Semiparametric Research Articles

Local polynomial software reliability models and their application

In this paper, we propose local polynomial software reliability models (SRMs), which can be categorized into a semi-parametric modeling framework. Our models belong to the common non-homogeneous Poisson process (NHPP)-based SRMs, but possess a flexible structure to approximate an arbitrary mean value function by controlling the polynomial degree. More specifically, we develop two types of local polynomial NHPP-based SRMs; finite-failure (type-I) and infinite-failure (type-II) SRMs, which are substantial extensions of the existing NHPP-based SRMs in the similar categories. We also develop two maximum likelihood estimation algorithms in both estimation and prediction phases, where the former is used for the testing period experienced in the past, and the latter for the prediction in the future. In numerical experiments with actual 8 software fault count time-interval data sets, we compare our local polynomial NHPP-based SRMs with the well-known existing parametric NHPP-based SRMs in terms of goodness-of-fit and predictive performances. Finally, it can be concluded that our local polynomial NHPP-based SRMs with lower polynomial degrees could outperform the existing NHPP-based SRMs in several cases and should be listed as candidates for the representative NHPP-based SRMs in software reliability analysis.

What Can We Learn from a Semiparametric Factor Analysis of Item Responses and Response Time? An Illustration with the PISA 2015 Data.

It is widely believed that a joint factor analysis of item responses and response time (RT) may yield more precise ability scores that are conventionally predicted from responses only. For this purpose, a simple-structure factor model is often preferred as it only requires specifying an additional measurement model for item-level RT while leaving the original item response theory (IRT) model for responses intact. The added speed factor indicated by item-level RT correlates with the ability factor in the IRT model, allowing RT data to carry additional information about respondents' ability. However, parametric simple-structure factor models are often restrictive and fit poorly to empirical data, which prompts under-confidence in the suitablity of a simple factor structure. In the present paper, we analyze the 2015 Programme for International Student Assessment mathematics data using a semiparametric simple-structure model. We conclude that a simple factor structure attains a decent fit after further parametric assumptions in the measurement model are sufficiently relaxed. Furthermore, our semiparametric model implies that the association between latent ability and speed/slowness is strong in the population, but the form of association is nonlinear. It follows that scoring based on the fitted model can substantially improve the precision of ability scores.

Statistical analysis of actigraphy data with generalised additive models.

There is a growing interest in the use of physical activity data in clinical studies, particularly in diseases that limit mobility in patients. High-frequency data collected with digital sensors are typically summarised into actigraphy features aggregated at epoch level (e.g., by minute). The statistical analysis of such volume of data is not straightforward. The general trend is to derive metrics, capturing specific aspects of physical activity, that condense (say) a week worth of data into a single numerical value. Here we propose to analyse the entire time-series data using Generalised Additive Models (GAMs). GAMs are semi-parametric models that allow inclusion of both parametric and non-parametric terms in the linear predictor. The latter are smooth terms (e.g., splines) and, in the context of actigraphy minute-by-minute data analysis, they can be used to assess daily patterns of physical activity. This in turn can be used to better understand changes over time in longitudinal studies as well as to compare treatment groups. We illustrate the application of GAMs in two clinical studies where actigraphy data was collected: a non-drug, single-arm study in patients with amyotrophic lateral sclerosis, and a physical-activity sub-study included in a phase 2b clinical trial in patients with chronic obstructive pulmonary disease.

Inference in models with partially identified control functions

In multiple contributions to the literature, James L. Powell and coauthors have developed estimators for semiparametric models where sample selectivity and/or endogeneity can be handled through a “control function”. Their methods rely on pairwise comparisons of observations which match (asymptotically) the control functions. Conditional on this matching, a moment condition can identify the parameters of the model. However, there exist instances where the control functions are unobserved, but we have bounds for them which depend on observable covariates. These bounds can arise directly from the nature of the data available (e.g, with interval data), or they can be derived from an economic model. The inability to observe the control functions precludes the matching proposed in Powell’s methods. In this paper we show that, under certain conditions, testable implications can still be obtained through pairwise comparisons of observations for which the control-function bounds are disjoint. Testable implications now take the form of pairwise functional inequalities. We propose an inferential procedure based on these pairwise inequalities and we analyze its properties.

