Gate-tunable subband degeneracy in semiconductor nanowires.

Degeneracy and symmetry have a profound relation in quantum systems. Here, we report gate-tunable subband degeneracy in PbTe nanowires with a nearly symmetric cross-sectional shape. The degeneracy is revealed in electron transport by the absence of a quantized plateau. Utilizing a dual gate design, we can apply an electric field to lift the degeneracy, reflected as emergence of the plateau. This degeneracy and its tunable lifting were challenging to observe in previous nanowire experiments, possibly due to disorder. Numerical simulations can qualitatively capture our observation, shedding light on device parameters for future applications.

Selective-Area-Grown PbTe-Pb Planar Josephson Junctions for Quantum Devices.

Planar Josephson junctions are predicted to host Majorana zero modes. The material platforms in previous studies are two-dimensional electron gases (InAs, InSb, InAsSb, and HgTe) coupled to a superconductor such as Al or Nb. Here, we introduce a new material platform for planar JJs, the PbTe-Pb hybrid. The semiconductor, PbTe, was grown as a thin film via selective area epitaxy. The Josephson junction was defined by a shadow wall during the deposition of superconductor Pb. Scanning transmission electron microscopy reveals a sharp semiconductor-superconductor interface. Gate-tunable supercurrents and multiple Andreev reflections are observed. A perpendicular magnetic field causes interference patterns of the switching current, exhibiting Fraunhofer-like and SQUID-like behaviors. We further demonstrate a prototype device for Majorana detection wherein phase bias and tunneling spectroscopy are applicable.

Semi-automatic proximal humeral trabecular bone density assessment tool: technique application and clinical validation.

PURPOSE: This study aimed to apply a newly developed semi-automatic phantom-less QCT (PL-QCT) to measure proximal humerus trabecular bone density based on chest CT and verify its accuracy and precision. METHODS: Subcutaneous fat of the shoulder joint and trapezius muscle were used as calibration references for PL-QCT BMD measurement. A self-developed algorithm based on a convolution map was utilized in PL-QCT for semi-automatic BMD measurements. CT values of ROIs used in PL-QCT measurements were directly used for phantom-based quantitative computed tomography (PB-QCT) BMD assessment. The study included 376 proximal humerus for comparison between PB-QCT and PL-QCT. Two sports medicine doctors measured the proximal humerus with PB-QCT and PL-QCT without knowing each other's results. Among them, 100 proximal humerus were included in the inter-operative and intra-operative BMD measurements for evaluating the repeatability and reproducibility of PL-QCT and PB-QCT. RESULTS: A total of 188 patients with 376 shoulders were involved in this study. The consistency analysis indicated that the average bias between proximal humerus BMDs measured by PB-QCT and PL-QCT was 1.0 mg/cc (agreement range - 9.4 to 11.4; P > 0.05, no significant difference). Regression analysis between PB-QCT and PL-QCT indicated a good correlation (R-square is 0.9723). Short-term repeatability and reproducibility of proximal humerus BMDs measured by PB-QCT (CV: 5.10% and 3.41%) were slightly better than those of PL-QCT (CV: 6.17% and 5.64%). CONCLUSIONS: We evaluated the bone quality of the proximal humeral using chest CT through the semi-automatic PL-QCT system for the first time. Comparison between it and PB-QCT indicated that it could be a reliable shoulder BMD assessment tool with acceptable accuracy and precision. This study developed and verify a semi-automatic PL-QCT for assessment of proximal humeral bone density based on CT to assist in the assessment of proximal humeral osteoporosis and development of individualized treatment plans for shoulders.

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.

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.

Ballistic PbTe Nanowire Devices.

Disorder is the primary obstacle in the current Majorana nanowire experiments. Reducing disorder or achieving ballistic transport is thus of paramount importance. In clean and ballistic nanowire devices, quantized conductance is expected, with plateau quality serving as a benchmark for disorder assessment. Here, we introduce ballistic PbTe nanowire devices grown by using the selective-area-growth (SAG) technique. Quantized conductance plateaus in units of 2e2/h are observed at zero magnetic field. This observation represents an advancement in diminishing disorder within SAG nanowires as most of the previously studied SAG nanowires (InSb or InAs) have not exhibited zero-field ballistic transport. Notably, the plateau values indicate that the ubiquitous valley degeneracy in PbTe is lifted in nanowire devices. This degeneracy lifting addresses an additional concern in the pursuit of Majorana realization. Moreover, these ballistic PbTe nanowires may enable the search for clean signatures of the spin-orbit helical gap in future devices.

