Explore the vast range of titles available.

Despite the unprecedented performance of deep learning algorithms in clinical domains, full reviews of algorithmic predictions by human experts remain mandatory. Under these circumstances, artificial intelligence (AI) models are primarily designed as clinical decision support systems (CDSSs). However, from the perspective of clinical practitioners, the lack of clinical interpretability and user-centered interfaces hinders the adoption of these AI systems in practice. This study aims to develop an AI-based CDSS for assisting polysomnographic technicians in reviewing AI-predicted sleep staging results. This study proposed and evaluated a CDSS that provides clinically sound explanations for AI predictions in a user-centered manner. Our study is based on a user-centered design framework for developing explanations in a CDSS that identifies why explanations are needed, what information should be contained in explanations, and how explanations can be provided in the CDSS. We conducted user interviews, user observation sessions, and an iterative design process to identify three key aspects for designing explanations in the CDSS. After constructing the CDSS, the tool was evaluated to investigate how the CDSS explanations helped technicians. We measured the accuracy of sleep staging and interrater reliability with macro-F1 and Cohen κ scores to assess quantitative improvements after our tool was adopted. We assessed qualitative improvements through participant interviews that established how participants perceived and used the tool. The user study revealed that technicians desire explanations that are relevant to key electroencephalogram (EEG) patterns for sleep staging when assessing the correctness of AI predictions. Here, technicians wanted explanations that could be used to evaluate whether the AI models properly locate and use these patterns during prediction. On the basis of this, information that is closely related to sleep EEG patterns was formulated for the AI models. In the iterative design phase, we developed a different visualization strategy for each pattern based on how technicians interpreted the EEG recordings with these patterns during their workflows. Our evaluation study on 9 polysomnographic technicians quantitatively and qualitatively investigated the helpfulness of the tool. For technicians with <5 years of work experience, their quantitative sleep staging performance improved significantly from 56.75 to 60.59 with a P value of .05. Qualitatively, participants reported that the information provided effectively supported them, and they could develop notable adoption strategies for the tool. Our findings indicate that formulating clinical explanations for automated predictions using the information in the AI with a user-centered design process is an effective strategy for developing a CDSS for sleep staging.

Multiple relaxation times are used to capture the numerous stress relaxation modes found in bulk polymer melts. Herein, inverse vulcanization is used to synthesize high sulfur content (≥50 wt%) polymers that only need a single relaxation time to describe their stress relaxation. The S-S bonds in these organopolysulfides undergo dissociative bond exchange when exposed to elevated temperatures, making the bond exchange dominate the stress relaxation. Through the introduction of a dimeric norbornadiene crosslinker that improves thermomechanical properties, we show that it is possible for the Maxwell model of viscoelasticity to describe both dissociative covalent adaptable networks and living polymers, which is one of the few experimental realizations of a Maxwellian material. Rheological master curves utilizing time-temperature superposition were constructed using relaxation times as nonarbitrary horizontal shift factors. Despite advances in inverse vulcanization, this is the first complete characterization of the rheological properties of this class of unique polymeric material. Polymers typically exhibit rheology with multiple relaxation times to fully capture stress relaxation processes to terminal flow. Here, the authors use inverse vulcanization to synthesize polymers that exhibit a single relaxation time due to dynamic covalent disulfide bond reorganization that dominate the rheological properties of these materials.

Dysphagia is a common and debilitating complication in patients with lateral medullary infarction (LMI), affecting up to 100% of cases and significantly impairing quality of life. Accurate classification of early dysphagia severity is essential for timely intervention and personalized rehabilitation planning. This study aimed to develop and validate a deep learning algorithm using acute-phase diffusion-weighted MRI to classify dysphagia severity in LMI patients. A retrospective cohort of 163 patients with confirmed acute LMI was analyzed. Dysphagia severity was determined by videofluoroscopic swallowing studies (VFSS), categorizing patients into severe and non-severe groups. Lesion regions were manually labeled and preprocessed for model training. Transformer-based deep learning architecture, the Hierarchical Vision Transformer (Hier-ViT), was employed due to its capacity to model spatial hierarchies and global image context. The model achieved an accuracy of 0.85, with a precision of 0.70, recall of 0.75, F1-score of 0.72, and an area under the ROC curve (AUC) of 0.69. These findings suggest that Hier-ViT can effectively classify dysphagia severity in LMI patients using early MRI, offering a potential tool for early risk stratification. While the model shows a high accuracy, the modest AUC suggests that further refinement and multi-modal integration are necessary to improve its discriminative power in imbalanced clinical datasets.

