Multiple Predictor Variables Research Articles

Enhancing indoor PM2.5 predictions based on land use and indoor environmental factors by applying machine learning and spatial modeling approaches

The presence of fine particulate matter (PM2.5) indoors constitutes a significant component of overall PM2.5 exposure, as individuals spend 90% of their time indoors; however, personal monitoring for large cohorts is often impractical. In light of this, this study seeks to employ a novel geospatial artificial intelligence (Geo-AI) coupled with machine learning (ML) approaches to develop indoor PM2.5 models. Multiple predictor variables were collected from 102 residential households, including meteorological data; elevation; land use; indoor environmental factors including human activities, building characteristics, infiltration factors, and real-time measurements; and various other factors. Geo-AI, which integrates land use regression, inverse distance weighting, and ML algorithms, was utilized to construct outdoor PM2.5 and PM10 estimates for residential households. The most influential variables were identified via correlation analysis and stepwise regression. Three ML methods, namely support vector machine, multiple linear regression, and multilayer perceptron (MLP) were used to estimate indoor PM2.5 concentration. Then, MLP was employed to blend three ML algorithms. The resulting model demonstrated commendable performance, achieving a 10-fold cross-validation R2 of 0.92 and a root mean square error of 2.3 μg/m3 for indoor PM2.5 estimations. Notably, the combination of Geo-AI and ensembled ML models in this study outperformed all other individual models. In addition, the present study pointed out the most influential factors for indoor PM2.5 model were outdoor PM2.5, PM2.5/PM10 ratio, sampling month, infiltration factor, located near factory, cleaning frequency, number of door entrance linked with outdoor, and wall material. Further exploration of diverse ensemble model formats to integrate estimates from different models could enhance overall performance. Consequently, the potential applications of this model extend to estimating real individual exposure to PM2.5 for further epidemiological research. Moreover, the model offers valuable insights for efficient indoor air quality management and control strategies.

The association between ethnoracial characteristics and subjective well-being: a perspective considering social inequalities

ABSTRACT This study explored the association between subjective well-being (measured by life satisfaction) and ethnoracial characteristics (i.e. self-ascription, skin color, and speaking an Indigenous language) in Mexico and the role of socioeconomic inequalities in mediating this relationship. The emerging questions were: ‘What are the associations between subjective well-being and ethnoracial characteristics in Mexico?’ and ‘Are these associations affected by socioeconomic inequalities?.’ A multinomial logistic analysis was conducted, which estimates associations among multiple categories and predictor variables, using the data from the 2019 Project on Ethnoracial Discrimination in Mexico (PRODER, N = 7,037). The results indicated that Indigenous and white self-ascriptions were positively related to life satisfaction, whereas Mestizo and African Mexican identification did not have any association. Concerning skin color, the digital colorimeter measurements indicated that those with a lighter skin color had greater probabilities of having higher levels of life satisfaction. Additionally, those who reported speaking or who have parents speaking an Indigenous language were less likely to be in higher categories of life satisfaction. These results have central implications for the design and implementation of inclusive public policies, and for the design and modification of public programs.

Overall survival (OS) in a u.s. Asian population with stage IV NSCLC with EGFR mutations treated with first-line (1L) osimertinib (Osi) compared to earlier generation (Gen) of TKIs or sequential treatment (Tx).

e20597 Background: Osi, a 3rd-gen EGFR tyrosine kinase inhibitor (TKI), was approved as 1L tx for metastatic non-small-cell lung cancer (NSCLC) with EGFR mutations (ex19del or L858R) in 2018. This was based on the FLAURA trial, showing improved progression-free survival and OS of 1L osi compared to 1st-gen TKIs. Despite this, subgroup analyses revealed no OS difference in Asian or L858R patients (pts). Studies such as GioTag and UpSwinG showed better median OS in Asians with ex19del mutations on sequential afatinib and osi tx, prompting the question if sequencing of tx may also benefit L858R pts. We conducted this analysis of real-world outcomes in U.S. Asian pts with EGFR mutated NSCLC treated with 1L osi, 1st- or 2nd- gen TKIs (prior-TKIs-only), or sequential 1st- or 2nd- gen TKI followed by osi (sequential-TKI-osi). Methods: We conducted a single-institution IRB-approved retrospective study at NYU, including Asian pts diagnosed with stage IV NSCLC with EGFR ex19del or L858R, who received any gen of TKIs from 1/1/2010 to 1/13/2023. We compared 3-year (3y) OS based on tx and mutation subtypes, excluding pts with less than 3 years of follow-up. The analysis utilized the Cox proportional-hazards model to calculate hazard ratios (HR) and P values of OS. Survival curves were estimated using the Kaplan-Meier method. The log-rank tests were used to assess survival differences between tx groups. Additionally, a multivariable Cox proportional-hazards model explored the association between pts' survival time and multiple predictor variables. Results: We analyzed 139 cases: 103 (74%) females, 68 (49%) L858R, 113 (81%) never smokers, and age 31-96 years. The 3y OS analysis revealed no significant difference in the OS in L858R pts who received prior-TKIs-only (p = 0.83) or sequential-TKI-osi (p = 0.90), compared to 1L osi (median OS not reached in all three groups). However, in ex19del pts, prior-TKIs-only (HR 0.31, 95% CI 0.13-0.76) and sequential-TKI-osi (HR 0.30, 95% CI 0.11-0.85) txs showed superior OS compared to 1L osi, with a median OS of 24.7 mo in 1L osi and not reached in other two txs. Among all predictor variables (tx, age, sex, EGFR subtypes, and smoking status), only age had a significant but small impact on OS (HR 1.03, 95% CI 1.01-1.06). Conclusions: Our real-world analysis revealed that Asian stage IV NSCLC pts with L858R treated with 1L osi had a similar 3y OS compared to those treated with prior-TKIs-only and sequential-TKI-osi. Whereas, 1L osi was inferior to both txs in OS for ex19del pts. This finding may be unique and significant in Asian ex19del pts, though our analysis is limited by the small cohort of a retrospective study. Larger cohorts from retrospective studies or prospective trials are needed to investigate the response of Asian ex19del pts to 1L osi, while underling the need for novel tx options for L858R pts.

