Nearest Neighbor Research Articles

Analysis of ensemble machine learning classification comparison on the skin cancer MNIST dataset

This study aims to analyze the performance of various ensemble machine learning methods, such as Adaboost, Bagging, and Stacking, in the context of skin cancer classification using the skin cancer MNIST dataset. We also evaluate the impact of handling dataset imbalance on the classification model’s performance by applying imbalanced data methods such as random under sampling (RUS), random over sampling (ROS), synthetic minority over-sampling technique (SMOTE), and synthetic minority over-sampling technique with edited nearest neighbor (SMOTEENN). The research findings indicate that Adaboost is effective in addressing data imbalance, while imbalanced data methods can significantly improve accuracy. However, the selection of imbalanced data methods should be carefully tailored to the dataset characteristics and clinical objectives. In conclusion, addressing data imbalance can enhance skin cancer classification accuracy, with Adaboost being an exception that shows a decrease in accuracy after applying imbalanced data methods.

Fluctuations of the Occupation Density for a Parking Process

Consider the following simple parking process on Λn:={-n,…,n}d,d≥1\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\Lambda _n:= \\{-n, \\ldots , n\\}^d,d\\ge 1$$\\end{document}: at each step, a site i is chosen at random in Λn\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\Lambda _n$$\\end{document} and if i and all its nearest neighbor sites are empty, i is occupied. Once occupied, a site remains so forever. The process continues until all sites in Λn\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\Lambda _n$$\\end{document} are either occupied or have at least one of their nearest neighbors occupied. The final configuration (occupancy) of Λn\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\Lambda _n$$\\end{document} is called the jamming limit and is denoted by XΛn\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$X_{\\Lambda _n}$$\\end{document}. Ritchie (J Stat Phys 122:381–398, 2006) constructed a stationary random field on Zd\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\mathbb {Z}^d$$\\end{document} obtained as a (thermodynamic) limit of the XΛn\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$X_{\\Lambda _n}$$\\end{document}’s as n tends to infinity. As a consequence of his construction, he proved a strong law of large numbers for the proportion of occupied sites in the box Λn\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\Lambda _n$$\\end{document} for the random field X. Here we prove the central limit theorem, the law of iterated logarithm, and a gaussian concentration inequality for the same statistics. A particular attention will be given to the case d=1\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$d=1$$\\end{document}, in which we also obtain new asymptotic properties for the sequence XΛn,n≥1\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$X_{\\Lambda _n},n\\ge 1$$\\end{document}.

Analysis of Big Data Network Security Defense Mechanism Application of Artificial Intelligence

In the context of the close integration of computer network technology and daily life, big data network security faces many challenges. With its powerful information processing ability, this AI can effectively identify and handle potential threats in the network, thereby improving network security. This paper discusses the application of artificial intelligence (AI) in enhancing big data network security defense, especially in the threat detection link. This paper proposes a detection algorithm that combines support vector machine (SVM) and K nearest neighbor (KNN), namely SVM-KNN algorithm, for network attack detection and defense. When the hazard data is 60 under the test sample, the detection accuracy of KNN, SVM, and SVM-KNN is 86.88%, 89.51%, and 96.75% respectively; when the hazard data is 60 under the experimental sample, the detection accuracy of KNN, SVM, and SVM-KNN is 82.70%, 83.88%, and 89.26% respectively.response.

How Do Primordial Black Holes Change the Halo Mass Function and Structure?

We examine the effects of massive primordial black holes (PBHs) on cosmic structure formation, employing both a semianalytical approach and cosmological simulations. Our simulations incorporate PBHs with a monochromatic mass distribution centered around 106 M ⊙, constituting a fraction of 10−2 to 10−4 of the dark matter (DM) in the Universe, with the remainder being collisionless particle DM. Additionally, we conduct a ΛCDM simulation for comparative analysis with runs that include PBHs. At smaller scales, halos containing PBHs exhibit similar density and velocity dispersion profiles to those without PBHs. Conversely, at larger scales, PBHs can expedite the formation of massive halos and reside at their centers owing to the “seed effect.” To analyze the relative distribution of PBH host halos compared to non-PBH halos, we apply nearest neighbor statistics. Our results suggest that PBH host halos, through gravitational influence, significantly impact the structure formation process, compared to the ΛCDM case, by attracting and engulfing nearby newly formed minihalos. Should PBHs constitute a fraction of DM significantly larger than ∼10−3, almost all newly formed halos will be absorbed by PBH-seeded halos. Consequently, our simulations predict a bimodal feature in the halo mass function, with most of the massive halos containing at least one PBH at their core and the rest being less massive non-PBH halos.