Background Aromatic L-amino acid decarboxylase (AADC) deficiency is an autosomal recessive neurotransmitter metabolism disorder and is clinically characterized by infancy hypotonia, ophthalmic crisis, and developmental delay. With the emergence of gene therapy for AADC deficiency, accurate prediction of AADC deficiency is required. This study aimed to analyze the carrier frequency and expected incidence of AADC deficiency using exome data from the Genome Aggregation Database (gnomAD). Methods We analyzed 125,748 exomes from gnomAD, including 9197 East Asian exomes, for the DDC gene. All identified variants were classified according to the 2015 American College of Medical Genetics and Genomics and the Association for Molecular Pathology guidelines. Results The worldwide carrier frequency of AADC deficiency was 0.17%; the highest frequency was observed in East Asians at 0.78%, and the lowest was in Latinos at 0.07%. The estimated incidence of AADC deficiency was 1 in 1,374,129 worldwide and 1 in 65,266 in East Asians. Conclusion The results demonstrated that East Asians have a higher carrier frequency of AADC deficiency than other ethnic groups. The variant spectrum of DDC genes in East Asian populations differed greatly from those of other ethnic groups. Our data will serve as a reference for further investigation of AADC deficiency. Impact This study analyzed exome data from the Genome Aggregation Database (gnomAD) to estimate the carrier frequency and expected incidence of aromatic L-amino acid decarboxylase (AADC) deficiency. The article provides updated carrier frequency and incidence estimates for AADC deficiency, particularly in East Asian populations, and emphasizes the significant differences in the variant spectrum of DDC genes in this population compared to other ethnic groups. The study provides important information for accurate prediction and early diagnosis of AADC deficiency, particularly in high-risk populations, and may aid in the development of more effective targeted screening programs and gene therapies for this disorder.

This study proposes a process for detecting anomalies in the manufacturing industry, where data imbalance is a frequent problem. The labeling of anomalies can be challenging owing to the different types of anomalies. To address this issue, we used clustering based on the distribution of acquired normal data. We extracted latent vector values from normal image data as features using the Style-GAN method, after conversion of the time-series data. Subsequently, we performed dimensionality reduction through Locally Linear Embedding (LLE) using the extracted latent vector values and selected the Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) for anomaly detection. We verified the proposed process using a milling dataset that included measurements of vibration, force, and noise. The evaluation of the process included dimensionality reduction methods such as Locally Linear Embedding (LLE), Principal Component Analysis (PCA), Kernel PCA, Singular Value Decomposition (SVD), and ISOmetric mapping (ISO) produced an F-1 score of 0.86.

This study aims to develop an artificial intelligence-based model for analyzing the condition and detecting anomalies by encoding time-series data from manufacturing processes as images. Deep learning has demonstrated the significance of data analysis and anomaly detection in the vision field, and Convolutional Neural Networks (CNN) models have shown exceptional performance and high applicability in image analysis. Based on this, our study intends to utilize image encoding techniques to perform anomaly detection on time-series data. Data such as force, vibration, and sound from equipment during the manufacturing process are collected and transformed into images using various methods, including Gramian Difference Angular Field, Gramian Summation Angular Field, Markov Transition Field, and Recurrence Plot (RP). The transformed image data is then trained and classified for equipment conditions using various CNN models. Finally, we adopt the RP image encoding method and ResNet50 model, which demonstrated the highest accuracy of 99.6%, and compare them to the top 5 models. Based on the high accuracy demonstrated by the top five models, our proposed approach has proven to have significant performance, exhibiting a high success rate of over 90% even when applied to actual data for CNC-machining process. Through this, we propose a process that utilizes the explainable AI Grad-CAM system to identify the feature layer area of the image and confirm the presence of anomalies. With the proposed process, workers can identify abnormal areas or segments of abnormal conditions in the transformed image graph. By providing evidence for state judgment, even inexperienced workers can easily check the condition of manufacturing equipment.

GPCR proteins belong to diverse families of proteins that are defined at multiple hierarchical levels. Inspecting relationships between GPCR proteins on the hierarchical structure is important, since characteristics of the protein can be inferred from proteins in similar hierarchical information. However, modeling of GPCR families has been performed separately for each of the family, subfamily, and sub-subfamily level. Relationships between GPCR proteins are ignored in these approaches as they process the information in the proteins with several disconnected models. In this study, we propose DeepHier, a deep learning model to simultaneously learn representations of GPCR family hierarchy from the protein sequences with a unified single model. Novel loss term based on metric learning is introduced to incorporate hierarchical relations between proteins. We tested our approach using a public GPCR sequence dataset. Metric distances in the deep feature space corresponded to the hierarchical family relation between GPCR proteins. Furthermore, we demonstrated that further downstream tasks, like phylogenetic reconstruction and motif discovery, are feasible in the constructed embedding space. These results show that hierarchical relations between sequences were successfully captured in both of technical and biological aspects.

