Flagging unusual clusters based on linear mixed models using weighted and self-calibrated predictors.

Statistical models incorporating cluster-specific intercepts are commonly used in hierarchical settings, for example, observations clustered within patients or patients clustered within hospitals. Predicted values of these intercepts are often used to identify or "flag" extreme or outlying clusters, such as poorly performing hospitals or patients with rapid declines in their health. We consider a variety of flagging rules, assessing different predictors, and using different accuracy measures. Using theoretical calculations and comprehensive numerical evaluation, we show that previously proposed rules based on the 2 most commonly used predictors, the usual best linear unbiased predictor and fixed effects predictor, perform extremely poorly: the incorrect flagging rates are either unacceptably high (approaching 0.5 in the limit) or overly conservative (eg, much <0.05 for reasonable parameter values, leading to very low correct flagging rates). We develop novel methods for flagging extreme clusters that can control the incorrect flagging rates, including very simple-to-use versions that we call "self-calibrated." The new methods have substantially higher correct flagging rates than previously proposed methods for flagging extreme values, while controlling the incorrect flagging rates. We illustrate their application using data on length of stay in pediatric hospitals for children admitted for asthma diagnoses.

Deep partially linear cox model for current status data.

Deep learning has continuously attained huge success in diverse fields, while its application to survival data analysis remains limited and deserves further exploration. For the analysis of current status data, a deep partially linear Cox model is proposed to circumvent the curse of dimensionality. Modeling flexibility is attained by using deep neural networks (DNNs) to accommodate nonlinear covariate effects and monotone splines to approximate the baseline cumulative hazard function. We establish the convergence rate of the proposed maximum likelihood estimators. Moreover, we derive that the finite-dimensional estimator for treatment covariate effects is $\sqrt{n}$-consistent, asymptotically normal, and attains semiparametric efficiency. Finally, we demonstrate the performance of our procedures through extensive simulation studies and application to real-world data on news popularity.

The effective sample size in Bayesian information criterion for level-specific fixed and random-effect selection in a two-level nested model.

Popular statistical software provides the Bayesian information criterion (BIC) for multi-level models or linear mixed models. However, it has been observed that the combination of statistical literature and software documentation has led to discrepancies in the formulas of the BIC and uncertainties as to the proper use of the BIC in selecting a multi-level model with respect to level-specific fixed and random effects. These discrepancies and uncertainties result from different specifications of sample size in the BIC's penalty term for multi-level models. In this study, we derive the BIC's penalty term for level-specific fixed- and random-effect selection in a two-level nested design. In this new version of BIC, called BIC E 1 , this penalty term is decomposed into two parts if the random-effect variance-covariance matrix has full rank: (a) a term with the log of average sample size per cluster and (b) the total number of parameters times the log of the total number of clusters. Furthermore, we derive the new version of BIC, called BIC E 2 , in the presence of redundant random effects. We show that the derived formulae, BIC E 1 and BIC E 2 , adhere to empirical values via numerical demonstration and that BIC E ( E indicating either E 1 or E 2 ) is the best global selection criterion, as it performs at least as well as BIC with the total sample size and BIC with the number of clusters across various multi-level conditions through a simulation study. In addition, the use of BIC E 1 is illustrated with a textbook example dataset.

Examination of factors associated with the temporal stability assessment of crash severity by using generalised linear model-A case study.

Road crashes are a major public safety concern in Pakistan. Prior studies in Pakistan investigated the impact of different factors on road crashes but did not consider the temporal stability of crash data. This means that the recommendations based on these studies are not fully effective, as the impact of certain factors may change over time. To address this gap in the literature, this study aims to identify the factors contributing to crash severity in road crashes and examine how their impact varies over time. In this comprehensive study, we utilized Generalised Linear Model (GLM) on the crash data between the years 2013 to 2017, encompassing a total sample of 802 road crashes occurred on the N-5 road section in Pakistan, a 429-kilometer stretch connecting two big cities of Pakistan, i.e., Peshawar and Lahore. The purpose of the GLM was to quantify the temporal stability of the factors contributing crash severity in each year from 2013 to 2017. Within this dataset, 60% (n = 471) were fatal crashes, while the remaining 40% (n = 321) were non-fatal. The results revealed that the factors including the day of the week, the location of the crashes, weather conditions, causes of the crashes, and the types of vehicles involved, exhibited the temporal instability over time. In summary, our study provides in-depth insights aimed at reducing crash severity and potentially aiding in the development of effective crash mitigation policies in Pakistan and other nations having similar road safety problems. This research holds great promise in exploring the dynamic safety implications of emerging transportation technologies, particularly in the context of the widespread adoption of connected and autonomous vehicles.

