Zero-inflated Models Research Articles

Investigating interaction effects of social risk factors and exposure to air pollution on pediatric lymphoma cancer in Georgia, United States

Childhood cancer constitutes a major cause of death in children. In a recent study of the Georgia Cancer Registry, joint exposures to environmental and social/behavioral stressors were associated with spatial clustering of lymphomas and reticuloendothelial neoplasms among the 159 counties in Georgia, USA. The present study aims to further investigate these associations on a more granular level. Bayesian Poisson and zero-inflated Poisson regression models with spatial and non-spatial variance structures were utilized to investigate whether county-specific cancer patterns may be explained by single or combinations of social stressors and ambient air pollution while adjusting for confounding and accounting for overfitting using differences in expected log predictive densities. While we did not find associations between lymphoma rates and social variables, air pollution, or their interactions, our proposed analysis workflow can serve as a blueprint for future studies investigating dependencies in regression models that feature combinations of unobserved and observed dependency structures.

Prospective comparison of temporal myocardial function in men vs women after anterior ST-elevation myocardial infarction

Abstract Background Compared to men, women have been reported to have increased morbidity and mortality after ST-elevation myocardial infarction (STEMI), but sex differences in cardiac function in the acute and subacute phases of STEMI are incompletely understood. Objective To prospectively compare changes in cardiac function over the acute and subacute phases after anterior STEMI with timely reperfusion in women versus men. Methods The Stunning in Takotsubo versus Acute Myocardial Infarction (STAMI) study prospectively enrolled 94 men and 36 women with anterior STEMI. Echocardiography and blood sampling were performed within 4 hours of admission and at 1, 2, 3, 7, 14 and 30 days after admission. The primary outcome was akinesia recovery, defined as the difference in the per cent akinesia observed at baseline versus follow-up. Secondary outcomes included wall motion score index (WMSI), left ventricular ejection fraction (LVEF) and global longitudinal strain (GLS). Mixed effects linear regression or zero-inflated tobit models with random intercepts were used to model echocardiographic parameters over time. Results Baseline patient characteristics were similar in both groups. The difference between women and men in akinesia recovery at 30 days was 8.4% (95% confidence interval [CI] 1.23-14.99). The covariate-adjusted Bayesian posterior probability that akinesia recovery and WMSI improvement at 30 days are more significant in women than men were 95% and 99%, respectively. Similar but less pronounced trends towards greater improvement in women than men were observed for LVEF and GLS. Conclusions After anterior STEMI with timely reperfusion, cardiac dysfunction recovered to a greater extent in women than in men.

Matrix Factorization and Prediction for High-Dimensional Co-Occurrence Count Data via Shared Parameter Alternating Zero Inflated Gamma Model

High-dimensional sparse matrix data frequently arise in various applications. A notable example is the weighted word–word co-occurrence count data, which summarizes the weighted frequency of word pairs appearing within the same context window. This type of data typically contains highly skewed non-negative values with an abundance of zeros. Another example is the co-occurrence of item–item or user–item pairs in e-commerce, which also generates high-dimensional data. The objective is to utilize these data to predict the relevance between items or users. In this paper, we assume that items or users can be represented by unknown dense vectors. The model treats the co-occurrence counts as arising from zero-inflated Gamma random variables and employs cosine similarity between the unknown vectors to summarize item–item relevance. The unknown values are estimated using the shared parameter alternating zero-inflated Gamma regression models (SA-ZIG). Both canonical link and log link models are considered. Two parameter updating schemes are proposed, along with an algorithm to estimate the unknown parameters. Convergence analysis is presented analytically. Numerical studies demonstrate that the SA-ZIG using Fisher scoring without learning rate adjustment may fail to find the maximum likelihood estimate. However, the SA-ZIG with learning rate adjustment performs satisfactorily in our simulation studies.