Oral mucosal graft ureteroplasty versus ileal ureteric replacement: a meta-analysis.

OBJECTIVES: To describe outcomes of oral mucosal graft ureteroplasty (OMGU) and ileal ureter replacement (IUR) and determine the relative merits of both procedures. METHODS: Databases (including PubMed, Embase and Cochrane) were interrogated for eligible trials that assessed outcomes of OMGU or IUR from 2000 to 30 July 2022. The variables analysed were reconstruction success rates, stricture length, hospital stays, perioperative complications and long-term complications. RESULTS: A total of 23 single-arm studies were included. The pooled reconstruction success rates for OMGU and IUR were 94.9% (95% confidence interval [CI] 91.0%-97.7%) and 85.8% (95% CI 81.0%-90.0%), respectively. Stricture length of patients in the OMGU and IUR groups were 3.73 (95% CI 3.17-4.28) and 11.55 (95% CI 9.82-13.29) cm, respectively. The maximal stricture length repaired by OMGU was 8 cm. The hospital stays were 5.85 (95% CI 3.88-7.82) and 11.55 (95% CI 6.93-16.17) days in the OMGU and IUR groups, respectively. The incidences of low-grade postoperative complications were 13.6% (95% CI 6.9%-20.3%) and 27.3% (95% CI 19.5%-35.1%), high-grade postoperative complications were 4.6% (95% CI 1.8I-8.5%) and 13.0% (95% CI 9.4%-17.1%), and long-term complications (occurred at > 3months) were 9.0% (95% CI 1.7%-20.0%) and 35.4% (95% CI 25.8%-45.6%) in the OMGU and IUR groups, respectively. CONCLUSION: An OMGU is an effective, minimally invasive, and safe alternative to IUR for the management of long ureteric strictures. OMGU was the preferred treatment for long ureteric strictures, especially obstructed ureter segments of ≤8 cm.

Contextualized medication information extraction using Transformer-based deep learning architectures.

OBJECTIVE: To develop a natural language processing (NLP) system to extract medications and contextual information that help understand drug changes. This project is part of the 2022 n2c2 challenge. MATERIALS AND METHODS: We developed NLP systems for medication mention extraction, event classification (indicating medication changes discussed or not), and context classification to classify medication changes context into 5 orthogonal dimensions related to drug changes. We explored 6 state-of-the-art pretrained transformer models for the three subtasks, including GatorTron, a large language model pretrained using > 90 billion words of text (including > 80 billion words from > 290 million clinical notes identified at the University of Florida Health). We evaluated our NLP systems using annotated data and evaluation scripts provided by the 2022 n2c2 organizers. RESULTS: Our GatorTron models achieved the best F1-scores of 0.9828 for medication extraction (ranked 3rd), 0.9379 for event classification (ranked 2nd), and the best micro-average accuracy of 0.9126 for context classification. GatorTron outperformed existing transformer models pretrained using smaller general English text and clinical text corpora, indicating the advantage of large language models. CONCLUSION: This study demonstrated the advantage of using large transformer models for contextual medication information extraction from clinical narratives.

Identify diabetic retinopathy-related clinical concepts and their attributes using transformer-based natural language processing methods.

BACKGROUND: Diabetic retinopathy (DR) is a leading cause of blindness in American adults. If detected, DR can be treated to prevent further damage causing blindness. There is an increasing interest in developing artificial intelligence (AI) technologies to help detect DR using electronic health records. The lesion-related information documented in fundus image reports is a valuable resource that could help diagnoses of DR in clinical decision support systems. However, most studies for AI-based DR diagnoses are mainly based on medical images; there is limited studies to explore the lesion-related information captured in the free text image reports. METHODS: In this study, we examined two state-of-the-art transformer-based natural language processing (NLP) models, including BERT and RoBERTa, compared them with a recurrent neural network implemented using Long short-term memory (LSTM) to extract DR-related concepts from clinical narratives. We identified four different categories of DR-related clinical concepts including lesions, eye parts, laterality, and severity, developed annotation guidelines, annotated a DR-corpus of 536 image reports, and developed transformer-based NLP models for clinical concept extraction and relation extraction. We also examined the relation extraction under two settings including 'gold-standard' setting-where gold-standard concepts were used-and end-to-end setting. RESULTS: For concept extraction, the BERT model pretrained with the MIMIC III dataset achieve the best performance (0.9503 and 0.9645 for strict/lenient evaluation). For relation extraction, BERT model pretrained using general English text achieved the best strict/lenient F1-score of 0.9316. The end-to-end system, BERT_general_e2e, achieved the best strict/lenient F1-score of 0.8578 and 0.8881, respectively. Another end-to-end system based on the RoBERTa architecture, RoBERTa_general_e2e, also achieved the same performance as BERT_general_e2e in strict scores. CONCLUSIONS: This study demonstrated the efficiency of transformer-based NLP models for clinical concept extraction and relation extraction. Our results show that it's necessary to pretrain transformer models using clinical text to optimize the performance for clinical concept extraction. Whereas, for relation extraction, transformers pretrained using general English text perform better.

