Specific Scores Research Articles

Comparative Analysis of ML Models with Selection Methods for Early Predictive Analytics of Sepsis in ICU

Objectives: This study aims to make early prediction of Sepsis using ML algorithms and provide comparative analysis of different feature selection techniques. Methods: In this study, the Physionet website dataset has been used. Sepsis categorization is done on the basis of Sepsis-3 criteria. The dataset used is highly imbalanced, with only 2% of the data belonging to Sepsis. The SmoteTomek technique is used to handle an imbalanced dataset. Various filter, embedded, and wrapper feature selection techniques, like tree-based feature selection technique, recursive feature elimination (RFE), information gain, Bhattacharya distance, lasso, etc., have been applied for the top-performing classification ML models. These selection techniques were applied to RandomForest, K Nearest Neighbors (KNN), and Decision Tree models. We compared the impact of these selection techniques on the aforesaid machine learning models. Findings: After applying the RFE technique, the Area Under the Receiver Operating Characteristic curve (AUROC) score of the RandomForest model has slightly increased from 0.996 to 0.9974. KNN model with a tree-based feature selection technique showed the highest sensitivity of 0.934. which is slightly higher than the sensitivity of 0.922, which was without applying any feature selection technique. Along with the AUROC score, the highest performance, in terms of specificity (0.9976), accuracy (0.9959), and f-measure score (0.9062), is achieved when RFE is applied to the RandomForest model. The best selection algorithm for decision trees and KNN is the tree-based selection technique. RFE is the best selection technique for RandomForest. Novelty: In this research, the AUROC score is slightly increased to 0.9974, which has not been achieved yet. Instead of 40, the number of features chosen is 20. This research also provides a comparison of different feature selection techniques like tree-based feature selection, information gain, Bhattacharya, and RFE. It also analyses their impact on the performance of models, which has not been done yet with the same set of selection techniques. Keywords: Sepsis, Machine Learning, Feature selection, Early prediction, Predictive Analytics

Predictors of explicit and implicit anthropomorphism in house facades.

Anthropomorphism describes the tendency to endow objects with human characteristics, with some individuals being more inclined to do this than others. In an ambiguous environment, this phenomenon can offer guidance. This study investigates the relationship between self-reported attribution and evoked anthropomorphism when viewing house facades. Data was collected from three countries (Germany, Denmark, Canada; N = 305). Implicit house anthropomorphism was measured using the Global Vectors for Word Representation method. Explicit anthropomorphism was assessed using the Individual Differences in Anthropomorphism Questionnaire (IDAQ) and a specific House Anthropomorphism Score (EHAS). No significant relationship was found between implicit and explicit house anthropomorphism. Individual IDAQ scores were significantly associated with EHAS across all participants, regardless of country. Additionally, a high degree of agreement in explicit ratings between countries suggests that cultural differences are rather negligible. When objects are given human personality traits and people interact with them because emotions are triggered, it is important to understand which aspects elicit positive and reactive behaviors. In particular, houses, which have high psychological significance as objects of self-expression, might contribute to well-being, so research in this area can provide important knowledge for urban design and architecture.

Prediction models for ischemic stroke and bleeding in dialysis patients: a systematic review and meta-analysis

Abstract Background Patients with kidney failure on maintenance dialysis have a high stroke and bleeding risk. Multivariable prediction models can be used to estimate the risk of ischemic stroke and bleeding. A systematic review and meta-analysis was performed to determine the performance of the existing models in patients on dialysis. Methods MEDLINE and Embase databases were searched, from inception through January 12, 2024, for studies of prediction models for stroke or bleeding, derived or validated in dialysis cohorts. Discrimination measures for models with c-statistic data from ≥ 3 cohorts were pooled by random effects meta-analysis and a 95% prediction interval (PI) was calculated. Risk of bias was assessed using PROBAST. The review was conducted according to the PRISMA statement and the CHARMS checklist. Results Eight studies were included in this systematic review. All the included studies validated pre-existing models that were derived in cohorts from the general population. None of the identified studies reported the development of a new dialysis specific prediction model for stroke, while dialysis specific risk scores for bleeding were proposed by two studies. In meta-analysis of c-statistics, the CHA2DS2-VASc, CHADS2, ATRIA, HEMORR(2)HAGES and HAS-BLED scores showed very poor discriminative ability in the dialysis population. Six of the eight included studies were at low or unclear risk of bias and certainty of evidence was moderate. Conclusions The existing prediction models for stroke and bleeding have very poor performance in the dialysis population. New dialysis-specific risk scores should be developed to guide clinical decision making in these patients.

