Hybrid-Pattern Recognition Modeling with Arrhythmia Signal Processing for Ubiquitous Health Management.

We established a web-based ubiquitous health management (UHM) system, "ECG4UHM", for processing ECG signals with AI-enabled models to recognize hybrid arrhythmia patterns, including atrial premature atrial complex (APC), atrial fibrillation (AFib), ventricular premature complex (VPC), and ventricular tachycardia (VT), versus normal sinus rhythm (NSR). The analytical model coupled machine learning methods, such as multiple layer perceptron (MLP), random forest (RF), support vector machine (SVM), and naive Bayes (NB), to process the hybrid patterns of four arrhythmia symptoms for AI computation. The data pre-processing used Hilbert-Huang transform (HHT) with empirical mode decomposition to calculate ECGs' intrinsic mode functions (IMFs). The area centroids of the IMFs' marginal Hilbert spectrum were suggested as the HHT-based features. We engaged the MATLABTM compiler and runtime server in the ECG4UHM to build the recognition modules for driving AI computation to identify the arrhythmia symptoms. The modeling extracted the crucial data sets from the MIT-BIH arrhythmia open database. The validated models, including the premature pattern (i.e., APC-VPC) and the fibril-rapid pattern (i.e., AFib-VT) against NSR, could reach the best area under the curve (AUC) of the receiver operating characteristic (ROC) of approximately 0.99. The models for all hybrid patterns, without VPC versus AFib and VT, achieved an average accuracy of approximately 90%. With the prediction test, the respective AUCs of the NSR and APC versus the AFib, VPC, and VT were 0.94 and 0.93 for the RF and SVM on average. The average accuracy and the AUC of the MLP, RF, and SVM models for APC-VT reached the value of 0.98. The self-developed system with AI computation modeling can be the backend of the intelligent social-health system that can recognize hybrid arrhythmia patterns in the UHM and home-isolated cares.

Personalized Rehabilitation Recognition for Ubiquitous Healthcare Measurements.

The physical therapeutic application needs personalized rehabilitation recognition (PRR) for ubiquitous healthcare measurements (UHMs). This study employed the adaptive neuro-fuzzy inference system (ANFIS) to generate a PRR model for a self-development system of UHM. The subjects wore a sensor-enabled wristband during physiotherapy exercises to measure the scheduled motions of their limbs. In the model, the sampling data collected from the scheduled motions are labeled by an arbitrary number within a defined range. The sample datasets are referred as the design of an initial fuzzy inference system (FIS) with data preprocessing, feature visualizing, fuzzification, and fuzzy logic rules. The ANFIS then processes data training to adjust the FIS for optimization. The trained FIS then can infer the motion labels via defuzzification to recognize the features in the test data. The average recognition rate was higher than 90% for the testing motions if the subject followed the sampling schedule. With model implementation, the middle section of motion datasets in each second is recommended for recognition in the UHM system which also includes a mobile App to retrieve the personalized FIS in order to trace the exercise. This approach contributes a PRR model with trackable diagrams for the physicians to explore the rehabilitation motions in details.

Performance of ChatGPT incorporated chain-of-thought method in bilingual nuclear medicine physician board examinations.

Objective: This research explores the performance of ChatGPT, compared to human doctors, in bilingual, Mandarin Chinese and English, medical specialty exam in Nuclear Medicine in Taiwan. Methods: The study employed generative pre-trained transformer (GPT-4) and integrated chain-of-thoughts (COT) method to enhance performance by triggering and explaining the thinking process to answer the question in a coherent and logical manner. Questions from the Taiwanese Nuclear Medicine Specialty Exam served as the basis for testing. The research analyzed the correctness of AI responses in different sections of the exam and explored the influence of question length and language proportion on accuracy. Results: AI, especially ChatGPT with COT, exhibited exceptional capabilities in theoretical knowledge, clinical medicine, and handling integrated questions, often surpassing, or matching human doctor performance. However, AI struggled with questions related to medical regulations. The analysis of question length showed that questions within the 109-163 words range yielded the highest accuracy. Moreover, an increase in the proportion of English words in questions improved both AI and human accuracy. Conclusions: This research highlights the potential and challenges of AI in the medical field. ChatGPT demonstrates significant competence in various aspects of medical knowledge. However, areas like medical regulations require improvement. The study also suggests that AI may help in evaluating exam question difficulty and maintaining fairness in examinations. These findings shed light on AI role in the medical field, with potential applications in healthcare education, exam preparation, and multilingual environments. Ongoing AI advancements are expected to further enhance AI utility in the medical domain.

