Simple Algorithm Research Articles

Home Blood Pressure Variability Risk Prediction Score for Cardiovascular Disease Using Data From the J-HOP Study.

Home blood pressure (BP) is more closely associated with cardiovascular event risk than office BP, but cardiovascular risk prediction based on home BP variability is lacking. This study developed a simple cardiovascular event prediction score, including home BP variability data, from the J-HOP study (Japan Morning Surge-Home Blood Pressure). The J-HOP study extended follow-up from December 2017 to May 2018 generated the study data set (4231 patients). Cardiovascular events included fatal/nonfatal stroke (n=94), coronary heart disease (n=124), heart failure (n=42), and aortic dissection (n=8). Cox proportional hazards models were used to predict overall cardiovascular risk. Potential covariates included age, sex, body mass index, smoking, history of diabetes, statin use, history of cardiovascular disease, total cholesterol:high-density lipoprotein cholesterol ratio, office systolic BP (SBP), mean of morning-evening average (MEave), home SBP, and average real variability of MEave home SBP. A risk score and models were constructed, and model performance was assessed. Model performance was best when average real variability of MEave SBP was included (C statistic, 0.760). The risk score assigns points for age (5-year bands), sex, cardiovascular disease history, high-density lipoprotein cholesterol, mean MEave home SBP, and average real variability of MEave home SBP. Estimated 10-year cardiovascular risk ranged from ≤0.6% (score ≤0) to >32% (score ≥26). Calibration 2 statistics values for the model (2.66) and risk score (5.29) indicated excellent goodness of fit. This simple cardiovascular disease prediction algorithm, including day-by-day home BP variability, could be used as part of a home BP-centered approach to hypertension management in clinical practice.

Smooth Gowdy-symmetric generalised Taub-NUT solutions with polynomial initial data

Abstract We consider smooth Gowdy-symmetric generalised Taub-NUT solutions, a class of inhomogeneous cosmological models with spatial three-sphere topology. They are characterised by existence of a smooth past Cauchy horizon and, with the exception of certain singular cases, they also develop a regular future Cauchy horizon. Several examples of exact solutions were previously constructed, where the initial data (in form of the initial Ernst potentials) are polynomials of low degree. Here, we generalise to polynomial initial data of arbitrary degree. Utilising methods from soliton theory, we obtain a simple algorithm that allows us to construct the resulting Ernst potential with purely algebraic calculations. We also derive an explicit formula in terms of determinants, and we illustrate the method with two examples.

Simplified control algorithm for stable and efficient standalone PV systems: An assessment based on real climatic conditions

This research addresses the critical challenge of optimizing efficiency and performance in solar photovoltaic (PV) systems. It focuses on duty cycle optimization of DC/DC converters for maximum power point tracking (MPPT). The study introduces an innovative hybrid MPPT solution that integrates a novel temperature-based single-sensor approach with an integral backstepping controller. This method precisely achieves the PV array's maximum power point (MPP) under varying weather conditions while optimizing the converter's duty cycle to best align with the MPP voltage. Comprehensive simulations in MATLAB/Simulink reveal that the hybrid method surpasses conventional MPPT systems in key metrics, achieving faster convergence time (below 0.66 ms), reduced power ripple (<0.3 W), and enhanced tracking efficiency (exceeding 97.67 %). Notably, experimental data validates the practical efficacy of the proposed system under real-world conditions in the context of El Jadida, Morocco. This integrated approach advances the theoretical understanding of MPPT optimization and demonstrates tangible improvements in PV system performance, offering significant potential for enhancing solar energy utilization in variable climate regions.

Disaggregation and Nowcasting of Regional GDP Series with a Simple Smoothing Algorithm

We propose a simple smoothing method for the spatiotemporal disaggregation of economic time series. Contrary to the existing methods, our approach does not require exogenous regressors and can therefore be used for countries lacking long and reliable series of regional economic indicators. The proposed method can also be applied sequentially, implying that one needs to revise only the estimates for the last low-frequency period when new data are disaggregated. This is a convenient feature when historical estimates are of interest. We apply this method to disaggregate annual real GDP data for Polish regions into quarterly series and compare the results with the series obtained from a multivariate linear regression-based procedure, considering the differences between the estimates and the consequences for regional recession dating. We also examine the nowcasting performance of the smoothing algorithm and find that it is superior to the regression-based alternative for most of the studied sample lengths and horizons up to a year.

