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.

Predicting Overall Survival with Deep Learning from 18F-FDG PET-CT Images in Patients with Hepatocellular Carcinoma before Liver Transplantation.

Positron emission tomography and computed tomography with 18F-fluorodeoxyglucose (18F-FDG PET-CT) were used to predict outcomes after liver transplantation in patients with hepatocellular carcinoma (HCC). However, few approaches for prediction based on 18F-FDG PET-CT images that leverage automatic liver segmentation and deep learning were proposed. This study evaluated the performance of deep learning from 18F-FDG PET-CT images to predict overall survival in HCC patients before liver transplantation (LT). We retrospectively included 304 patients with HCC who underwent 18F-FDG PET/CT before LT between January 2010 and December 2016. The hepatic areas of 273 of the patients were segmented by software, while the other 31 were delineated manually. We analyzed the predictive value of the deep learning model from both FDG PET/CT images and CT images alone. The results of the developed prognostic model were obtained by combining FDG PET-CT images and combining FDG CT images (0.807 AUC vs. 0.743 AUC). The model based on FDG PET-CT images achieved somewhat better sensitivity than the model based on CT images alone (0.571 SEN vs. 0.432 SEN). Automatic liver segmentation from 18F-FDG PET-CT images is feasible and can be utilized to train deep-learning models. The proposed predictive tool can effectively determine prognosis (i.e., overall survival) and, thereby, select an optimal candidate of LT for patients with HCC.

Differentiation Between Malignant and Benign Pulmonary Nodules by Using Automated Three-Dimensional High-Resolution Representation Learning With Fluorodeoxyglucose Positron Emission Tomography-Computed Tomography.

Background: The investigation of incidental pulmonary nodules has rapidly become one of the main indications for 18F-fluorodeoxyglucose (FDG) positron emission tomography (PET), currently combined with computed tomography (PET-CT). There is also a growing trend to use artificial Intelligence for optimization and interpretation of PET-CT Images. Therefore, we proposed a novel deep learning model that aided in the automatic differentiation between malignant and benign pulmonary nodules on FDG PET-CT. Methods: In total, 112 participants with pulmonary nodules who underwent FDG PET-CT before surgery were enrolled retrospectively. We designed a novel deep learning three-dimensional (3D) high-resolution representation learning (HRRL) model for the automated classification of pulmonary nodules based on FDG PET-CT images without manual annotation by experts. For the images to be localized more precisely, we defined the territories of the lungs through a novel artificial intelligence-driven image-processing algorithm, instead of the conventional segmentation method, without the aid of an expert; this algorithm is based on deep HRRL, which is used to perform high-resolution classification. In addition, the 2D model was converted to a 3D model. Results: All pulmonary lesions were confirmed through pathological studies (79 malignant and 33 benign). We evaluated its diagnostic performance in the differentiation of malignant and benign nodules. The area under the receiver operating characteristic curve (AUC) of the deep learning model was used to indicate classification performance in an evaluation using fivefold cross-validation. The nodule-based prediction performance of the model had an AUC, sensitivity, specificity, and accuracy of 78.1, 89.9, 54.5, and 79.4%, respectively. Conclusion: Our results suggest that a deep learning algorithm using HRRL without manual annotation from experts might aid in the classification of pulmonary nodules discovered through clinical FDG PET-CT images.

Catalpol improves impaired neurovascular unit in ischemic stroke rats via enhancing VEGF-PI3K/AKT and VEGF-MEK1/2/ERK1/2 signaling.

Neurovascular unit (NVU) is organized multi-cellular and multi-component networks that are essential for brain health and brain homeostasis maintaining. Neurovascular unit dysfunction is the central pathogenesis process of ischemic stroke. Thus integrated protection of NVU holds great therapeutic potential for ischemic stroke. Catalpol, classified into the iridoid monosaccharide glycoside, is the main active ingredient of the radix from traditional Chinese medicine, Rehmannia glutinosa Libosch, that exhibits protective effects in several brain-related diseases. In the present study, we investigated whether catalpol exerted protective effects for NVU in ischemic stroke and the underlying mechanisms. MCAO rats were administered catalpol (2.5, 5.0, 10.0 mg·kg-1·d-1, i.v.) for 14 days. We showed that catalpol treatment dose-dependently reduced the infarction volume and significantly attenuated neurological deficits score in MCAO rats. Furthermore, catalpol treatment significantly ameliorated impaired NVU in ischemic region by protecting vessel-neuron-astrocyte structures and morphology, and promoting angiogenesis and neurogenesis to replenish lost vessels and neurons. Moreover, catalpol treatment significantly increased the expression of vascular endothelial growth factor (VEGF) through up-regulating PI3K/AKT signaling, followed by increasing FAK and Paxillin and activating PI3K/AKT and MEK1/2/ERK1/2 pathways. The protective mechanisms of catalpol were confirmed in an in vitro three-dimensional NVU model subjected to oxygen-glucose deprivation. In conclusion, catalpol protects NVU in ischemic region via activation of PI3K/AKT signaling and increased VEGF production; VEGF further enhances PI3K/AKT and MEK1/2/ERK1/2 signaling, which may trigger a partly feed-forward loop to protect NVU from ischemic stroke.