Intensive 2-days training on perfused human placenta for microvascular anastomoses.

We report on an intensive two-day training program on microanastomoses performed on perfused human placenta models. A specific scoring system was elaborated to evaluate the participants' microsurgical skills and report the participants' results. Trainees who attended the Zurich Microsurgery Courses in 2023 were included in the study. Before performing the microanastomoses, each participant received a visual didactic training. Training was made on perfused human placenta models. To perform the microvascular anastomoses, vessels of different diameters were chosen, and 9-0 and 10-0 microsutures were used. The course was structured in two days. On day one, participants practiced microvascular dissection, microsuturing and end-to-end anastomoses, while the second day was dedicated to end-to-side and to repeat the most useful microanastomosis depending on the specialty. A score system for the evaluation of a successful microanastomosis was developed and applied to assess the participants' anastomoses. User satisfaction was measured by means of a survey-based questionnaire. Fifty-two participants from different institutions, specializations and levels of experience were included. A significant improvement in the overall microsurgical skills of the included cohort was documented (p < 0.005). The initial average score per anastomosis of 3.56 points (SD 0.71) increased to an average of 3.8 points (SD 0.87) at the end of the course. The steepest learning curve was observed in the placement of knots (Δ 0.48 points, p = 0.003) and microvascular dissection (Δ 0.44 points, p = 0.002). Most participants rated the fidelity and importance of the placental microsuturing course as extremely high. The two-day training program is efficient to teach microvascular dissection and microanastomosis techniques. A significant improvement of participants' microsurgical skills was reported. The human placenta model proved to be a high-fidelity simulator with great user satisfaction.

Abstract 4138248: Outcomes of Patients with Radiation-Associated Cardiac Disease Undergoing Cardiothoracic Surgery: Development of a Disease Specific Risk Score

Background: Radiation-associated cardiac disease (RACD) has significant long-term mortality and morbidity, often requiring cardiac surgery(CS). Hypothesis: We sought to study factors associated with longer-term survival in RACD patients and develop a specific risk score associated with 5-year survival following CS. Methods: This was an observational cohort study of 351 patients with documented RACD (252 [72%] had mantle radiation for lymphoma at a mean of 18 years prior), who underwent CS at a tertiary care center between 1991-2018. Clinical characteristics were collected, and Society of Thoracic Surgeons (STS) score was calculated. The primary endpoint was mortality. Multivariable analysis for 5-year mortality was performed using age, sex, history of lymphoma, New York Heart Association class, prior cardiac surgery, atrial fibrillation, constriction, chronic pulmonary disease, serum creatinine, left ventricular ejection fraction, right ventricular systolic pressure and valvular surgery(aortic, mitral or tricuspid). Results: Clinical characteristics are shown in Figure 1. Mean follow-up was 6.2±4.6 years&amp;5-year mortality occurred in 123 (35%) patients (7 [2%] in-hospital deaths). Cox 5-year survival analysis results are shown in Figure 2A. A receiver operator curve analysis for 5-year mortality showed an area under curve of 0.70 (95% confidence interval 0.64-76, p&lt;0.001). Subsequently, a 5-year risk score (0-7 points) was generated (Figure 2 A); with an increasing risk of mortality at 5 years, based on increasing risk score (Figure 2C). Cardiac reoperation was not associated with worse outcomes. Conclusion: RACD patients undergoing CTS have a high rate of 5-year mortality, despite a low baseline STS score&amp;perioperative mortality. A novel RACD-specific risk score (incorporating higher age, abnormal renal/pulmonary, constrictive pericarditis&amp;need for concomitant mitral valve surgery) provides good discrimination for 5-year survival&amp;could be used for shared-decision making.