A Simple and Efficient Algorithm to Identify the Chirality of Polymer Knots Based on the Alexander Polynomial

A Simple and Efficient Algorithm to Identify the Chirality of Polymer Knots Based on the Alexander Polynomial

Monitoring anomalies on large-scale energy and water balance components by coupling remote sensing parameters and gridded weather data.

The SAFER (Simple Algorithm for Evapotranspiration Retrieving) algorithm was applied with MODIS images and gridded weather data from 2007 to 2021, to monitor the energy balance components and their anomalies, in the Atlantic Forest (AF) and Caatinga (CT) biomes inside the coastal agricultural growing zone, Northeast Brazil. Considering the long-term data, the Rn values between the biomes are not significantly different, however presenting distinct Rn partitions into latent (λE), sensible (H), and ground (G) heat fluxes between biomes. The Rn values annual averages are 9.40 ± 0.21 and 9.50 ± 0.23MJm-2 d-1, for AF and CT, respectively. However, for respectively AF and CT, they are respectively 5.10 ± 1.14MJm-2 d-1 and 4.00 ± 0.99MJm-2 d-1 for λE; 3.80 ± 1.12MJm-2 d-1 and 5.00 ± 1.00MJm-2 d-1 for H; 0.50 ± 0.12MJm-2 d-1 and 0.40 ± 0.10MJm-2 d-1 for G, yielding respective mean evaporative fraction (Ef = λE/(Rn - G) values of 0.60 ± 0.12 and 0.50 ± 0.15. Anomalies on λE, H, and Ef were detected through standardized index for these energy balance components by comparing the results for the years 2018 to 2021 with the long-term values from 2007 to each of these years, showing that the energy fluxes between surfaces and the lower atmosphere, and then the root-zone moisture conditions for both biomes, may strongly vary along seasons and years, with alternate positive and negative anomalies. These assessments are important for water policies as they can picture suitable periods and places for rainfed agriculture as well as the irrigation needs in irrigated agriculture, allowing rational agricultural environmental management while minimizing water competitions among other water users, under climate and land-use changes conditions.

A Machine Learning Approach to Concussion Risk Estimation Among Players Exhibiting Visible Signs in Professional Hockey.

The identification of concussion risk factors, such as visible signs and mechanisms of injury, improves concussion identification. Exploring individual risk factors, such as concussion history, may help to improve existing concussion risk models and algorithms. The primary aim of the current study was to use machine learning techniques to develop a comprehensive, prospectively coded concussion risk model in professional hockey among players exhibiting visible signs. The secondary aim was to examine whether including concussion history improves model performance. Data from the National Hockey League (NHL) spotter program, including coded visible signs and mechanisms of injury associated with possible concussive events, were extracted from the 2018-2019 to the 2021-2022 seasons. Each unique spotter event was matched with data extracted from the medical record to determine whether the event was associated with a subsequent physician diagnosed concussion. We compared the ability of three machine learning-based approaches to identify the likelihood of physician diagnosed concussion: conditional inference tree, conditional inference random forest, and logistic regression. A total of 1563 unique events with visible signs were identified by spotters (183 leading to a concussion diagnosis). A randomly selected training sample had 1250 events (146 concussions) and the remaining set-aside test sample had 313 events (37 concussions). The obtained models performed at a high level with large effects in the training [area under the receiver operating characteristic curve (AUC) = 0.79] and set-aside test data (AUC = 0.82). Concussion history was retained in the tree and logistic regression models, with each additional prior concussion associated with a 1.32 times increased odds of concussion diagnosis. We present simple tree and logistic algorithms for concussion screening and as diagnostic aids. Our results show that player concussion history can explain additional risk above and beyond that explained by visible signs and mechanisms of injury alone.

