Search

Abstract Background Undetected atrial fibrillation (AF) poses a significant risk of stroke and cardiovascular mortality. However, diagnosing AF in real-time can be challenging as the arrhythmia is often not captured instantly. To address this issue, a deep-learning model was developed to diagnose AF even during periods of arrhythmia-free windows. Methods The proposed method introduces a novel approach that integrates clinical data and electrocardiograms (ECGs) using a colorization technique. This technique recolors ECG images based on patients' demographic information while preserving their original characteristics and incorporating color correlations from statistical data features. Our primary objective is to enhance atrial fibrillation (AF) detection by fusing ECG images with demographic data for colorization. To ensure the reliability of our dataset for training, validation, and testing, we rigorously maintained separation to prevent cross-contamination among these sets. We designed a Dual-input Mixed Neural Network (DMNN) that effectively handles different types of inputs, including demographic and image data, leveraging their mixed characteristics to optimize prediction performance. Unlike previous approaches, this method introduces demographic data through color transformation within ECG images, enriching the diversity of features for improved learning outcomes. Results The proposed approach yielded promising results on the independent test set, achieving an impressive AUC of 83.4%. This outperformed the AUC of 75.8% obtained when using only the original signal values as input for the CNN. The evaluation of performance improvement revealed significant enhancements, including a 7.6% increase in AUC, an 11.3% boost in accuracy, a 9.4% improvement in sensitivity, an 11.6% enhancement in specificity, and a substantial 25.1% increase in the F1 score. Notably, AI diagnosis of AF was associated with future cardiovascular mortality. For clinical application, over a median follow-up of 71.6 ± 29.1 months, high-risk AI-predicted AF patients exhibited significantly higher cardiovascular mortality (AF vs. non-AF; 47 [18.7%] vs. 34 [4.8%]) and all-cause mortality (176 [52.9%] vs. 216 [26.3%]) compared to non-AF patients. In the low-risk group, AI-predicted AF patients showed slightly elevated cardiovascular (7 [0.7%] vs. 1 [0.3%]) and all-cause mortality (103 [9.0%] vs. 26 [6.4%]) than AI-predicted non-AF patients during six-year follow-up. These findings underscore the potential clinical utility of the AI model in predicting AF-related outcomes. Conclusions This study introduces an ECG colorization approach to enhance atrial fibrillation (AF) detection using deep learning and demographic data, improving performance compared to ECG-only methods. This method is effective in identifying high-risk and low-risk populations, providing valuable features for future AF research and clinical applications, as well as benefiting ECG-based classification studies.

Abstract Healthcare‐associated infection (HAI) is the most common adverse medical event that affects patients. Internationally, healthcare workers (HCWs) are monitored for hand hygiene compliance to reduce HAI risk. While direct observation is considered the gold standard for monitoring, it has several disadvantages. To address this, the study focused on developing a comprehensive hand hygiene system that integrates the Internet of Things (IoT) hand hygiene with soap and water (HHW) and alcohol‐based formulation (HHA) monitoring, incorporates real‐time data visualization on a web interface to track HCWs' hand hygiene practices, and provides instant calculations of compliance and accuracy rates. This IoT system uses Bluetooth for HCW positioning and HHW detection, ultrasonic sensors for handwashing duration, and pressure sensors for HHA detection. Furthermore, a cloud server, database, and website are established to manage and display the data received by the IoT devices. To reduce HAI in Taiwan, hospitals must provide both HHW and HHA systems, and HCWs can choose either method when hand hygiene is necessary. The system achieved 72% accuracy in clinical practice within an adult intensive care unit (ICU).

For various sexually mature insects, including the brown planthopper (BPH, Nilaparvata lugens), the abdominal vibration (AV) signal is the initiation of the mating process, and it is critical to the success of mating. Currently, there are few studies on the genetic and molecular mechanisms of AV regulation. Our previous AV-related transcriptomic study in female BPH identified myoinhibitory peptide (NlMIP) as a gene that potentially affects AV status in females, but how NlMIP affects AV status remains unknown. In this study, we confirmed that NlMIP regulates AV production and mating behavior in female BPH. When the RNAi knockdown efficiency of NlMIP was 59.00%, the probability of females producing AV and the mating rate in 1 h decreased by 38.89 and 61.11%, respectively. In addition, six mature peptides of NlMIP were synthesized and they were able to regulate AV production and mating behavior in females, with NlMIP2 having the strongest effect. The A-family neuropeptide GPCR 10 (NlA10) was found to be a potential receptor for NlMIP based on a phylogenetic tree analysis and the fact that NlMIP mature peptides effectively activated NlA10. After NlA10 was knocked down, the probability of females producing AV and the mating rate in 1 h had reductions of 28.89 and 43.33%, respectively. When activated by NlMIP2, NlA10 coupled the Gαi/q signalling pathways, thereby inhibiting the downstream AC/cAMP/PKA, activating the PLC/Ca2+/PKC signalling pathways and then activating MEK1/2 in a cascade to mediate the phosphorylation of ERK1/2, and finally regulating the AV of females. These results provide a basis for the prevention and control of the brown planthopper pest by disrupting female AV.

