Neighbor Algorithm Research Articles

Numerical Modeling on Ocean-Bottom Seismograph P-Wave Receiver Function to Analyze Influences of Seawater and Sedimentary Layers

It is challenging to apply the receiver function method to teleseisms recorded by ocean-bottom seismographs (OBSs) due to a specific working environment that differs from land stations. Teleseismic incident waveforms reaching the area beneath stations are affected by multiple reflections generated by seawater and sediments and noise resulting from currents. Furthermore, inadequate coupling between OBSs and the seabed basement and the poor fidelity of OBSs reduce the signal-to-noise ratio (SNR) of seismograms, leading to the poor quality of extracted receiver functions or even the wrong deconvolution results. For instance, the poor results cause strong ambiguities regarding the Moho depth. This study uses numerical modeling to analyze the influences of multiple reflections generated by seawater and sediments on H-kappa stacking and the neighborhood algorithm. Numerical modeling shows that seawater multiple reflections are mixed with the coda waves of the direct P-wave and slightly impact the extracted receiver functions and can thus be ignored in subsequent inversion processing. However, synthetic seismograms have strong responses to the sediments. Compared to the waveforms of horizontal and vertical components, the sedimentary responses are too strong to identify the converted waves clearly. The extracted receiver functions correspond to the above influences, resulting in divergent results of H-kappa stacking (i.e., the Moho depth and crustal average VP/VS ratio are unstable and have great uncertainties). Fortunately, waveform inversion approaches (e.g., the neighborhood algorithm) are available and valid for obtaining the S-wave velocity structure of the crust–upper mantle beneath the station, with sediments varying in thickness and velocity.

A Novel Method for Anomaly Detection and Correction of GNSS Time Series

Abstract Global Navigation Satellite Systems (GNSS) provides a novel means for deformation monitoring, which is an important guarantee for structures. Accurately separating its linear and nonlinear signals, and noise in GNSS time series is the foundation for analyzing deformation mechanisms and the prerequisite for assessing the status. However, extracting deformation signals is a challenging obstacle to applying GNSS for deformation monitoring. Aimed at that, a new method is proposed in this study. Fine-tuning the window size and threshold of the Hampel filter through grid search allows for initial anomaly detection and correction. Optimizing the K parameter of the K-Nearest Neighbors (KNN) algorithm via rigorous K-Fold Cross-Validation ensures further smoothing of the filtered data, which overcomes the limitations of the Hampel filter in handling continuous anomalies. Experimental results demonstrate that the proposed method improves performance by approximately 62% compared to traditional methods and by around 40% relative to IQR and other methods. This study presents an effective approach for detecting and eliminating outliers in GNSS deformation monitoring, offering noteworthy theoretical and practical implications.

BIOM-39. GENOMIC AND CLINICAL ASSOCIATIONS WITH RADIATION NECROSIS IN PATIENTS WITH DIFFUSE INFILTRATING GLIOMAS

Abstract BACKGROUND Radiation necrosis (RN) is a complication of radiotherapy (RT) that can significantly affect quality of life and outcomes in patients with gliomas. Clinical and molecular factors predisposing patients to RN are not clearly established. We hypothesize that clinicogenomic data can be leveraged to identify patients at high risk for RN. METHODS We identified patients from 2014-2024 with diffuse gliomas and RN diagnosed based on Advanced-Brain-Tumor-Imaging which includes conventional MRI, 3 perfusion parameters, spectroscopy and/or pathology at MD Anderson. Inclusion criteria included diagnosis of RN 12-weeks after RT and concordance of 4 ABTI parameters. For each case, we identified 2 controls who were gender-,diagnosis-, and age-matched using a nearest neighborhood algorithm. We evaluated the correlation between 15 most mutated genes in baseline tissue and occurance of RN. A logistic regression model was employed to assess the multivariable relationship between patient characteristics, gene mutations, and RN. RESULTS We identified 62 patients with RN; 50 glioblastoma (80.6%), 8 diffuse astrocytoma (12.9%) and 4 oligodendroglioma (6.5%). Time from RT to RN diagnosis was 254 days (IQR 154-483). 18(29%) of RN cases and 29(24.4%) of controls had received more than one course of RT. Patients treated with bevacizumab before RT had significantly lower odds of developing RN compared to those who did not receive bevacizumab (OR 0.103 [0.011 – 0.960], p=0.0459). BRAF mutations were more frequent in the RN cohort (8.1% vs. 2.4%) and patients with BRAF mutation were more likely to have RN than those without BRAF mutation (OR 6.842 [1.2, 39.01], p=0.0304). Age, gender, diagnosis, IDH, MGMT or 1p19q status were not associated with RN. CONCLUSION We found that bevacizumab administration was associated with a significant reduction in RN development. We also found a novel association between presence of BRAF mutations and increased risk of RN in glioma patients, which warrants further investigation.