Cheminformatic Identification of Tyrosyl-DNA Phosphodiesterase 1 (Tdp1) Inhibitors: A Comparative Study of SMILES-Based Supervised Machine Learning Models

Background: Tyrosyl-DNA phosphodiesterase 1 (Tdp1) repairs damages in DNA induced by abortive topoisomerase 1 activity; however, maintenance of genetic integrity may sustain cellular division of neoplastic cells. It follows that Tdp1-targeting chemical inhibitors could synergize well with existing chemotherapy drugs to deny cancer growth; therefore, identification of Tdp1 inhibitors may advance precision medicine in oncology. Objective: Current computational research efforts focus primarily on molecular docking simulations, though datasets involving three-dimensional molecular structures are often hard to curate and computationally expensive to store and process. We propose the use of simplified molecular input line entry system (SMILES) chemical representations to train supervised machine learning (ML) models, aiming to predict potential Tdp1 inhibitors. Methods: An open-sourced consensus dataset containing the inhibitory activity of numerous chemicals against Tdp1 was obtained from Kaggle. Various ML algorithms were trained, ranging from simple algorithms to ensemble methods and deep neural networks. For algorithms requiring numerical data, SMILES were converted to chemical descriptors using RDKit, an open-sourced Python cheminformatics library. Results: Out of 13 optimized ML models with rigorously tuned hyperparameters, the random forest model gave the best results, yielding a receiver operating characteristics-area under curve of 0.7421, testing accuracy of 0.6815, sensitivity of 0.6444, specificity of 0.7156, precision of 0.6753, and F1 score of 0.6595. Conclusions: Ensemble methods, especially the bootstrap aggregation mechanism adopted by random forest, outperformed other ML algorithms in classifying Tdp1 inhibitors from non-inhibitors using SMILES. The discovery of Tdp1 inhibitors could unlock more treatment regimens for cancer patients, allowing for therapies tailored to the patient’s condition.

Ten Recommendations for Accelerating Hypertension and Diabetes Control to Reduce Stroke, Heart, and Renal Disease with the Aim to Save Lives in Cameroon Through Partnerships and Collaborations.

Hypertension and diabetes are currently the most common, treatable, and controllable cardiovascular and metabolic risk factors for stroke, heart, and renal diseases in Cameroon. Hypertension affects 30% of adults aged≥20years with 90% as uncontrolled cases, while type 2 diabetes affects 6% of the same population, with 70% remaining underdiagnosed. Despite publication of the first Roadmap on raised blood pressure by the World Heart Federation in 2015, the Pan African Society of Cardiology Roadmap in 2017, andthe technical package for cardiovascular disease management in primary health care (WHO-HEARTS) in 2020, very little progress has been made in improving the diagnosis, treatment, and control of cardiovascular risk factors and diseases in Cameroon. The Cameroon Cardiac Society and a dozen Cameroon non-communicable diseases societies, national organizations from the community and the civil society, along with researchers and members of academia and the health sector, came together under the patronage of representatives of the government to propose new strategies to improve hypertension and diabetes control and save lives in Cameroon. Two simple and practical algorithms for the management of hypertension and diabetes were developed. The ten recommendations tailored to be efficiently implemented in our country were summarized under the acronym 'A SMART VIEW' (Awareness, Screening, Manufacture, Activity, Research, Task-shifting, HIV/AIDS, Insurance, Education, and WHO-HEARTS). It is our hope that all stakeholders will further collaborate to remove barriers and enhance facilitators to deploy the proposed actions and reduce the burden of uncontrolled hypertension and untreated diabetes in Cameroon.

Seismic performance of friction damped posttensioned steel frame equipped with SMA strands

The post-tensioned friction dissipating (PTFD) connection for steel frames has drawn significant attention from researchers due to its excellent seismic performance. A simplified numerical algorithm suitable for modeling the SMA strands is proposed. The simplified numerical model of the SMA-PTFD is established. Parametric analysis is performed based on hysteresis analysis and transient dynamic analysis to reveal the influence of SMA strands on the seismic performance of SMA-PTFD frames. The changing rule of seismic response of SMA-PTFD frames, along with the fmax for SMA strands and the Fmax for the friction device, is systematically investigated. The value of the objective function can be reduced by about 50 % when the fmax is increased from 1 kN to 13 kN. The fundamental frequency is 1.25 Hz for three analyzed conditions. The value of the second frequency is significantly affected by Fmax. The values of the second frequency are 1.5 Hz, 1.58 Hz, and 1.42 Hz. The characteristics of seismic response, including displacement and cable force, are deeply studied. The seismic response is also investigated in the frequency domain. The results presented in this work reveal the collaborative energy dissipation mechanism of the friction device and SMA strands.