Abstract 4138620: Assessment of the Accuracy of the Perioperative Mortality Risk in Adults with Congenital Heart Disease (PEACH) Score

INTRODUCTION: Previous mortality risk scores for adult cardiac surgery patients did not include adult congenital heart disease (ACHD) patients. Development of ACHD specific mortality risk scores include the procedure-specific ACHS score and recently derived PEACH score. While validated in Europe, further evaluation of the PEACH score in additional settings is necessary. RESEARCH QUESTION: We assessed the efficacy of the PEACH score to predict mortality in ACHD patients undergoing congenital cardiac surgery at our institution. We compared the PEACH score to the ACHS and STS scores and assessed for additional risk factors which may further augment the PEACH score. Methods: A retrospective cohort study was conducted of patients who underwent congenital cardiac surgery at the University of Colorado Hospital and Children’s Hospital Colorado between 2010-2022. Patients were identified by the institutional STS congenital cardiac surgery database and were eligible if 18 years or older and underwent congenital cardiac surgery. Components of the PEACH score and additional postulated risk factors were evaluated by univariate analysis. A receiver operating characteristic (ROC) curve was used to compare the PEACH score to existing risk models. Logistic regression analysis determined additional risk factors to augment the PEACH score. Results: A total of 516 patients were included with a median age of 30 (IQR 23-42) and 51% were male. There were nine deaths overall. The PEACH score was predictive of mortality (OR: 2.09, p&lt;0.001) with a score of 0: 0 deaths/240 patients (0%); 1-2: 6 deaths/229 patients (2.6%); 3+: 3 deaths/41 patients (7.3%). Of additional risk factors tested, platelets less than 184,000 per mcL (OR: 8.36, p=0.01) was significantly associated with mortality. Comparison of the models revealed PEACH score AUC 0.832 (95% CI: 0.740,0.924), ACHS score AUC 0.869 (95% CI: 0.806, 0.932), and STAT AUC 0.769 (95% CI: 0.616, 0.922, Figure 1). The addition of platelet level improved the predictive ability of the PEACH score (AUC 0.881). Conclusion: In this single-center analysis, the PEACH score provided strong predictive ability for peri-operative mortality. The addition of platelet levels may further augment this score.

RADT-12. DERIVING IMAGING BIOMARKERS FOR PRIMARY CENTRAL NERVOUS SYSTEM LYMPHOMA USING DEEP LEARNING

Abstract PURPOSE Primary central nervous system lymphoma (PCNSL) is typically treated with chemotherapy, steroids, and/or whole brain radiotherapy (WBRT). Determining which patients benefit from WBRT after chemotherapy and which are adequately treated with chemotherapy alone remains a clinical challenge. Although WBRT is associated with improved outcomes, it also carries a risk of neurocognitive side effects. This study aims to refine PCNSL patient phenotyping by leveraging deep learning (DL) extracted imaging biomarkers to enable personalized therapy. METHODS Our study included 71 patients treated between 2009-2021. The primary outcome of interest was overall survival (OS) assessed at one- and two-year cutoffs. The DL model leveraged an 8-layer 2D convolutional neural network analyzing individual slices of post-contrast T1-weighted pre-treatment MRI scans. Survival predictions utilized a weighted voting system related to tumor size. Model performance was assessed with accuracy, sensitivity, specificity, and F1 scores. Time-dependent AUCs were calculated and C-statistics were computed to summarize the results. Kaplan-Meier (KM) survival analysis assessed differences between low and high-risk groups and were evaluated using the log-rank test. RESULTS The cohort’s average age was 65.6 years with average OS of 2.80 years. For one-year OS, the model achieved an AUC of 0.73 (0.60-0.85), accuracy of 0.73 (0.61-0.82), sensitivity of 0.72 (0.54–0.85), and specificity of 0.73 (0.58–0.84). For two-year OS, the model achieved an AUC of 0.70 (0.58-0.82), accuracy of 0.70 (0.58-0.79), sensitivity of 0.68 (0.55–0.81), and specificity of 0.71 (0.55–0.84). Model performance is presented with respective 95% confidence intervals. KM curves showed the one and two-year models effectively discriminated between low- and high-risk group, reporting c-statistics of 0.73 (p&amp;lt;.001) and 0.71 (p&amp;lt;.001) respectively. A sub-analysis confirmed consistent model performance across different tumor volumes and focality. CONCLUSION DL classifiers of PCNSL MRIs can stratify patient phenotypes beyond traditional risk paradigms. Given dissensus surrounding PCNSL treatment, DL can augment risk stratification and treatment personalization, especially with regards to WBRT decision making.