Respiratory modulation of the heart rate: A potential biomarker of cardiorespiratory function in human.

In recent decade, wearable digital devices have shown potentials for the discovery of novel biomarkers of humans' physiology and behavior. Heart rate (HR) and respiration rate (RR) are most crucial bio-signals in humans' digital phenotyping research. HR is a continuous and non-invasive proxy to autonomic nervous system and ample evidence pinpoints the critical role of respiratory modulation of cardiac function. In the present study, we recorded longitudinal (7 days, 4.63 ± 1.52) HR and RR of 89 freely behaving human subjects (Female: 39, age 57.28 ± 5.67, Male: 50, age 58.48 ± 6.32) and analyzed their dynamics using linear models and information theoretic measures. While HR's linear and nonlinear characteristics were expressed within the plane of the HR-RR directed flow of information (HR→RR - RR→HR), their dynamics were determined by its RR→HR axis. More importantly, RR→HR quantified the effect of alcohol consumption on individuals' cardiorespiratory function independent of their consumed amount of alcohol, thereby signifying the presence of this habit in their daily life activities. The present findings provided evidence for the critical role of the respiratory modulation of HR, which was previously only studied in non-human animals. These results can contribute to humans' phenotyping research by presenting RR→HR as a digital diagnosis/prognosis marker of humans' cardiorespiratory pathology.

COVID-19 vaccine intercountry distribution inequality and its underlying factors: a combined concentration index analysis and multiple linear regression analysis.

Introduction: Inequitable access to COVID-19 vaccines among countries is a pressing global health issue. Factors such as economic power, political power, political stability, and health system strength contribute to disparities in vaccine distribution. This study aims to assess the inequality in vaccine distribution among countries based on these factors and identify their relationship with COVID-19 vaccine distribution. Methods: A Concentration Index (CI) analysis was conducted to evaluate inequalities in the distribution of COVID-19 vaccines among countries based on four separate variables: GDP per capita, political stability (PS), World Power Index (WPI), and Universal Health Coverage (UHC). Additionally, Multiple Linear Regression (MLR) analysis was employed to explore the relationship between vaccine distribution and these independent variables. Two vaccine distribution variables were utilized for result reliability. Results: The analysis revealed significant inequalities in COVID-19 vaccine distribution according to the countries' GDP/capita, PS, WPI, and UHC. However, the multiple linear regression analysis showed that there is no significant relationship between COVID-19 vaccine distribution and the countries' GDP/capita and that UHC is the most influential factor impacting COVID-19 vaccine distribution and accessibility. Discussion: The findings underscore the complex interplay between economic, political, and health system factors in shaping vaccine distribution patterns. To improve the accessibility to vaccines in future pandemics, Global Health Governance (GHG) and countries should consider working on three areas; enhance political stabilities in countries, separate the political power from decision-making at the global level and most importantly support countries to achieve UHC.

The entropy rate of Linear Additive Markov Processes.

This work derives a theoretical value for the entropy of a Linear Additive Markov Process (LAMP), an expressive but simple model able to generate sequences with a given autocorrelation structure. Our research establishes that the theoretical entropy rate of a LAMP model is equivalent to the theoretical entropy rate of the underlying first-order Markov Chain. The LAMP model captures complex relationships and long-range dependencies in data with similar expressibility to a higher-order Markov process. While a higher-order Markov process has a polynomial parameter space, a LAMP model is characterised only by a probability distribution and the transition matrix of an underlying first-order Markov Chain. This surprising result can be explained by the information balance between the additional structure imposed by the next state distribution of the LAMP model, and the additional randomness of each new transition. Understanding the entropy of the LAMP model provides a tool to model complex dependencies in data while retaining useful theoretical results. To emphasise the practical applications, we use the LAMP model to estimate the entropy rate of the LastFM, BrightKite, Wikispeedia and Reuters-21578 datasets. We compare estimates calculated using frequency probability estimates, a first-order Markov model and the LAMP model, also considering two approaches to ensure the transition matrix is irreducible. In most cases the LAMP entropy rates are lower than those of the alternatives, suggesting that LAMP model is better at accommodating structural dependencies in the processes, achieving a more accurate estimate of the true entropy.