Early prediction of distant metastasis in patients with uterine cervical cancer treated with definitive chemoradiotherapy by deep learning using pretreatment [ 18 F]fluorodeoxyglucose positron emission tomography/computed tomography.

OBJECTIVES: A deep learning (DL) model using image data from pretreatment [ 18 F]fluorodeoxyglucose ([ 18 F] FDG)-PET or computed tomography (CT) augmented with a novel imaging augmentation approach was developed for the early prediction of distant metastases in patients with locally advanced uterine cervical cancer. METHODS: This study used baseline [18F]FDG-PET/CT images of newly diagnosed uterine cervical cancer patients. Data from 186 to 25 patients were analyzed for training and validation cohort, respectively. All patients received chemoradiotherapy (CRT) and follow-up. PET and CT images were augmented by using three-dimensional techniques. The proposed model employed DL to predict distant metastases. Receiver operating characteristic (ROC) curve analysis was performed to measure the model's predictive performance. RESULTS: The area under the ROC curves of the training and validation cohorts were 0.818 and 0.830 for predicting distant metastasis, respectively. In the training cohort, the sensitivity, specificity, and accuracy were 80.0%, 78.0%, and 78.5%, whereas, the sensitivity, specificity, and accuracy for distant failure were 73.3%, 75.5%, and 75.2% in the validation cohort, respectively. CONCLUSION: Through the use of baseline [ 18 F]FDG-PET/CT images, the proposed DL model can predict the development of distant metastases for patients with locally advanced uterine cervical cancer treatment by CRT. External validation must be conducted to determine the model's predictive performance.

Improving pharmaceutical protein production in Oryza sativa.

Application of plant expression systems in the production of recombinant proteins has several advantages, such as low maintenance cost, absence of human pathogens, and possession of complex post-translational glycosylation capabilities. Plants have been successfully used to produce recombinant cytokines, vaccines, antibodies, and other proteins, and rice (Oryza sativa) is a potential plant used as recombinant protein expression system. After successful transformation, transgenic rice cells can be either regenerated into whole plants or grown as cell cultures that can be upscaled into bioreactors. This review summarizes recent advances in the production of different recombinant protein produced in rice and describes their production methods as well as methods to improve protein yield and quality. Glycosylation and its impact in plant development and protein production are discussed, and several methods of improving yield and quality that have not been incorporated in rice expression systems are also proposed. Finally, different bioreactor options are explored and their advantages are analyzed.

Imaging prediction of KRAS mutation in patients with rectal cancer through deep metric learning using pretreatment [18F]Fluorodeoxyglucose positron emission tomography/computed tomography.

OBJECTIVES: To predict KRAS mutation in rectal cancer (RC) through computer vision of [18F]fluorodeoxyglucose (18F-FDG) positron emission tomography (PET)/computed tomography (CT) by using metric learning (ML). METHODS: This study included 160 patients with RC who had undergone preoperative PET/CT. KRAS mutation was identified through polymerase chain reaction analysis. This model combined ML with the deep-learning framework to analyze PET data with or without CT images. The Batch Balance Wrapper framework and K-fold cross-validation were employed during the learning process. A receiver operating characteristic (ROC) curve analysis was performed to assess the model's predictive performance. RESULTS: Genetic alterations in KRAS were identified in 82 (51%) tumors. Both PET and CT images were used, and the proposed model had an area under the ROC curve of 0.836 for its ability to predict a mutation status. The sensitivity, specificity, and accuracy were 75.3%, 79.3%, and 77.5%, respectively. When PET images alone were used, the area under the curve was 0.817, whereas the sensitivity, specificity, and accuracy were 73.2%, 79.6%, and 76.2%, respectively. CONCLUSIONS: The ML model presented herein revealed that baseline 18F-FDG PET/CT images could provide supplemental information to determine KRAS mutation in RC. Additional studies are required to maximize the predictive accuracy. ADVANCES IN KNOWLEDGE: The results of the ML model presented herein indicate that baseline 18F-FDG PET/CT images could provide supplemental information for determining KRAS mutation in RC.The predictive accuracy of the model was 77.5% when both image types were used and 76.2% when PET images alone were used. Additional studies are required to maximize the predictive accuracy.