Evaluation of the Labor Impact of the National Program of Direct Support to the Poorest - JUNTOS in Peru

The objective of this research is to estimate the labor impact of the National Program of direct support to the poorest JUNTOS in Peru for the year 2021. The methodology used is the Propensity Score Matching (PSM) through the nearest neighbor method; the database of the National Household Survey ENAHO 2021 is used as a source of information. The results of the logit model indicate that poverty, unsatisfied basic needs and education do influence the probability of participation in the Juntos Social Program and are statistically significant at a 1% level; the expected signs of the coefficients of the logit model are correct. On the other hand, the effect of the Juntos Social Program on the length of the working day is negative for the year 2021; it is found that the value of the average treatment effect in the treated population (ATT) is -1.167, which is highly significant at a 1% level. This indicates that participation in the Juntos Social Program is associated with an average reduction of 1.167 hours per week in working hours. This suggests that the economic transfer provided by the program is not sufficient to replace the workday, which implies that beneficiaries must continue to participate in the labor field.

SPATIAL ANALYSIS OF PHYSICAL ACCESSIBILITY TO PUBLIC PRIMARY HEALTHCARE CENTERS IN KADUNA STATE, NIGERIA

The rising call for spatial justice in the distribution and access to public facilities especially health necessitated this study. The study sets out to assess the spatial patterns of physical accessibility to PPHCs in Kaduna State. Four physical accessibility parameters were used in this study: travel time, travel distance to the nearest Public Primary Healthcare Centers (PPHCs), mean distances between and within PPHCs, and effective geographic catchment area coverage of PPHCs. Both travel time and distance to the nearest PPHC were evaluated using a questionnaire. The mean distance between and within PPHCs for LGAs was estimated from the Nearest Neighbor Analysis. The effective geographic catchment area of a PPHC was determined using the geospatial Thiessen polygon method. Findings showed that 42% of the respondents, live close (< 2 km) to a PPHC facility. The proximity of the respondents from Igabi (52%), Zaria (49%), and Zangon-Kataf (51%) is closer than the other LGAs. Thiessen catchment area showed a wide range of variations with some PPHCs with very large areas (426 -615 km2) mostly found in the central senatorial zone, especially in Birnin Gwari and Chikun LGAs. The most widespread are PPHCs with relatively moderate catchment sizes of (187–339 km2) found across parts of northern, central, and southern senatorial and LGAs. The study concludes that areal and topographic factors as revealed by the polygon-derived catchment areas should also guide the decision for the siting of PPHCs in the state. Hence, additional PPHCs are recommended especially LGAs with extensive land masses.

Machine Learning in Agriculture: KNN-Based Classification of Fruits and Vegetables

In modern agriculture and the food industry, it is essential to classify fruits and vegetables accurately and efficiently to meet growing consumer demand and reduce post-harvest losses. Traditional manual methods are often labor-intensive and error prone, highlighting the need for automated solutions. This paper discusses the application of the k Nearest Neighbor (KNN) algorithm to fruit and vegetable recognition using image processing technology. In this study, image data sets are used for feature extraction using Directional Gradient Histogram (HOG) and dimensionality reduction using Principal Component Analysis (PCA). The accuracy of KNN model on verification set and test set reaches 97%, which proves its validity. Confusion matrix analysis and F1 score evaluation further revealed the strengths and areas of improvement of the model, particularly in distinguishing visually similar categories. The results show that the integration of artificial intelligence (especially KNN) offers great potential for the automation of agricultural classification tasks. Future studies could combine more advanced models, such as CNNS, with larger datasets to improve accuracy and robustness.