Enhancement of Anticancer Potential of Pterostilbene Derivative by Chalcone Hybridization.

Pterostilbene, a natural metabolite of resveratrol, has been indicated as a potent anticancer molecule. Recently, several pterostilbene derivatives have been reported to exhibit better anticancer activities than that of the parent pterostilbene molecule. In the present study, a series of pterostilbene derivatives were designed and synthesized by the hybridization of pterostilbene, chalcone, and cinnamic acid. The cytotoxic effect of these hybrid molecules was determined using two oral cancer cell lines, HSC-3 and OECM-1. (E)-3-(2-((E)-4-Hydroxystyryl)-4,6-dimethoxyphenyl)-1-(2-methoxyphenyl)prop-2-en-1-one (4d), with IC50 of 16.38 and 18.06 µM against OECM-1 and HSC-3, respectively, was selected for further anticancer mechanism studies. Results indicated that compound 4d effectively inhibited cell proliferation and induced G2/M cell cycle arrest via modulating p21, cyclin B1, and cyclin A2. Compound 4d ultimately induced cell apoptosis by reducing the expression of Bcl-2 and surviving. In addition, cleavage of PARP and caspase-3 were enhanced following the treatment of compound 4d with increased dose. To conclude, a number of pterostilbene derivatives were discovered to possess potent anticancer potentials. Among them, compound 4d was the most active, more active than the parent pterostilbene.

Electronic medical record-based deep data cleaning and phenotyping improve the diagnostic validity and mortality assessment of infective endocarditis: medical big data initiative of CMUH.

BACKGROUND: International Classification of Diseases (ICD) code-based claims databases are often used to study infective endocarditis (IE). However, the quality of ICD coding can influence the reliability of IE research. The impact of complementing the ICD-only approach with data extracted from electronic medical records (EMRs) has yet to be explored. METHODS: We selected the information of adult patients with discharge ICD codes for IE (ICD-9: 421, 112.81, 036.42, 098.84, 115.04, 115.14, 115.94, 424.9; ICD-10: I33, I38, I39) during 2005-2016 in China Medical University Hospital. Data extraction was conducted on the basis of the modified Duke criteria to establish a reference group comprising patients with definite or possible IE. Clinical characteristics and in-hospital mortality were compared between ICD-identified and Duke-confirmed cases. The positive predictive value (PPV) was used to quantify the IE identification performance of various phenotyping algorithms. RESULTS: A total of 593 patients with discharge ICD codes for IE were identified, only 56.7% met the modified Duke criteria. The crude in-hospital mortality for Duke-confirmed and Duke-rejected IE were 24.4% and 8.2%, respectively. The adjusted in-hospital mortality for ICD-identified IE was lower than that for Duke-confirmed IE by a difference of 5.1%. The best PPV was achieved (0.90, 95% CI 0.86-0.93) when major components of the Duke criteria (positive blood culture and vegetation) were integrated with ICD codes. CONCLUSION: Integrating EMR data can considerably improve the accuracy of ICD-only approaches in phenotyping IE, which can improve the validity of EMR-based studies and their applications, including real-time surveillance and clinical decision support.

Novel histone deacetylase inhibitor AR-42 exhibits antitumor activity in pancreatic cancer cells by affecting multiple biochemical pathways.