Shrinkage estimation of gene interaction networks in single-cell RNA sequencing data

BackgroundGene interaction networks are graphs in which nodes represent genes and edges represent functional interactions between them. These interactions can be at multiple levels, for instance, gene regulation, protein-protein interaction, or metabolic pathways. To analyse gene interaction networks at a large scale, gene co-expression network analysis is often applied on high-throughput gene expression data such as RNA sequencing data. With the advance in sequencing technology, expression of genes can be measured in individual cells. Single-cell RNA sequencing (scRNAseq) provides insights of cellular development, differentiation and characteristics at the transcriptomic level. High sparsity and high-dimensional data structures pose challenges in scRNAseq data analysis.ResultsIn this study, a sparse inverse covariance matrix estimation framework for scRNAseq data is developed to capture direct functional interactions between genes. Comparative analyses highlight high performance and fast computation of Stein-type shrinkage in high-dimensional data using simulated scRNAseq data. Data transformation approaches also show improvement in performance of shrinkage methods in non-Gaussian distributed data. Zero-inflated modelling of scRNAseq data based on a negative binomial distribution enhances shrinkage performance in zero-inflated data without interference on non zero-inflated count data.ConclusionThe proposed framework broadens application of graphical model in scRNAseq analysis with flexibility in sparsity of count data resulting from dropout events, high performance, and fast computational time. Implementation of the framework is in a reproducible Snakemake workflow https://github.com/calathea24/ZINBGraphicalModel and R package ZINBStein https://github.com/calathea24/ZINBStein.

Double robust semiparametric weighted M-estimators of a zero-inflated Poisson regression with missing data in covariates

Frequently, the covariates in the linear predictors of a zero-inflated Poisson regression model are prone to missingness. When the missing data process is at random, the naive estimator and the inverse probability weighted estimator of the model parameter are known to be biased or less efficient. Hence, we propose four different semiparametric double robust weighting M-estimators of a zero-inflated Poisson model. In particular, these estimators differ in term of the nature and the combination of the nuisance components in the estimating equation. The Nadaraya kernel and the generalized additive models are the two smoothing approaches used to estimate the nuisance parameters in step 1. Each estimator in step 2 is a solution to a specific M-estimating equation which requires two distinct nonparametric nuisance components including the selection probability and the augmentation term. The resulting semiparametric weighted M-estimators are double robust and relatively more efficient than their parametric counterpart and related inverse probability weighted estimators. We examine the performance of the proposed estimators by conducting a simulation study and exploring a road traffic dataset. Overall, the performance of the proposed estimators is satisfactory and potential for various extensions.

Interactions between sexual signaling and wing size drive ecology and evolution of wing colors in Odonata

Insect coloration has evolved in response to multiple pressures, and in Odonata (dragonflies and damselflies) a body of work supports a role of wing color in a variety of visual signals and potentially in thermoregulation. Previous efforts have focused primarily on melanistic coloration even though wings are often multicolored, and there has yet to be comprehensive comparative analyses of wing color across broad geographic regions and phylogenetic groups. Percher vs. flier flight-style, a trait with thermoregulatory and signaling consequences, has not yet been studied with regard to color. We used a new color clustering approach to quantify color across a dataset of over 8,000 odonate wing images representing 343 Nearctic species. We then utilized phylogenetically informed Bayesian zero-inflated mixture models to test how color varies with mean ambient temperature, body size, sex and flight-style. We found that wing coloration clustered into two groups across all specimens - light brown-yellow and black-dark brown - with black-dark brown being a much more cohesive grouping. Male perchers have a greater proportion of black-dark brown color on their wings as do species with longer wings. In colder climates, odonates were more likely to have black-dark brown color present, but we found no relationship between the proportion of black and temperature. Light brown-yellow showed similar scaling with wing length, but no relationship with temperature. Our results suggest that black-dark brown coloration may have a limited role in thermoregulation, while light brown-yellow does not have such a role. We also find that the odonate sexes are divergent in wing color in percher species only, suggesting a strong role for color in signaling in more territorial males. Our research contributes to an understanding of complex interactions driving ecological and evolutionary dynamics of color in animals.

Hybrid Machine Learning Approach to Zero-Inflated Data Improves Accuracy of Dengue Prediction.