CLAP. I. Resolving miscalibration for deep learning-based galaxy photometric redshift estimation

Obtaining well-calibrated photometric redshift probability densities for galaxies without a spectroscopic measurement remains a challenge. Deep learning discriminative models, typically fed with multi-band galaxy images, can produce outputs that mimic probability densities and achieve state-of-the-art accuracy. However, several previous studies have found that such models may be affected by miscalibration, an issue that would result in discrepancies between the model outputs and the actual distributions of true redshifts. Our work develops a novel method called the C ontrastive L earning and A daptive KNN for P hotometric Redshift (CLAP) that resolves this issue. It leverages supervised contrastive learning (SCL) and $k$-nearest neighbours (KNN) to construct and calibrate raw probability density estimates, and implements a refitting procedure to resume end-to-end discriminative models ready to produce final estimates for large-scale imaging data, bypassing the intensive computation required for KNN. The harmonic mean is adopted to combine an ensemble of estimates from multiple realisations for improving accuracy. Our experiments demonstrate that CLAP takes advantage of both deep learning and KNN, outperforming benchmark methods on the calibration of probability density estimates and retaining high accuracy and computational efficiency. With reference to CLAP, a deeper investigation on miscalibration for conventional deep learning is presented. We point out that miscalibration is particularly sensitive to the method-induced excessive correlations among data instances in addition to the unaccounted-for epistemic uncertainties. Reducing the uncertainties may not guarantee the removal of miscalibration due to the presence of such excessive correlations, yet this is a problem for conventional methods rather than CLAP. These discussions underscore the robustness of CLAP for obtaining photometric redshift probability densities required by astrophysical and cosmological applications. This is the first paper in our series on CLAP.

Resume Optimization Model Using Machine Learning Techniques

In the contemporary job market, where competition is fierce and employers are inundated with an ever-growing pool of resumes, the need for effective resume optimization has become paramount. Resumes serve as the first point of contact between job seekers and potential employers, playing a pivotal role in shaping initial perceptions. However, the traditional approach to resume crafting often lacks a systematic and data-driven methodology. A well-crafted resume plays a crucial role in securing employment opportunities. However, crafting an effective resume that resonates with both human recruiters and Applicant Tracking Systems (ATS) can be a daunting task. By employing natural language processing (NLP) and machine learning algorithms Multinomidal Naïve Bayes (MNB) and K Nearest Neighbour (KNN), this system extracts relevant features from resumes, such as keyword relevance, formatting styles, content organization, and overall readability. Through supervised learning models trained on a diverse dataset of resumes, the system can predict the effectiveness of a resume and generate actionable insights. Overall, the KNN model demonstrated effectiveness in automating the resume screening process, of 87% accuracy. The developed system not only provides accurate predictions but also offers interpretable explanations, enabling users to understand the factors contributing to the model's decisions. The system has the potential to benefit both job seekers and employers by facilitating better matches between candidates' qualifications and job requirements.

Enhancing Portfolio Optimization: A Two-Stage Approach with Deep Learning and Portfolio Optimization

The portfolio selection problem has been a central focus in financial research. A complete portfolio selection process includes two stages: stock pre-selection and portfolio optimization. However, most existing studies focus on portfolio optimization, often overlooking stock pre-selection. To address this problem, this paper presents a novel two-stage approach that integrates deep learning with portfolio optimization. In the first stage, we develop a stock trend prediction model for stock pre-selection called the AGC-CNN model, which leverages a convolutional neural network (CNN), self-attention mechanism, Graph Convolutional Network (GCN), and k-reciprocal nearest neighbors (k-reciprocal NN). Specifically, we utilize a CNN to capture individual stock information and a GCN to capture relationships among stocks. Moreover, we incorporate the self-attention mechanism into the GCN to extract deeper data features and employ k-reciprocal NN to enhance the accuracy and robustness of the graph structure in the GCN. In the second stage, we employ the Global Minimum Variance (GMV) model for portfolio optimization, culminating in the AGC-CNN+GMV two-stage approach. We empirically validate the proposed two-stage approach using real-world data through numerical studies, achieving a roughly 35% increase in Cumulative Returns compared to portfolio optimization models without stock pre-selection, demonstrating its robust performance in the Average Return, Sharp Ratio, Turnover-adjusted Sharp Ratio, and Sortino Ratio.