Deep-GB: A novel deep learning model for globular protein prediction using CNN-BiLSTM architecture and enhanced PSSM with trisection strategy.

Globular proteins (GPs) play vital roles in a wide range of biological processes, encompassing enzymatic catalysis and immune responses. Enzymes, among these globular proteins, facilitate biochemical reactions, while others, such as haemoglobin, contribute to essential physiological functions such as oxygen transport. Given the importance of these considerations, accurately identifying Globular proteins is essential. To address the need for precise GP identification, this research introduces an innovative approach that employs a hybrid-based deep learning model called Deep-GP. We generated two datasets based on primary sequences and developed a novel feature descriptor called, Consensus Sequence-based Trisection-Position Specific Scoring Matrix (CST-PSSM). The model training phase involved the application of deep learning techniques, including the bidirectional long short-term memory network (BiLSTM), gated recurrent unit (GRU), and convolutional neural network (CNN). The BiLSTM and CNN were hybridised for ensemble learning. The CST-PSSM-based ensemble model achieved the most accurate predictive outcomes, outperforming other competitive predictors across both training and testing datasets. This demonstrates the potential of harnessing deep learning for precise GB prediction as a robust tool to expedite research, streamline drug discovery, and unveil novel therapeutic targets.

Establishing an AI model and application for automated capsule endoscopy recognition based on convolutional neural networks (with video).

Although capsule endoscopy (CE) is a crucial tool for diagnosing small bowel diseases, the need to process a vast number of images imposes a significant workload on physicians, leading to a high risk of missed diagnoses. This study aims to develop an artificial intelligence (AI) model and application based on convolutional neural networks that can automatically recognize various lesions in small bowel capsule endoscopy. Three small bowel capsule endoscopy datasets were used for AI model training, validation, and testing, encompassing 12 categories of images. The model's performance was evaluated using metrics such as AUC, sensitivity, specificity, precision, accuracy, and F1 score to select the best model. A human-machine comparison experiment was conducted using the best model and endoscopists with varying levels of experience. Model interpretability was analyzed using Grad-CAM and SHAP techniques. Finally, a clinical application was developed based on the best model using PyQt5 technology. A total of 34,303 images were included in this study. The best model, MobileNetv3-large, achieved a weighted average sensitivity of 87.17%, specificity of 98.77%, and an AUC of 0.9897 across all categories. The application developed based on this model performed exceptionally well in comparison with endoscopists, achieving an accuracy of 87.17% and a processing speed of 75.04 frames per second, surpassing endoscopists of varying experience levels. The AI model and application developed based on convolutional neural networks can quickly and accurately identify 12 types of small bowel lesions. With its high sensitivity, this system can effectively assist physicians in interpreting small bowel capsule endoscopy images.Future studies will validate the AI system for video evaluations and real-world clinical integration.

A deep learning approach for gastroscopic manifestation recognition based on Kyoto Gastritis Score.