Frequentist Prediction Sets for Species Abundance using Indirect Information

Abstract Citizen science databases that consist of volunteer-led sampling efforts of species communities are relied on as essential sources of data in ecology. Summarising such data across counties with frequentist-valid prediction sets for each county provides an interpretable comparison across counties of varying size or composition. As citizen science data often feature unequal sampling efforts across a spatial domain, prediction sets constructed with indirect methods that share information across counties may be used to improve precision. In this article, we present a nonparametric framework to obtain precise prediction sets for a multinomial random sample based on indirect information that maintain frequentist coverage guarantees for each county. We detail a simple algorithm to obtain prediction sets for each county using indirect information where the computation time does not depend on the sample size and scales nicely with the number of species considered. The indirect information may be estimated by a proposed empirical Bayes procedure based on information from auxiliary data. Our approach makes inference for under-sampled counties more precise, while maintaining area-specific frequentist validity for each county. Our method is used to provide a useful description of avian species abundance in North Carolina, USA based on citizen science data from the eBird database.

Parameterized approximation algorithms for weighted vertex cover

A vertex cover of a graph is a set of vertices of the graph such that every edge has at least one endpoint in it. In this work, we study Weighted Vertex Cover with solution size as a parameter. Formally, in the (k,W)-Vertex Cover problem, given a graph G, an integer k, a positive rational W, and a weight function w:V(G)→Q+, the question is whether G has a vertex cover of size at most k of weight at most W, with k being the parameter. An (a,b)-bi-criteria approximation algorithm for (k,W)-Vertex Cover either produces a vertex cover S such that |S|≤ak and w(S)≤bW, or decides that there is no vertex cover of size at most k of weight at most W. We obtain the following results.•A simple (2,2)-bi-criteria approximation algorithm for (k,W)-Vertex Cover in polynomial time by modifying the standard LP-rounding algorithm.•A simple exact parameterized algorithm for (k,W)-Vertex Cover running in O⁎(1.4656k) time1.•A (1+ϵ,2)-approximation algorithm for (k,W)-Vertex Cover running in O⁎(1.4656(1−ϵ)k) time.•A (1.5,1.5)-approximation algorithm for (k,W)-Vertex Cover running in O⁎(1.414k) time.•A (2−δ,2−δ)-approximation algorithm for (k,W)-Vertex Cover running in O⁎(∑i=δk(1−2δ)1+2δδk(1−2δ)2δ(δk+iδk−2iδ1−2δ)) time for any δ<0.5. For example, for (1.75,1.75) and (1.9,1.9)-approximation algorithms, we get running times of O⁎(1.272k) and O⁎(1.151k) respectively.Our algorithms (expectedly) do not improve upon the running times of the existing algorithms for the unweighted version of Vertex Cover. When compared to algorithms for the weighted version, our algorithms are the first ones to the best of our knowledge which work with arbitrary weights, and they perform well when the solution size is much smaller than the total weight of the desired solution.

Exploring meta-heuristics for partitional clustering: methods, metrics, datasets, and challenges

Partitional clustering is a type of clustering that can organize the data into non-overlapping groups or clusters. This technique has diverse applications across the different various domains like image processing, pattern recognition, data mining, rule-based systems, customer segmentation, image segmentation, and anomaly detection, etc. Hence, this survey aims to identify the key concepts and approaches in partitional clustering. Further, it also highlights its widespread applicability including major advantages and challenges. Partitional clustering faces challenges like selecting the optimal number of clusters, local optima, sensitivity to initial centroids, etc. Therefore, this survey describes the clustering problems as partitional clustering, dynamic clustering, automatic clustering, and fuzzy clustering. The objective of this survey is to identify the meta-heuristic algorithms for the aforementioned clustering. Further, the meta-heuristic algorithms are also categorised into simple meta-heuristic algorithms, improved meta-heuristic algorithms, and hybrid meta-heuristic algorithms. Hence, this work also focuses on the adoption of new meta-heuristic algorithms, improving existing methods and novel techniques that enhance clustering performance and robustness, making partitional clustering a critical tool for data analysis and machine learning. This survey also highlights the different objective functions and benchmark datasets adopted for measuring the effectiveness of clustering algorithms. Before the literature survey, several research questions are formulated to ensure the effectiveness and efficiency of the survey such as what are the various meta-heuristic techniques available for clustering problems? How to handle automatic data clustering? What are the main reasons for hybridizing clustering algorithms? The survey identifies shortcomings associated with existing algorithms and clustering problems and highlights the active area of research in the clustering field to overcome these limitations and improve performance.