Semiparametric Integrated and Additive Spatio-Temporal Single-Index Models

In this paper, we introduce two semiparametric single-index models for spatially and temporally correlated data. Our first model has spatially and temporally correlated random effects that are additive to the nonparametric function, which we refer to as the “semiparametric spatio-temporal single-index model (ST-SIM)”. The second model integrates the spatially correlated effects into the nonparametric function, and the time random effects are additive to the single-index function. We refer to our second model as the “semiparametric integrated spatio-temporal single-index model (IST-SIM)”. Two algorithms based on a Markov chain expectation maximization are introduced to simultaneously estimate the model parameters, spatial effects, and time effects of the two models. We compare the performance of our models using several simulation studies. The proposed models are then applied to mortality data from six major cities in South Korea. Our results suggest that IST-SIM (1) is more flexible than ST-SIM because the former can estimate various nonparametric functions for different locations, while ST-SIM enforces the mortality functions having the same shape over locations; (2) provides better estimation and prediction, and (3) does not need restrictions for the single-index coefficients to fix the identifiability problem.

Complete f-moment convergence for m-asymptotic negatively associated random variables and related statistical applications

In this article, the complete f-moment convergence for m-asymptotic negatively associated random variables is investigated. As applications, we establish the strong consistency of the least square estimator in the simple linear errors-in-variables models and the complete consistency for estimator in the semiparametric regression model based on m-asymptotic negatively associated errors. We also give some simulations to assess the finite sample performance of the theoretical results.

A data-driven semi-parametric model of SARS-CoV-2 transmission in the United States.

To support decision-making and policy for managing epidemics of emerging pathogens, we present a model for inference and scenario analysis of SARS-CoV-2 transmission in the USA. The stochastic SEIR-type model includes compartments for latent, asymptomatic, detected and undetected symptomatic individuals, and hospitalized cases, and features realistic interval distributions for presymptomatic and symptomatic periods, time varying rates of case detection, diagnosis, and mortality. The model accounts for the effects on transmission of human mobility using anonymized mobility data collected from cellular devices, and of difficult to quantify environmental and behavioral factors using a latent process. The baseline transmission rate is the product of a human mobility metric obtained from data and this fitted latent process. We fit the model to incident case and death reports for each state in the USA and Washington D.C., using likelihood Maximization by Iterated particle Filtering (MIF). Observations (daily case and death reports) are modeled as arising from a negative binomial reporting process. We estimate time-varying transmission rate, parameters of a sigmoidal time-varying fraction of hospitalized cases that result in death, extra-demographic process noise, two dispersion parameters of the observation process, and the initial sizes of the latent, asymptomatic, and symptomatic classes. In a retrospective analysis covering March-December 2020, we show how mobility and transmission strength became decoupled across two distinct phases of the pandemic. The decoupling demonstrates the need for flexible, semi-parametric approaches for modeling infectious disease dynamics in real-time.

Penalised semi-parametric copula method for semi-competing risks data: application to hip fracture in elderly

Abstract Hip fracture is a severe complication in the elderly. The affected people are at a higher risk of second fracture and death occurrence, and the best treatment for hip fractures is still being debated. Aside from the treatment, many factors, such as comorbidity conditions, may be associated with second fracture and death occurrence. This study aims to identify effective treatments and important covariates and estimate their effects on the progression of second fracture and death occurrence in hip fracture elderly patients using the semi-competing risks framework, because death dependently censors a second fracture but not vice versa. Due to the complex semi-competing risks data, performing variable selection simultaneously for second fracture and death occurrence is difficult. We propose a penalised semi-parametric copula method for semi-competing risks data. Specifically, we use separate Cox semi-parametric models for both margins and employ a copula to model the two margins’ dependence. We develop a coordinate-wise optimisation algorithm that takes into account the data structure and copula function’s complexities. Simulations show that the proposed method outperforms the traditional penalised marginal method. We apply the proposed method to a population-based cohort study of hip fracture elderly patients, providing new insights into their treatment and clinical management.