The risk of gastric cancer can be predicted by gastroscopic manifestation recognition and the Kyoto Gastritis Score. This study aims to validate the applicability of AI approaches for recognizing gastroscopic manifestations according to the definition of Kyoto Gastritis Score, with the goal of improving early gastric cancer detection and reducing gastric cancer mortality. In this retrospective study, 29013 gastric endoscopy images were collected and carefully annotated into five categories according to the Kyoto Gastritis Score, i.e. atrophy (A), diffuse redness (DR), enlarged folds (H), intestinal metaplasia (IM), and nodularity (N). As a multi-label recognition task, we propose a deep learning approach composed of five GAM-EfficientNet models, each performing a multiple classification to quantify gastroscopic manifestations, i.e. no presentation or the severity score 0-2. This approach was compared with endoscopists of varying years of experience in terms of accuracy, specificity, precision, recall, and F1 score. The approach demonstrated good performance in identifying the five manifestations of the Kyoto Gastritis Score, with an average accuracy, specificity, precision, recall, and F1 score of 78.70%, 91.92%, 80.23%, 78.70%, and 0.78, respectively. The average performance of five experienced endoscopists was 72.63%, 90.00%, 77.68%, 72.63%, and 0.73, while that of five less experienced endoscopists was 66.60%, 87.44%, 70.88%, 66.60%, and 0.66, respectively. The sample t-test indicates that the approach's average accuracy, specificity, precision, recall, and F1 score for identifying the five manifestations were significantly higher than those of less experienced endoscopists, experienced endoscopists, and all endoscopists on average (p < 0.05). Our study demonstrates the potential of deep learning approaches on gastric manifestation recognition over junior, even senior endoscopists. Thus, the deep learning approach holds potential as an auxiliary tool, although prospective validation is still needed to assess its clinical applicability.

Detection of suicidality from medical text using privacy-preserving large language models.

Attempts to use artificial intelligence (AI) in psychiatric disorders show moderate success, highlighting the potential of incorporating information from clinical assessments to improve the models. This study focuses on using large language models (LLMs) to detect suicide risk from medical text in psychiatric care. To extract information about suicidality status from the admission notes in electronic health records (EHRs) using privacy-sensitive, locally hosted LLMs, specifically evaluating the efficacy of Llama-2 models. We compared the performance of several variants of the open source LLM Llama-2 in extracting suicidality status from 100 psychiatric reports against a ground truth defined by human experts, assessing accuracy, sensitivity, specificity and F1 score across different prompting strategies. A German fine-tuned Llama-2 model showed the highest accuracy (87.5%), sensitivity (83.0%) and specificity (91.8%) in identifying suicidality, with significant improvements in sensitivity and specificity across various prompt designs. The study demonstrates the capability of LLMs, particularly Llama-2, in accurately extracting information on suicidality from psychiatric records while preserving data privacy. This suggests their application in surveillance systems for psychiatric emergencies and improving the clinical management of suicidality by improving systematic quality control and research.

Long-term outcomes and quality of life in congenital diaphragmatic hernia survivors treated with extracorporeal life support: A cross-sectional survey.

Few reports have shown Quality-of-Life long-term outcomes in children with congenital diaphragmatic hernia (CDH) who received extracorporeal membrane oxygenation (ECMO) support. We reviewed the short- and long-term outcomes in CDH patients that were supported with ECMO during their neonatal treatment. Telephone interviews of parents of CDH children were performed. The Functional Status Scale (FSS) and the Paediatric Quality of Life Inventory (PedQL, Version 4.0) were completed with the parents. All children with a CDH and supported with ECMO from 2010 to 2023 were included in the study. Twenty children were identified, with two having two ECMO runs. Birth weight was 3.2 kg (median). ECMO support lasted for (median) 13.6 days (range 3.8 to 39). Twelve patients were alive at the time of the survey. The age (median) at time of the interview was 6.3 years (range 1 to 12). The FSS score showed no impairment (FSS score 6) in any domain in eight patients. Two patients had a score of 7, and two patients had a score of 8 and 9, respectively. The PedQL showed a median score 84.5, with a physical health summary score of 92.5 and a psychosocial health summary score of 78.7. The cardiac specific PedQL inventory score was 77. ECMO support for CDH patients is associated with functional and Quality of Life outcomes that are similar to that in other PICU discharge populations. Denying ECMO support to CDH patients on the basis of predicted poor long-term outcomes does not appear to be justified.