Spatiotemporal dengue forecasting using machine learning (ML) can contribute to the development of prevention and control strategies for impending dengue outbreaks. However, training data for dengue incidence may be inflated with frequent zero values because of the rarity of cases, which lowers the prediction accuracy. This study aimed to understand the influence of spatiotemporal resolutions of data on the accuracy of dengue incidence prediction using ML models, to understand how the influence of spatiotemporal resolution differs between quantitative and qualitative predictions of dengue incidence, and to improve the accuracy of dengue incidence prediction with zero-inflated data. We predicted dengue incidence at six spatiotemporal resolutions and compared their prediction accuracy. Six ML algorithms were compared: generalized additive models, random forests, conditional inference forest, artificial neural networks, support vector machines and regression, and extreme gradient boosting. Data from 2009 to 2012 were used for training, and data from 2013 were used for model validation with quantitative and qualitative dengue variables. To address the inaccuracy in the quantitative prediction of dengue incidence due to zero-inflated data at fine spatiotemporal scales, we developed a hybrid approach in which the second-stage quantitative prediction is performed only when/where the first-stage qualitative model predicts the occurrence of dengue cases. At higher resolutions, the dengue incidence data were zero-inflated, which was insufficient for quantitative pattern extraction of relationships between dengue incidence and environmental variables by ML. Qualitative models, used as binary variables, eased the effect of data distribution. Our novel hybrid approach of combining qualitative and quantitative predictions demonstrated high potential for predicting zero-inflated or rare phenomena, such as dengue. Our research contributes valuable insights to the field of spatiotemporal dengue prediction and provides an alternative solution to enhance prediction accuracy in zero-inflated data where hurdle or zero-inflated models cannot be applied.

Inbreeding Effect on Maternal Mortality and Fertility in the Habsburg Dynasty.

We investigated inbreeding effects on longevity and fertility in the House of Habsburg, one of the principal royal dynasties of Europe. A total number of 124 Habsburg marriages, involving 107 men and 124 women, in the period of approximately 1450-1800 were considered for the analysis. Kinship and inbreeding coefficients were computed from genealogical information, which included more than 8000 individuals. We found a significant negative association between age of death and inbreeding coefficient (F) in those women who had children (regression coefficient b = -1.06, p = 0.0008). This result led us to investigate possible inbreeding effects on maternal mortality in the period of 4 weeks after the childbirth. A strong inbreeding depression on maternal survival was detected through the Kaplan-Meier curve for groups of women with different level of inbreeding (log-rank test p = 0.0001) and the Cox proportional hazards regression analysis (hazard ratio = 2.36, p = 0.0008). Effect on fertility was also found as more inbred women had longer interbirth intervals (b = 154.66, p = 0.022). Effects of male or female inbreeding on the number of children per woman were not detected through zero-inflated regression models suggesting that reproductive compensation might be occurring among the more inbred and less-fecund women. The effect of inbreeding in adulthood in the Habsburg lineage was at least as important as that previously reported on prereproductive survival. To our knowledge, our results are the first evidence of an inbreeding effect on maternal mortality in humans.

Transcriptomic markers of biological aging in breast cancer survivors: a longitudinal study.

The purpose of this study was to examine the impact of breast cancer therapy on biological aging as measured by expression of genes for cellular senescence (p16INK4a, SenMayo), DNA damage response, and proinflammatory senescence-associated secretory phenotype. This longitudinal, observational study evaluated women diagnosed with breast cancer (stage 0-III) prior to radiation therapy (RT) and/or chemotherapy (CT) and at repeated visits out to 2 years. Peripheral blood mononuclear cell gene expression was assessed using RNA sequencing on quality-verified RNA. Longitudinal data were analyzed using mixed linear models and a zero-inflated 2-part model. Women (mean age = 55.5 years) receiving CT with or without RT (n = 73) had higher odds (odds ratio = 2.97, 95% confidence interval = 1.52 to 5.8) of having detectable p16INK4a following treatment compared with RT (n = 76) or surgery alone (n = 37). The proportion of women expressing 16INK4a over the follow-up period increased in all treatment groups (P < .001), with no interaction by treatment. All groups also increased over time in DNA damage response (P < .001), SenMayo (P < .001), and senescence-associated secretory phenotype (P < .001). Groups differed in the pattern of increase over time with statistically significant quadratic time by group differences for CT with or without RT compared with RT alone for DNA damage response (P = .05), SenMayo (P = .006), and the senescence-associated secretory phenotype (P = .02). Results revealed activation of genes associated with biological aging in women with breast cancer from diagnosis through early survivorship, including DNA damage response, cell senescence, and the inflammatory secretome. Increases were evident across cancer treatments, although women receiving CT showed sustained increases, whereas RT exhibited slowing at later time points. Overall, findings suggest that women treated for breast cancer are aging within their immune cells.