Long-term metal fume exposure assessment of workers in a shipbuilding factory.

This study aims to assess the metal fume exposure of welders and to determine exposure rates for similar exposure groups in a shipyard through the use of Near-field/Far-field (NF/FF) mathematical model and Bayesian decision analysis (BDA) technique. Emission rates of various metal fumes (i.e., total chromium (Cr), iron (Fe), lead (Pb), manganese (Mn), and nickel (Ni)) were experimentally determined for the gas metal arc welding and flux cored arc welding processes, which are commonly used in shipyards. Then the NF/FF field model which used the emission rates were further validated by welding simulation experiment, and together with long-term operation condition data obtained from the investigated shipyard, the predicted long-term exposure concentrations of workers was established and used as the prior distribution in the BDA. Along with the field monitoring metal fume concentrations which served as the likelihood distribution, the posterior decision distributions in the BDA were determined and used to assess workers' long-term metal exposures. Results show that the predicted exposure concentrations (Cp) and the field worker's exposure concentrations (Cm) were statistically correlated, and the high R2 (= 0.81-0.94) indicates that the proposed surrogate predicting method by the NF and FF model was adequate for predicting metal fume concentrations. The consistency in both prior and likelihood distributions suggests the resultant posterior would be more feasible to assess workers' long-term exposures. Welders' Fe, Mn and Pb exposures were found to exceed their corresponding action levels with a high probability (= 54%), indicating preventive measures should be taken immediately. The proposed approach provides a universal solution for conducting exposure assessment with usual limited number of personal exposure data.

A novel low-molecular-weight chitosan/gamma-polyglutamic acid polyplexes for nucleic acid delivery into zebrafish larvae.

Many challenges, such as virus infection, extreme weather and long cultivation periods, during the development of fish larvae have been observed, especially in aquaculture. Gene delivery is a useful method to express functional genes to defend against these challengers. However, the methods for fish larvae are insufficient. In our earlier report, low-molecular-weight chitosan (LMWCS) showed a strong positive charge and may be useful for polyplex formulation. Herein, we present a simple self-assembly of LMWCS polyplexes (LMWCSrNPs) for gene delivery into zebrafish larvae. Different weight ratios of LMWCS/gamma-polyglutamic acid (γ-PGA)/plasmid DNA were analyzed by gel mobility assay. Delivery efficiency determined by green fluorescent protein (GFP) expression in zebrafish liver (ZFL) cells showed that delivery efficiency at a weight ratio of 20:8:1 was higher than others. Zeta potential and transmission electron microscopy (TEM) analysis showed that the round shape of the particle size varied. In our earlier reports, IRF9S2C could induce interferon-stimulated gene (ISG) expression to induce innate immunity in zebrafish and pufferfish. Further delivery of pcDNA3-IRF9S2C-HA plasmid DNA into ZFL cells and zebrafish larvae by LMWCSrNP successfully induced ISG expression. Collectively, LMWCSrNP could be a novel gene delivery system for zebrafish larvae and might be used to improve applications in aquaculture.

UBE2S activates NF-κB signaling by binding with IκBα and promotes metastasis of lung adenocarcinoma cells.

