In Frontiers in cardiovascular medicine

OBJECTIVES : Idiopathic pulmonary artery hypertension (IPAH) is a rare but life-threaten disease. However, the mechanism underlying IPAH is unclear. In this study, underlying mechanism, infiltration of immune cells, and immune-related hub genes of IPAH were analyzed via bioinformatics.

METHODS : GSE15197, GSE48149, GSE113439, and GSE117261 were merged as lung dataset. Weighted gene correlation network analysis (WGCNA) was used to construct the co-expression gene networks of IPAH. Gene Ontology and pathway enrichment analysis were performed using DAVID, gene set enrichment analysis (GSEA), and gene set variation analysis (GSVA). Infiltration of immune cells in lung samples was analyzed using CIBERSORT. GSE22356 and GSE33463 were merged as peripheral blood mononuclear cells (PBMCs) dataset. Immune-related differentially expressed genes (IRDEGs) of lung and PBMCs dataset were analyzed. Based on the intersection between two sets of IRDEGs, hub genes were screened using machine learning algorithms and validated by RT-qPCR. Finally, competing endogenous RNA (ceRNA) networks of hub genes were constructed.

RESULTS : The gray module was the most relevant module and genes in the module enriched in terms like inflammatory and immune responses. The results of GSEA and GSVA indicated that increasement in cytosolic calcium ion, and metabolism dysregulation play important roles in IPAH. The proportions of T cells CD4 memory resting and macrophage M1 were significantly greater in IPAH group, while the proportions of monocytes and neutrophils were significantly lower in IPAH group. IRDEGs of two datasets were analyzed and the intersection between two set of IRDEGs were identified as candidate hub genes. Predictive models for IPAH were constructed using data from PBMCs dataset with candidate hub genes as potential features via LASSO regression and XGBoost algorithm, respectively. CXCL10 and VIPR1 were identified as hub genes and ceRNA networks of CXCL10 was constructed.

CONCLUSION : Inflammatory response, increasement in cytosolic calcium ion, and metabolism dysregulation play important roles in IPAH. T cells CD4 memory resting and macrophage M1 were significantly infiltrated in lung samples from patients with IPAH. IRDEGs of lung dataset and PBMCs dataset were analyzed, and CXCL10 and VIPR1 were identified as hub genes.

Chen Yubin, Ouyang Tianyu, Yin Yue, Fang Cheng, Tang Can-E, Jiang Longtan, Luo Fanyan

2023

biomarker, ceRNA network, idiopathic pulmonary artery hypertension, immune cells, immune gene, inflammation

In Cureus

Malani Sagar N, Shrivastava Deepti, Raka Mayur S

2023-Feb

artificial intelligence in medicine, artificial neural networks, gynecology, obstetrics, postpartum period, ultrasonography

In Heliyon

Slavin Boris B

2023-Mar

Architectural approach, Artificial intelligence, Artificial intelligence modeling, General artificial intelligence, Intelligence subjectivity

In Frontiers in psychology ; h5-index 92.0

INTRODUCTION : Social media infuses modern relationships with vitality and brings a series of information dissemination with subjective consciousness. Studies have indicated that official Chinese media channels are transforming their communication style from didactic hard persuasion to softened emotional management in the digital era. However, previous studies have rarely provided valid empirical evidence for the communicational transformation. The study fills the gap by providing a longitudinal time-series analysis to reveal the pattern of communication of Chinese digital Chinese official media from 2019 to 2022.

METHOD : The study crawler collected 43,259 posts from the People's Daily's Weibo account from 2019 to 2021. The study analyzed the textual data with using trained artificial intelligence models.

RESULTS : This study explored the practices of the People's Daily's Weibo account from 2019 to 2021, COVID-19 is hardly normalized as it is still used as the justification for extraordinary measures in China. This study confirmed that People's Daily's Weibo account posts are undergoing softenization transformation, with the use of soft news, positive energy promotion, and the embedding of sentiment. Although the outburst of COVID-19 temporarily increased the media's use of hard news, it only occur at the initial stage of the pandemic. Emotional posts occupy a nonnegligible amount of the People's Daily Weibo content. However, the majority of posts are emotionally neutral and contribute to shaping the authoritative image of the party press.

DISCUSSION : Overall, the People's Daily has softened their communication style on digital platforms and used emotional mobilization, distraction, and timely information provision to balance the political logic of building an authoritative media agency and the media logic of constructing audience relevance.

Zhang Chang, Zhang Dechun, Shao Hsuan Lei

2023

COVID-19, China, Weibo, propoganda, state-run media

In Frontiers in oncology

BACKGROUND : Demand for head and neck cancer (HNC) radiotherapy data in algorithmic development has prompted increased image dataset sharing. Medical images must comply with data protection requirements so that re-use is enabled without disclosing patient identifiers. Defacing, i.e., the removal of facial features from images, is often considered a reasonable compromise between data protection and re-usability for neuroimaging data. While defacing tools have been developed by the neuroimaging community, their acceptability for radiotherapy applications have not been explored. Therefore, this study systematically investigated the impact of available defacing algorithms on HNC organs at risk (OARs).