Mutagenesis of putative ciliary genes with the CRISPR/Cas9 system in zebrafish identifies genes required for retinal development.

Cilia are conserved microtubule-based organelles that function as mechanical and chemical sensors in various cell types. By bioinformatic, genomic, and proteomic studies, more than 2000 proteins have been identified as cilium-associated proteins or putative ciliary proteins; these proteins are referred to as the ciliary proteome or the ciliome. However, little is known about the function of these numerous putative ciliary proteins in cilia. To identify the possible new functional proteins or pathways in cilia, we carried out a small-scale genetic screen targeting 54 putative ciliary genes by using the clustered regularly interspaced short palindromic repeats/CRISPR-associated protein 9 (CRISPR/Cas9) system. We successfully constructed 54 zebrafish mutants, and 8 of them displayed microphthalmias. Three of these 8 genes encode proteins for protein transport, suggesting the important roles of protein transport in retinal development. In situ hybridization revealed that all these genes are expressed in zebrafish eyes. Furthermore, polo-like kinase 1 was required for ciliogenesis in neural tube. We uncovered the potential function of the ciliary genes for the retinal development of zebrafish.-Hu, R., Huang, W., Liu, J., Jin, M., Wu, Y., Li, J., Wang, J., Yu, Z., Wang, H., Cao, Y. Mutagenesis of putative ciliary genes with the CRISPR/Cas9 system in zebrafish identifies genes required for retinal development.

DebSDF: Delving into the Details and Bias of Neural Indoor Scene Reconstruction.

In recent years, the neural implicit surface has emerged as a powerful representation for multi-view surface reconstruction due to its simplicity and state-of-the-art performance. However, reconstructing smooth and detailed surfaces in indoor scenes from multi-view images presents unique challenges. Indoor scenes typically contain large texture-less regions, making the photometric loss unreliable for optimizing the implicit surface. Previous work utilizes monocular geometry priors to improve the reconstruction in indoor scenes. However, monocular priors often contain substantial errors in thin structure regions due to domain gaps and the inherent inconsistencies when derived independently from different views. This paper presents DebSDF to address these challenges, focusing on the utilization of uncertainty in monocular priors and the bias in SDF-based volume rendering. We propose an uncertainty modeling technique that associates larger uncertainties with larger errors in the monocular priors. High-uncertainty priors are then excluded from optimization to prevent bias. This uncertainty measure also informs an importance-guided ray sampling and adaptive smoothness regularization, enhancing the learning of fine structures. We further introduce a bias-aware signed distance function to density transformation that takes into account the curvature and the angle between the view direction and the SDF normals to reconstruct fine details better. Our approach has been validated through extensive experiments on several challenging datasets, demonstrating improved qualitative and quantitative results in reconstructing thin structures in indoor scenes, thereby outperforming previous work.

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.

LncRNA MACC1-AS1 induces gemcitabine resistance in pancreatic cancer cells through suppressing ferroptosis.