Around the clock: unveiling giraffe rest-activity rhythms and social dynamics

Understanding the daily activity patterns and social dynamics of giraffes (Giraffa camelopardalis) is crucial for their management and conservation. In this study, a comprehensive 24-hour observational analysis of three female reticulated giraffes kept for three weeks at the Opel-Zoo in Kronberg, Germany, was conducted. Using infrared-sensitive cameras, the study captured behavioral data across baseline and two intervention phases involving changes in group composition. Social network analysis was performed using the Mantel test to assess changes in social interactions between day and night and across different study periods, while the MRQAP was applied to evaluate the influence of individual subtypes on the social structure. During the day, the giraffes exhibited a high level of activity, primarily engaging in walking, standing, and feeding behaviors. Diurnal resting was minimal, with sporadic lying phases. Night-time behavior was markedly different, with the giraffes spending most of the night lying down, interspersed with periods of feeding. The presence of a male giraffe during one intervention phase significantly altered diurnal activity patterns, increasing standing behaviors and decreasing feeding time. Social interactions, including nearest neighbor preferences, varied across day and night periods and changed with alterations in group composition. The study highlights the complexity of giraffe social dynamics and their adaptation to different social contexts. These findings provide valuable insights into the natural behavioral rhythms and social behaviors of giraffes, which are essential for effective zoo management and conservation strategies.

Spatiotemporal distribution of toponymic cultural heritage in Jiangsu Province and its historical and geographical influencing factors

As a typical intangible cultural heritage, Toponymic Cultural Heritage (TCH) is rich in geographic information and semantic and physical connotations. In the context of the heritage conservation era, it is highly important to study the spatiotemporal distribution characteristics of toponymic cultural heritage and explore its historical and geographic influencing factors on the sustainable conservation and development of toponymic cultural heritage. However, most existing studies focus on the toponym cultural landscape, and less attention has been given to TCH. Therefore, on the basis of the data of 357 provincial TCH items in Jiangsu Province, this study investigated the spatiotemporal distribution characteristics and historical–geographical influencing factors of the TCH by using geospatial analysis methods, such as the average nearest neighbor, tyson polygon, kernel density estimation, standard deviational ellipse, and superposition coupling analysis, and proposed several strategies for adaptive reuse of TCH. The results show that (1) the TCHs of Jiangsu Province have a spatial distribution characteristic of "sparse in the north, scattered in the middle and dense in the south" and form a high-density agglomeration around the southern part of Jiangsu Province. In the distribution of cultural districts, the Jinling cultural district, the Wu cultural district, and the Huaiyang cultural district have the largest number of TCHs. (2) From the Pre-Qin period to the Ming and Qing Dynasties, TCHs, such as Nanjing, Yangzhou, Zhenjiang, Changzhou, and Suzhou, tended to merge in the southern part of Jiangsu. (3) In terms of type, the roads, streets and alleys of TCHs are the richest, and all types of TCHs are spatially clustered in the southern part of Jiangsu Province, which has a high level of urbanization, industrialization, and a superior geographic environment. (4) TCHs have spatial tendencies toward low altitudes and hydrophilicity, and relatively favorable natural geographical conditions provide a high-quality environment for TCHs in southern Jiangsu Province. Influenced by historical, humanistic, and geographical factors, TCH is unevenly developed spatially. As a historical population concentration area, an important political, economic, and cultural core area, and a center of gravity for cultural development, more TCH resources have survived in the southern part of Jiangsu Province. This study provides a new perspective for interpreting and recognizing TCH as a special intangible cultural heritage and can provide a reference for the sustainable conservation and development of TCH.

Do Children With Accidental Gunshot-related Fractures Experience Greater Risk of Mental Illness and Psychiatric Disorders? A Propensity-matched Study.