Semi-parametric single-index predictive regression models with cointegrated regressors

This paper considers the estimation of a semi-parametric single-index regression model that allows for nonlinear predictive relationships. This model is useful for predicting financial asset returns, whose observed behaviour resembles a stationary process, if the multiple nonstationary predictors are cointegrated. The presence of cointegrated regressors imposes a single-index structure in the model, and this structure not only balances the nonstationarity properties of the multiple predictors with the stationarity properties of asset returns but also avoids the curse of dimensionality associated with nonparametric regression function estimation. An orthogonal series expansion is used to approximate the unknown link function for the single-index component. We consider the constrained nonlinear least squares estimator of the single-index (or the cointegrating) parameters and the plug-in estimator of the link function, and derive their asymptotic properties. In an empirical application, we find some evidence of in-sample nonlinear predictability of U.S. stock returns using cointegrated predictors. We also find that the single-index model in general produces better out-of-sample forecasts than both the historical average benchmark and the linear predictive regression model.

Dynamic robust portfolio selection under market distress

This article proposes a dynamic robust portfolio selection model that is based on minimizing portfolio’s worst case scenarios using the Conditional Value at Risk as relevant risk measure. Our proposed empirical model for the dynamics of portfolio constituents has three main features: i) accommodates tail dependence between assets by means of a mixture of copula functions; ii) conditional heteroscedasticity and leverage effects are considered through the implementation of a GJR-GARCH model; and iii) extreme events are taken into account by considering parametric and semiparametric hybrid models for the marginal distribution of asset returns. We illustrate the performance of this portfolio before and during the COVID-19 pandemic using statistical measures such as the Sharpe ratio, cumulative returns, and volatility. The results show the outperformance of our WCVaR portfolio during the turmoil period against benchmark portfolios commonly used by practitioners. The method also exhibits good performance during calm periods.

Bayesian Inference for High Dimensional Cox Models with Gaussian and Diffused-Gamma Priors: A Case Study of Mortality in COVID-19 Patients Admitted to the ICU.

Bayesian approaches have been utilized to address the challenge of variable selection and statistical inference in high-dimensional survival analysis. However, the discontinuity of the -norm prior, including the useful spike-and-slab prior, may lead to computational and implementation challenges, potentially limiting the widespread use of Bayesian methods. The Gaussian and diffused-gamma (GD) prior has emerged as a promising alternative due to its continuous-and-differentiable -norm approximation and computational efficiency in generalized linear models. In this paper, we extend the GD prior to semi-parametric Cox models by proposing a rank-based Bayesian inference procedure with the Cox partial likelihood. We develop a computationally efficient algorithm based on the iterative conditional mode (ICM) and Markov chain Monte Carlo methods for posterior inference. Our simulations demonstrate the effectiveness of the proposed method, and we apply it to an electronic health record dataset to identify risk factors associated with COVID-19 mortality in ICU patients at a regional medical center.

Pooled Exposure-Response (ER) and Quantitative Benefit/Risk (B/R) Analyses Support the Approved Copanlisib Intermittent Dosing Regimen