PURPOSE: Nuclear factor (NF)-κB signaling in cancer cells has been reported to be involved in tumorigenesis. Phosphorylation and degradation of inhibitor of NF-κBα (IκBα) is a canonical pathway of NF-κB signaling. Here, we aimed to identify and characterize noncanonical activation of NF-κB signaling by ubiquitin-conjugating enzyme E2S (UBE2S) in lung adenocarcinoma cells. METHODS: TCGA and the Human Atlas Protein Database were used to analyze the survival rate of lung adenocarcinoma patients in conjunction with UBE2S expression. In addition, PC9, H460, H441 and A549 lung adenocarcinoma cells were used in this study. PC9 and H460 cells were selected for further analysis because they expressed different UBE2S protein levels. Specific IKK inhibitors, PS1145 and SC514, were used to assess IκBα phosphorylation. Western blot analysis was used to assess protein levels in PC9 and H460 cells. A scratch wound-healing assay was used to analyze the migrative abilities of PC9 and H460 cells. Overexpression and knockdown of UBE2S in H460 and PC9 cells were used to analyze their effects on downstream protein levels. Immunoprecipitation, immunofluorescent staining, glutathione S transferase (GST) pull-down and in vitro binding assays were used to analyze the interaction between UBE2S and IκBα. A luciferase assay was used to analyze activation of NF-κB signaling regulated by UBE2S. An in vivo zebrafish xenograft model was used to assess metastasis of PC9 cells regulated by UBE2S. RESULTS: We found that UBE2S expression in lung adenocarcinoma patients was negatively related to survival rate. The protein level of UBE2S was higher in PC9 cells than in H460 cells, which was opposite to that observed for IκBα. PC9 cells showed a higher UBE2S expression and migrative ability than H460 cells. Phosphorylation of IκBα was not changed by treatment with the IKK-specific inhibitors PS1145 and SC514 in PC9 and H460 cells. Overexpression and knockdown of UBE2S in H460 and PC9 cells revealed that the protein levels of IκBα were inversely regulated. Immunoprecipitation, immunofluorescent staining, GST pull-down and in vitro binding assays revealed direct binding of UBE2S with IκBα. Nuclear P65 protein levels and luciferase assays showed that NF-κB signaling was regulated by UBE2S. The expression of epithelial-to-mesenchymal (EMT) markers and the migrative ability of lung adenocarcinoma cells were also regulated by UBE2S. A zebrafish xenograft tumor model showed a reduction in the metastasis of PC9 cells that was induced by UBE2S knockdown. CONCLUSIONS: Higher UBE2S expression in lung adenocarcinomas may lead to increased binding with IκBα to activate NF-κB signaling and promote adenocarcinoma cell metastasis. UBE2S may serve as a potential therapeutic target for lung adenocarcinomas.

Exposure profiles of workers from indium tin oxide target manufacturing and recycling factories in Taiwan.

Indium tin oxide exposure poses a potential health risk, but the exposure assessment in occupational setting remains incomplete and continues to be a significant challenge. To this end, we investigated the association of work type, airborne indium concentration, respirable fraction of total indium, and cumulative indium exposure index (CEI) with the levels of plasma indium (P-In) and urinary indium (U-In) among 302 indium tin oxide target manufacturing and recycling workers in Taiwan. We observed that recycling-crushing produced the highest concentrations of total indium (area: 2084.8 µg/m3; personal: 3494.5 µg/m3) and respirable indium (area: 533.4 µg/m3; personal: 742.0 µg/m3). Powdering produced the highest respirable fraction of total indium (area: 58.6%; personal: 81.5%), where the workers had the highest levels of P-In (geometric mean: 2.0 µg/L) and U-In (1.0 µg/g creatinine). After adjusting for the confounder, the CEIs of powdering (ßPR = 0.78; ßPR = 0.44), bonding (ßPT = 0.61; ßPT = 0.37), and processing workers (ßPT = 0.43; ßPT = 0.28) showed significant associations with P-In and U-In, validating its utility in monitoring the exposure. Also, the respirable fraction of total indium significantly contributed to the increased levels of P-In and U-In among workers. The varying levels of relationship noted between indium exposure and the levels of P-In and U-In among workers with different work types suggested that setting the exposure limits among different work types is warranted.

Prediction of Neoadjuvant Chemoradiotherapy Response in Rectal Cancer with Metric Learning Using Pretreatment 18F-Fluorodeoxyglucose Positron Emission Tomography.

OBJECTIVES: Neoadjuvant chemoradiotherapy (NCRT) followed by surgery is the mainstay of treatment for patients with locally advanced rectal cancer. Based on baseline 18F-fluorodeoxyglucose ([18F]-FDG)-positron emission tomography (PET)/computed tomography (CT), a new artificial intelligence model using metric learning (ML) was introduced to predict responses to NCRT. PATIENTS AND METHODS: This study used the data of 236 patients with newly diagnosed rectal cancer; the data of 202 and 34 patients were for training and validation, respectively. All patients received pretreatment [18F]FDG-PET/CT, NCRT, and surgery. The treatment response was scored by Dworak tumor regression grade (TRG); TRG3 and TRG4 indicated favorable responses. The model employed ML combined with the Uniform Manifold Approximation and Projection for dimensionality reduction. A receiver operating characteristic (ROC) curve analysis was performed to assess the model's predictive performance. RESULTS: In the training cohort, 115 patients (57%) achieved TRG3 or TRG4 responses. The area under the ROC curve was 0.96 for the prediction of a favorable response. The sensitivity, specificity, and accuracy were 98.3%, 96.5%, and 97.5%, respectively. The sensitivity, specificity, and accuracy for the validation cohort were 95.0%, 100%, and 98.8%, respectively. CONCLUSIONS: The new ML model presented herein was used to determined that baseline 18F[FDG]-PET/CT images could predict a favorable response to NCRT in patients with rectal cancer. External validation is required to verify the model's predictive value.