A cross-sectional study on personal values of medical students: the differences from their instructors, their associations with mental wellbeing, and the influences of gender.

BACKGROUND: Personal values of Thai medical students have been observed to be diverging from those of their seniors, but the differences remain uncharacterized. Despite its potential association with mental wellbeing, the issue remain unexplored in the population. This study aimed to explore (1) the difference in personal values between medical students and instructors and (2) the association between student's value adherence to mental well-being and the interaction by gender. METHODS: An online survey was performed in 2022. Participants rated their adherence to five groups of values, namely, Self-Direction, Hedonism, Achievement & Power, Universalism & Benevolence, and Tradition. Participants also rated their mental wellbeing. Comparisons were made between the personal values of students and instructors. The association between the personal values of students and their mental wellbeing and the interaction between values and gender were analyzed in linear regression. RESULTS: Compared to instructors, students rated higher on Universalism & Benevolence, marginally higher on Hedonism, and lower on Tradition. Students' ratings on Self-Direction, Universalism & Benevolence, and Tradition predicted better mental wellbeing. Their rating on Hedonism predicted poorer mental wellbeing, the effect of which was marginally stronger in males. Ratings on Achievement & Power marginally predicted poorer mental wellbeing in females. CONCLUSION: Difference in personal values between medical students and instructors have been observed. Some of these values hold potentials over student's mental wellbeing. Curricular and medical school environmental accommodation for the changes in the characters of learners may be necessary to mitigate the adverse effects on their mental wellbeing and foster development of desirable professional characteristics.

Prevalence of dyslipidaemia within Polish nurses. Cross-sectional study - single and multiple linear regression models and ROC analysis.

BACKGROUND: Maintaining good health is vital not only for own well-being, but also to ensure high-quality patient care. The aim of this study was to evaluate the prevalence of dyslipidaemia and to determine the factors responsible for the development of this disorder among Polish nurses. Lipid profile disorders are the most prevalent and challenging risk factors for the development of cardiovascular disease. Nurses have significant potential and play a crucial role in providing care and treatment services. METHODS: This cross-sectional study involved nurses and included measurements of body weight composition (Tanita MC-980), body mass index, waist circumference, blood pressure (Welch Allyn 4200B), lipid profile, and fasting blood glucose (CardioChek PA). RESULTS: The results revealed that more than half of the nurses (60.09%) were overweight or obese, with 57.28% exhibiting elevated blood pressure, 32.25% having fasting glucose levels, and 69.14% experiencing dyslipidaemia. Multiple model evaluation using ROC curves demonstrated that multiple models accurately predicted hypercholesterolemia (AUC = 0.715), elevated LDL (AUC = 0.727), and elevated TC (AUC = 0.723) among Polish nurses. CONCLUSION: Comprehensive education programmes should be implemented that include the latest advances in cardiovascular disease prevention. Regular check-ups, as well as the promotion and availability of healthy food in hospital canteens, are essential.

Association between Life's Essential 8 score and high-sensitivity C-reactive protein: A cross-sectional study from NHANES 2015-2018.