Handheld Cellphone Use and Risky Driving in Adolescents

Handheld cellphone use while driving is associated with increased motor vehicle crash risk among adolescents. To examine the association of handheld cellphone use while driving with kinematic risky driving (KRD) events-hard braking and rapid acceleration-in adolescent drivers. Adolescents aged 16.50 to 17.99 years licensed 365 days or less in Pennsylvania were eligible to participate in this cross-sectional study. Enrollment occurred from July 29, 2021, to June 6, 2022. Participants downloaded a smartphone telematics cellphone app to record driving data for 60 days. Trip characteristics, including frequency, length, and duration; presence of speeding; frequency and duration of handheld cellphone use; time of day; and presence of precipitation. Kinematic risky driving events per 100 miles driven. Zero-inflated Poisson regression models examined whether individual characteristics and trip characteristics were associated with KRD. Incidence rate ratios were computed. Of 405 adolescents who responded to recruitment, 151 enrolled, 140 completed study procedures, and 119 with 12 360 trips were included in the analytic sample (60 female participants [50.4%]; mean [SD] age, 17.2 [0.4] years). Adolescents drove a mean (SD) of 103.8 (65.7) trips, 565.0 (487.3) miles, and 25.1 (19.3) hours. Adolescents had minimal night trips (1.5% [192]), and few trips with precipitation present (9.0% [1097]). Speeding occurred in 43.9% (5428) of the trips and handheld cellphone use occurred in 34.1% (4214) of the trips. Kinematic risky driving events occurred in 10.9% (1358) of the trips at a rate of 2.65 per 100 miles. In adjusted models, increased KRD events were associated with handheld cellphone use (incidence rate ratio [IRR], 2.62; 95% CI, 1.53-4.48), speeding (IRR, 2.12; 95% CI, 1.06-4.26), and minutes driving (IRR, 1.02; 95% CI, 1.01-1.02). Trips at night, precipitation presence, licensure for less than 6 months, and sex were not associated with increased KRD events. In this cross-sectional study of adolescent drivers, trips with handheld cellphone use and speeding were associated with higher rates of KRD, while individual characteristics were not. The findings suggest that smartphone telematics apps provide an opportunity to observe behaviors as well as surveil changes due to intervention efforts.

Zero-Inflated Binary Classification Model with Elastic Net Regularization

Zero-Inflated Binary Classification Model with Elastic Net Regularization

Trajectories of work disability among individuals with anxiety-, mood/affective-, or stress-related disorders in a primary healthcare setting