OBJECTIVE: Pancreatic cancer is one of the most lethal types of cancer with a 5-year survival rate of ~5%. Histone deacetylases (HDACs) participate in many cellular processes, including carcinogenesis, and pharmacological inhibition of HDACs has emerged as a potential therapeutic strategy. In this study, we explored antitumor activity of the novel HDAC inhibitor AR-42 in pancreatic cancer. METHODS: Human pancreatic cancer cell lines BxPC-3 and PANC-1 were used in this study. Real-time PCR, RT-PCR, and western blotting were employed to investigate expression of specific genes and proteins, respectively. Translocation of apoptosis-inducing factor was investigated by immunofluorescence and subcellular fractionation. The number of apoptotic cells, cell cycle stages, and reactive oxygen species (ROS) generation levels were determined by flow cytometry. Cell invasiveness was examined by the Matrigel invasion assay. Efficacy of AR-42 in vivo was evaluated by utilizing BxPC-3 xenograft mouse model. RESULTS: AR-42 inhibited pancreatic cancer cell proliferation by causing G2/M cell cycle arrest via regulating expression levels of genes and proteins involved in cell cycle. AR-42 also induced ROS generation and DNA damage, triggering apoptosis of pancreatic cancer cells via both caspase-3-dependent and caspase-3-independent pathways. In addition, AR-42 increased expression levels of negative regulators of p53 (miR-125b, miR-30d, and miR33), which could contribute to lower expression level of mutant p53 in pancreatic cancer cells. Cell invasion assay showed that AR-42 reduced cancer cell aggressiveness and significantly diminished BxPC-3 xenograft tumor growth in vivo. CONCLUSION: AR-42, a novel HDAC inhibitor, inhibited pancreatic cancer cells by regulating p53 expression, inducing cell cycle arrest, particularly at the G2/M stage, and activating multiple apoptosis pathways. Additionally, AR-42 inhibited cell invasiveness and potently suppressed pancreatic cancer tumors in vivo. We conclude that by virtue of its multiple mechanisms of action, AR-42 possesses a considerable potential as an antitumor agent in pancreatic cancer.

OSU-A9 inhibits pancreatic cancer cell lines by modulating p38-JAK-STAT3 signaling.

Pancreatic cancer is an aggressive malignancy that is the fourth leading cause of death worldwide. Since there is a dire need for novel and effective therapies to improve the poor survival rates of advanced pancreatic cancer patients, we analyzed the antitumor effects of OSU-A9, an indole-3-carbinol derivative, on pancreatic cancer cell lines in vitro and in vivo. OSU-A9 exhibited a stronger antitumor effect than gemcitabine on two pancreatic cancer cell lines, including gemcitabine-resistant PANC-1 cells. OSU-A9 treatment induced apoptosis, the down-regulation of Akt phosphorylation, up-regulation of p38 phosphorylation and decreased phosphorylation of JAK and STAT3. Cell migration and invasiveness assays showed that OSU-A9 reduced cancer cell aggressiveness and inhibited BxPC-3 xenograft growth in nude mice. These results suggest that OSU-A9 modulates the p38-JAK-STAT3 signaling module, thereby inducing cytotoxicity in pancreatic cancer cells. Continued evaluation of OSU-A9 as a potential therapeutic agent for pancreatic cancer thus appears warrented.

Mutagenesis identifies the critical amino acid residues of human endonuclease G involved in catalysis, magnesium coordination, and substrate specificity.

BACKGROUND: Endonuclease G (EndoG), a member of DNA/RNA nonspecific betabetaalpha-Me-finger nucleases, is involved in apoptosis and normal cellular proliferation. In this study, we analyzed the critical amino acid residues of EndoG and proposed the catalytic mechanism of EndoG. METHODS: To identify the critical amino acid residues of human EndoG, we replaced the conserved histidine, asparagine, and arginine residues with alanine. The catalytic efficacies of Escherichia coli-expressed EndoG variants were further analyzed by kinetic studies. RESULTS: Diethyl pyrocarbonate modification assay revealed that histidine residues were involved in EndoG activity. His-141, Asn-163, and Asn-172 in the H-N-H motif of EndoG were critical for catalysis and substrate specificity. H141A mutant required a higher magnesium concentration to achieve its activity, suggesting the unique role of His-141 in both catalysis and magnesium coordination. Furthermore, an additional catalytic residue (Asn-251) and an additional metal ion binding site (Glu-271) of human EndoG were identified. CONCLUSION: Based on the mutational analysis and homology modeling, we proposed that human EndoG shared a similar catalytic mechanism with nuclease A from Anabaena.