Pancreatic ductal adenocarcinoma (PDA) mortality is primarily attributed to metastasis and chemotherapy resistance. In this research, the long non-coding RNA MACC1-AS1 was studied, playing a significant role in regulating lipid oxidation processes. This regulation could further lead to the inhibition of ferroptosis induced by chemotherapeutic drugs, making it a contributing factor to gemcitabine resistance in PDA. In both gemcitabine-resistant PDA patients and mouse models, the elevated expression level of MACC1-AS1 in the tumors was noted. Additionally, overexpression of MACC1-AS1 in pancreatic cancer cells was found to enhance tolerance to gemcitabine and suppress ferroptosis. Proteomic analysis of drug-resistant pancreatic cells revealed that overexpressed MACC1-AS1 inhibited the ubiquitination degradation of residues in the protein kinase STK33 by MDM4. Furthermore, its accumulation in the cytoplasm activated STK33, further activating the ferroptosis-suppressing proteins GPX4, thereby counteracting gemcitabine-induced cellular oxidative damage. These findings suggested that the long non-coding RNA MACC1-AS1 could play a significant role in the ability of pancreatic cancer cells to evade iron-mediated ferroptosis induced by gemcitabine. This discovery holds promise for developing clinical therapeutic strategies to combat chemotherapy resistance in pancreatic cancer.

TransFuser: Imitation With Transformer-Based Sensor Fusion for Autonomous Driving.

How should we integrate representations from complementary sensors for autonomous driving? Geometry-based fusion has shown promise for perception (e.g., object detection, motion forecasting). However, in the context of end-to-end driving, we find that imitation learning based on existing sensor fusion methods underperforms in complex driving scenarios with a high density of dynamic agents. Therefore, we propose TransFuser, a mechanism to integrate image and LiDAR representations using self-attention. Our approach uses transformer modules at multiple resolutions to fuse perspective view and bird's eye view feature maps. We experimentally validate its efficacy on a challenging new benchmark with long routes and dense traffic, as well as the official leaderboard of the CARLA urban driving simulator. At the time of submission, TransFuser outperforms all prior work on the CARLA leaderboard in terms of driving score by a large margin. Compared to geometry-based fusion, TransFuser reduces the average collisions per kilometer by 48%.

Machine learning-based prediction of surgical benefit in borderline resectable and locally advanced pancreatic cancer.

INTRODUCTION: Surgery represents a primary therapeutic approach for borderline resectable and locally advanced pancreatic cancer (BR/LAPC). However, BR/LAPC lesions exhibit high heterogeneity and not all BR/LAPC patients who undergo surgery can derive beneficial outcomes. The present study aims to employ machine learning (ML) algorithms to identify those who would obtain benefits from the primary tumor surgery. METHODS: We retrieved clinical data of patients with BR/LAPC from the Surveillance, Epidemiology, and End Results (SEER) database and classified them into surgery and non-surgery groups based on primary tumor surgery status. To eliminate confounding factors, propensity score matching (PSM) was employed. We hypothesized that patients who underwent surgery and had a longer median cancer-specific survival (CSS) than those who did not undergo surgery would certainly benefit from surgical intervention. Clinical and pathological features were utilized to construct six ML models, and model effectiveness was compared through measures such as the area under curve (AUC), calibration plots, and decision curve analysis (DCA). We selected the best-performing algorithm (i.e., XGBoost) to predict postoperative benefits. The SHapley Additive exPlanations (SHAP) approach was used to interpret the XGBoost model. Additionally, data from 53 Chinese patients prospectively collected was used for external validation of the model. RESULTS: According to the results of the tenfold cross-validation in the training cohort, the XGBoost model yielded the best performance (AUC = 0.823, 95%CI 0.707-0.938). The internal (74.3% accuracy) and external (84.3% accuracy) validation demonstrated the generalizability of the model. The SHAP analysis provided explanations independent of the model, highlighting important factors related to postoperative survival benefits in BR/LAPC, with age, chemotherapy, and radiation therapy being the top three important factors. CONCLUSION: By integrating of ML algorithms and clinical data, we have established a highly efficient model to facilitate clinical decision-making and assist clinicians in selecting the population that would benefit from surgery.

Clinical concept and relation extraction using prompt-based machine reading comprehension.