Abstract Background Anxiety-, mood/affective-, or stress-related disorders affect up to one-third of individuals during their lives and often impact their ability to work. This study aimed to delineate trajectories of work disability (WD) among individuals diagnosed with anxiety-, mood/affective-, or stress-related disorder in primary healthcare and to examine associations between trajectory group membership and sociodemographic, clinical, and clinical-related factors. Methods The study population included working-age individuals, aged 22–62 years, living in Stockholm County, Sweden, who experienced a new episode of any anxiety-, mood/affective, or stress-related disorder in primary healthcare in 2017 (N = 11,304). Data were obtained from Swedish national and regional registers and were linked using pseudonymised unique personal identification numbers. The primary outcome was days with WD (sum of sickness absence and disability pension days) during the three years before and three years after a diagnosis of anxiety-, mood/affective-, or stress-related disorders in primary healthcare. A zero-inflated Poisson group-based trajectory model was used to identify groups of individuals with similar patterns of WD over the study period, with a multinomial logistic regression used to examine associations of sociodemographic, clinical, and clinical-related factors with trajectory group membership. Results Four distinct trajectory groups were found, high increasing (5.1%), with high levels, from 16 to 80 days of WD in six-monthly intervals during follow-up, peak (11.1%), with a peak in WD, up to 32 days of WD, around the time of the diagnosis, low increasing (12.8%), with an increase in days of WD from 4 to 22 during the study period, and constant low (71.1%), with almost no WD over the study period. In multinomial regression models, diagnostic category, psychotropic medication use, a diagnosis of a psychiatric disorder within secondary healthcare, age at diagnosis, and occupation were associated with WD trajectory groups. Conclusions Around two-thirds of individuals treated for a new episode of any anxiety-, mood/affective-, or stress-related disorder in primary healthcare have an excellent prognosis regarding WD. Several sociodemographic and clinical characteristics were associated with group membership; these factors could identify individuals at risk of long-term welfare dependency and who might benefit from interventions to promote a return to work.

Comparison of thoracic epidural catheter and continuous peripheral infusion for management of traumatic rib fracture pain.

Thoracic epidural catheters (TECs) are useful adjuncts to multimodal pain regimens in traumatic rib fractures. However, TEC placement is limited by contraindications, patient risk profile, and provider availability. Continuous peripheral infusion of ketamine and/or lidocaine is an alternative that has a modest risk profile and few contraindications. We hypothesized that patients with multiple traumatic rib fractures receiving TECs would have better pain control, in terms of daily morphine milligram equivalents (MMEs) and mean pain scores (MPSs) when compared with continuous peripheral infusions of ketamine and/or lidocaine. We retrospectively analyzed traumatic rib fracture admissions to a level 1 trauma center between January 2018 and December 2020. We evaluated two treatment groups: TEC only and continuous infusion only (drip only). A linear mixed-effects model evaluated the association of MME with treatment group. An interaction term of treatment group by time (days 1-7) was included to allow estimating potential time-dependent treatment effect on MME. A zero-inflated Poisson mixed-effects model evaluated the association of treatment with MPS. Both models adjusted for confounders. A total of 1,647 patients were included. After multivariable analysis, a significant, time-varying dose-response relationship between treatment group and MME was found, indicating an opioid-sparing effect favoring the TEC-only group. The opioid-sparing benefit for TEC-only therapy was most prominent at day 3 (27.4 vs 36.5 MME) and day 4 (27.3 vs 36.2 MME) (p < 0.01). The drip-only group had 1.21 times greater MPS than patients with TEC only (p < 0.001). Drip-only analgesia is associated with higher daily MME use and MPS, compared with TEC only. The maximal benefit of TEC therapy appears to be on days 3 and 4. Prospective, randomized comparison between groups is necessary to evaluate the magnitude of the treatment effect. Therapeutic/Care Management; Level III.

Bayesian spatio-temporal analysis of dengue transmission in Lao PDR

Dengue, a zoonotic viral disease transmitted by Aedes mosquitoes, poses a significant public health concern throughout the Lao People’s Democratic Republic (Lao PDR). This study aimed to describe spatial–temporal patterns and quantify the effects of environmental and climate variables on dengue transmission at the district level. The dengue data from 2015 to 2020 across 148 districts of Lao PDR were obtained from the Lao PDR National Center for Laboratory and Epidemiology (NCLE). The association between monthly dengue occurrences and environmental and climate variations was investigated using a multivariable Zero-inflated Poisson regression model developed in a Bayesian framework. The study analyzed a total of 72,471 dengue cases with an incidence rate of 174 per 100,000 population. Each year, incidence peaked from June to September and a large spike was observed in 2019. The Bayesian spatio-temporal model revealed a 9.1% decrease (95% credible interval [CrI] 8.9%, 9.2%) in dengue incidence for a 0.1 unit increase in monthly normalized difference vegetation index at a 1-month lag and a 5.7% decrease (95% CrI 5.3%, 6.2%) for a 1 cm increase in monthly precipitation at a 6-month lag. Conversely, dengue incidence increased by 43% (95% CrI 41%, 45%) for a 1 °C increase in monthly mean temperature at a 3-month lag. After accounting for covariates, the most significant high-risk spatial clusters were detected in the southern regions of Lao PDR. Probability analysis highlighted elevated trends in 45 districts, emphasizing the importance of targeted control strategies in high-risk areas. This research underscores the impact of climate and environmental factors on dengue transmission, emphasizing the need for proactive public health interventions tailored to specific contexts in Lao PDR.

