Multivariate Cluster Research Articles

Multivariate Functional Clustering with Variable Selection and Application to Sensor Data from Engineering Systems

Multisensor data that track system operating behaviors are widely available nowadays from various engineering systems. Measurements from each sensor over time form a curve and can be viewed as functional data. Clustering of these multivariate functional curves is important for studying the operating patterns of systems. One complication in such applications is the possible presence of sensors whose data do not contain relevant information. Hence, it is desirable for the clustering method to equip with an automatic sensor selection procedure. Motivated by a real engineering application, we propose a functional data clustering method that simultaneously removes noninformative sensors and groups functional curves into clusters using informative sensors. Functional principal component analysis is used to transform multivariate functional data into a coefficient matrix for data reduction. We then model the transformed data by a Gaussian mixture distribution to perform model-based clustering with variable selection. Three types of penalties, the individual, variable, and group penalties, are considered to achieve automatic variable selection. Extensive simulations are conducted to assess the clustering and variable selection performance of the proposed methods. The application of the proposed methods to an engineering system with multiple sensors shows the promise of the methods and reveals interesting patterns in the sensor data. History: Kwok Tsui served as the senior editor for this article. Funding: The research by J. Min and Y. Hong was partially supported by the National Science Foundation [Grant CMMI-1904165] to Virginia Tech. The work by Y. Hong was partially supported by the Virginia Tech College of Science Research Equipment Fund. Data Ethics & Reproducibility Note: The original dataset is proprietary and cannot be shared. The full code to replicate the results in this paper, based on summary statistics of the original data, is available at https://github.com/jiem3/MultiFuncClustering . The code applied to a simplified version is available at https://codeocean.com/capsule/4041000/tree/v1 , which covers the data analysis and part of the simulation scenarios with a single dataset under each scenario using a fixed set of hyperparameters, for reducing computation time, and at https://doi.org/10.1287/ijds.2022.0034 .

Multivariate Hypocenter Clustering and Source Mechanism of 2017 Mw 6.2 and 2019 Mw 6.5 in the South Seram Subduction System

Multivariate Hypocenter Clustering and Source Mechanism of 2017 Mw 6.2 and 2019 Mw 6.5 in the South Seram Subduction System

A New 4-Thiazolidinone Derivative (Les-6490) as a Gut Microbiota Modulator: Antimicrobial and Prebiotic Perspectives.

A novel 4-thiazolidinone derivative Les-6490 (pyrazol-4-thiazolidinone hybrid) was designed, synthesized, and characterized by spectral data. The compound was screened for its antimicrobial activity against some pathogenic bacteria and fungi and showed activity against Staphylococcus and Saccharomyces cerevisiae (the Minimum Inhibitory Concentration (MIC) 820 μM). The compound was studied in the rat adjuvant arthritis model (Freund's Adjuvant) in vivo. Parietal and fecal microbial composition using 16S rRNA metagenome sequences was checked. We employed a range of analytical techniques, including Taxonomic Profiling (Taxa Analysis), Diversity Metrics (Alpha and Beta Diversity Analysis), Multivariate Statistical Methods (Principal Coordinates Analysis, Principal Component Analysis, Non-Metric Multidimensional Scaling), Clustering Analysis (Unweighted Pair-group Method with Arithmetic Mean), and Comparative Statistical Approaches (Community Differences Analysis, Between Group Variation Analysis, Metastat Analysis). The compound significantly impacted an increasing level of anti-inflammatory microorganisms (Blautia, Faecalibacterium prausnitzii, Succivibrionaceae, and Coriobacteriales) relative recovery of fecal microbiota composition. Anti-Treponemal activity in vivo was also noted. The tested compound Les-6490 has potential prebiotic activity with an indirect anti-inflammatory effect.

Combining user-centered design and behavioral theory to enhance health technologies: A personas-based approach for a primary-care based multifactorial falls risk assessment tool