Impact of histological remission for predicting clinical relapse in Crohn's disease: a post-hoc analysis of the prospective STORI cohort.

Achieving deep remission, encompassing clinical, endoscopic, and biological remission, is the goal in managing Crohn's disease (CD). The role of histological remission remains unclear. This study aimed to examine the impact of histological inflammation on clinical relapse risk in CD and explore the relationship between histology, endoscopic scores, and biomarkers. Patients from the prospective STORI cohort underwent ileocolonoscopy with CDEIS calculation and 2 biopsies from the most inflamed or previously inflamed areas. Histological scores (Robarts, Geboes, modified Geboes, Nancy, and IBD-DCA) were determined by two independent pathologists in a central reading process. Histological remission was defined by specific score thresholds. Clinical relapse, defined by CDAI >250 or a CDAI increase of 70 points over two weeks, was monitored for at least one year. Out of 115 patients included in STORI, 160 biopsies (44 ileal and 116 colonic) from 76 patients were analyzed. Histological remission rates were 46% (Nancy), 55% (Robarts), 61% (Geboes), and 41% (IBD-DCA). During follow-up, 35 patients (46%) experienced a clinical relapse: 37% with histological remission and 56% without, based on the Nancy score. Among the mucosal healing (MH) subgroup (45 patients), 34% with histological remission and 44% without relapsed (p=0.18). Histological scores did not predict clinical relapse. Only faecal calprotectin (FC) was a significant predictor in multivariate analysis (p=0.029). Despite correlations with endoscopy and biomarkers, histological scores did not predict clinical relapse in CD patients in remission. Thus, these scores are not recommended for clinical practice to assess relapse risk in CD.

Solid-State Fluorophores with Synergic Excited State Intramolecular Proton Transfer (ESIPT) and Aggregation-Induced Emission (AIE) Properties as Effective Non-Doped Emitters for Electroluminescent Devices

Here, we present the concept of combining excited-state intramolecular proton transfer (ESIPT) and aggregation-induced emission (AIE) features into a single molecule as a strategy to generate high-performance ESIPT-based non-doped organic light-emitting diodes (OLEDs). Two ESIPT-AIE-type green fluorophores, TBzHPI and TBzHI, are meticulously designed and synthesized by incorporating a conventional AIE moiety of triphenylethylene (TPE) with specific ESIPT cores of 2-(benzo[d]thiazol-2-yl)-6-(1-phenyl-1H-phenanthro[9,10-d]imidazol-2-yl)phenol (BzHPI) and 2-(benzo[d]thiazol-2-yl)-6-(1,4,5-triphenyl-1H-imidazol-2-yl)phenol (BzHI), respectively. The ESIPT and AIE properties are thoroughly validated through both theoretical calculations and experimental investigations. Both TBzHPI and TBzHI exhibit large Stokes shifted emissions (135-146 nm) and strong green emission of the pure keto form in the solid state owing to the collective effects of ESIPT and AIE properties in molecules. Their uses as non-doped emitters in OLEDs have been accomplished, with all devices showing strong keto-form emissions and low turn-on voltages of 2.8 V. Particularly, TBzHPI-based device demonstrates a remarkably high luminance of 54,825 cd m2, a current efficiency (CE) of 18.42 cd A-1, and an external quantum efficiency (EQE) of 5.76%, with only a slight decrease in efficiency. This finding is significant as it represents the highest EQE reported so far for ESIPT molecules used as non-doped emitters in fluorescent OLEDs.