Application of longitudinal multilevel zero inflated Poisson regression in modeling of infectious diseases among infants in Ethiopia

BackgroundIn sub-Saharan African countries, preventable and manageable diseases such as diarrhea and acute respiratory infections still claim the lives of children. Hence, this study aims to estimate the rate of change in the log expected number of days a child suffers from Diarrhea (NOD) and flu/common cold (NOF) among children aged 6 to 11 months at the baseline of the study.MethodologyThis study used secondary data which exhibit a longitudinal and multilevel structure. Based on the results of exploratory analysis, a multilevel zero-inflated Poisson regression model with a rate of change in the log expected NOD and NOF described by a quadratic trend was proposed to efficiently analyze both outcomes accounting for correlation between observations and individuals through random effects. Furthermore, residual plots were used to assess the goodness of fit of the model.ResultsConsidering subject and cluster-specific random effects, the results revealed a quadratic trend in the rate of change of the log expected NOD. Initially, low dose iron Micronutrient Powder (MNP) users exhibited a higher rate of change compared to non-users, but this trend reversed over time. Similarly, the log expected NOF decreased for children who used MNP and exclusively breastfed for six months, in comparison to their counterparts. In addition, the odds of not having flu decreased with each two-week increment for MNP users, as compared to non-MNP users. Furthermore, an increase in NOD resulted in an increase in the log expected NOF. Region and exclusive breastfeeding also have a significant relationships with both NOD and NOF.ConclusionThe findings of this study underscore the importance of commencing analysis of data generated from a study with exploratory analysis. The study highlights the critical role of promoting EBF for the first six months and supporting children with additional food after six months to reduce the burden of infectious diseases.

A zero-inflated Poisson integer-valued autoregressive model with time-varying coefficients covariates

For integer-valued time series, we may be interested in how a covariate affects the series. In the existing models, it is commonly assumed that the coefficients of the covariates are constant, and the innovation process follows a Poisson distribution. However, in practice, the influence of covariates may vary with time, and there may be a large number of zeros. To address this situation, this paper proposes an integer-valued autoregressive model with time-varying coefficients on covariates, incorporating a zero-inflated Poisson innovation process. The binomial thinning parameters and unknown functions of the proposed model are estimated based on approximate conditional least squares and the cubic spline method. The consistency and asymptotic properties of the binomial thinning parameters are investigated. Simulation studies and real data analysis support the flexibility and good performance of the proposed model.

Zero-inflated multivariate tobit regression modeling

A frequent challenge encountered in real-world applications is data having a high proportion of zeros. Focusing on ecological abundance data, much attention has been given to zero-inflated count data. Models for non-negative continuous abundance data with an excess of zeros are rarely discussed. Work presented here considers the creation of a point mass at zero through a left-censoring approach or through a hurdle approach. We incorporate both mechanisms to capture the analog of zero-inflation for count data. Additionally, primary attention has been given to univariate zero-inflated modeling (e.g., single species), whereas data often arise jointly (e.g., a collection of species). With multivariate abundance data, a key issue is to capture dependence among the species at a site, both in terms of positive abundance as well as absence. Therefore, our contribution is a model for multivariate zero-inflated continuous data that are non-negative. Working in a Bayesian framework, we discuss the issue of separating the two sources of zeros and offer model comparison metrics for multivariate zero-inflated data. In an application, we model the total biomass for five tree species obtained from plots established in the Forest Inventory Analysis database in the Northeast region of the United States.