IntroductionMultifactorial falls risk assessment tools (FRATs) can be an effective falls prevention method for older adults, but are often underutilized by health care professionals (HCPs). This study aims to enhance the use and implementation of multifactorial FRATs by combining behavioral theory with the user-centered design (UCD) method of personas construction. Specifically, the study aimed to (1) construct personas that are based on external (i.e., needs, preferences) and intrinsic user characteristics (i.e., behavioral determinants); and (2) use these insights to inform requirements for optimizing an existing Dutch multifactorial FRAT (i.e., the ‘Valanalyse’). MethodsSurvey data from HCPs (n = 31) was used to construct personas of the ‘Valanalyse.’ To examine differences between clusters on 68 clustering variables, a multivariate cluster analysis technique with non-parametric analyses and computational methods was used. The aggregated external and intrinsic user characteristics of personas were used to inform key design and implementation requirements for the ‘Valanalyse,’ respectively, whereby intrinsic user characteristics were matched with appropriate behavior change techniques to guide implementation. ResultsSignificant differences between clusters were observed in 20 clustering variables (e.g., behavioral beliefs, situations for use). These variables were used to construct six personas representing users of each cluster. Together, the six personas helped operationalize four key design requirements (e.g., guide treatment-related decision making) and 14 implementation strategies (e.g., planning coping responses) for optimizing the ‘Valanalyse’ in Dutch geriatric, primary care settings. ConclusionThe findings suggest that theory- and evidence-based personas that encompass both external and intrinsic user characteristics are a useful method for understanding how the use and implementation of multifactorial FRATs can be optimized with and for HCPs, providing important implications for developers and eHealth interventions with regards to encouraging technology adoption.

Clustering policy for urban competitiveness: One‐size‐fits‐all? Evidence from Tehran

Urban competitiveness is commonly attributed to necessitating particular types of socio‐spatial frameworks such as clustering on the basis of models of Marshall–Arrow–Romer (MAR), Porter, or Jacobs, since proximity is known as a key perquisite for knowledge spillover, innovation, and hence urban competitiveness. Nevertheless, it is unjustifiable to unconditionally endorse the ‘clustering’ policy. Consequently, this research aims to examine the spatiality and geography of competition and innovation contingent upon varying spatial prerequisites and contextual circumstances. In this regard, two questions have been raised: under what circumstances urban competitiveness depends on spatial agglomeration, and whether this agglomeration follows a clustering development pattern. Through the implementation of a causal research design utilizing both in‐depth interviews and social survey methodology, this study has determined the innovative characteristics and techniques for knowledge acquisition, as well as spatial behaviors and preferences of competitive industries located within Tehran. The spatially constrained multivariate clustering method was employed to group competitive industries according to their distinct substantive dissimilarities, socio‐spatial behaviors, and characteristics. Then, on the basis of the structural equation modeling, the most appropriate spatial development frameworks of competitiveness were extracted with regard to the specific conditions of Tehran. Findings show that innovation, and hence competitiveness, are not always the result of clustering; clusters, as a spatial policy‐making tool, have been found to be highly conducive to collaborative and intensive knowledge production, as they provide access to spillover knowledge, thereby increasing competitiveness. Despite complex economic dependencies and collaborations, some competitive industries have greater mobility and are footloose due to their Schumpeterian linear knowledge source and virtual nature. What matters for this elusive, light, fluid category free from the shackles of place is institutional and organizational proximity, which proves its conditions are up to the government. As the main finding of the research, the geography and spatiality of innovation, and therefore the competitiveness, depend on two factors, including: (a) the relationships and interactions, that is, types of activity units and (b) the source and method of acquiring knowledge required for innovation and competitive advantage. In some activities, on the basis of their knowledge intensity, interaction type, and knowledge source, competitiveness is not related to clusters; in others, it depends on a specific location; and some are independent of location.

Pollen morphology of Rosales from Brazilian forest fragments of Cerrado

ABSTRACT Rosales, a well-supported order of angiosperms encompassing heterogeneous plants, holds significant representation in Brazilian territory, particularly Cerrado regions. These areas are susceptible to human impact. In this context, pollen data is vital in supporting taxonomic and ecological studies for species preservation. We analyzed pollen grains from 15 native Rosales species found in Brazilian Cerrado forest fragments belonging to the Cannabaceae, Moraceae, Rhamnaceae, and Rosaceae families using light and scanning electron microscopy. The pollen grains underwent acetolysis, qualitative description, and measurements, with statistical analysis, including multivariate methods, applied to quantitative data. Qualitative findings were organized for pollen description and multivariate cluster analysis. Our observations revealed pollen grains in monads, isopolar, small to medium, with subcircular, circular, or subtriangular amb, and suboblate, oblate-spheroidal, or prolate-spheroidal. Apertures include 2–3-porate, 3-colpate, or 3-colporate, with long or short ectoapertures, lalongate or circular endoapertures. The exine is thin, microreticulate, psilate-perforate, microgranulate, nanoechinate, or striate ornamentation, with the sexine thicker than the nexine. The key characteristics distinguishing families are number, type of apertures, and exine ornamentation. Quantitative data (length and width of ectoapertures, equatorial diameter in polar view, and polar diameter in equatorial view) contribute to the understanding of the palynology of Rosales from forest fragments, as these characteristics allow us to identify species or groups of species. Our findings confirm Rosales as eurypalinous, while the genera analyzed demonstrate stenopalynous traits. The qualitative and quantitative characteristics of pollen identified here expand the morphological knowledge of the species and can be used to understand the relationship among them.