Firearm violence is the leading cause of death and is a major source of morbidity for children in the United States. While gunshot wounds (GSWs) are known to cause lasting psychological repercussions beyond physical injury, these effects are not well documented compared with the physical implications. Our study explores the association between accidental gunshot-related fractures in children and subsequent psychiatric outcomes. Relative to non-GSW-related fractures, do children sustaining an accidental GSW-related fracture experience higher risk of mental illness and psychiatric disorders? This study utilized the TriNetX US Collaborative Network as it provides comprehensive inpatient and outpatient data, longitudinal follow-up, and complete medical records across different facilities, closely reflecting real-world patient outcomes in orthopaedic practice. We retrospectively evaluated children diagnosed with an accidental GSW-related fracture and compared mental health diagnoses to children who experienced non-GSW-related fractures. Between January 1, 2003, and March 1, 2023, a total of 5071 children in the United States without preexisting anxiety, mood, psychotic, substance use, or insomnia disorders were reported to have experienced an accidental GSW-related fracture. Among these patients, 55% (2773) had a follow-up period of at least 1 year and met the inclusion criteria for the exposure cohort. In the non-GSW-related fracture cohort, a total of 61% (985,070) of children among 1,613,891 without the preexisting aforementioned conditions had a minimum follow-up period of 1 year and met the inclusion criteria. A total of 2769 children were successfully matched in each cohort using a greedy nearest neighbor propensity score-matching algorithm. Matching was based on age, gender, race, fracture location, and BMI, as these characteristics were identified through a regression analysis as potentially associated with psychiatric outcomes (p < 0.01). The mean ± SD age was 15 ± 4 years, and 16% (451) in the GSW cohort were girls. In the non-GSW cohort 17% (474) were girls. With respect to race and ethnicity, 62% (1709 in the GSW cohort; 1679 in the non-GSW cohort) were Black and 14% (384 in the GSW cohort; 386 in the non-GSW cohort) were Hispanic. Outcomes of interest were recorded for up to 3 years after the index event. The accidental GSW-related fracture cohort experienced a greater hazard of developing anxiety disorders (HR 3.8 [95% confidence interval (CI) 3.2 to 4.6]; p < 0.001), substance use disorders (HR 3.6 [95% CI 3.0 to 4.2]; p < 0.001), mood disorders (HR 2.4 [95% CI 1.9 to 3.1]; p < 0.001), non-mood psychotic disorders (HR 2.4 [95% CI 1.5 to 3.9]; p < 0.001), and insomnia (HR 1.8 [95% CI 1.4 to 2.3]; p < 0.001). Orthopaedic surgeons should implement early psychiatric screenings and integrate mental health support for children with gunshot-related fractures to address elevated risk of anxiety disorders, psychotic disorders, mood disorders, substance abuse, and insomnia. Future studies should focus on identifying effective interventions that mitigate these long-term psychological outcomes, with an emphasis on practical, targeted approaches in clinical care. Level III, prognostic study.

Identifying at-risk patients for atrial high-rate episodes by machine learning

Abstract Background Current evidence suggests that atrial high rate episodes (AHRE)/subclinical atrial fibrillation (AF) are associated with increasing risk of clinical AF, and subsequently, ischaemic stroke and other adverse cardiovascular events. Purpose To construct a high-performance model by machine learning (ML) for the prediction of AHRE detected by a cardiac implantable electronic device (CIED) capable of atrial sensing in a European cohort. Methods We utilized data from a prospective cohort of patients with CIED. AHRE was defined as an episode lasting at least 5 minutes with atrial rate ≥ 175 beats per minute. We divided the cohort into training and internal validation cohorts in 7:3 and used 5-fold cross-validation in the training cohort to assess model performance and prevent model overfitting. Pre-selected features were imported into eight common ML algorithms to predict AHRE, including light gradient boosting machine (LightGBM), random forest (RF), logistic regression, support vector machine, multiple perceptron, eXtreme gradient boosting machine (XGBoost), Gaussian naïve Bayes, and K nearest neighbours. The importance ranking of the features was interpreted by calculating the SHapley Additive exPlanationation (SHAP) value for each feature within the optimal model. Results A total of 500 consecutive patients with CIEDs (mean age 70.2±13.3; 39.2% female) were included. Of these, 164 patients (32.8%) were found to have AHRE. Among all ML models, RF was the best performing model, which obtained the highest AUC (0.738), recall (0.673) and F1-score (0.584) in the internal validation cohort. The results of SHAP showed that antiplatelet, statin, age, white blood cell count, and cardiomyopathy were the first five important features, indicating that the RF model had good interpretability and reliability. Conclusion Our study is the first to demonstrate in a European cohort the effectiveness and feasibility of ML algorithms in predicting AHRE in patients detected by CIEDs. The best RF models require further external validation to assess generalizability to other cohorts.Figure 1Figure 2

