BACKGROUND: Workplace accidents in the petroleum industry can cause catastrophic damage to people, property, and the environment. Earlier studies in this domain indicate that the majority of the accident report information is available in unstructured text format. Conventional techniques for the analysis of accident data are time-consuming and heavily dependent on experts\' subject knowledge, experience, and judgment. There is a need to develop a machine learning-based decision support system to analyze the vast amounts of unstructured text data that are frequently overlooked due to a lack of appropriate methodology.
METHODS: To address this gap in the literature, we propose a hybrid methodology that uses improved text-mining techniques combined with an un-bias group decision-making framework to combine the output of objective weights (based on text mining) and subjective weights (based on expert opinion) of risk factors to prioritize them. Based on the contextual word embedding models and term frequencies, we extracted five important clusters of risk factors comprising more than 32 risk sub-factors. A heterogeneous group of experts and employees in the petroleum industry were contacted to obtain their opinions on the extracted risk factors, and the best-worst method was used to convert their opinions to weights.
CONCLUSIONS: The applicability of our proposed framework was tested on the data compiled from the accident data released by the petroleum industries in India. Our framework can be extended to accident data from any industry, to reduce analysis time and improve the accuracy in classifying and prioritizing risk factors.

The present study recorded indigenous knowledge of medicinal plants in Shahrbabak, Iran. We described a method using data mining algorithms to predict medicinal plants\' mode of application. Twenty-oneindividuals aged 28 to 81 were interviewed. Firstly, data were collected and analyzed based on quantitative indices such as the informant consensus factor (ICF), the cultural importance index (CI), and the relative frequency of citation (RFC). Secondly, the data was classified by support vector machines, J48 decision trees, neural networks, and logistic regression. So, 141 medicinal plants from 43 botanical families were documented. Lamiaceae, with 18 species, was the dominant family among plants, and plant leaves were most frequently used for medicinal purposes. The decoction was the most commonly used preparation method (56%), and therophytes were the most dominant (48.93%) among plants. Regarding the RFC index, the most important species are Adiantum capillus-veneris L. and Plantago ovata Forssk., while Artemisia auseri Boiss. ranked first based on the CI index. The ICF index demonstrated that metabolic disorders are the most common problems among plants in the Shahrbabak region. Finally, the J48 decision tree algorithm consistently outperforms other methods, achieving 95% accuracy in 10-fold cross-validation and 70-30 data split scenarios. The developed model detects with maximum accuracy how to consume medicinal plants.

BACKGROUND: The semantics of entities extracted from a clinical text can be dramatically altered by modifiers, including entity negation, uncertainty, conditionality, severity, and subject. Existing models for determining modifiers of clinical entities involve regular expression or features weights that are trained independently for each modifier.
METHODS: We develop and evaluate a multi-task transformer architecture design where modifiers are learned and predicted jointly using the publicly available SemEval 2015 Task 14 corpus and a new Opioid Use Disorder (OUD) data set that contains modifiers shared with SemEval as well as novel modifiers specific for OUD. We evaluate the effectiveness of our multi-task learning approach versus previously published systems and assess the feasibility of transfer learning for clinical entity modifiers when only a portion of clinical modifiers are shared.
RESULTS: Our approach achieved state-of-the-art results on the ShARe corpus from SemEval 2015 Task 14, showing an increase of 1.1% on weighted accuracy, 1.7% on unweighted accuracy, and 10% on micro F1 scores.
CONCLUSIONS: We show that learned weights from our shared model can be effectively transferred to a new partially matched data set, validating the use of transfer learning for clinical text modifiers.