METHODS : A publicly available dataset of magnetic resonance imaging scans for 55 HNC patients with eight segmented OARs (bilateral submandibular glands, parotid glands, level II neck lymph nodes, level III neck lymph nodes) was utilized. Eight publicly available defacing algorithms were investigated: afni_refacer, DeepDefacer, defacer, fsl_deface, mask_face, mri_deface, pydeface, and quickshear. Using a subset of scans where defacing succeeded (N=29), a 5-fold cross-validation 3D U-net based OAR auto-segmentation model was utilized to perform two main experiments: 1.) comparing original and defaced data for training when evaluated on original data; 2.) using original data for training and comparing the model evaluation on original and defaced data. Models were primarily assessed using the Dice similarity coefficient (DSC).

RESULTS : Most defacing methods were unable to produce any usable images for evaluation, while mask_face, fsl_deface, and pydeface were unable to remove the face for 29%, 18%, and 24% of subjects, respectively. When using the original data for evaluation, the composite OAR DSC was statistically higher (p ≤ 0.05) for the model trained with the original data with a DSC of 0.760 compared to the mask_face, fsl_deface, and pydeface models with DSCs of 0.742, 0.736, and 0.449, respectively. Moreover, the model trained with original data had decreased performance (p ≤ 0.05) when evaluated on the defaced data with DSCs of 0.673, 0.693, and 0.406 for mask_face, fsl_deface, and pydeface, respectively.

CONCLUSION : Defacing algorithms may have a significant impact on HNC OAR auto-segmentation model training and testing. This work highlights the need for further development of HNC-specific image anonymization methods.

Sahlsten Jaakko, Wahid Kareem A, Glerean Enrico, Jaskari Joel, Naser Mohamed A, He Renjie, Kann Benjamin H, Mäkitie Antti, Fuller Clifton D, Kaski Kimmo

2023

MRI, anonymization, artificial intelligence (AI), autosegmentation, defacing, head and neck cancer, medical imaging, radiotherapy

In Frontiers in oncology

PURPOSE : Artificial intelligence applications in radiation oncology have been the focus of study in the last decade. The introduction of automated and intelligent solutions for routine clinical tasks, such as treatment planning and quality assurance, has the potential to increase safety and efficiency of radiotherapy. In this work, we present a multi-institutional study across three different institutions internationally on a Bayesian network (BN)-based initial plan review assistive tool that alerts radiotherapy professionals for potential erroneous or suboptimal treatment plans.

METHODS : Clinical data were collected from the oncology information systems in three institutes in Europe (Maastro clinic - 8753 patients treated between 2012 and 2020) and the United States of America (University of Vermont Medical Center [UVMMC] - 2733 patients, University of Washington [UW] - 6180 patients, treated between 2018 and 2021). We trained the BN model to detect potential errors in radiotherapy treatment plans using different combinations of institutional data and performed single-site and cross-site validation with simulated plans with embedded errors. The simulated errors consisted of three different categories: i) patient setup, ii) treatment planning and iii) prescription. We also compared the strategy of using only diagnostic parameters or all variables as evidence for the BN. We evaluated the model performance utilizing the area under the receiver-operating characteristic curve (AUC).

RESULTS : The best network performance was observed when the BN model is trained and validated using the dataset in the same center. In particular, the testing and validation using UVMMC data has achieved an AUC of 0.92 with all parameters used as evidence. In cross-validation studies, we observed that the BN model performed better when it was trained and validated in institutes with similar technology and treatment protocols (for instance, when testing on UVMMC data, the model trained on UW data achieved an AUC of 0.84, compared with an AUC of 0.64 for the model trained on Maastro data). Also, combining training data from larger clinics (UW and Maastro clinic) and using it on smaller clinics (UVMMC) leads to satisfactory performance with an AUC of 0.85. Lastly, we found that in general the BN model performed better when all variables are considered as evidence.

CONCLUSION : We have developed and validated a Bayesian network model to assist initial treatment plan review using multi-institutional data with different technology and clinical practices. The model has shown good performance even when trained on data from clinics with divergent profiles, suggesting that the model is able to adapt to different data distributions.

Kalendralis Petros, Luk Samuel M H, Canters Richard, Eyssen Denis, Vaniqui Ana, Wolfs Cecile, Murrer Lars, van Elmpt Wouter, Kalet Alan M, Dekker Andre, van Soest Johan, Fijten Rianne, Zegers Catharina M L, Bermejo Inigo

2023

AI, Bayesian network, plan review, quality assurance, radiotherapy