. To promote the healing of diabetic wounds, chitosan/gelatin hydrogels containing ceria nanoparticles (CNPs) of various sizes were created in the current study. CNPs' efficacy in removing O 2 • - $$ {\mathrm{O}}_2^{\bullet -} $$ , •OH, and H2 O2 was demonstrated, and the scavenging ability of CNPs of varying sizes was compared. The in vitro experiments demonstrated that hydrogels containing CNPs could effectively protect cells from ROS-induced damage and facilitate mouse fibroblast migration. Furthermore, during the treatment of diabetic wounds in vivo, hydrogels containing CNPs exhibited anti-inflammatory activity and could reduce the expression of the pro-inflammatory factors TNF-α (above 30%), IL-6 (above 90%), and IL-1ß (above 80%), and effectively promote wound closure (above 80%) by inducing re-epithelialization, collagen deposition, and angiogenesis. In addition, the biological properties and therapeutic effects of hydrogels containing CNPs of various sizes were compared and discussed. The finding revealed that hydrogels with 4 nm CNPs exhibited more significant biological properties and had implications for diabetic wound treatment.

Thyroid Ultrasound Appropriateness Identification Through Natural Language Processing of Electronic Health Records.

Objective: To address thyroid cancer overdiagnosis, we aim to develop a natural language processing (NLP) algorithm to determine the appropriateness of thyroid ultrasounds (TUS). Patients and Methods: Between 2017 and 2021, we identified 18,000 TUS patients at Mayo Clinic and selected 628 for chart review to create a ground truth dataset based on consensus. We developed a rule-based NLP pipeline to identify TUS as appropriate TUS (aTUS) or inappropriate TUS (iTUS) using patients' clinical notes and additional meta information. In addition, we designed an abbreviated NLP pipeline (aNLP) solely focusing on labels from TUS order requisitions to facilitate deployment at other health care systems. Our dataset was split into a training set of 468 (75%) and a test set of 160 (25%), using the former for rule development and the latter for performance evaluation. Results: There were 449 (95.9%) patients identified as aTUS and 19 (4.06%) as iTUS in the training set; there are 155 (96.88%) patients identified as aTUS and 5 (3.12%) were iTUS in the test set. In the training set, the pipeline achieved a sensitivity of 0.99, specificity of 0.95, and positive predictive value of 1.0 for detecting aTUS. The testing cohort revealed a sensitivity of 0.96, specificity of 0.80, and positive predictive value of 0.99. Similar performance metrics were observed in the aNLP pipeline. Conclusion: The NLP models can accurately identify the appropriateness of a thyroid ultrasound from clinical documentation and order requisition information, a critical initial step toward evaluating the drivers and outcomes of TUS use and subsequent thyroid cancer overdiagnosis.

Model tuning or prompt Tuning? a study of large language models for clinical concept and relation extraction.

OBJECTIVE: To develop soft prompt-based learning architecture for large language models (LLMs), examine prompt-tuning using frozen/unfrozen LLMs, and assess their abilities in transfer learning and few-shot learning. METHODS: We developed a soft prompt-based learning architecture and compared 4 strategies including (1) fine-tuning without prompts; (2) hard-prompting with unfrozen LLMs; (3) soft-prompting with unfrozen LLMs; and (4) soft-prompting with frozen LLMs. We evaluated GatorTron, a clinical LLM with up to 8.9 billion parameters, and compared GatorTron with 4 existing transformer models for clinical concept and relation extraction on 2 benchmark datasets for adverse drug events and social determinants of health (SDoH). We evaluated the few-shot learning ability and generalizability for cross-institution applications. RESULTS AND CONCLUSION: When LLMs are unfrozen, GatorTron-3.9B with soft prompting achieves the best strict F1-scores of 0.9118 and 0.8604 for concept extraction, outperforming the traditional fine-tuning and hard prompt-based models by 0.6 âˆ¼ 3.1 % and 1.2 âˆ¼ 2.9 %, respectively; GatorTron-345 M with soft prompting achieves the best F1-scores of 0.8332 and 0.7488 for end-to-end relation extraction, outperforming other two models by 0.2 âˆ¼ 2 % and 0.6 âˆ¼ 11.7 %, respectively. When LLMs are frozen, small LLMs have a big gap to be competitive with unfrozen models; scaling LLMs up to billions of parameters makes frozen LLMs competitive with unfrozen models. Soft prompting with a frozen GatorTron-8.9B model achieved the best performance for cross-institution evaluation. We demonstrate that (1) machines can learn soft prompts better than hard prompts composed by human, (2) frozen LLMs have good few-shot learning ability and generalizability for cross-institution applications, (3) frozen LLMs reduce computing cost to 2.5 âˆ¼ 6 % of previous methods using unfrozen LLMs, and (4) frozen LLMs require large models (e.g., over several billions of parameters) for good performance.