BACKGROUND: Earlier studies showed a negative correlation between life's simple 7 (LS7) and high-sensitivity C-reactive protein (hs-CRP), but no association has been found between life's essential 8 (LE8), an improved version of LS7, and hs-CRP. HYPOTHESIS: This study investigated the association between LE8 and hs-CRP utilizing data from the National Health and Nutritional Examination Survey. METHODS: A total of 7229 adults were incorporated in our study. LE8 was scored according to American Heart Association guidelines, and LE8 was divided into health behaviors and health factors. Serum samples of the participants were used to measure hs-CRP. To investigate the association between LE8 and hs-CRP, weighted linear regression, and restricted cubic spline were utilized. RESULTS: Among 7229 participants, the average age was 48.03 ± 16.88 years, 3689 (51.2%) were females and the median hs-CRP was 1.92 (0.81-4.49) mg/L. In adjusted weighted linear regression, a negative correlation was observed between the LE8 score and hs-CRP. Compared with the low LE8 score, the moderate LE8 score ß was -0.533 (-0.646 to -0.420), and the high LE8 score ß was -1.237 (-1.376 to -1.097). Health behaviors and health factors were also negatively associated with hs-CRP. In stratified analyses, the negative correlation between LE8 and hs-CRP remained consistent across subgroups. CONCLUSION: There was a negative correlation between LE8 as well as its sub-indicator scores and hs-CRP. Maintaining a positive LE8 score may be conducive to lowering the level of hs-CRP.

An additive-multiplicative model for longitudinal data with informative observation times.

Designed clinical studies often assess outcomes at pre-planned time points. In most situations, standard statistical models, such as generalized linear mixed models and generalized additive models, are sufficient to depict the temporal trends of the outcome and produce valid inference. Complicating factors, however, do exist in practical data analyses. One complication arises when the outcome and observational processes are interdependent, that is, the observational process is informative; another challenge is patient characteristics may influence the longitudinally observed outcomes in non-additive ways, for example, by multiplicative factors. In this research, we extend the standard longitudinal models to accommodate informative observation through a more flexible modeling structure-one with additive-multiplicative components that do not require explicit specification of the dependency structure between the outcome and observation processes. Along this vein, we provide the essential theory for inference in such models. Simulation studies showed the proposed method performs well for finite-sample scenarios, and the method was applied to analyze a motivating example from an alcohol-associated hepatitis observational study.

Prediction of cross-border spread of the COVID-19 pandemic: A predictive model for imported cases outside China.

The COVID-19 pandemic has been present globally for more than three years, and cross-border transmission has played an important role in its spread. Currently, most predictions of COVID-19 spread are limited to a country (or a region), and models for cross-border transmission risk assessment remain lacking. Information on imported COVID-19 cases reported from March 2020 to June 2022 was collected from the National Health Commission of China, and COVID-19 epidemic data of the countries of origin of the imported cases were collected on data websites such as WHO and Our World in Data. It is proposed to establish a prediction model suitable for the prevention and control of overseas importation of COVID-19. Firstly, the SIR model was used to fit the epidemic infection status of the countries where the cases were exported, and most of the r2 values of the fitted curves obtained were above 0.75, which indicated that the SIR model could well fit different countries and the infection status of the region. After fitting the epidemic infection status data of overseas exporting countries, on this basis, a SIR-multiple linear regression overseas import risk prediction combination model was established, which can predict the risk of overseas case importation, and the established overseas import risk model overall P <0.05, the adjusted R2 = 0.7, indicating that the SIR-multivariate linear regression overseas import risk prediction combination model can obtain better prediction results. Our model effectively estimates the risk of imported cases of COVID-19 from abroad.

Estimating genetic parameters of digital behavior traits and their relationship with production traits in purebred pigs.