SOCIAL MEDIA FAKE ACCOUNT IDENTIFICATION USING ML

The proliferation of social media platforms has led to an increase in the creation of fake accounts. These accounts are used for various malicious activities, such as spreading false information, phishing, and identity theft. As a result, there is a growing need for effective methods to identify and eliminate fake accounts. This paper proposes a machine learning-based approach for social media fake account identification. This paper proposes a machine learning-based approach to identify fake accounts on social media platforms. Our method leverages a combination of feature extraction techniques and supervised learning algorithms to classify accounts as genuine or fake. We collect a large dataset of labeled social media accounts, including both genuine and fake profiles, and extract features from various sources such as profile information, network behavior, and content analysis. We experiment with multiple machine learning models, including Support vector machines(SVM),K-Nearest Neighbors Algorithm(KNN),Random forest, Logistic Regression & Artificial Neural Network(ANN) to evaluate their performance in identifying fake accounts. Our proposed method has significant implications for social media platform operators, policymakers, and researchers seeking to combat fake accounts and maintain online trust. The approach can be integrated with existing social media moderation tools to enhance the accuracy and efficiency of fake account identification. Key Words: Support vector machines(SVM),K-Nearest Neighbors Algorithm(KNN),Random forest, Logistic Regression & Artificial Neural Network(ANN),Python.

Analysis of K-NN with the Integration of Bag of Words, TF-IDF, and N-Grams for Hate Speech Classification on Twitter

Social media has emerged as one of the primary communication channels in the modern world, but it has simultaneously become a platform where hate speech can spread easily. This study attempts to evaluate the performance of a hate speech classification model using the K-Nearest Neighbors (K-NN) algorithm along with various feature extraction techniques, specifically Bag of Words (BoW), Term Frequency-Inverse Document Frequency (TF-IDF), and N-Grams. The dataset used in this study consists of 13169 entries, which represent a diverse range of hate speech examples commonly encountered on social media platforms. In this experimental investigation, we assess the efficacy of the model using each feature extraction technique. The findings reveal that the K-NN model exhibits optimal performance when the k parameter is set to 3 (k=3). Under this configuration, the model achieves an accuracy of 86.88%, with a precision of 88.27%, a recall of 86.88%, and an F1-Score of 86.50%. These results show that the integration of TF-IDF feature extraction technique with K-NN algorithm produces superior performance in hate speech classification.

Improved indoor localization using k‐medoids and k‐nearest neighbour algorithms with context similarity coefficient‐based fingerprint similarity metric

AbstractFingerprint database clustering and localization using k‐medoids and k‐nearest neighbour (k‐NN) algorithms respectively typically use distance‐based fingerprint similarity metrics, with their performances dependent on the type of distance metric used. This paper proposes employing a pattern‐based metric, the context similarity coefficient (CSC), for both algorithms instead of traditional distance‐based metrics. The CSC accounts for fingerprint behaviour and the non‐linear relationships among fingerprints during the similarity measurement. The performance of both algorithms with the CSC as the similarity metric is evaluated on four publicly available fingerprint databases, using position root mean square error (RMSE) and silhouette score as performance metrics. These results are compared to those of the same algorithms using five distance‐based metrics: Euclidean, square Euclidean, Manhattan, cosine, and Chebyshev distances. The k‐medoids algorithm with CSC shows moderate clustering performance compared to the five distance‐based metrics considered. However, when combined with the k‐NN algorithm also using CSC, it achieves the highest localization accuracy, with at least a 29% improvement in position RMSE across all four databases. The results indicate that while k‐medoids with CSC may not create well‐separated clusters, combining it with the k‐NN algorithm with CSC as its similarity metric significantly enhances localization accuracy compared to distance‐based metrics.