Topological Approach to Void Finding Applied to the SDSS Galaxy Map

The structure of the low redshift Universe is dominated by a multiscale void distribution delineated by filaments and walls of galaxies. The characteristics of voids, such as morphology, average density profile, and correlation function, can be used as cosmological probes. However, their physical properties are difficult to infer due to shot noise and the general lack of tracer particles used to define them. In this work, we construct a robust, topology-based void-finding algorithm that utilizes Persistent Homology to detect persistent features in the data. We apply this approach to a volume-limited subsample of galaxies in the SDSS I/II Main Galaxy catalog with the r-band absolute magnitude brighter than M r = −20.19, and a set of mock catalogs constructed using the Horizon Run 4 cosmological N-body simulation. We measure the size distribution of voids, their averaged radial profile, sphericity, and the centroid nearest neighbor separation, using conservative values for the threshold and persistence. We find 32 topologically robust voids in the SDSS data over the redshift range 0.02 ≤ z ≤ 0.116, with effective radii in the range 21−56 h −1 Mpc. The median nearest neighbor void separation is found to be ∼57 h −1 Mpc, and the median radial void profile is consistent with the expected shape from the mock data.

Mild intracerebral bleeding does not adversely affect survival and neurological outcome of surgical therapy for left-sided infective endocarditis

Abstract Background Intracerebral bleeding (IB) is a serious condition that requires increased attention and has implications for treatment options. For patients with infective endocarditis (IE), current guidelines recommend postponing surgery if IB is present. IB can be classified into four relevant groups (following European Cooperative Acute Stroke Study and Heidelberger Bleeding classification): hemorrhagic transformation (HT) 1 and 2, and parenchymal hemorrhage (PH) 1 and 2. PH2 is the only IB with neurological deterioration. These classifications were originally introduced for stroke patients following thrombolysis but without IE. The hypothesis tested in our study is that IB may influence IE treatment and thus outcome. Method Patients were retrospectively identifyied who were operated for left-sided IE, neuroradiologists re-evaluated and classified preoperative cerebral imaging for any IB. Outcome was quantified using the modified Rankin score (mRS), and mRS were extracted from the patients’ hospital chart at admission and by follow-up telephone call (FU), also including mortality. To ensure that the influence of IB was comparable, patients with IB (IB+) were propensity matched (EuroScore 2, Charlson Comorbidity Index, C-reactive protein; nearest neighbor match) to patients without IB (IB-) who also received surgical IE therapy. All IB+ patients underwent a careful risk-benefit analysis before therapy. Results Of 286 consecutive patients (January 2015 - November 2022) operated for left-sided IE, 36 had IB (65±13 years, 26% female): 11 with HT1, 9 with HT2, 8 with PH1, and 8 with PH2. These patients were matched with 36 operated IB- patients. Survival analysis showed no overall effect of IB+ vs. IB- (p = 0.112, 95% CI of hazard ratio was 0.246-1.243 vs. 0.709-3.572). Although there was no effect of IB on survival in the mild IB subgroup (HT1/2, Figure A), there was a difference in patients with severe IB (PH1/2) with less survival in IB+ (Figure B). Neurological outcome (ΔmRS) showed an effect of IB grade in the two-way ANOVA analysis (p = 0.029). Intergroup comparison showed a significantly better outcome for IB- (vs. IB+) in the PH2 subgroup (p = 0.034), but not in other subgroups. For all groups, the mean ΔmRS for IB+ was 1.1±1.6 vs. 0.70±1.4 for IB- (p = 0.256). The mean FU time was 2.6±2.1 years. Conclusion In patients operated for left-sided IE, mild IB did not affect survival or neurological outcome. In the more severe forms of IB, i.e. PH1 and PH2, survival was less favorable compared to matched controls. Furthermore, we observed a difference in neurological outcome in patients with severe IB. Thus, surgical therapy of left-sided IE should be avoided in patients with severe IB, whereas we can add evidence to the safety of surgical therapy in mild IB. Therefore, we recommend regular assessment of the degree of IB in such patients.Figure

Cardiovascular mortality with oral potassium-binders in patients with CKD and heart failure