FaceFinder: A Machine Learning Tool for Identification of Facial Images from Heterogenous Datasets

PurposeTo develop an algorithm to automate the organization of large photo databases using the Haar cascade algorithm for face and eye detection using machine learning tools in Python. DesignRetrospective study for the purposes of clinical tool development. MethodsWe developed an algorithm, termed FaceFinder, to identify front facing images in a large dataset of facial, orthodontal and miscellaneous images. FaceFinder works by detecting the presence of faces and at least two eyes using the Haar cascade. Execution time was recorded using different-sized datasets. A total of 895 images were analyzed by FaceFinder using various thresholds for face and eye detection. Precision, recall, specificity, accuracy, and F1 score were computed by comparison to ground truth labels of the images as determined by a human grader. ResultsUsing medium thresholds for face and eye detection, FaceFinder reached recall, accuracy, and F1 score of 89.3%, 91.6%, and 92.9%, respectively with an execution time per image was 0.91 seconds. Using the highest threshold for face and eye detection, FaceFinder achieved precision and specificity values of 98.3% and 99.2% respectively. ConclusionsFaceFinder is capable of sorting through a heterogenous dataset of photos of patients with craniofacial disease and identifying high-quality front-facing facial images. This capability allows for automated sorting of large databases that can facilitate and expedite data preparation for further downstream analyses involving artificial intelligence and facial landmarking.

디지털 매체 및 인공지능 기반의 과정 중심 음악창작 수업 모형 제안

This study aims to provide specific procedures and core teaching-learning contents for music education in school while suggesting an instructional model for process-centered music creation employing digital media and artificial intelligence. To this end, the researcher reviews the several instructional models for music creation in the field of music education, and identifies the key process for digital media and AI-based music activities. Based on the finding, the researcher introduces a novel instructional model for process-centered music creation based on digital media and AI tools. Furthermore, in the light of the instructional model, the researcher demonstrates how music textbooks can be effectively reorganized using digital media and AI tools. Additionally, the researcher proposes specific educational suggestions for teaching and learning activities and process-centered evaluation, thereby contributing to enhance the quality of music creation process for music education in school.

Evaluation of the UV Protection Properties of Para-Aramid Woven Fabrics with Various Specialty Core Yarns.

Para-aramid fibers, known for their remarkable strength and thermal stability, are frequently employed in protective textiles for military and aerospace applications. However, continuous exposure to ultraviolet (UV) radiation can damage their protective characteristics. This study analyzes the ultraviolet protection factor (UPF) and UV transmittance of woven fabrics produced from 30/2 Ne spun para-aramid yarns in the warp and 10 Ne core-spun yarns in the weft. The weft yarns consisted of three sheath fibers-para-aramid, meta-aramid, and polyester-in combination with different specialty core materials. The results show significant differences in UPF before and after UV exposure, with para-aramid sheaths giving the highest improvement. UV exposure caused structural changes in the fibers, resulting in increased UV protection, particularly in fabrics with para-aramid sheaths. This study concludes that the combination of para-aramid fibers with specific core materials significantly enhances UV protection, making them well-suited for applications in high UV exposure environments.

Development and validation of a machine learning-based diagnostic model for Parkinson's disease in community-dwelling populations: Evidence from the China health and retirement longitudinal study (CHARLS)

BackgroundParkinson's disease (PD) is a major neurodegenerative disorder in Middle-aged and elderly people.There is a pressing need for effective predictive models, particularly in chinese population. Objective:This study aims to develop and validate a machine learning-based diagnostic model to identify individuals with PD in community-dwelling populations using data from the China Health and Retirement Longitudinal Study (CHARLS). MethodsWe utilized data from 19,134 individuals aged 45 and above from the CHARLS dataset, with 265 adults reported to have PD. The external validation cohort included 1500 individuals, with 21 (1.4 %) having PD.The random forest (RF) algorithm was used to develop an interpretable PD prediction model, which was internally validated using 10-fold cross-validation and externally validated with a dataset from Northern Jiangsu People's Hospital. SHapley Additive exPlanation (SHAP) values were employed to elucidate the model's predictions. ResultsThe RF model demonstrated robust performance with an Area Under the Curve (AUC) of 0.884 and high sensitivity, specificity, and F1 scores. The model's performance in external validation cohort, highlighting an AUC of 0.82 and an accuracy of 0.99. The model's performance remained consistent across internal and external validation cohorts. SHAP analysis provided insights into the importance and interaction of various predictors, enhancing model interpretability. ConclusionThe study presents a highly accurate and interpretable machine learning-based diagnostic model to identify individuals with PD in middle-aged and older Chinese adults. By combined with predictive risk factors and chronic disease information, the model offers valuable insights for early identification and intervention, potentially mitigating PD progression.