OBJECTIVE: To develop a natural language processing system that solves both clinical concept extraction and relation extraction in a unified prompt-based machine reading comprehension (MRC) architecture with good generalizability for cross-institution applications. METHODS: We formulate both clinical concept extraction and relation extraction using a unified prompt-based MRC architecture and explore state-of-the-art transformer models. We compare our MRC models with existing deep learning models for concept extraction and end-to-end relation extraction using 2 benchmark datasets developed by the 2018 National NLP Clinical Challenges (n2c2) challenge (medications and adverse drug events) and the 2022 n2c2 challenge (relations of social determinants of health [SDoH]). We also evaluate the transfer learning ability of the proposed MRC models in a cross-institution setting. We perform error analyses and examine how different prompting strategies affect the performance of MRC models. RESULTS AND CONCLUSION: The proposed MRC models achieve state-of-the-art performance for clinical concept and relation extraction on the 2 benchmark datasets, outperforming previous non-MRC transformer models. GatorTron-MRC achieves the best strict and lenient F1-scores for concept extraction, outperforming previous deep learning models on the 2 datasets by 1%-3% and 0.7%-1.3%, respectively. For end-to-end relation extraction, GatorTron-MRC and BERT-MIMIC-MRC achieve the best F1-scores, outperforming previous deep learning models by 0.9%-2.4% and 10%-11%, respectively. For cross-institution evaluation, GatorTron-MRC outperforms traditional GatorTron by 6.4% and 16% for the 2 datasets, respectively. The proposed method is better at handling nested/overlapped concepts, extracting relations, and has good portability for cross-institute applications. Our clinical MRC package is publicly available at https://github.com/uf-hobi-informatics-lab/ClinicalTransformerMRC.

Mild photothermal therapy assist in promoting bone repair: Related mechanism and materials.

Achieving precision treatment in bone tissue engineering (BTE) remains a challenge. Photothermal therapy (PTT), as a form of precision therapy, has been extensively investigated for its safety and efficacy. It has demonstrated significant potential in the treatment of orthopedic diseases such as bone tumors, postoperative infections and osteoarthritis. However, the high temperatures associated with PTT can lead to certain limitations and drawbacks. In recent years, researchers have explored the use of biomaterials for mild photothermal therapy (MPT), which offers a promising approach for addressing these limitations. This review provides a comprehensive overview of the mechanisms underlying MPT and presents a compilation of photothermal agents and their utilization strategies for bone tissue repair. Additionally, the paper discusses the future prospects of MPT-assisted bone tissue regeneration, aiming to provide insights and recommendations for optimizing material design in this field.

Extracting Thyroid Nodules Characteristics from Ultrasound Reports Using Transformer-based Natural Language Processing Methods.

The ultrasound characteristics of thyroid nodules guide the evaluation of thyroid cancer in patients with thyroid nodules. However, the characteristics of thyroid nodules are often documented in clinical narratives such as ultrasound reports. Previous studies have examined natural language processing (NLP) methods in extracting a limited number of characteristics (<9) using rule-based NLP systems. In this study, a multidisciplinary team of NLP experts and thyroid specialists, identified thyroid nodule characteristics that are important for clinical care, composed annotation guidelines, developed a corpus, and compared 5 state-of-the-art transformer-based NLP methods, including BERT, RoBERTa, LongFormer, DeBERTa, and GatorTron, for extraction of thyroid nodule characteristics from ultrasound reports. Our GatorTron model, a transformer-based large language model trained using over 90 billion words of text, achieved the best strict and lenient F1-score of 0.8851 and 0.9495 for the extraction of a total number of 16 thyroid nodule characteristics, and 0.9321 for linking characteristics to nodules, outperforming other clinical transformer models. To the best of our knowledge, this is the first study to systematically categorize and apply transformer-based NLP models to extract a large number of clinical relevant thyroid nodule characteristics from ultrasound reports. This study lays ground for assessing the documentation quality of thyroid ultrasound reports and examining outcomes of patients with thyroid nodules using electronic health records.

Assessing the Documentation of Social Determinants of Health for Lung Cancer Patients in Clinical Narratives.

Social determinants of health (SDoH) are important factors associated with cancer risk and treatment outcomes. There is an increasing interest in exploring SDoH captured in electronic health records (EHRs) to assess cancer risk and outcomes; however, most SDoH are only captured in free-text clinical narratives such as physicians' notes that are not readily accessible. In this study, we applied a natural language processing (NLP) system to identify 15 categories of SDoH from a total of 10,855 lung cancer patients at the University of Florida Health. We aggregated the SDoH concepts into patient-level and assessed how each of the 15 categories of SDoH were documented in cancer patient's notes. To the best of our knowledge, this is one of the first studies to examine the documentation of SDoH in clinical narratives from a real-world lung cancer patient cohort. This study could guide future studies to better utilize SDoH information documented in clinical narratives.