Abstract Introduction Hyperkalemia is an inherent consequence of advancing chronic kidney disease (CKD) as a result of the kidney’s decreased ability to excrete potassium. Heart failure patients with concomitant CKD may not tolerate maximum doses of guideline-directed medical therapies (GDMT) like ACE inhibitors (ACEi), angiotensin receptor blockers (ARB), angiotensin receptor/neprilysin inhibitors (ARNI) and mineralocorticoid receptor antagonists (MRA) due to dose-limiting hyperkalemia. Many randomized controlled trials in heart failure exclude patients with advanced CKD. Two oral therapies exist to manage hyperkalemia - patiromer sorbitex calcium and sodium zirconium cyclosilicate. This study aims to identify the potassium-binder with better outcomes as defined by less readmissions, hyperkalemia episodes, and death. Purpose This project was undertaken to better understand the impact of using potassium-binders in CKD patients with heart failure. Improved management of hyperkalemia will be an avenue for optimization of GDMT in this population. Methods and materials The TriNetX research network was used for this study. Two cohorts of patients were created by using International Classification of Disease 10 (ICD-10) codes and CPT codes. Both cohorts consisted of patients with no prior history of hyperkalemia within 30 days of hospital discharge at which time one cohort was prescribed patiromer and the other received sodium zirconium cyclosilicate. Each cohort was prohibited from exposure to the other medication. The cohorts were balanced by propensity score matching and the greedy nearest neighbor algorithm for age, race, gender, ethnicity. They were also balanced for systolic and diastolic heart failure diagnoses, and for each individual stage of CKD (1 through 5 and end stage). They were also balanced for use of ACEi, ARBs, and MRAs. This resulted in 8,921 patients in each arm. They were then evaluated for the outcomes of hospital readmission, hyperkalemia episodes (&amp;gt;6.1 mmol/L), and death within 12 months. Results Patients treated with patiromer were more likely to be hospitalized over the following twelve months (44% vs 40%, RR 1.11, 95% CI (1.07,1.15), p value &amp;lt;0.0001). They were also more likely to experience hyperkalemia (11.7% vs 9.2%, RR 1.27, 95% CI (1.16,1.38), p value &amp;lt;0.0001). Patiromer was also associated with slightly greater all cause mortality (27% vs 25%, RR 1.08, 95% CI (1.03,1.13), p value 0.0021). Discussion This study demonstrates patiromer has more readmissions and hyperkalemia episodes along with greater mortality. In conclusion, sodium zirconium cyclosilicate was found to have better outcomes compared to that of patiromer. Further studies are necessary to better understand the utility of using sodium zirconium cyclosilicate as maintenance therapy for hyperkalemia in order to maximize GDMT in CKD patients with heart failure.

Comparison of ventricular tachyarrhythmias in HF patients on dapagliflozin versus empagliflozin

Abstract Background Ventricular tachycardia (VT) and ventricular fibrillation (VF) are devastating tachyarrhythmias that can cause sudden cardiac death in patients with heart failure (HF) if not anticipated or treated promptly. Although post-hoc analysis in DAPA-HF showed promise in their benefit, Sodium-glucose transport protein 2 inhibitors (SGLT2i) have not yet been evaluated for their effect on these tachyarrhythmias. This retrospective analysis aims to compare the 2 most commonly used SGLT2i agents, dapagliflozin and empagliflozin, and the incidence of VT in patients with HF. Methods The TriNetX Research network was used for this study. The two initial patient cohorts were created using ICD-10 codes and medication codes from the TriNetX platform. Both cohorts consisted of patients over age 60 with a history of heart failure and either VF or VT. One cohort was on treatment with dapagliflozin and the other with empagliflozin. The cohorts were balanced by propensity score matching and the greedy nearest neighbor algorithm for age, gender, race, ethnicity, hyperkalemia, and the current use of spironolactone, amiodarone, metoprolol, and carvedilol, resulting in 9,841 patients in each arm. The cohorts were then evaluated for the development of VF or VT over the subsequent five years as well as all-cause mortality. Additional cohorts were created to evaluate dapagliflozin vs empagliflozin in diabetics, nondiabetics, and patients with ejection fractions less than 35% Results Dapagliflozin was associated with an increased risk of ventricular arrhythmia in heart failure patients compared to empagliflozin (46.0% vs. 40.8%, RR 1.13, 95% CI (1.09,1.16), P value &amp;lt; 0.0001). It was also associated with higher mortality at five years (RR 1.10, 95% CI (1.03,1.18), P value 0.0034). Conclusions In comparisons between dapagliflozin and empagliflozin in heart failure patients with previously documented ventricular arrhythmias, empagliflozin had 13% less risk of recurrence of ventricular arrhythmias. Secondarily, the empagliflozin cohort also exhibited lower all-cause mortality (14.8% vs 16.3%) at five years from starting the drug. Our analysis does not disprove findings in DAPA-HF, but rather may support the potential class effect of SGLT2 inhibitors in their ability to suppress VT.(1) Importantly, the overall incidence of ventricular tachyarrhythmias is high in both cohort, given we selected a high-risk population. Notably, our documented recurrence rate is similar to past reports of recurrence after VT ablation, the gold standard for treatment of VT. (2) SGLT2 inhibitors have shown clear benefit in multiple placebo-controlled studies in terms of heart failure outcomes like mortality and readmission, but their effect on arrhythmias is one more additional benefit this class may have. (3) Given these associations, empagliflozin may be a more favorable options for HF patients who have already had VT or VF.