Introduction: Copanlisib is a potent and highly selective pan-class phosphatidylinositol 3-kinase (PI3K) inhibitor with preferential activity against the p110α and p110δ isoforms. Unlike other PI3K inhibitors, copanlisib is uniquely administered intravenously using an intermittent schedule, supported by preclinical data and literature model-based analyses showing high tumor residence and time intervals enabling for recovery of normal tissue. The pivotal studies, CHRONOS-1 and CHRONOS-3, established the benefit/risk of copanlisib 60 mg on Day 1, 8, 15 of 28-day cycle as monotherapy in 3L+ relapsed follicular lymphoma and in combination with rituximab in 2L+ non-Hodgkin's lymphoma, respectively. While prior ER analyses in CHRONOS-1 suggested a positive ER trend for copanlisib safety, similar to oral continuously dosed PI3K inhibitors (2022 FDA ODAC), ER analyses from the larger Phase 3 study, CHRONOS-3, revealed no significant ER for safety (Morcos et al. CPT Pharmacometrics Syst Pharmacol 2023). This analysis investigates pooled ER relationships for copanlisib safety across the pivotal studies and considers them in the context of the ER for efficacy in CHRONOS-3, as part of a quantitative B/R analysis for the approved copanlisib intermittent dosing regimen. Methods: Individual static and time-varying exposure metrics in CHRONOS-1 and CHRONOS-3 were derived from a previously established comprehensive population pharmacokinetics (popPK) analysis (Morcos et al. CPT Pharmacometrics Syst Pharmacol 2023). ER analyses investigated the relationship to the efficacy endpoint: progression-free survival (PFS) in CHRONOS-3 using 2-year follow-up; and to the safety endpoints: time-to-first Grade ≥ 3 adverse events (Gr≥3 AEs) and serious adverse events (SAEs), and frequency of individual AEs associated with copanlisib treatment (hyperglycemia, diarrhea, hypertension, nausea, fatigue, neutropenia, and lung infections of any grade), pooled across CHRONOS-1 using 6-year follow-up and CHRONOS-3 using 2-year follow-up. Multivariate parametric time-to-event (TTE) and logistic regression models investigated ER relationships at a prespecified significance level of p<0.01 after accounting for other potentially prognostic demographic, laboratory, and disease related baseline covariates. To quantitatively assess the B/R of the copanlisib 60 mg intermittent dosing regimen, a clinical utility index (CUI) function was defined with a 1:1 weighting for efficacy and safety to consider the tradeoffs between any identified ER relationships for efficacy and safety. Results: In CHRONOS-3, the parametric TTE ER analysis for PFS was characterized by a 2-knot spline baseline hazard function and demonstrated a statistically significant positive ER relationship (p<0.00001). Analysis results are consistent with a prior ER analysis using a semi-parametric Cox proportional hazards model of earlier 1-year follow-up (Morcos et al. CPT Pharmacometrics Syst Pharmacol 2023). Therefore, greater copanlisib exposure is associated with more prolonged PFS. Across pooled CHRONOS-1 and CHRONOS-3, parametric TTE for first Gr≥3 AEs and SAEs were characterized by 2-knot spline baseline hazard functions and demonstrated a borderline significant ER for Gr≥3 AEs (p=0.014) and no significant ER for SAEs (p=0.26). Multivariate logistic regression analyses showed no significant ER for individual AEs after adjusting for relevant baseline covariates. Across the range of exposures achieved with the copanlisib 60 mg intermittent dosing regimen, a steeper relationship for the hazard ratio relative to placebo in is seen for the significant ER of PFS compared with the borderline ER of Gr≥3 AEs (Figure 1). The CUI accounting for the quantitative ER relationships confirmed the favorable B/R across the range of copanlisib exposures. Thus, lower copanlisib doses may result in lower efficacy while not necessarily resulting in substantially improved safety. Conclusions: The completed quantitative analyses substantiate the favorable B/R for the copanlisib 60 mg on days 1, 8, and 15 of a 28-day cycle dosing regimen.