Morphological Characterisation of Three Populations of Heterobranchus longifilis from Nigeria.

This study attempted to discriminate the population of Heterobranchus longifilis in Nigeria using their morphological characteristics. Therefore, 60 sexually mature wild samples of H. longifilis (1:1 for the male and female ratio) of relatively similar size (40 cm) were collected from three eco-regions namely, Guinea Savanna (Benue River, Makurdi), Rainforest Savanna (Niger River, Onitsha) and Sahel Savanna (Rima River, Sokoto). They were transported to the hatchery unit of the Fisheries and Aquaculture Department, Joseph Sarwan Tarka University Makurdi where the morphometric data was collected. The data for 39 traditional morphometric measurements and 5 meristic counts obtained from each fish were subjected to univariate and multivariate analysis. While significant differences were observed in some parameters following univariate analysis; it was revealed that the morphometric parameters and meristic counts could not separate the fish from the different ecoregions into distinct multivariate spaces or clusters following Principal Component Analysis. Hence, this suggests that morphological parameters cannot be used to discriminate H. longifilis from the different ecoregions. Studies using molecular markers are needed to further characterise the distinctiveness of the different populations.

Unsupervised Anomaly Detection and Diagnosis in Power Electronic Networks: Informative Leverage and Multivariate Functional Clustering Approaches

Unsupervised Anomaly Detection and Diagnosis in Power Electronic Networks: Informative Leverage and Multivariate Functional Clustering Approaches

Improving demand forecasting for customers with missing downstream data in intermittent demand supply chains with supervised multivariate clustering

AbstractIn a collaborative supply chain arrangement like vendor‐managed inventory, information on product demand at the point of sale is expected to be shared among members of the supply chain. However, in practice, obtaining such information can be costly, and some members may be unwilling or unable to provide the necessary access to the data. As such, large collaborative supply chains with multiple members may operate under a mixed‐information scenario where point‐of‐sale demand information is not known for all customers. Other sources of demand information exist and are becoming more available along supply chains using Industry 4.0 technologies and can serve as a substitute, but the data may be noisy, distorted, and partially missing. Under mixed information, leveraging existing customers' point‐of‐sale demand to improve the intermittent demand forecast of customers with missing information has yet to be explored. We propose a supervised demand forecasting method that uses multivariate time series clustering to map multiple sources of demand data. Members with missing downstream demand data have their resulting demand forecast improved by averaging over customers with similar delivery patterns for their final demand forecast. Our results show up to a 10% accuracy improvement over traditional intermittent demand forecasting methods with missing information.

Exploring elucidation of red dye mixtures on woolen historical textiles via non-destructive spectroscopic analysis and multivariate cluster analysis

One of the foremost challenges facing analysis of historical textiles is that the gold standard technique—high performance liquid chromatography (HPLC)—is inherently destructive. This is especially problematic considering many historical textiles are exceptionally fragile, be it from age, poor care over time, etc. One proposed solution to this is the implementation of non-destructive, namely spectroscopic, techniques, such as diffuse reflectance (Fiber Optic Reflectance Spectroscopy, FORS). In this work, 204 well-provenanced red Norwich textiles were measured with FORS and analyzed to attempt to determine chromophore combinations used to dye the original textiles. To these ends, cluster analysis algorithms and spectroscopic domain knowledge were coupled with selective HPLC validation to assess overall ability of FORS to discern changes in chromophore combinations. It was found that the near infrared (NIR) region of the spectrum contained little meaningful information in multivariate space, while the VIS region, particularly 380–469 nm, showed a narrow visible region that was primarily responsible for clustering behavior that correlates with HPLC-validated samples. This indicates that FORS shows promise for discerning chromophores in textile swatches. Additionally, X-ray fluorescence (XRF) analysis was used to confirm that the observed FORS spectral inflection point shift in the 600 nm region did not correlate with the presence or type of mordant used when dying these textiles. From this work, three main conclusions can be drawn: (1) FORS adequately identifies visual infon, which shows reasonable correlation to HPLC-validated dye recipes, warranting further investigation, and indicating utility for cois or use for those with visual impairments; (2) XRF analysis confirms that the ~ 600 nm inflection point shift and mordant are not correlated when measuring dyed textiles, unless mordant is present below analytical detection limits or not present at all; (3) many documented structural-to-spectral relationships established in the conservation literature are too weak in dyed textiles for statistical analysis and, by extension, expert spectral identification.