Refining Cellular Data for Accurate Trip Chain Identification: A Novel Approach for Urban Travel Analysis

Cellular data play a crucial role in supporting travel demand assessment and urban traffic planning because of their cost-effectiveness and extensive coverage. However, inherent inaccuracies, such as imprecise positioning, data duplication, and abnormal communication frequencies, hinder their ability to depict travelers’ trips accurately. In this paper, we present a novel approach to mitigate these issues by employing base station mapping to refine positioning data, eliminating duplicates and abnormal frequency records. This refinement enables more effective utilization of cellular data for trip chain identification. We address the ping-pong handover effect by employing a finite automaton machine and an approximate nearest neighbor searching method with carefully selected seeds to identify activities. Our method’s accuracy is validated through ground truth value analysis, focusing on permanent resident population estimation and metro passenger flow estimation. Furthermore, we demonstrate the practical effectiveness and value of our proposed method through a series of representative applications in a real-world case study in the city of Nanning, Guangxi Province, China.

Comparison of cardiovascular outcomes in patients with diabetes treated with tirzepatide versus semaglutide: a multi-institutional analysis

Abstract Introduction Glucagon-like-peptide-1 (GLP-1) receptor agonists have been demonstrated to have cardiovascular benefits in patients with diabetes. Two of the most prescribed medications in this class are tirzepatide and semaglutide. Tirzepatide is a dual glucose-dependent insulinotropic polypeptide and GLP-1 receptor agonist, while semaglutide is a selective GLP-1 receptor agonist. Tirzepatide and semaglutide have previously been directly compared to assess efficacy in glycemic control as the primary endpoint. However, there is limited data directly comparing cardiovascular outcomes between the two medications in patients with diabetes. This retrospective cohort study compares the incidence of major adverse cardiovascular events (MACE) in patients with diabetes treated with tirzepatide or semaglutide. Purpose The purpose of this study is to identify differences in cardiovascular outcomes between patients with diabetes treated with tirzepatide as compared to semaglutide. Materials and Methods The TriNetX research network was used for this study. Two patient cohorts were generated using International Classification of Disease 10 (ICD-10) codes and medication codes in the TriNetX system. Both cohorts of patients had a history of diabetes (E08-E13) and no prior history of cerebral vascular accident (I63) or myocardial infarction (I21). One cohort received semaglutide and the other tirzepatide. Each cohort was prohibited from receiving the other agent. The cohorts were balanced for age, race, gender, and ethnicity by propensity score matching and the greedy nearest neighbor algorithm resulting in 36,212 patients in each arm. They were then evaluated for the 3-year outcomes of major adverse cardiovascular events (myocardial infarction, cerebral vascular accident, and death). Results Tirzepatide was associated with statistically significantly fewer MACE outcomes compared to semaglutide for each of the individual endpoints as well as the overall composite endpoint over the 3 year follow up period. Table 1. MACE events for semaglutide and tirzepatide. Table 2. Relative risks for semaglutide MACE endpoints compared to tirzepatide. Conclusions In this retrospective cohort study, tirzepatide was associated with a lower incidence of major adverse cardiovascular events compared to semaglutide in patients with diabetes. These findings suggest that tirzepatide offers superior cardiovascular protection for primary prevention compared to semaglutide and warrant further investigation in future studies and clinical trials.Table 1Table 2