Background Smith–Lemli–Opitz syndrome (SLOS) is an autosomal, recessively inherited congenital malformation syndrome characterized by multiple congenital anomalies such as microcephaly with mental defects, distinctive facial features, genital abnormalities, and 2–3 syndactyly of the toes. SLOS is caused by defective 7-dehydrocholesterol reductase, which is encoded by the DHCR7 gene. This study aimed to analyze the carrier frequency and expected incidence of SLOS in East Asians and Koreans using exome data from the Genome Aggregation Database (gnomAD) through the 2015 American College of Medical Genetics and Genomics and the Association for Molecular Pathology guideline (2015 ACMG-AMP guideline). Methods We analyzed 9197 exomes for East Asian populations from gnomAD, comprising 1909 Korean, 76 Japanese, and 7212 other East Asian populations. All identified variants were classified according to the 2015 ACMG-AMP guideline. Results According to the 2015 ACMG-AMP guideline, 15 pathogenic variant/likely pathogenic variant (PV/LPV) cases were identified in 33 East Asian individuals (33/9191 = 0.4%). Among them, four PVs/LPVs were identified in 19 Korean individuals (19/1909 = 1.0%). The predicted incidence, based upon the carrier rates of PV/LPV of DHCR7 alleles, is 1 in 310,688 in East Asians and l in 40,380 in Koreans. Conclusions This study is the first to identify carrier frequencies in East Asians and Koreans using gnomAD. It was confirmed that East Asians (0.4%) had a lower carrier frequency than did other ethnicities (1–3%) and Koreans (1.0%) had similar or lower carrier frequencies than other ethnicities. The variant spectrums of DHCR7 in East Asian and Korean populations differed greatly from those of other ethnic groups.

Background Inherited retinal diseases (IRDs) are clinically and genetically heterogenous disorders leading to visual impairment and blindness. Because gene therapy for RPE65 -associated IRDs was recently approved, it is necessary to predict the carrier frequency and prevalence for RPE65 -associated IRDs. This study aimed to analyze the carrier frequency and expected incidence of RPE65 -associated IRDs in East Asians and Koreans using exome data from the Genome Aggregation Database (gnomAD) and the Korean Reference Genome Database (KRGDB). Methods We analyzed 9,197 exomes for East Asian populations from gnomAD comprising 1,909 Korean and 1,722 Korean genomes from KRGDB. All identified RPE65 variants were classified according to the 2015 American College of Medical Genetics and Genomics and the Association for Molecular Pathology guidelines. Results The total carrier frequencies of East Asians and Koreans from both gnomAD and KRGDB were 0.10% (11/10,919) and 0.06% (2/3,631), respectively. The estimated incidence of RPE65 -associated IRDs was 1/3,941,308 in East Asians and 1/13,184,161 in Koreans. Conclusion This study identified carrier frequencies of RPE65 -associated IRDs in East Asians and Koreans using gnomAD and KRGDB. We confirmed that the carrier frequency of RPE65 -associated IRDs patients was low in Koreans among all East Asian populations, and the incidence was also predicted to be lower than in other East Asian populations. The variant spectrum of RPE65 gene in East Asian and Korean populations differed greatly from those of other ethnic groups.

Cell growth control is a critical process underlying diverse biological events, including survival, development, tissue repair, and disease. Growth regulation is orchestrated by a combination of external and internal cues, involving a multitude of signaling pathways. Nevertheless, our comprehension of the regulation of growth-associated signaling pathways is still incomplete. In this study, we discovered that microRNA miR-33 overexpression in Drosophila S2 cells resulted in a reduction in cell proliferation. This growth inhibition was attributed to the inactivation of ERK signaling, which is mediated through Ras64B, a direct target of miR-33-5p. In accordance with these observations in S2 cells, miR-33 inactivation in Drosophila wings led to an increase in cell number, while its overexpression resulted in a decrease. Notably, miR-33-induced wing reduction was associated with diminished ERK signaling, and this wing defect was rescued by co-expression of Ras64B or a constitutively active ERK variant. Consequently, these findings establish miR-33–Ras64B–ERK as a regulatory axis, providing new mechanistic insights into growth control in Drosophila.