Characterization and evaluation of the morphological attributes of Ethiopian mustard (Brassica carinata A. Braun) landraces

Ethiopian mustard (Brassica carinata A. Braun) is one of the Brassica leafy vegetables and oilseed crops, which can withstand adverse environmental conditions. This study was conducted to characterize and evaluate the leaf attributes of 313 Ethiopian mustard accessions grown in the greenhouse and field in 2018/19 in Beijing, China. Data on 18 different leaf morphological attributes were collected based on the IBPGR for Brassica and Raphanus descriptor format and Fiji Image J. The collected data were subjected to descriptive statistics using JMP version 14 software. Results indicate that the majority of the accessions had serrated leaf margin, intermediate juvenile development, rounded apex leaf shape, absence of leaf pubescence, number of lobes > 5 and had intermediate number of leaves per plant with frequencies of 101, 213, 223, 244, 183 and 289, respectively. The accessions had also white midrib color, light green leaf color, purple petiole color, purple stem color and purple apex leaf color pigments with frequencies of 168, 165, 104, 113 and 122, respectively. Significant differences were observed among the accessions for leaf size attributes (p < 0.001) indicating their potential as leafy vegetables. Furthermore, there were significant accession × environment effects for the laminal length, total leaf length, leaf area, leaf weight and petiole length. Notably, 71% of the accessions had an average of 81 days flowering time. The multivariate cluster and principal component analyses divided the 313 accessions into eight groups with distinctive information; consisting of 81, 37, 79, 38, 14, 11, 6 and 47 accessions. Thus, this study provides important information about Ethiopian mustard germplasms that is vital for further advancement and genetic improvement of the crop.

Spatial differentiation and geographical similarity of traditional villages--Take the Yellow River Basin and the Yangtze River Basin as examples.

The preservation and advancement of Traditional Villages are intricately linked to the perpetuation of cultural heritage. However, existing research on the spatial disparities among Traditional Villages has yet to consider the impact of cultural factors. Moreover, the geographical similarities shared by Traditional Villages have not been thoroughly examined. Therefore, this study takes the Yellow River Basin and the Yangtze River Basin, both pivotal in the genesis of Chinese culture, as case studies. We employ an Optimal Parameter-based GeoDetector alongside the Spatially Constrained Multivariate Clustering method to delve into the factors influencing the spatial differentiation and geographical similarities of Traditional Villages within these two significant river basins. Subsequently, we offer recommendations for fostering the sustainable preservation and development of Traditional Villages in these regions. The results indicate that the Rural Residents Per Capita Disposable Income has the greatest impact on the spatial differentiation of Traditional Villages in the Yellow River Basin, while the Density of National Intangible Cultural Heritage Inheritors has the most significant influence in the Yangtze River Basin. The interaction effects of the driving factors are more powerful, with a q-value of 0.9544 for the interplay between the Density of National Cultural Protection Units and the Tourism Income in the Yellow River Basin and a value of 0.9099 for the interaction between the Density of National Intangible Cultural Heritage Inheritors and the Transportation in the Yangtze River Basin. Regarding geographical similarity, the Traditional Villages in the Yellow River Basin are divided into three major clusters, while those in the Yangtze River Basin are divided into two.

Resolving taphonomic and preparation biases in silicified faunas through paired acid residues and X-ray microscopy.