Order-sensitive competitive revenue maximization for viral marketing in social networks

The Competitive Influence Maximization (CIM) problem is a critical issue in viral marketing, focusing on selecting a set of influential individuals, known as seed users, for competitors to maximize their revenue. These seed users have significant sway in social networks and serve as valuable marketing resources provided by the platform. They are often displayed in a certain order launched by the platform and the potential information hidden in the order can profoundly affect the final marketing outcomes. However, current CIM research predominantly emphasizes designing effective algorithms for seed selection while ignoring the impact of the seed order launched by the platform. Therefore, this paper focuses on identifying the optimal seed order to maximize platform revenue in a competitive market environment. Specifically, we introduce a new problem called Order-Sensitive Competitive Revenue Maximization (OSCRM) to investigate the CIM problem from a new practical perspective. We prove the problem to be NP-hard and present a simple greedy algorithm with a 1/3-approximate ratio. To address it more efficiently, we further propose an enhanced greedy algorithm called GMST. This algorithm leverages the maximum spanning tree (MST) and achieves a 1/2-approximate ratio. Extensive experiments on four real-world datasets demonstrate the effectiveness of our proposed GMST algorithm.

Simple olfactory navigation in air and water

Two simple algorithms based on combining odor concentration differences across time and space along with information on the flow direction are tested for their ability to locate an odor source in four different odor landscapes. Image data taken from air plumes in three different regimes and a water plume are used as test environments for a bilateral (“stereo sampling”) algorithm using concentration differences across two sensors and a “casting” algorithm that uses successive samples to decide orientation. Agents are started at random locations and orientations in the landscape and allowed to move until they reach the source of the odor (success) or leave the imaged area (failure). Parameters for the algorithm are chosen to optimize success and to minimize path length to the source. Success rates over 90% are consistently obtained with path lengths that can be as low as twice the starting distance from the source in air and four times the distance in the highly turbulent water plumes. We find that parameters that optimize success often lead to more exploratory pathways to the source. Information about the direction from which the odor is coming is necessary for successful navigation in the water plume and reduces the path length in the three tested air plumes.

Clinical Phenotyping for Prognosis and Immunotherapy Guidance in Bacterial Sepsis and COVID-19.

It is suggested that sepsis may be classified into four clinical phenotypes, using an algorithm employing 29 admission parameters. We applied a simplified phenotyping algorithm among patients with bacterial sepsis and severe COVID-19 and assessed characteristics and outcomes of the derived phenotypes. Retrospective analysis of data from prospective clinical studies. Greek ICUs and Internal Medicine departments. We analyzed 1498 patients, 620 with bacterial sepsis and 878 with severe COVID-19. We implemented a six-parameter algorithm (creatinine, lactate, aspartate transaminase, bilirubin, C-reactive protein, and international normalized ratio) to classify patients with bacterial sepsis intro previously defined phenotypes. Patients with severe COVID-19, included in two open-label immunotherapy trials were subsequently classified. Heterogeneity of treatment effect of anakinra was assessed. The primary outcome was 28-day mortality. The algorithm validated the presence of the four phenotypes across the cohort of bacterial sepsis and the individual studies included in this cohort. Phenotype α represented younger patients with low risk of death, β was associated with high comorbidity burden, and δ with the highest mortality. Phenotype assignment was independently associated with outcome, even after adjustment for Charlson Comorbidity Index. Phenotype distribution and outcomes in severe COVID-19 followed a similar pattern. A simplified algorithm successfully identified previously derived phenotypes of bacterial sepsis, which were predictive of outcome. This classification may apply to patients with severe COVID-19 with prognostic implications.

Immersive Photorealistic Three-Dimensional Neurosurgical Anatomy of the Cerebral Arteries: A Photogrammetry-Based Anatomic Study.