Routing Algorithms for SDM Flexible Optical Networks

This paper considers the online routing, modulation, spectrum, and core allocation problem in elastic optical networks. Three algorithms are proposed to minimize the bandwidth blocking probability while taking into account the impact of interference from established lightpaths. These algorithms are based on a sequence of alternative paths, ordered in terms of increasing lengths, determined by Yen’s algorithm. Each of the algorithms for the selected single or dual lightpath enforces the constraints of spectrum continuity, contiguity of the slots, and non-overlapping of the spectra with the established lightpaths, maximizes the number of bits per symbol, and selects a specific core on each link of the path. Simulation studies performed for two sample networks showed that the crosstalk has a significant impact on the bandwidth blocking probability. The best results were obtained by iterating over all paths and all slots, selecting the lightpath with the lowest average crosstalk per slot, consisting of the most loaded cores.

Long-term outcomes of patients with apical hypertrophic cardiomyopathy: incorporation of a novel risk score

Abstract Background Apical hypertrophic cardiomyopathy (aHCM) is a subtype of HCM characterized by left ventricular hypertrophy predominantly in the apex. There is still limited data on factors associated with adverse outcomes in patients with aHCM. Objectives To a) describe the characteristics and b) develop a novel risk score associated with outcomes in aHCM patients. Methods A total of 462 patients (mean age 58±15 years, 68% male and 70% white) diagnosed with aHCM based on clinical, echocardiographic, and cardiac magnetic resonance (CMR) evaluation were included. The primary endpoint was all-cause death or aborted sudden cardiac death. Using the cox regression analysis, variables showing potential association with the composite endpoint were considered to develop an aHCM specific risk score. Results On echocardiography, the mean LV ejection fraction (LVEF) was 64±8%, and the mean LV mass was 223±72 g. A baseline CMR was performed in 246 (53%) patients, with delayed gadolinium enhancement in 170 (71%) patients with a mean percentage of 5±7%. Patients were followed-up for a mean of 68 months (range 1-248), with composite events occurring in 80 (17%) patients (death in 62 [13%] patients). Univariate Cox regression analysis identified age hazard ratio (HR) 1.06 (95% Confidence Interval or CI 1.04-1.08; p&amp;lt; 0.001), apical aneurysm HR 2.32 (95% CI 1.24-4.34 p=0.008), lower LVEF HR 0.96 (95% CI 0.94-0.99 p=0.002), higher right ventricular systolic pressure (RVSP) HR 1.04 (95% CI 1.02-1.06 p&amp;lt; 0.001), New York Heart Association Class IV HR 11.69 (95% CI 3.59-38.08 p&amp;lt; 0.001) and the presence of Atrial fibrillation HR 1.77 (95% CI 1.14-2.76 p=0.012). An aHCM specific risk score was subsequently created (Figure 1), with good discrimination (c-statistic=0.75) and good calibration with expected to observed ratio of 1.02 and a calibration slope of 0.91 (p-value for difference between expected and observed probabilities =0.22). The risk score ranges between 0 and 8 points, with higher score associated with a higher rate of composite events (Figure 2). Conclusion We developed a novel risk score which demonstrated incremental prognostic value for hard events in aHCM patients.Risk prediction modelKaplan Meier event-free survival curves