Paired petrography and acid maceration has shown that preferential silicification of shelly faunas can bias recovery based on taxon and body size. Here, silicified fossils from the Upper Ordovician Edinburg Formation, Strasburg Junction, Virginia, USA, were analyzed using X-ray tomographic microscopy (μCT) in conjunction with recovered residues from acid maceration of the same materials to further examine sources of potential bias. Results reveal that very small (<~1 mm) fossils are poorly resolved in μCT when scanning at lower resolutions (~30 µm), underestimating abundance of taxa including ostracods and bryozoans. Acid maceration, meanwhile, fails to recover poorly silicified fossils prone to disarticulation and/or fragmentation during digestion. Tests for patterns of breakage, however, indicate no significant size or taxonomic bias during extraction. Comparisons of individual fossils from 3-D fossil renders and maceration residues reveal patterns of fragmentation that are taxon-specific and allow the differentiation of biostratinomic and preparational breakage. Multivariate ordinations and cluster analyses of μCT and residue data in general produce concordant results but indicate that the variation in taxonomic composition of our samples is compromised by the resolvability of small size classes in μCT imaging, limiting the utility of this method for addressing paleoecological questions in these specific samples. We suggest that comparability of results will depend strongly on the sample size, taphonomic history, textural, and compositional characteristics of the samples in question, as well as μCT scan parameters. Additionally, applying these methods to different deposits will test the general applicability of the conclusions drawn on the relative strengths and weaknesses of the methods.

Upscaling Soil Organic Carbon Measurements at the Continental Scale Using Multivariate Clustering Analysis and Machine Learning

AbstractEstimates of soil organic carbon (SOC) stocks are essential for many environmental applications. However, significant inconsistencies exist in SOC stock estimates for the U.S. across current SOC maps. We propose a framework that combines unsupervised multivariate geographic clustering (MGC) and supervised Random Forests regression, improving SOC maps by capturing heterogeneous relationships with SOC drivers. We first used MGC to divide the U.S. into 20 SOC regions based on the similarity of covariates (soil biogeochemical, bioclimatic, biological, and physiographic variables). Subsequently, separate Random Forests models were trained for each SOC region, utilizing environmental covariates and SOC observations. Our estimated SOC stocks for the U.S. (52.6 ± 3.2 Pg for 0–30 cm and 108.3 ± 8.2 Pg for 0–100 cm depth) were within the range estimated by existing products like Harmonized World Soil Database, HWSD (46.7 Pg for 0–30 cm and 90.7 Pg for 0–100 cm depth) and SoilGrids 2.0 (45.7 Pg for 0–30 cm and 133.0 Pg for 0–100 cm depth). However, independent validation with soil profile data from the National Ecological Observatory Network showed that our approach (R2 = 0.51) outperformed the estimates obtained from Harmonized World Soil Database (R2 = 0.23) and SoilGrids 2.0 (R2 = 0.39) for the topsoil (0–30 cm). Uncertainty analysis (e.g., low representativeness and high coefficients of variation) identified regions requiring more measurements, such as Alaska and the deserts of the U.S. Southwest. Our approach effectively captures the heterogeneous relationships between widely available predictors and the current SOC baseline across regions, offering reliable SOC estimates at 1 km resolution for benchmarking Earth system models.

Temporal and Multivariate Similarity Clustering of 5G Performance Data

Temporal and Multivariate Similarity Clustering of 5G Performance Data

Constructing digital economy acceptance index (DEAI): A comparative analysis of developed and developing countries

The digital economy is a phenomenon that has emerged in today's modern era. Digitalization is expected to be able to support the progress of the economic aspect. However, it turns out that not all people in parts of the world are able to keep up with this change in the phenomenon of economic digitalization. This study aims to identify, classify, and analyze the factors that influence the conditions of acceptance of the digital economy in developed and developing countries as measured through the Digital Economy Acceptance Index (DEAI). This research used a quantitative approach with research objects from countries in the world during the past years. The methods used in this research are composite index and multivariate statistical cluster analysis. The results showed that countries with high DEAI consisted of the United States, Canada, Japan, Australia, New Zealand, Austria, Belgium, Denmark, Finland, France, Germany, Ireland, Netherlands, Spain, Sweden, Switzerland, and Singapore. Countries with moderate DEAI consist of Greece, Italy, Portugal, Brunei Darussalam, China, Indonesia, Malaysia, South Africa, Libya, Brazil, Philippines, Thailand, Vietnam, Iran. As well as countries that have low DEAI, namely Cambodia, Myanmar, Egypt, Laos, India, Pakistan, and Sri Lanka.