Bayesian and Classical Semi-parametric Estimation of the Balanced Longitudinal Data Model

The primary objective of this study is to employ semi-parametric regression techniques in the balanced longitudinal data model. Where the parametric regression models are plagued by the problem of strict constraints, while non-parametric regression models, despite their flexibility, suffer from the problem of the curse of dimensionality. Consequently, semi-parametric regression presents a suitable solution to address the problems in parametric and non-parametric regression methods. The advantage of this model is that it contains all the positive properties included in the previous two models such as containing strict restrictions in its parametric component, complete flexibility in its non-parametric component, and clarity of the interaction between its parametric and non-parametric components. According to the above, two methods were used to estimate a semi-parametric balanced longitudinal data model. The first is the Bayesian estimating method; the second is the Speckman method, which estimated the unknown nonparametric smoothing function by employing the kernel smoothing Nadaraya & Watson method. The Aim was to make a comparison between the Bayesian estimation method and the classical estimation method. Based on simulation experiments conducted on three different sample sizes (50, 100, and 200), it was concluded that the Bayes method is best at the variance levels (1,5). In contrast, the Profile least square method is best at the variance level (10).

COMPARATIVE ANALYSIS OF COX MIXED CURE MODEL WITH PARAMETRIC MODELS USING TOXIC DATA

The investigation focused on examining of the survival analysis which entails the design and study of the occurrence and time of survival events. The study aimed to compare the result of the analysis using semi parametric model; cox mixed cure model and two parametric models; weibull and lognormal model to determine the model that fit the toxic data. The data was obtained from State Special Hospital Maiduguri (SSH) from 2016-2020. Akaike information criterion (AIC) was used to compare and evaluate the models. Results show that Cox mixed cure model has 13.65 with least AIC value, Weibull with 18.29 and lognormal with 18.30 with highest AIC value. The study concludes that semi parametric cox mixed cure model is the suitable to fit the toxic data.

Zastosowanie jednowskaźnikowego semiparametrycznego modelu ekonometrycznego w analizie ryzyka inwestycyjnego

One of the tasks of applied econometrics and statistics is the estimation of the conditional mean function of the assumed model. The available methods for estimating such a function and the estimation results depend mostly on the a priori assumptions about the population or process that generates the data. The aim of the research presented in this paper is to apply single-index semiparametric econometric model to measure investment risk on the Warsaw Stock Exchange (WSE). Such a model is characterised by some assumptions less restrictive than in the case of other parametric models for the conditional mean function, such as a linear model or a binary probit model. At the same time, a single-index model retains many of the desirable features of a linear model and a least squares method. The presented model was used to measure investment risk for 10 IT companies quoted on the WSE in the period from 2018 to 2021. The data came from the Bloomberg financial service. Rates of return of two stock market indices, WIG20 (Poland) and S&P 500 (USA), were adopted as risk factors. The results indicate that the Polish market determines the volatility of returns of the analysed companies to a much larger extent than is the case with the US market. Furthermore, semiparametric models proved more flexible than the parametric ones regarding theoretical assumptions, which in the event of a large inflow of information might facilitate making correct investment decisions.

Diffusion in the corpus callosum predicts persistence of clinical symptoms after mild traumatic brain injury, a multi-scanner study.