Neurosurgeons need a profound knowledge of the surgical anatomy of the cerebral arteries to safely treat patients. This is a challenge because of numerous branches, segments, and tortuosity of the main blood vessels that supply the brain. The objective of this study was to create high-quality three-dimensional (3D) anatomic photorealistic models based on dissections of the brain arterial anatomy and to incorporate this data into a virtual reality (VR) environment. Two formaldehyde-fixed heads were used. The vessels were injected with radiopaque material and colored silicone and latex. Before the dissections, the specimens were computed tomography scanned. Stratigraphical anatomic dissection of the neck and brain was performed to present the relevant vascular anatomy. A simplified surface scanning method using a mobile phone-based photogrammetry application was used, and the data were incorporated into a VR 3D modeling software for post-processing and presentation. Fifteen detailed layered photorealistic and two computed tomography angiography-based 3D models were generated. The models allow manipulation in VR environment with sufficient photographic detail to present the structures of interest. Topographical relevant anatomic structures and landmarks were annotated and uploaded for web-viewing and in VR. Despite that the VR application is a dedicated 3D modeling platform, it provided all necessary tools to be suitable for self-VR study and multiplayer scenarios with several participants in one immersive environment. Cerebral vascular anatomy presented with photogrammetry surface scanning method allows sufficient detail to present individual vessel's course and even small perforating arteries in photorealistic 3D models. These features, including VR visualization, provide new teaching prospects. The whole study was done with simplified algorithms and free or open-source software platforms allowing creation of 3D databases especially useful in cases with limited body donor-based dissection training availability.

Optimal milling cutter helix selection for period doubling chatter suppression

In high speed milling, interrupted cutting conditions can lead to period doubling chatter vibrations. While many studies have already confirmed that the use of helical tools can effectively shrink or remove these regions of unstable cutting, none of them has provided clear guidance to select the minimum helix that completely cancels the period doubling lobes. This study addresses this gap by introducing a novel analytical formula for a critical tool helix pitch: if the helix pitch is below the critical flip depth of cut of the straight helix cutter multiplied by π, the flip lobes will totally vanish. This rule is not only valuable for chatter-free process planning purposes, but it also establishes exact limit below which the fast and simple zeroth order stability algorithm can provide exact stability boundaries for helical tools. The effectiveness of the formula is numerically corroborated over three different milling scenarios: thin wall milling, slender tool and machine tool structure chatter cases. Finally, the findings are validated through experimental cutting tests.

A Cohort Tree-based Representation and a Multimorbidity Progression Across Pregnancies in Scotland

Pregnancy-related research using routinely collected data is increasing. Electronic Health Records (EHR) are a robust resource because they can provide information on a large population of pregnant women covering prolonged periods at a reasonable cost. Moreover, information is collected prospectively and is thus free from recall bias. However, these data sources also present challenges. Information is gathered for clinical purposes and often recorded in different datasets (prescriptions, hospital admission, demography, birth records, etc.). Therefore, a significant data management effort must be made to convert all the information into structured and meaningful datasets in which identifying the timing of conception, outcomes of interest, multiple pregnancies, and interpregnancy periods can easily be done. In this study, we linked Scottish Maternity Records between 2007 and 2021 (1,575,153 pregnancies, 493,629 women) to demographics data, datasets with International Classification of Diseases (ICD) diagnostic codes for all inpatient stays and day cases in hospitals, and Prescribing Information System (PIS) for data on all medications from primary care. After combining these datasets using R codes, we developed a simple tree-based algorithm that visually represents each woman at each pregnancy and the related health conditions. Presenting data in this way helps identify relevant clinical questions and the temporal relation of different pregnancies. As an example, we identified the progression of multimorbidity through pregnancies and characterised how multimorbidity changes from one pregnancy to another, considering the woman's health conditions and social class.

What’s in a name field?

The National Center for Health Statistics (NCHS) has a data linkage program that combines national survey data with key sources of health outcomes and health care utilization. The overall accuracy and quality of a data linkage depends on the quality of the data fields. This applies in a variety of data linkage methods, including clear text and privacy preserving record linkage. Data pre-processing and cleaning are essential to address data quality issues in most linkage tasks. Automating data cleaning prevents time-consuming manual reviews particularly when linkages involve a large number of records. For some data fields, these activities are relatively straightforward. For example, dates typically have a limited number of plausible values that make checking and cleaning relatively easy and straightforward. Unique identifiers (e.g., social security number) often conform to some set format or have restrictions on the values that would be expected. Other data fields such as first name and last name present greater challenges with respect to automating the cleaning process. For some data sources, first name and last name fields may contain non-name text that needs to be identified and removed. In this project, we examined the use of an artificial intelligence (AI) based large language model (LLM) and a simple rule-based algorithm to identify non-name text in name fields that should be removed prior to linkage. We also investigated the impact of automated name clean-up algorithms on the quality of an example linkage.