UNASSIGNED: To identify the most commonly reported drugs associated with QT interval prolongation in the FDA Adverse Event Reporting System (FAERS) and evaluate their risk for QT interval prolongation.
UNASSIGNED: We employed the preferred term (PT) \"electrocardiogram QT prolonged\" from the Medical Dictionary for Regulatory Activities (MedDRA) 26.0 to identify adverse drug events (ADEs) of QT interval prolongation in the FAERS database from the period 2004-2022. Reporting odds ratio (ROR) was performed to quantify the signals of ADEs.
UNASSIGNED: We listed the top 40 drugs that caused QT interval prolongation. Among them, the 3 drugs with the highest number of cases were quetiapine (1,151 cases, ROR = 7.62), olanzapine (754 cases, ROR = 7.92), and citalopram (720 cases, ROR = 13.63). The two most frequently reported first-level Anatomical Therapeutic Chemical (ATC) groups were the drugs for the nervous system (n = 19, 47.50%) and antiinfectives for systemic use (n = 7, 17.50%). Patients with missing gender (n = 3,482, 23.68%) aside, there were more females (7,536, 51.24%) than males (5,158, 35.07%) were involved. 3,720 patients (25.29%) suffered serious clinical outcomes resulting in deaths or life-threatening conditions. Overall, most drugs that caused QT interval prolongation had early failure types according to the assessment of the Weibull\'s shape parameter (WSP) analysis.
UNASSIGNED: Our study offered a list of drugs that frequently caused QT interval prolongation based on the FAERS system, along with a description of some risk profiles for QT interval prolongation brought on by these drugs. When prescribing these drugs in clinical practice, we should closely monitor the occurrence of ADE for QT interval prolongation.

To evaluate natural language processing (NLP) methods to infer metastatic sites from radiology reports.
A set of 4,522 computed tomography (CT) reports of 550 patients with 14 types of cancer was used to fine-tune four clinical large language models (LLMs) for multilabel classification of metastatic sites. We also developed an NLP information extraction (IE) system (on the basis of named entity recognition, assertion status detection, and relation extraction) for comparison. Model performances were measured by F1 scores on test and three external validation sets. The best model was used to facilitate analysis of metastatic frequencies in a cohort study of 6,555 patients with 53,838 CT reports.
The RadBERT, BioBERT, GatorTron-base, and GatorTron-medium LLMs achieved F1 scores of 0.84, 0.87, 0.89, and 0.91, respectively, on the test set. The IE system performed best, achieving an F1 score of 0.93. F1 scores of the IE system by individual cancer type ranged from 0.89 to 0.96. The IE system attained F1 scores of 0.89, 0.83, and 0.81, respectively, on external validation sets including additional cancer types, positron emission tomography-CT ,and magnetic resonance imaging scans, respectively. In our cohort study, we found that for colorectal cancer, liver-only metastases were higher in de novo stage IV versus recurrent patients (29.7% v 12.2%; P < .001). Conversely, lung-only metastases were more frequent in recurrent versus de novo stage IV patients (17.2% v 7.3%; P < .001).
We developed an IE system that accurately infers metastatic sites in multiple primary cancers from radiology reports. It has explainable methods and performs better than some clinical LLMs. The inferred metastatic phenotypes could enhance cancer research databases and clinical trial matching, and identify potential patients for oligometastatic interventions.

This paper explores the potential of leveraging electronic health records (EHRs) for personalized health research through the application of artificial intelligence (AI) techniques, specifically Named Entity Recognition (NER). By extracting crucial patient information from clinical texts, including diagnoses, medications, symptoms, and lab tests, AI facilitates the rapid identification of relevant data, paving the way for future care paradigms. The study focuses on Non-small cell lung cancer (NSCLC) in Italian clinical notes, introducing a novel set of 29 clinical entities that include both presence or absence (negation) of relevant information associated with NSCLC. Using a state-of-the-art model pretrained on Italian biomedical texts, we achieve promising results (average F1-score of 80.8%), demonstrating the feasibility of employing AI for extracting biomedical information in the Italian language.

This study investigates the relationship between ambient temperature, weather conditions, and types of road accidents in Qazvin province, Iran. The research addresses a significant societal challenge of road accidents, particularly in developing countries like Iran. The objectives are to analyze the correlation between temperature and accident types and to develop a predictive model using data mining techniques. The study employs a quantitative approach, analyzing over 15,000 accident records from 2010 to 2020. The findings reveal a connection between the temperature variable and the type of road accidents as well as weather conditions. Additionally, data mining analysis identifies a predictable pattern among temperature variables, types of road accidents, and weather conditions. Implications of the study underscore the importance of considering temperature and weather conditions as secondary factors influencing accidents. The predictive model can aid decision-makers in formulating effective strategies to reduce accidents. Understanding the relationship between temperature, weather, and accident types enables the design of targeted interventions to enhance road safety. This research contributes valuable insights to accident reduction efforts and emphasizes the significance of addressing environmental variables in road safety planning and policy-making. Moreover, the results of the data mining pattern analysis indicate that car overturning accidents in various weather conditions are the primary type of accidents, followed by chain accidents. However, the types of accidents vary based on different weather conditions and temperatures. The study highlights the intricate connection between weather conditions, temperature, and types of road accidents. By utilizing data mining techniques, the research provides a predictive model for accident patterns, offering valuable insights to enhance road safety strategies.

