Search

Objective The classification of clinical note sections is a critical step before doing more fine-grained natural language processing tasks such as social determinants of health extraction and temporal information extraction. Often, clinical note section classification models that achieve high accuracy for 1 institution experience a large drop of accuracy when transferred to another institution. The objective of this study is to develop methods that classify clinical note sections under the SOAP ("Subjective," "Object," "Assessment," and "Plan") framework with improved transferability. Materials and methods We trained the baseline models by fine-tuning BERT-based models, and enhanced their transferability with continued pretraining, including domain-adaptive pretraining and task-adaptive pretraining. We added in-domain annotated samples during fine-tuning and observed model performance over a varying number of annotated sample size. Finally, we quantified the impact of continued pretraining in equivalence of the number of in-domain annotated samples added. Results We found continued pretraining improved models only when combined with in-domain annotated samples, improving the F 1 score from 0.756 to 0.808, averaged across 3 datasets. This improvement was equivalent to adding 35 in-domain annotated samples. Discussion Although considered a straightforward task when performing in-domain, section classification is still a considerably difficult task when performing cross-domain, even using highly sophisticated neural network-based methods. Conclusion Continued pretraining improved model transferability for cross-domain clinical note section classification in the presence of a small amount of in-domain labeled samples. [ABSTRACT FROM AUTHOR]

Objective Identifying study-eligible patients within clinical databases is a critical step in clinical research. However, accurate query design typically requires extensive technical and biomedical expertise. We sought to create a system capable of generating data model-agnostic queries while also providing novel logical reasoning capabilities for complex clinical trial eligibility criteria. Materials and Methods The task of query creation from eligibility criteria requires solving several text-processing problems, including named entity recognition and relation extraction, sequence-to-sequence transformation, normalization, and reasoning. We incorporated hybrid deep learning and rule-based modules for these, as well as a knowledge base of the Unified Medical Language System (UMLS) and linked ontologies. To enable data-model agnostic query creation, we introduce a novel method for tagging database schema elements using UMLS concepts. To evaluate our system, called LeafAI, we compared the capability of LeafAI to a human database programmer to identify patients who had been enrolled in 8 clinical trials conducted at our institution. We measured performance by the number of actual enrolled patients matched by generated queries. Results LeafAI matched a mean 43% of enrolled patients with 27 225 eligible across 8 clinical trials, compared to 27% matched and 14 587 eligible in queries by a human database programmer. The human programmer spent 26 total hours crafting queries compared to several minutes by LeafAI. Conclusions Our work contributes a state-of-the-art data model-agnostic query generation system capable of conditional reasoning using a knowledge base. We demonstrate that LeafAI can rival an experienced human programmer in finding patients eligible for clinical trials. [ABSTRACT FROM AUTHOR]

With the development of remote monitoring technology and highly integrated circuit technology, the achievement and usage of self-powered wireless low-power electronic components has become a hot research topic nowadays. Harvesting vibration energy from the environment can meet the power consumption requirements of these devices, while it is also of great significance to fully utilize the hidden energy in the environment. The mechanism and three typical working modes of piezoelectric vibration energy harvesting technology are introduced, along with the classification of different excitation types of collectors. The progress of research related to piezoelectric vibration energy harvesting technology is reviewed. Finally, challenging problems in the study of piezoelectric energy harvesting technology are summarized, and the future research and development trend of piezoelectric vibration energy harvesting technology is discussed in the light of the current research status of piezoelectric vibration energy harvesting technology. [ABSTRACT FROM AUTHOR]

Atmospheric pressure chemical vapor deposition (CVD) is presently a promising approach for preparing two-dimensional (2D) MoS2 crystals at high temperatures on SiO2/Si substrates. In this work, we propose an improved CVD method without hydrogen, which can increase formula flexibility by controlling the heating temperature of MoO3 powder and sulfur powder. The results show that the size and coverage of MoS2 domains vary largely, from discrete triangles to continuous film, on substrate. We find that the formation of MoS2 domains is dependent on the nucleation density of MoS2. Laminar flow theory is employed to elucidate the cause of the different shapes of MoS2 domains. The distribution of carrier gas speeds at the substrate surface leads to a change of nucleation density and a variation of domain morphology. Thus, nucleation density and domain morphology can be actively controlled by adjusting the carrier gas flow rate in the experimental system. These results are of significance for understanding the growth regulation of 2D MoS2 crystals. [ABSTRACT FROM AUTHOR]