Multivariate Time-Series Cluster Analysis for Multiple Functional Domains to Identify Recovery Patterns of Patients With Fragility Hip Fracture After Surgery

Multivariate Time-Series Cluster Analysis for Multiple Functional Domains to Identify Recovery Patterns of Patients With Fragility Hip Fracture After Surgery

Análise das características multidimensionais de sementes de Tabernaemontana heterophylla

ABSTRACT The analysis of Tabernaemontana heterophylla seeds entails morphological characterization and the study of genetic variability between batches. This knowledge is fundamental for evolutionary biology and agronomic and conservation practices. Crop productivity, species preservation, reforestation, and post-harvest processing can all benefit from understanding and considering seed size. This work aimed to determine the multidimensional characteristics and mass of the seeds using multivariate cluster analysis. We investigated multidimensional characteristics by measuring the dimensions and mass of the seeds and computing their physical attributes. Several statistical measures were used to assess the morphometric data, including the mean, amplitude, coefficient of variation, relative frequency, arithmetic mean, standard deviation, and confidence interval. In addition, grouping patterns and inter-variable dependencies were examined by multivariate cluster analysis using Ward’s method. The results revealed significant variability in seed dimensions, indicating morphological unevenness in the seeds of this species. Euclidean distance analysis identified the formation of subclusters, implying distinct groupings based on seed size and mass. The finding highlights the significance of segregating lots with similar physical characteristics and defining representative properties for management practices. These variations reflect the genetic diversity required for adaptability and ecological resilience, ensuring forest ecosystems’ survival and proper functioning. Alternatively, classifying and standardizing seed lots based on these physical traits can optimize post-harvest processing and increase agronomic productivity.

Evaluation of the Irrigation Water Quality of a Canal Contaminated with Textile Dyeing Industry Effluent

The textile dyeing industries discharge untreated effluent into nearby surface water bodies and introduce large numbers of inorganic, organic toxic compounds containing suspended solids, color, etc., which pose a threat to use for irrigated agricultural lands and human health. The study aimed to assess the irrigation water quality of textile dyeing industry effluent-contaminated canal water. The canal water samples were collected from several locations, analyzed for various physicochemical parameters, and assessed for water quality using multivariate statistical analysis and several water quality indices. The analysis results illustrated that the high levels of electrical conductivity (EC), total suspended solids (TSS), turbidity, Na+, NO3-, PO43-, HCO3-, BOD, and COD in the wastewater samples exceeded the DoE-BD standard limits, indicating a higher level of pollution of the canal water. Concerning heavy metal concentrations, Pb was found to be at a higher level in the water. Moreover, irrigation water quality indices such as permeability index (PI), Kelly’s ratio (KR), sodium adsorption ratio (SAR), and magnesium adsorption ratio (MAR) were found to be higher than the standard limits. The multivariate cluster analysis showed that the two clusters were found among the eighteen sampling sites that included heavily contaminated sites. The discharge of industrial effluent into canal water has a detrimental effect on agricultural products. The study observed that the canal water is not suitable for irrigation purposes, and thus the textile dyeing industrial effluent must be treated by installing an environmentally friendly effluent treatment plant (ETP) before being dumped into surface water bodies, which will help reduce environmental pollution as well as develop sustainable surface water resource management.

Less qualitative multiparametric magnetic resonance imaging in prostate cancer can underestimate extraprostatic extension in higher grade tumors.

Multiparametric magnetic resonance imaging (mpMRI) is increasingly used for risk stratification and preoperative staging of prostate cancer. It remains unclear how Grade Group (GG) interacts with the ability of mpMRI to determine the presence of extraprostatic extension (EPE) on surgical pathology. A retrospective review of a robotic assisted laparoscopic radical prostatectomy (RALP) database from 2016-2020 was performed. Radiology mpMRI reports by multiple attending radiologists and without clear standardization or quality control were retrospectively assessed for EPE findings and compared with surgical pathology reports. The data were stratified by biopsy-based GG and a multivariable cluster analysis was performed to incorporate additional preoperative variables (age at diagnosis, PSA, etc.). Hazard ratios were calculated to determine how mpMRI findings and radiographic EPE relate to positive surgical margins. 289 patients underwent at least one mpMRI prior to RALP. Preoperative mpMRI demonstrated sensitivity of 39.3% and specificity of 88.8% for pathological EPE and had a negative predictive value (NPV) of 49.5%, and positive predictive value (PPV) of 84.0%. Stratification of NPV by GG yielded the following values: GG 1-5 (49.5%), GG 3-5 (40.8%), GG 4-5 (43.4%), and GG 5 (30.4%). Additionally, positive EPE on preoperative mpMRI was associated with a significantly decreased risk of positive surgical margins (RR: 0.655; 95% CI: 0.557-0.771). NPV of prostate mpMRI for EPE may be decreased for higher grade tumors. A detailed reference reading and image quality optimization may improve performance. However, urologists should exercise caution in nerve sparing approaches in these patients.