Relationship between high-level color features and temperature mapping of magnesium alloy surface images based on the K-nearest neighbor algorithm

Relationship between high-level color features and temperature mapping of magnesium alloy surface images based on the K-nearest neighbor algorithm

Non-linear Optimization by Generalized Neighborhood Algorithm (GNA) and its Application for Magnetotellurics (MT) Layered-Earth Modeling

Population-based optimization algorithms are often used to resolve highly non-linear inverse problems by performing iterative and stochastic searches of the model space for solutions. These techniques rely on a combination of global and local searches associated with the exploration and exploitation capabilities, respectively. The iterative process usually converges to models very close to each other, leading to unrealistic solution’s uncertainties extracted from the final population. In this paper, we are more interested in the model space exploration leading to more representative uncertainties of the solutions. We divide the search agents into two groups, each randomly distributed in the whole model space and in the vicinity of a promising solution or best model. The additional tuning parameter in the relatively new Generalized Neighborhood Algorithm (GNA) is quite simple to choose, i.e., the extent of search in the neighborhood of the best model. The method was tested to invert magnetotelluric (MT) synthetic data of various representative cases with good results, i.e., recovery of the synthetic models with response that fits the synthetic data. Application of GNA to field data showed that the subsurface resistivity distribution agrees well with the geology of the study area.

Application of K-Nearest Neighbor Algorithm for Consumer Behaviour Identification and Product Personalisation Based on Big Data Analysis

The rapid digital transformation has fundamentally altered the retail industry, presenting challenges such as shifting consumer behavior and intensified market competition. This research explores the application of the K-Nearest Neighbor (KNN) algorithm for identifying consumer behavior and developing product personalization systems based on big data insights. Utilizing a dataset comprising 10,000 transaction records from January to December 2023 and 5,302 product types, we implemented the KNN algorithm to predict consumer purchases. The data was processed into 89,908 distinct transaction records. Our evaluation, using 5-fold cross-validation, demonstrated that the optimal performance of the KNN model was achieved with 𝑘=10, yielding a precision of 0.8319, recall of 0.8311, and an F1-score of 0.8312. These findings highlight the effectiveness of KNN in enhancing consumer satisfaction through precise product recommendations. This study provides strategic insights for modern retailers aiming to leverage AI and big data to remain competitive and meet evolving consumer expectations.

Application of machine learning in predicting health perception through military personnel's sense of empowerment.

The promotion of health and provision of care services for new recruits are issues of constant concern for military leaders and healthcare providers, as they are crucial to maintaining and operating military forces. The enhancement of military personnel's empowerment has been recognized as a core value in promoting health perception. However, the pathways between military personnel's sense of empowerment and health perception have not been thoroughly explored. The primary aim of this study is to examine the predictive power of different dimensions of empowerment (personal, interpersonal, and socio-political) on new recruits' health perception, and to further observe differences among subgroups, which will help us grasp the nuances of future health intervention measures. The research data were extracted from the "Military Career Development Study," analyzing personal empowerment data from Wave 1 (W1) and perceived health data from Wave 2 (W2) (N = 2,232). In terms of analytical methods, five ML classifiers, including Decision Tree, Random Forest, Support Vector Machine, AdaBoost, and k-Nearest Neighbors (KNN) algorithms, were used for prediction in both the full sample and subsamples (gender and socioeconomic status). Results show that among the five ML classifiers, the Decision Tree performed best overall, achieving a prediction accuracy of 95.4%. The results by gender show that the ML models perform best for both males and females with the Decision Tree and Random Forest methods. For the Decision Tree, the accuracy rates were 94.9% for males and 95.1% for females; the F1 scores were 92.9% for males and 93.2% for females. For the Random Forest, the accuracy rates were 94.9% for males and 95.4% for females; the F1 scores were 92.7% for males and 93.2% for females. Regarding SES, the Decision Tree and Random Forest methods performed best. In the SES Low group, both methods achieved a prediction accuracy of 95.6% and an F1 score of 93.7%; in the SES high group, they achieved a prediction accuracy of 95.4% and an F1 score of 93.3%. However, the contribution of different dimensions of empowerment features varied significantly among subgroups. These findings can provide important information on the differences in health perception among military personnel.