Mild traumatic brain injuries (mTBIs) comprise 80% of all TBI, but conventional MRI techniques are often insensitive to the subtle changes and injuries produced in a concussion. Diffusion tensor imaging (DTI) is one of the most sensitive MRI techniques for mTBI studies with outcome and symptom associations described. The corpus callosum (CC) is one of the most studied fiber tracts in TBI and mTBI, but the comprehensive post-mTBI symptom relationship has not fully been explored. This is a retrospective observational study of how quantitative DTI data of the CC and its sub-regions may relate to clinical presentation of symptoms and timing of resolution of symptoms in patients diagnosed with uncomplicated mTBI. DTI and clinical data were obtained retrospectively from 446 (mean age 42 years, range 13-82) civilian patients. From patient medical charts, presentation of the following common post-concussive symptoms was noted: headache, balance issues, cognitive deficits, fatigue, anxiety, depression, and emotional lability. Also recorded was the time between injury and a visit to the physician when improvement or resolution of a particular symptom was reported. FA values from the total CC and 3 subregions of the CC (genu or anterior, mid body, and splenium or posterior) were obtained from hand tracing on the Olea Sphere v3.0 SP12 free-standing workstation. DTI data was obtained from 8 different 3T MRI scanners and harmonized via ComBat harmonization. The statistical models used to explore the association between regional Fractional Anisotropy (FA) values and symptom presentation and time to symptom resolution were logistic regression and interval-censored semi-parametric Cox proportional hazard models, respectively. Subgroups related to age and timing of first scan were also analyzed. Patients with the highest FA in the total CC (p = 0.01), anterior CC (p < 0.01), and mid-body CC (p = 0.03), but not the posterior CC (p = 0.91) recovered faster from post-concussive cognitive deficits. Patients with the highest FA in the posterior CC recovered faster from depression (p = 0.04) and emotional lability (p = 0.01). There was no evidence that FA in the CC or any of its sub-regions was associated with symptom presentation or with time to resolution of headache, balance issues, fatigue, or anxiety. Patients with mTBI under 40 had higher FA in the CC and the anterior and mid-body subregions (but not the posterior subregion: p = 1.00) compared to patients 40 or over (p ≤ 0.01). There was no evidence for differences in symptom presentation based on loss of consciousness (LOC) or sex (p ≥ 0.18). This study suggests that FA of the CC has diagnostic and prognostic value for clinical assessment of mTBI in a large diverse civilian population, particularly in patients with cognitive symptoms.

Time to death and its determinant factors of visceral leishmaniasis with HIV co-infected patients during treatment period admitted at Metema hospital, Metema, Ethiopia: a hospital-based cross-sectional study design

BackgroundVisceral leishmaniasis is caused by the parasites Leishmania donovani spices complex that can spread to internal organs and the disease is fatal with a fatality rate of nearly 100% if left untreated. Visceral Leishmania-HIV (HIV1) coinfection disease is a new clinical form of leishmaniasis very serious disease in the endemic part of the world. It also served as the primary cause of death in the lowlands of Ethiopia with the endemic Humara and Metema that are located near the Sudanese border.MethodsA total of 153 visceral leishmaniases with HIV co-infection secondary data was taken from the medical chart of patients from January 2015 to January 2021 and a hospital-based cross-sectional study design was carried out to retrieve relevant information. The data entered by SPSS and analysed using STATA version 14 and R4.2.1 statistical software packages using a non-parametric Model, semi-parametric Cox proportional hazard survival models at 5% significance level.ResultAmong the total visceral leishmaniasis with HIV co-infected patients 3.27% were females and 96.73% were males, 19 (12.42%) patients died and 134(87.58%) patients were censored. The Cox proportional hazard model result indicates that severe acute malnutrition, baseline CD4+ cell count ≥100, and underweight significantly contributed to the survival time of a patient. Cox proportional hazard model shows that severe acute malnutrition (HR=4.40027, 95% CI= 2.455061 262.7934, P-value=0.007), baseline CD4+cell count ≥100 (HR=0.2714623, 95% CI= 0.0764089 0.9644395, P-value=0.044), and Underweight (HR=4.678169, 95% CI= 1.970097 11.10872, P-value=0.040) significantly contributed to a shorter survival time.ConclusionVisceral leishmaniases with HIV co-infected patients show a large number of deaths occurred in the earlier days of treatment this implies that Visceral leishmaniasis accelerates HIV replication and disease progression death. The researcher suggests that people be aware of the burden posed by those risk factors and knowledgeable about the diseases. So, the researcher recommended that to health workers implement primary health care in those patients and careful consideration of a neglected parasitic disease.

Kernel Cox partially linear regression: Building predictive models for cancer patients' survival.