Should Zeros Count? Modeling the Galaxy–Globular Cluster Scaling Relation with(out) Zero-inflated Count Models

The scaling relation between the size of a galaxy’s globular cluster (GC) population (N GC) and the galaxy’s stellar mass (M *) is usually described with a continuous, linear model, but in reality it is a count relationship that should be modeled as such. For massive galaxies, a negative binomial (NB) model has been shown to describe the data well, but it is unclear how the scaling relation behaves at low galaxy masses where a substantial portion of galaxies have N GC = 0. In this work, we test the utility of Poisson and NB models for describing the low-mass end of the N GC−M * scaling relation. We introduce the use of zero-inflated versions of these models, which allow for larger zero populations (e.g., galaxies without GCs) than would otherwise be predicted. We evaluate our models with a variety of predictive model comparison methods, including predictive intervals, the leave-one-out cross-validation criterion, and posterior predictive comparisons. We find that the NB model is consistent with our data, but the naive Poisson is not. Moreover, we find that zero inflation of the models is not necessary to describe the population of low-mass galaxies that lack GCs, suggesting that a single formation and evolutionary process acts over all galaxy masses. Under the NB model, there does not appear to be anything unique about the lack of GCs in many low-mass galaxies; they are simply the low-mass extension of the larger N GC−M * scaling relation.

Advanced statistical approaches for predicting pain after pediatric thoracotomy: a cross-sectional study using zero-inflated and Poisson models

BackgroundThoracotomy is one of the surgical procedures most burdened by chronic post-operative pain. There is poor evidence regarding the possibility that even in pediatric patients, thoracotomy can be followed by post-operative pain. The primary objective of this analysis is to identify associations with home pain therapy, pain intensity, and possible protective factors acting on chronic pain in this population.MethodsA retrospective cross-sectional study was conducted at Ospedale Pediatrico Bambino Gesù IRCCS. The study included pediatric patients undergoing thoracotomy. For statistical analyses, a logistic model and a zero-inflated strategy were implemented to explore associations and predict factors related to home-based analgesic therapy and pain intensity.ResultsGender and age were identified as significant factors in the assignment of home therapy, with males having over seven times the risk compared to females (OR = 7.06, 95% CI = [2.11, 29.7]). At the last measurement, pain intensity was positively associated with age and the number of pain events during the week.ConclusionsThe study highlights significant factors influencing post-thoracotomy pain management in pediatric patients. These findings underscore the importance of tailored pain management strategies that consider gender and age to improve post-operative care and outcomes in pediatric thoracotomy patients.

Patent Keyword Analysis Using Bayesian Zero-Inflated Model and Text Mining

Patent keyword analysis is used to analyze the technology keywords extracted from collected patent documents for specific technological fields. Thus, various methods related to this type of analysis have been researched in the industrial engineering fields, such as technology management and new product development. To analyze the patent document data, we have to search for patents related to the target technology and preprocess them to construct the patent–keyword matrix for statistical and machine learning algorithms. In general, a patent–keyword matrix has an extreme zero-inflated problem. This is because each keyword occupies one column even if it is included in only one document among all patent documents. General zero-inflated models have a limit at which the performance of the model deteriorates when the proportion of zeros becomes extremely large. To solve this problem, we applied a Bayesian inference to a general zero-inflated model. In this paper, we propose a patent keyword analysis using a Bayesian zero-inflated model to overcome the extreme zero-inflated problem in the patent–keyword matrix. In our experiments, we collected practical patents related to digital therapeutics technology and used the patent–keyword matrix preprocessed from them. We compared the performance of our proposed method with other comparative methods. Finally, we showed the validity and improved performance of our patent keyword analysis. We expect that our research can contribute to solving the extreme zero-inflated problem that occurs not only in patent keyword analysis, but also in various text big data analyses.