OBJECTIVE: The Liver Imaging Reporting and Data System (LI-RADS) offers a standardized approach for imaging hepatocellular carcinoma. However, the diverse styles and structures of radiology reports complicate automatic data extraction. Large language models hold the potential for structured data extraction from free-text reports. Our objective was to evaluate the performance of Generative Pre-trained Transformer (GPT)-4 in extracting LI-RADS features and categories from free-text liver magnetic resonance imaging (MRI) reports.
METHODS: Three radiologists generated 160 fictitious free-text liver MRI reports written in Korean and English, simulating real-world practice. Of these, 20 were used for prompt engineering, and 140 formed the internal test cohort. Seventy-two genuine reports, authored by 17 radiologists were collected and de-identified for the external test cohort. LI-RADS features were extracted using GPT-4, with a Python script calculating categories. Accuracies in each test cohort were compared.
RESULTS: On the external test, the accuracy for the extraction of major LI-RADS features, which encompass size, nonrim arterial phase hyperenhancement, nonperipheral \'washout\', enhancing \'capsule\' and threshold growth, ranged from .92 to .99. For the rest of the LI-RADS features, the accuracy ranged from .86 to .97. For the LI-RADS category, the model showed an accuracy of .85 (95% CI: .76, .93).
CONCLUSIONS: GPT-4 shows promise in extracting LI-RADS features, yet further refinement of its prompting strategy and advancements in its neural network architecture are crucial for reliable use in processing complex real-world MRI reports.

Extracting knowledge from hybrid data, comprising both categorical and numerical data, poses significant challenges due to the inherent difficulty in preserving information and practical meanings during the conversion process. To address this challenge, hybrid data processing methods, combining complementary rough sets, have emerged as a promising approach for handling uncertainty. However, selecting an appropriate model and effectively utilizing it in data mining requires a thorough qualitative and quantitative comparison of existing hybrid data processing models. This research aims to contribute to the analysis of hybrid data processing models based on neighborhood rough sets by investigating the inherent relationships among these models. We propose a generic neighborhood rough set-based hybrid model specifically designed for processing hybrid data, thereby enhancing the efficacy of the data mining process without resorting to discretization and avoiding information loss or practical meaning degradation in datasets. The proposed scheme dynamically adapts the threshold value for the neighborhood approximation space according to the characteristics of the given datasets, ensuring optimal performance without sacrificing accuracy. To evaluate the effectiveness of the proposed scheme, we develop a testbed tailored for Parkinson\'s patients, a domain where hybrid data processing is particularly relevant. The experimental results demonstrate that the proposed scheme consistently outperforms existing schemes in adaptively handling both numerical and categorical data, achieving an impressive accuracy of 95% on the Parkinson\'s dataset. Overall, this research contributes to advancing hybrid data processing techniques by providing a robust and adaptive solution that addresses the challenges associated with handling hybrid data, particularly in the context of Parkinson\'s disease analysis.

In the production of air conditioners, there are various issues such as complex requirements, redundant stations, excessive man-hours, and low production line balance rate. This paper aims to address these problems by analyzing the historical data of H Company\'s commercial air conditioner production line. The data is categorized into five aspects: station, working hours, standard working hours, labor capacity, and presence of bottleneck processes. To optimize and improve the second production line, this paper applies the production line balance management method based on data mining. It utilizes the decision tree model in data mining and incorporates lean production knowledge from industrial engineering. The goal is to identify crucial factors that affect the balance of the production line and address the issues caused by these factors. The aim is to reduce and eliminate redundant working hours and enhance the balance rate of the production line. By implementing the approach outlined in this paper, the bottleneck time of the second production line was reduced from 96.67 s to 74.6 s, and the production line balance rate increased from 68% to 85%.