Objectives: Clinical note section identification helps locate relevant information and could be beneficial for downstream tasks such as named entity recognition. However, the traditional supervised methods suffer from transferability issues. This study proposes a new framework for using large language models (LLMs) for section identification to overcome the limitations., Materials and Methods: We framed section identification as question-answering and provided the section definitions in free-text. We evaluated multiple LLMs off-the-shelf without any training. We also fine-tune our LLMs to investigate how the size and the specificity of the fine-tuning dataset impacts model performance., Results: GPT4 achieved the highest F 1 score of 0.77. The best open-source model (Tulu2-70b) achieved 0.64 and is on par with GPT3.5 (ChatGPT). GPT4 is also found to obtain F 1 scores greater than 0.9 for 9 out of the 27 (33%) section types and greater than 0.8 for 15 out of 27 (56%) section types. For our fine-tuned models, we found they plateaued with an increasing size of the general domain dataset. We also found that adding a reasonable amount of section identification examples is beneficial., Discussion: These results indicate that GPT4 is nearly production-ready for section identification, and seemingly contains both knowledge of note structure and the ability to follow complex instructions, and the best current open-source LLM is catching up., Conclusion: Our study shows that LLMs are promising for generalizable clinical note section identification. They have the potential to be further improved by adding section identification examples to the fine-tuning dataset., Competing Interests: None declared., (© The Author(s) 2024. Published by Oxford University Press on behalf of the American Medical Informatics Association.)

Objective: The classification of clinical note sections is a critical step before doing more fine-grained natural language processing tasks such as social determinants of health extraction and temporal information extraction. Often, clinical note section classification models that achieve high accuracy for 1 institution experience a large drop of accuracy when transferred to another institution. The objective of this study is to develop methods that classify clinical note sections under the SOAP ("Subjective," "Object," "Assessment," and "Plan") framework with improved transferability., Materials and Methods: We trained the baseline models by fine-tuning BERT-based models, and enhanced their transferability with continued pretraining, including domain-adaptive pretraining and task-adaptive pretraining. We added in-domain annotated samples during fine-tuning and observed model performance over a varying number of annotated sample size. Finally, we quantified the impact of continued pretraining in equivalence of the number of in-domain annotated samples added., Results: We found continued pretraining improved models only when combined with in-domain annotated samples, improving the F1 score from 0.756 to 0.808, averaged across 3 datasets. This improvement was equivalent to adding 35 in-domain annotated samples., Discussion: Although considered a straightforward task when performing in-domain, section classification is still a considerably difficult task when performing cross-domain, even using highly sophisticated neural network-based methods., Conclusion: Continued pretraining improved model transferability for cross-domain clinical note section classification in the presence of a small amount of in-domain labeled samples., (© The Author(s) 2023. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For permissions, please email: journals.permissions@oup.com.)

Background: Firearm suicide has been more prevalent among males, but age-adjusted female firearm suicide rates increased by 20% from 2010 to 2020, outpacing the rate increase among males by about 8 percentage points, and female firearm suicide may have different contributing circumstances. In the United States, the National Violent Death Reporting System (NVDRS) is a comprehensive source of data on violent deaths and includes unstructured incident narrative reports from coroners or medical examiners and law enforcement. Conventional natural language processing approaches have been used to identify common circumstances preceding female firearm suicide deaths but failed to identify rarer circumstances due to insufficient training data., Objective: This study aimed to leverage a large language model approach to identify infrequent circumstances preceding female firearm suicide in the unstructured coroners or medical examiners and law enforcement narrative reports available in the NVDRS., Methods: We used the narrative reports of 1462 female firearm suicide decedents in the NVDRS from 2014 to 2018. The reports were written in English. We coded 9 infrequent circumstances preceding female firearm suicides. We experimented with predicting those circumstances by leveraging a large language model approach in a yes/no question-answer format. We measured the prediction accuracy with F 1 -score (ranging from 0 to 1). F 1 -score is the harmonic mean of precision (positive predictive value) and recall (true positive rate or sensitivity)., Results: Our large language model outperformed a conventional support vector machine-supervised machine learning approach by a wide margin. Compared to the support vector machine model, which had F 1 -scores less than 0.2 for most infrequent circumstances, our large language model approach achieved an F 1 -score of over 0.6 for 4 circumstances and 0.8 for 2 circumstances., Conclusions: The use of a large language model approach shows promise. Researchers interested in using natural language processing to identify infrequent circumstances in narrative report data may benefit from large language models., (©Weipeng Zhou, Laura C Prater, Evan V Goldstein, Stephen J Mooney. Originally published in JMIR Mental Health (https://mental.jmir.org), 17.10.2023.)