BACKGROUND: With the introduction of digital phenotyping and high-throughput data, traits that were previously difficult or impossible to measure directly have become easily accessible, offering the opportunity to enhance the efficiency and rate of genetic gain in animal production. It is of interest to assess how behavioral traits are indirectly related to the production traits during the performance testing period. The aim of this study was to assess the quality of behavior data extracted from day-wise video recordings and estimate the genetic parameters of behavior traits and their phenotypic and genetic correlations with production traits in pigs. Behavior was recorded for 70 days after on-test at about 10 weeks of age and ended at off-test for 2008 female purebred pigs, totaling 119,812 day-wise records. Behavior traits included time spent eating, drinking, laterally lying, sternally lying, sitting, standing, and meters of distance traveled. A quality control procedure was created for algorithm training and adjustment, standardizing recording hours, removing culled animals, and filtering unrealistic records. RESULTS: Production traits included average daily gain (ADG), back fat thickness (BF), and loin depth (LD). Single-trait linear models were used to estimate heritabilities of the behavior traits and two-trait linear models were used to estimate genetic correlations between behavior and production traits. The results indicated that all behavior traits are heritable, with heritability estimates ranging from 0.19 to 0.57, and showed low-to-moderate phenotypic and genetic correlations with production traits. Two-trait linear models were also used to compare traits at different intervals of the recording period. To analyze the redundancies in behavior data during the recording period, the averages of various recording time intervals for the behavior and production traits were compared. Overall, the average of the 55- to 68-day recording interval had the strongest phenotypic and genetic correlation estimates with the production traits. CONCLUSIONS: Digital phenotyping is a new and low-cost method to record behavior phenotypes, but thorough data cleaning procedures are needed. Evaluating behavioral traits at different time intervals offers a deeper insight into their changes throughout the growth periods and their relationship with production traits, which may be recorded at a less frequent basis.

Penalized weighted smoothed quantile regression for high-dimensional longitudinal data.

Quantile regression, known as a robust alternative to linear regression, has been widely used in statistical modeling and inference. In this paper, we propose a penalized weighted convolution-type smoothed method for variable selection and robust parameter estimation of the quantile regression with high dimensional longitudinal data. The proposed method utilizes a twice-differentiable and smoothed loss function instead of the check function in quantile regression without penalty, and can select the important covariates consistently using the efficient gradient-based iterative algorithms when the dimension of covariates is larger than the sample size. Moreover, the proposed method can circumvent the influence of outliers in the response variable and/or the covariates. To incorporate the correlation within each subject and enhance the accuracy of the parameter estimation, a two-step weighted estimation method is also established. Furthermore, we prove the oracle properties of the proposed method under some regularity conditions. Finally, the performance of the proposed method is demonstrated by simulation studies and two real examples.

Evaluation of surface roughness, wettability and adhesion of multispecies biofilm on 3D-printed resins for the base and teeth of complete dentures.

OBJECTIVE: This study evaluated the surface roughness, wettability and adhesion of multispecies biofilms (Candida albicans, Staphylococcus aureus and Streptococcus mutans) on 3D-printed resins for complete denture bases and teeth compared to conventional resins (heat-polymerized acrylic resin; artificial pre-fabricated teeth). METHODOLOGY: Circular specimens (n=39; 6.0 mm Ø × 2.0 mm) of each group were subjected to roughness (n=30), wettability (n=30) and biofilm adhesion (n=9) tests. Three roughness measurements were taken by laser confocal microscopy and a mean value was calculated. Wettability was evaluated by the contact angle of sessile drop method, considering the mean of the three evaluations per specimen. In parallel, microorganism adhesion to resin surfaces was evaluated using a multispecies biofilm model. Microbial load was evaluated by determining the number of Colony Forming Units (CFU/mL) and by scanning electron microscopy (SEM). Data were subjected to the Wald test in a generalized linear model with multiple comparisons and Bonferroni adjustment, as well as two-way ANOVA (α=5%). RESULTS: The roughness of the conventional base resin (0.01±0.04) was lower than that of the conventional tooth (0.14±0.04) (p=0.023) and 3D-printed base (0.18±0.08) (p<0.001). For wettability, conventional resin (84.20±5.57) showed a higher contact angle than the 3D-printed resin (60.58±6.18) (p<0.001). Higher microbial loads of S. mutans (p=0.023) and S. aureus (p=0.010) were observed on the surface of the conventional resin (S. mutans: 5.48±1.55; S. aureus: 7.01±0.57) compared to the 3D-printed resin (S. mutans: 4.11±1.96; S. aureus: 6.42±0.78). The adhesion of C. albicans was not affected by surface characteristics. The conventional base resin showed less roughness than the conventional dental resin and the printed base resin. CONCLUSION: The 3D-printed resins for base and tooth showed less hydrophobicity and less adhesion of S. mutans and S. aureus than conventional resins.