A challenge in accurately identifying and classifying left ventricular hypertrophy (LVH) is distinguishing it from hypertrophic cardiomyopathy (HCM) and Fabry disease. The reliance on imaging techniques often requires the expertise of multiple specialists, including cardiologists, radiologists, and geneticists. This variability in the interpretation and classification of LVH leads to inconsistent diagnoses. LVH, HCM, and Fabry cardiomyopathy can be differentiated using T1 mapping on cardiac magnetic resonance imaging (MRI). However, differentiation between HCM and Fabry cardiomyopathy using echocardiography or MRI cine images is challenging for cardiologists. Our proposed system named the MRI short-axis view left ventricular hypertrophy classifier (MSLVHC) is a high-accuracy standardized imaging classification model developed using AI and trained on MRI short-axis (SAX) view cine images to distinguish between HCM and Fabry disease. The model achieved impressive performance, with an F1-score of 0.846, an accuracy of 0.909, and an AUC of 0.914 when tested on the Taipei Veterans General Hospital (TVGH) dataset. Additionally, a single-blinding study and external testing using data from the Taichung Veterans General Hospital (TCVGH) demonstrated the reliability and effectiveness of the model, achieving an F1-score of 0.727, an accuracy of 0.806, and an AUC of 0.918, demonstrating the model’s reliability and usefulness. This AI model holds promise as a valuable tool for assisting specialists in diagnosing LVH diseases.

Fat metabolism is an important modifier of aging and longevity in Caenorhabditis elegans. Given the anatomy and hermaphroditic nature of C. elegans, a major challenge is to distinguish fats that serve the energetic needs of the parent from those that are allocated to the progeny. Broadband coherent anti-Stokes Raman scattering (BCARS) microscopy has revealed that the composition and dynamics of lipid particles are heterogeneous both within and between different tissues of this organism. Using BCARS, we have previously succeeded in distinguishing lipid-rich particles that serve as energetic reservoirs of the parent from those that are destined for the progeny. While BCARS microscopy produces high-resolution images with very high information content, it is not yet a widely available platform. Here we report a new approach combining the lipophilic vital dye Nile Red and two-photon fluorescence lifetime imaging microscopy (2p-FLIM) for the in vivo discrimination of lipid particle sub-types. While it is widely accepted that Nile Red staining yields unreliable results for detecting lipid structures in live C. elegans due to strong interference of autofluorescence and non-specific staining signals, our results show that simple FLIM phasor analysis can effectively separate those signals and is capable of differentiating the non-polar lipid-dominant (lipid-storage), polar lipid-dominant (yolk lipoprotein) particles, and the intermediates that have been observed using BCARS microscopy. An advantage of this approach is that images can be acquired using common, commercially available 2p-FLIM systems within about 10% of the time required to generate a BCARS image. Our work provides a novel, broadly accessible approach for analyzing lipid-containing structures in a complex, live whole organism context.

IntroductionFerroptosis is associated with multiple pathophysiological processes. Inhibition of ferroptosis has received much concern for some diseases. Nonetheless, there is no study comprehensively illustrating functions of ferroptosis-related genes (FRGs) in psoriasis.MethodsIn this study, FRGs together with psoriasis-associated data were obtained in Ferroptosis Database (FerrDb) and gene expression omnibus (GEO) database separately. This work identified altogether 199 psoriasis-associated DE-FRGs, and they were tightly associated with immunity and autophagy modulation. Thereafter, the present study utilized SVM-RFE and LASSO algorithms to identify NR5A2, CISD1, GCLC, PRKAA2, TRIB2, ABCC5, ACSF2, TIMM9, DCAF7, PEBP1, and MDM2 from those 199 DE-FRGs to be marker genes. As revealed by later functional annotation, the marker genes possibly had important effects on psoriasis through being involved in diverse psoriasis pathogenesis-related pathways such as cell cycle, toll-like receptor (TLR), chemokine, and nod-like receptor (NLR) pathways. Moreover, altogether 37 drugs that targeted 11 marker genes were acquired. Besides, based on CIBERSORT analysis, alterations of immune microenvironment in psoriasis cases were possibly associated with PRKAA2, PEBP1, CISD1, and ACSF2.DiscussionTaken together, this work established the diagnostic potency and shed more lights on psoriasis-related mechanism. More investigations are warranted to validate its value in diagnosing psoriasis before it is applied in clinic.