Applying Machine Learning to Elucidate Ultrafast Demagnetization Dynamics in Ni and Ni80Fe20

Understanding the correlation between fast and ultrafast demagnetization (UFD) processes is crucial for elucidating the microscopic mechanisms underlying UFD, which is pivotal for various applications in spintronics. Initial theoretical models attempt to establish this correlation but face challenges due to the complex interplay of physical phenomena. To address this, a variety of machine learning (ML) methods are employed, including supervised learning regression algorithms and symbolic regression (SR), to analyze limited experimental data and derive meaningful mathematical expressions between demagnetization time (τM) and the Gilbert damping factor (α). The results reveal that polynomial regression and K‐nearest neighbors algorithms perform best in predicting τM. Additionally, variable‐selection sure‐independence‐screening‐and‐sparsifying‐operator (VS‐SISSO) as a SR method suggests a direct correlation between τM and α for Ni and Ni80Fe20, indicating spin‐flip scattering predominantly influences the UFD mechanism. The developed models demonstrate promising predictive capabilities, validated against independent experimental data. Comparative analysis between different materials underscores the significant impact of material properties on UFD behavior. This study underscores the potential of ML in unraveling complex physical phenomena and offers valuable insights for future research in ultrafast magnetism.

Multimodal Operation Data Mining for Grid Operation Violation Risk Prediction

With the continuous expansion of the power grid, the issue of operational safety has attracted increasing attention. In power grid operation control, unauthorized operations are one of the primary causes of personal accidents. Therefore, preventing and monitoring unauthorized actions by power grid operators is of critical importance. First, multimodal violation data are integrated through information systems, such as the power grid management platform, to construct a historical case database. Next, word vectors for three types of operation-related factors are generated using natural language processing techniques, and key vectors are selected based on generalized correlation coefficients using mutual information, enabling effective dimensionality reduction. Independent component analysis is then employed for feature extraction and further dimensionality reduction, allowing for the effective characterization of operational scenarios. For each historical case, a risk score is derived from a violation risk prediction model constructed using the Random Forests (RF) algorithm. When a high-risk score is identified, the K-Nearest Neighbor (KNN) algorithm is applied to locate similar scenarios in the historical case database where violations may have occurred. Real-time violation risk assessment is performed for each operation, providing early warnings to operators, thereby reducing the likelihood of violations, and enhancing the safety of power grid operations.

Sentiment Analysis of Hate Speech against DPR-RI on Twitter Using Naive Bayes and KNN Algorithms

According to surveys, the rise in social media users has resulted in an increase of hate speech, and Twitter is one of the most popular platforms for this type of speech. The tweet feature on Twitter enables users to make repeated instances of hate speech, making Twitter data very intriguing to analyze. This study aims to investigate whether a tweet contains hate speech towards the Indonesian House of Representatives (DPR-RI). The research employed crawling techniques to gather data from Twitter using the Twitter API feature. The Naïve Bayes algorithm was applied, and the results were compared with the accuracy of the K-Nearest Neighbor. After preprocessing, the total data obtained was 1,494, with 956 test data and 538 training data. The study revealed that Twitter users' sentiment towards DPR-RI was 49.2% positive and 50.8% negative sentiment when tested using Naïve Bayes. Meanwhile, KNN showed 23.4% positive and 76.6% negative sentiment. The high negative sentiment in both classifiers suggests that Twitter users frequently express hate speech towards DPR-RI. Naïve Bayes algorithm showed the highest prediction accuracy at 98.32%, while the K-Nearest Neighbor algorithm had an accuracy of only 62.84%.

A Brownian Motion Restricted K-Nearest Neighbor Algorithm for Indoor Positioning

A Brownian Motion Restricted K-Nearest Neighbor Algorithm for Indoor Positioning

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.