Text in electronic health records is organized into sections, and classifying those sections into section categories is useful for downstream tasks. In this work, we attempt to improve the transferability of section classification models by combining the dataset-specific knowledge in supervised learning models with the world knowledge inside large language models (LLMs). Surprisingly, we find that zero-shot LLMs out-perform supervised BERT-based models applied to out-of-domain data. We also find that their strengths are synergistic, so that a simple ensemble technique leads to additional performance gains.

As a key component of automating the entire process of applying machine learning to solve real-world problems, automated machine learning model selection is in great need. Many automated methods have been proposed for machine learning model selection, but their inefficiency poses a major problem for handling large data sets. To expedite automated machine learning model selection and lower its resource requirements, we developed a progressive sampling-based Bayesian optimization (PSBO) method to efficiently automate the selection of machine learning algorithms and hyper-parameter values. Our PSBO method showed good performance in our previous tests and has 20 parameters. Each parameter has its own default value and impacts our PSBO method's performance. It is unclear for each of these parameters, how much room for improvement there is over its default value, how sensitive our PSBO method's performance is to it, and what its safe range is. In this paper, we perform a sensitivity analysis of these 20 parameters to answer these questions. Our results show that these parameters' default values work well. There is not much room for improvement over them. Also, each of these parameters has a reasonably large safe range, within which our PSBO method's performance is insensitive to parameter value changes.

BACKGROUND Liver cancer is a common cancer with high morbidity and mortality. Due to the large toxic side effects of chemotherapeutic drugs and the overexpression of multidrug resistance genes in liver cancer, no effective chemotherapeutic drug has yet been found. Therefore, the search for a highly effective, low-toxic, and safe natural anticancer therapy is a hot issue. MATERIAL AND METHODS SMMC-7721 cells (a hepatocellular carcinoma cell line) were treated with different concentrations of oleanolic acid (OA) plus autophagy inhibitor 3-methyladenine (3-MA) (3-MA+OA) or chloroquine (CQ) plus OA (CQ+OA). We used MTT and Hoechst 33258 staining methods to determine the proliferation and apoptotic effect of OA on cells. Flow cytometry was used to detect apoptosis. Mitochondrial function was assessed by measuring mitochondrial membrane potential and adenosine triphosphate (ATP) concentration. To evaluate the ability of OA on apoptosis and autophagy mechanisms on SMMC 7721 cells, the related protein expression for apoptosis, autophagy, and the autophagic pathway were detected and analyzed by western blot. RESULTS OA can inhibit and induce apoptosis of SMMC-7721 in a dose-dependent manner. Compared with the control group, OA significantly reduced the intracellular mitochondrial membrane potential, and the intracellular ATP concentration was also significantly reduced. Moreover, OA reduced the expression of p-Akt and p-mTOR. The expression of p62 was decreased, and LC3-II and Beclin-1 protein expression levels increased. After inhibiting autophagy with 3-MA or CQ, compared with OA alone, cell mitochondrial membrane potential and ATP concentration were significantly reduced, cell p62 expression was reduced, and LC3-II expression was increased, apoptosis-related protein Bax protein was increased, and Bcl-2 protein was decreased, which suggested that 3-MA or CQ treatment increased OA-induced apoptosis of SMMC-7721 cells. This suggested that OA activated autophagy of SMMC-7721 cells in a protective autophagic manner. CONCLUSIONS The study findings suggest that OA combined with autophagy inhibitor 3-MA can better exert its anticancer effect.