[Alcohol Abstinence and Accelerated Biological Aging Among Middle-Aged and Older Adults: Evidence From the UK Biobank]. / ä¸­è€å¹´ç¾¤ä½“é ’ç²¾æˆ’æ–­ä¸Žç”Ÿç‰©è¡°è€åŠ é€Ÿçš„å ³ç³»ï¼šåŸºäºŽè‹±å›½ç”Ÿç‰©é“¶è¡Œæ•°æ®åº“çš„ç ”ç©¶.

Objective: To investigate the longitudinal association between alcohol abstinence and accelerated biological aging among middle-aged and older adults and to explore the potential effect modifiers influencing the association. Methods: Utilizing the clinico-biochemical and anthropometric data from the baseline and first repeat survey of the UK Biobank (UKB), we employed the Klemera and Doubal method (KDM) to construct the biological age (BA) and calculate BA acceleration. Change analysis based on multivariate linear regression models was employed to explore the association between changes in alcohol abstinence and changes in BA acceleration. Age, sex, smoking status, tea and coffee consumption, and body mass index were considered as the stratification factors for conducting stratified analysis. Results: A total of 5 412 participants were included. Short-term alcohol abstinence (ß=1.00, 95% confidence interval [CI]: 0.15-1.86) was found to accelerate biological aging when compared to consistent never drinking, while long-term abstinence (ß=-0.20, 95% CI: -1.12-0.71) did not result in a significant acceleration of biological aging. Body mass index may be a potential effect modifier. Conclusion: Short-term alcohol abstinence was associated with accelerated biological aging, but the effect gradually diminishes over extended periods of abstinence.

The Association of Oncology Provider Density With Black-White Disparities in Cancer Mortality in US Counties.

BACKGROUND: Black-White racial disparities in cancer mortality are well-documented in the US. Given the estimated shortage of oncologists over the next decade, understanding how access to oncology care might influence cancer disparities is of considerable importance. We aim to examine the association between oncology provider density in a county and Black-White cancer mortality disparities. METHODS: An ecological study of 1048 US counties was performed. Oncology provider density was estimated using the 2013 National Plan and Provider Enumeration System data. Black:White cancer mortality ratio was calculated using 2014-2018 age-standardized cancer mortality rates from State Cancer Profiles. Linear regression with covariate adjustment was constructed to assess the association of provider density with (1) Black:White cancer mortality ratio, and (2) cancer mortality rates overall, and separately among Black and White persons. RESULTS: The mean Black:White cancer mortality ratio was 1.12, indicating that cancer mortality rate among Black persons was on average 12% higher than that among White persons. Oncology provider density was significantly associated with greater cancer mortality disparities: every 5 additional oncology providers per 100 000 in a county was associated with a .02 increase in the Black:White cancer mortality ratio (95% CI: .007 to .03); however, the unexpected finding may be explained by further analysis showing that the relationship between oncology provider density and cancer mortality was different by race group. Every 5 additional oncologists per 100 000 was associated with a 1.6 decrease per 100 000 in cancer mortality rates among White persons (95% CI: -3.0 to -.2), whereas oncology provider density was not associated with cancer mortality among Black persons. CONCLUSION: Greater oncology provider density was associated with significantly lower cancer mortality among White persons, but not among Black persons. Higher oncology provider density alone may not resolve cancer mortality disparities, thus attention to ensuring equitable care is critical.

Our study provides timely information to address the growing concern about the need to increase oncology supply and the impact it might have on racial disparities in cancer outcomes. This analysis of counties across the US is the first study to estimate the association of oncology provider density with Black-White racial disparities in cancer mortality. We show that having more oncology providers in a county is associated with significantly lower cancer mortality among the White population, but is not associated with cancer mortality among the Black population, thereby leading to a disparity. Our findings suggest that having more oncology providers alone may be insufficient to overcome existing disadvantages for Black patients to access and use high-quality cancer care. These findings have important implications for addressing racial disparities in cancer outcomes that are persistent and well-documented in the US.

Comparing the performance of two-stage residual inclusion methods when using physician's prescribing preference as an instrumental variable: unmeasured confounding and noncollapsibility.