Comparative Analysis of Fall Detection Using Artificial Neural Networks (ANN) and K-Nearest Neighbors (KNN) Algorithms

Fall detection is a critical area of research due to its implications for public health, particularly among older adults more vulnerable to fall-related injuries. This study explores the application of pervasive computing and machine learning algorithms in detecting falls using accelerometer and gyroscope sensors. Leveraging a dataset obtained from smartphone sensors, the study employs data processing techniques and classification algorithms, including K-Nearest Neighbors (KNN) and Artificial Neural Networks (ANN), to differentiate fall events from other activities. Evaluation metrics such as accuracy, precision, recall, and F1-score are utilized to assess the performance of the models. The results demonstrate the effectiveness of both the ANN and KNN models in accurately predicting fall detection with high precision and recall scores. The study highlights the potential of pervasive computing systems and machine learning methods to enhance fall detection capabilities, contributing to the development of proactive measures for ensuring the safety and well-being of individuals at risk of falls. Future research directions include exploring alternative algorithms and sensor modalities to improve fall detection systems further.

Machine learning‐driven microwave imaging for soil moisture estimation near leaky pipe

AbstractCharacterizing soil moisture around drip irrigation pipes is crucial for precise and optimized farming. Machine learning (ML) approaches are particularly suitable for this task as they can reduce uncertainties caused by soil conditions and the drip pipe positions, using features extracted from relevant datasets. This letter addresses local moisture detection in the vicinity of dripping pipes using a portable microwave imaging system. The employed ML approach is fed with two dimensional images generated using back projection as a radar‐based algorithm and the Born approximation as an inverse scattering method, based on spatio‐temporal (collected data at various positions over the soil surface and at different time points.) measurements at various frequencies. The study investigates the performance of K‐nearest neighbour (KNN) and convolutional neural networks (CNN) algorithms for moisture classification based on these imaging techniques. We also explore the potential of KNN and CNN for moisture estimation around the plant roots and in the presence of pebbles. In general, CNN outperforms KNN in moisture content detection from microwave data, especially after applying imaging algorithms. A combination of CNN as the ML approach and the back projection algorithm to provide training data, yielded accuracy more than other models for moisture content estimation. Also, the practical results demonstrate that our method can detect soil moisture with an estimation error of less than 10%.

LocustLens: leveraging environmental data fusion and machine learning for desert locust swarm prediction

The desert locust is one of the most destructive locusts recorded in human history, and it has caused significant food shortages, monetary losses, and environmental calamities. Prediction of locust attacks is complicated as it depends on various environmental and geographical factors. This research aims to develop a machine-learning model for predicting desert locust attacks in 42 countries that considers three predictors: soil moisture, maximum temperature, and precipitation. We developed the Global Locust Attack Database for 42 countries (GLAD42) by integrating TerraClimate’s environmental data with locust swarm attack data from the Food and Agriculture Organization (FAO). To improve the usability of spatial data, reverse geocoding which is the process of converting geographic coordinates (longitude and latitude) into human-readable location names (such as countries and regions) was employed. This step enhances the clarity and interpretability of the data by providing meaningful geographic context. This study’s initial dataset focused on instances where locust attacks were recorded (positive class). To ensure a comprehensive analysis, we also incorporated negative class instances, representing periods (specific years and months) in the same countries and regions where locust attacks did not occur. This research utilizes the benefits of lazy learners by employing the K-nearest neighbor algorithm (K-NN), which provides high accuracy and the benefit of no time-consuming retraining even if real-time updated data is periodically added to the system. This research also focuses on building an eco-friendly machine learning model by evaluating carbon emissions from ML models. The results obtained from LocustLens are compared with other machine learning models, including baseline–K-NN, decision trees (DT), Logistic regression (LR), AdaBoost Classifier, BaggingClassifier, and support vector classifier (SVC). LocustLens outperformed all competitors with an accuracy of 98%, while baseline-K-NN achieved 96%, SVC gave 91%, DT gave 97%, AdaBoost has accuracy of 91%, BaggingClassifier gave 94% and LR gave 83%, respectively. Carbon emissions from RAM and CPU electricity consumption are measured in kg gCO2. They are a minimum for AdaBoost Classifier equal to 0.02 and 0.07 for DT and a maximum of 9.03 for SVC. The carbon footprint of LocustLens is 4.87 kg gCO2.

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 < 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.

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 (>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 <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 <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.