Feasibility of Identifying Factors Related to Alzheimer's Disease and Related Dementia in Real-World Data.

A comprehensive view of factors associated with AD/ADRD will significantly aid in studies to develop new treatments for AD/ADRD and identify high-risk populations and patients for prevention efforts. In our study, we summarized the risk factors for AD/ADRD by reviewing existing meta-analyses and review articles on risk and preventive factors for AD/ADRD. In total, we extracted 477 risk factors in 10 categories from 537 studies. We constructed an interactive knowledge map to disseminate our study results. Most of the risk factors are accessible from structured Electronic Health Records (EHRs), and clinical narratives show promise as information sources. However, evaluating genomic risk factors using RWD remains a challenge, as genetic testing for AD/ADRD is still not a common practice and is poorly documented in both structured and unstructured EHRs. Considering the constantly evolving research on AD/ADRD risk factors, literature mining via NLP methods offers a solution to automatically update our knowledge map.

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.

Real-World Effectiveness of Lung Cancer Screening Using Deep Learning-Based Counterfactual Prediction.

The benefits and harms of lung cancer screening (LCS) for patients in the real-world clinical setting have been argued. Recently, discriminative prediction modeling of lung cancer with stratified risk factors has been developed to investigate the real-world effectiveness of LCS from observational data. However, most of these studies were conducted at the population level that only measured the difference in the average outcome between groups. In this study, we built counterfactual prediction models for lung cancer risk and mortality and examined for individual patients whether LCS as a hypothetical intervention reduces lung cancer risk and subsequent mortality. We investigated traditional and deep learning (DL)-based causal methods that provide individualized treatment effect (ITE) at the patient level and evaluated them with a cohort from the OneFlorida+ Clinical Research Consortium. We further discussed and demonstrated that the ITE estimation model can be used to personalize clinical decision support for a broader population.

Rational Photodeposition of Cobalt Phosphate on Flower-like ZnIn2S4 for Efficient Photocatalytic Hydrogen Evolution.

The high electrons and holes recombination rate of ZnIn2S4 significantly limits its photocatalytic performance. Herein, a simple in situ photodeposition strategy is adopted to introduce the cocatalyst cobalt phosphate (Co-Pi) on ZnIn2S4, aiming at facilitating the separation of electron-hole by promoting the transfer of photogenerated holes of ZnIn2S4. The study reveals that the composite catalyst has superior photocatalytic performance than blank ZnIn2S4. In particular, ZnIn2S4 loaded with 5% Co-Pi (ZnIn2S4/5%Co-Pi) has the best photocatalytic activity, and the H2 production rate reaches 3593 µmol·g-1·h-1, approximately double that of ZnIn2S4 alone. Subsequent characterization data demonstrate that the introduction of the cocatalyst Co-Pi facilitates the transfer of ZnIn2S4 holes, thus improving the efficiency of photogenerated carrier separation. This investigation focuses on the rational utilization of high-content and rich cocatalysts on earth to design low-cost and efficient composite catalysts to achieve sustainable photocatalytic hydrogen evolution.

Heterogeneous treatment effects of metformin on risk of dementia in patients with type 2 diabetes: A longitudinal observational study.

INTRODUCTION: Little is known about the heterogeneous treatment effects of metformin on dementia risk in people with type 2 diabetes (T2D). METHODS: Participants (≥ 50 years) with T2D and normal cognition at baseline were identified from the National Alzheimer's Coordinating Center database (2005-2021). We applied a doubly robust learning approach to estimate risk differences (RD) with a 95% confidence interval (CI) for dementia risk between metformin use and no use in the overall population and subgroups identified through a decision tree model. RESULTS: Among 1393 participants, 104 developed dementia over a 4-year median follow-up. Metformin was significantly associated with a lower risk of dementia in the overall population (RD, -3.2%; 95% CI, -6.2% to -0.2%). We identified four subgroups with varied risks for dementia, defined by neuropsychiatric disorders, non-steroidal anti-inflammatory drugs, and antidepressant use. DISCUSSION: Metformin use was significantly associated with a lower risk of dementia in individuals with T2D, with significant variability among subgroups.