Aim: The first objective is to compare the performance of two-stage residual inclusion (2SRI), two-stage least square (2SLS) with the multivariable generalized linear model (GLM) in terms of the reducing unmeasured confounding bias. The second objective is to demonstrate the ability of 2SRI and 2SPS in alleviating unmeasured confounding when noncollapsibility exists. Materials & methods: This study comprises a simulation study and an empirical example from a real-world UK population health dataset (Clinical Practice Research Datalink). The instrumental variable (IV) used is based on physicians' prescribing preferences (defined by prescribing history). Results: The percent bias of 2SRI in terms of treatment effect estimates to be lower than GLM and 2SPS and was less than 15% in most scenarios. Further, 2SRI was found to be robust to mild noncollapsibility with the percent bias less than 50%. As the level of unmeasured confounding increased, the ability to alleviate the noncollapsibility decreased. Strong IVs tended to be more robust to noncollapsibility than weak IVs. Conclusion: 2SRI tends to be less biased than GLM and 2SPS in terms of estimating treatment effect. It can be robust to noncollapsibility in the case of the mild unmeasured confounding effect.

Replace the Linear No-threshold Model with a Risk-informed Targeted Approach to Radiation Protection.

ABSTRACT: The linear no-threshold (LNT) model may be useful as a simple basis for developing radiation protection regulations and standards, but it bears little resemblance to scientific reality and is probably overly conservative at low doses and low dose rates. This paper is an appeal for a broader view of radiation protection that involves more than just optimization of radiation dose. It is suggested that the LNT model should be replaced with a risk-informed, targeted approach to limitation of overall risks, which include radiation and other types of risks and accidents/incidents. The focus should be on protection of the individual. Limitation of overall risk does not necessarily always equate to minimization of individual or collective doses, but in some cases it might. Instead, risk assessment (hazards analysis) should be performed for each facility/and or specific job or operation (straightforward for specialized work such as radiography), and this should guide how limited resources are used to protect workers and the public. A graded approach could be used to prioritize the most significant risks and identify exposure scenarios that are unlikely or non-existent. The dose limits would then represent an acceptable level of risk, below which no further reduction in dose would be needed. Less resources should be spent on ALARA and tracking small individual and collective doses. Present dose limits are thought to be conservative and should suffice in general. Two exceptions are possibly the need for a lower (lifetime) dose limit for lens of the eye for astronauts and raising the public limit to 5 mSv y -1 from 1 mSv y -1 . This would harmonize the public limit with the current limit for the embryo fetus of the declared pregnant worker. Eight case studies are presented that emphasize how diverse and complex radiation risks can be, and in some cases, chemical and industrial risks outweigh radiation risks. More focus is needed on prevention of accidents and incidents involving a variety of types of risks. A targeted approach is needed, and commitments should be complied with until they are changed or exemptions are granted. No criticism of regulators or nuclear industry personnel is intended here. Protection of workers and the public is everyone's goal. The question is how best to accomplish that.

A non-negative spike-and-slab lasso generalized linear stacking prediction modeling method for high-dimensional omics data.

BACKGROUND: High-dimensional omics data are increasingly utilized in clinical and public health research for disease risk prediction. Many previous sparse methods have been proposed that using prior knowledge, e.g., biological group structure information, to guide the model-building process. However, these methods are still based on a single model, offen leading to overconfident inferences and inferior generalization. RESULTS: We proposed a novel stacking strategy based on a non-negative spike-and-slab Lasso (nsslasso) generalized linear model (GLM) for disease risk prediction in the context of high-dimensional omics data. Briefly, we used prior biological knowledge to segment omics data into a set of sub-data. Each sub-model was trained separately using the features from the group via a proper base learner. Then, the predictions of sub-models were ensembled by a super learner using nsslasso GLM. The proposed method was compared to several competitors, such as the Lasso, grlasso, and gsslasso, using simulated data and two open-access breast cancer data. As a result, the proposed method showed robustly superior prediction performance to the optimal single-model method in high-noise simulated data and real-world data. Furthermore, compared to the traditional stacking method, the proposed nsslasso stacking method can efficiently handle redundant sub-models and identify important sub-models. CONCLUSIONS: The proposed nsslasso method demonstrated favorable predictive accuracy, stability, and biological interpretability. Additionally, the proposed method can also be used to detect new biomarkers and key group structures.