Wide heterogeneity exists in cancer patients' survival, ranging from a few months to several decades. To accurately predict clinical outcomes, it is vital to build an accurate predictive model that relates the patients' molecular profiles with the patients' survival. With complex relationships between survival and high-dimensional molecular predictors, it is challenging to conduct nonparametric modeling and irrelevant predictors removing simultaneously. In this article, we build a kernel Cox proportional hazards semi-parametric model and propose a novel regularized garrotized kernel machine (RegGKM) method to fit the model. We use the kernel machine method to describe the complex relationship between survival and predictors, while automatically removing irrelevant parametric and nonparametric predictors through a LASSO penalty. An efficient high-dimensional algorithm is developed for the proposed method. Comparison with other competing methods in simulation shows that the proposed method always has better predictive accuracy. We apply this method to analyze a multiple myeloma dataset and predict the patients' death burden based on their gene expressions. Our results can help classify patients into groups with different death risks, facilitating treatment for better clinical outcomes.

Study of the relationship between occurrence of Kawasaki disease and air pollution in Chengdu by parametric and semi-parametric models.

Kawasaki disease (KD) is a pediatric vasculitis of unknown etiology which is mainly associated with the development of coronary artery aneurysms. The etiology of KD seems to be multifactorial, but there is rare research on the association between KD and potential environmental risk factors. So, we would like to examine the correlation between KD and potential environmental risk factors in West China. We included KD patients in Chengdu from 2015 to 2021 and analyzed the correlation between air pollution indexes and climate condition indexes. The autocorrelation of the data was eliminated by first-order difference, the risk factors were screened by stepwise regression with AIC criterion, and the multiple regression model was established. Random forest and Winsorize were used to test the robustness of the screening results, and it was found that particulate matter with a diameter less than or equal to 2.5 μm (PM2.5) had a significant positive effect on the incidence of KD. In addition, several variables were positively correlated with KD incidence, but not statistically significant. The GAM model was used to explore the nonlinear correlation between PM2.5 and KD incidence. The results showed that PM2.5 concentration was positively correlated with KD incidence, and the effects varied among different concentration levels of PM2.5. Fisher's exact test was used to explore the influence of PM2.5 on the incidence of coronary tumors. It is found that PM2.5 may be a risk factor for it. This study suggested that exposure to high concentrations of PM2.5 may significantly increase the risk of KD. The evidence for the association between other environmental factors and KD incidence, as well as the association between PM2.5 and coronary tumors, was limited and needed further verification.

Complications and associated risk factors after surgical management of proximal femoral fractures.

This work aimed at answering the following research questions: 1) What is the rate of mechanical complications, nonunion and infection for head/neck femoral fractures, intertrochanteric fractures, and subtrochanteric fractures in the elderly USA population? and 2) Which factors influence adverse outcomes? Proximal femoral fractures occurred between 1 January 2009 and 31 December 2019 were identified from the Medicare Physician Service Records Data Base. The Kaplan-Meier method with Fine and Gray sub-distribution adaptation was used to determine rates for nonunion, infection, and mechanical complications. Semiparametric Cox regression model was applied incorporating 23 measures as covariates to identify risk factors. Union failure occured in 0.89% (95% confidence interval (CI) 0.83 to 0.95) after head/neck fracturs, in 0.92% (95% CI 0.84 to 1.01) after intertrochanteric fracture and in 1.99% (95% CI 1.69 to 2.33) after subtrochanteric fractures within 24 months. A fracture-related infection was more likely to occur after subtrochanteric fractures than after head/neck fractures (1.64% vs 1.59%, hazard ratio (HR) 1.01 (95% CI 0.87 to 1.17); p < 0.001) as well as after intertrochanteric fractures (1.64% vs 1.13%, HR 1.31 (95% CI 1.12 to 1.52); p < 0.001). Anticoagulant use, cerebrovascular disease, a concomitant fracture, diabetes mellitus, hypertension, obesity, open fracture, and rheumatoid disease was identified as risk factors. Mechanical complications after 24 months were most common after head/neck fractures with 3.52% (95% CI 3.41 to 3.64; currently at risk: 48,282). The determination of complication rates for each fracture type can be useful for informed patient-clinician communication. Risk factors for complications could be identified for distinct proximal femur fractures in elderly patients, which are accessible for therapeutical treatment in the management.