Assessment of airborne and dermal exposure to 2-ethoxyethyl acetate in an occupational environment.

BACKGROUND: Because of its chemical-physical properties, 2-ethoxyethyl acetate (EEAc) can penetrate through the skin. However, no actual occupational environmental studies or empirical dermal exposure measurements have been performed. METHODS: Twenty workers from a commercial label silk screening shop were recruited and they completed a questionnaire of demographic information. Environmental monitoring of EEAc exposure via respiratory and dermal routes was performed for five consecutive working days. RESULTS: Airborne EEAc concentration was over the permissible exposure limit of 5 ppm in 90% of the participants. The dermal EEAc concentration was highest on the palms. The EEAc concentration correlated with skin exposure level (P < 0.001). The dermal EEAc concentrations in individuals who did not wear gloves were higher than in those who wore gloves. CONCLUSIONS: EEAc on the skin is strongly associated with airborne EEAc. Wearing impermeable gloves during high-risk tasks (cleaning process) can reduce EEAc dermal exposure on the palms.

Correcting the gas and particle partitioning of PCDD/F congeners in the flue gas of an iron ore sinter plant.

This study was aimed at developing an approach for correcting the gas and particle partitioning of PCDD/F congeners for samples collected from the flue gas of an iron ore sinter plant. An iron ore sinter plant equipped with an electrostatic precipitator (EP) and a selective catalytic reduction (SCR) was selected. Flue gas samples were collected at EP inlet, EP outlet and SCR outlet. Both particle- and gas-phase PCDD/Fs were analyzed for each collected sample. PCDD/F contents in EP ashes (EP(ash)) were also analyzed and used to correct the gas and particle partitioning of PCDD/F congeners of the collected flue gas samples. Results show that PCDD/Fs in the flue gas were dominated by the gas-phase. Before correction, the removal efficiencies for the gas- and particle-phase PCDD/Fs for EP were -58.1% and 64.3%, respectively, and SCR were 39.4% and 83.9%, respectively. The above results were conflict with the expected results for both EP and SCR indicating the need for correcting the gas and particle partitioning of PCDD/F congeners for all collected flue gas samples. After correction, the removal efficiencies become more reasonable for EP (=4.22% and 97.7%, respectively), and SCR (=54.7% and 62.0%, respectively). The above results confirm the effectiveness of the approach developed by this study.

A pilot study for determining the optimal operation condition for simultaneously controlling the emissions of PCDD/Fs and PAHs from the iron ore sintering process.

In this study, the cost-benefit analysis technique was developed and incorporated into the Taguchi experimental design to determine the optimal operation combination for the purpose of providing a technique solution for controlling both emissions of PCDD/Fs and PAHs, and increasing both the sinter productivity (SP) and sinter strength (SS) simultaneously. Four operating parameters, including the water content, suction pressure, bed height, and type of hearth layer, were selected and all experimental campaigns were conducted on a pilot-scale sinter pot to simulate various sintering operating conditions of a real-scale sinter plant. The resultant optimal combination could reduce the total carcinogenic emissions arising from both emissions of PCDD/Fs and PAHs by 49.8%, and increase the sinter benefit associated with the increase in both SP and SS by 10.1%, as in comparison with the operation condition currently used in the real plant. The ANOVA results indicate that the suction pressure was the most dominant parameter in determining the optimal operation combination. The above result was theoretically plausible since the higher suction pressure provided more oxygen contents leading to the decrease in both PCDD/F and PAH emissions. But it should be noted that the results obtained from the present study were based on pilot scale experiments, conducting confirmation tests in a real scale plant are still necessary in the future.