Orthognathic Surgery in the US. What are the Risk Factors for Readmission?

Purpose: Contemporary orthognathic surgery is safe and predicable. However, there are opportunities for further improvement. The purpose of this study was to estimate the frequency and identify risk factors for readmission following orthognathic surgery in the US. Materials and methods: A retrospective cohort study was conducted using the Nationwide Readmissions Database (NRD) on patients who underwent orthognathic surgery in 2017 and 2018. There were multiple heterogenous predictor variables that were broadly comprised of patient characteristics and hospitalization characteristics. The primary outcome variable was readmission. Logistic regression analysis was used to determine risk factors for hospital readmission. A P-value less than .05 was considered statistically significant. Results: The final study sample consisted of 8578 patients (mean age, 27.2 years), of whom 74 patients (0.9%) readmitted. Relative to a length of stay (LOS) of 0 to 2 days, a LOS of >2 days (OR 1.90, P < .05) was a risk factor for readmission. Patients with acute post procedural pain were 3 times more likely to readmit ( P < .05). Conclusion: Patients with an LOS of >2 days were at risk for readmission relative to patients with an LOS of 0 to 2 days. Post-procedural pain was also a significant risk factor for readmission. Finally, patients with mandibular hypoplasia were less likely to readmit.

A Data Mining Approach for Health Transport Demand

Efficient planning and management of health transport services are crucial for improving accessibility and enhancing the quality of healthcare. This study focuses on the choice of determinant variables in the prediction of health transport demand using data mining and analysis techniques. Specifically, health transport services data from Asturias, spanning a seven-year period, are analyzed with the aim of developing accurate predictive models. The problem at hand requires the handling of large volumes of data and multiple predictor variables, leading to challenges in computational cost and interpretation of the results. Therefore, data mining techniques are applied to identify the most relevant variables in the design of predictive models. This approach allows for reducing the computational cost without sacrificing prediction accuracy. The findings of this study underscore that the selection of significant variables is essential for optimizing medical transport resources and improving the planning of emergency services. With the most relevant variables identified, a balance between prediction accuracy and computational efficiency is achieved. As a result, improved service management is observed to lead to increased accessibility to health services and better resource planning.

Estimating morning and evening commute period O3 concentration in Taiwan using a fine spatial-temporal resolution ensemble mixed spatial model with Geo-AI technology

Elevated levels of ground-level ozone (O3) can have harmful effects on health. While previous studies have focused mainly on daily averages and daytime patterns, it's crucial to consider the effects of air pollution during daily commutes, as this can significantly contribute to overall exposure. This study is also the first to employ an ensemble mixed spatial model (EMSM) that integrates multiple machine learning algorithms and predictor variables selected using Shapley Additive exExplanations (SHAP) values to predict spatial-temporal fluctuations in O3 concentrations across the entire island of Taiwan. We utilized geospatial-artificial intelligence (Geo-AI), incorporating kriging, land use regression (LUR), machine learning (random forest (RF), categorical boosting (CatBoost), gradient boosting (GBM), extreme gradient boosting (XGBoost), and light gradient boosting (LightGBM)), and ensemble learning techniques to develop ensemble mixed spatial models (EMSMs) for morning and evening commute periods. The EMSMs were used to estimate long-term spatiotemporal variations of O3 levels, accounting for in-situ measurements, meteorological factors, geospatial predictors, and social and seasonal influences over a 26-year period. Compared to conventional LUR-based approaches, the EMSMs improved performance by 58% for both commute periods, with high explanatory power and an adjusted R2 of 0.91. Internal and external validation procedures and verification of O3 concentrations at the upper percentile ranges (in 1%, 5%, 10%, 15%, 20%, and 25%) and other conditions (including rain, no rain, weekday, weekend, festival, and no festival) have demonstrated that the models are stable and free from overfitting issues. Estimation maps were generated to examine changes in O3 levels before and during the implementation of COVID-19 restrictions. These findings provide accurate variations of O3 levels in commute period with high spatiotemporal resolution of daily and 50m * 50m grid, which can support control pollution efforts and aid in epidemiological studies.

The effect of electricity consumption determinants in household load forecasting models

Usually, household electricity consumption fluctuates, often driven by several electrical consumption determinants such as income, household size, and price. Recently, research studies on the investigation of predictor variables in household electricity consumption have increased especially in the developing and newly industrialized countries. However, the studies just focus on identifying the predictor variables of household electricity consumption that influence load forecasting models. In Tanzania, for instance, scholars found that using the “income” determinant improves the performance of a forecasting model. The scholars suggest without any empirical bases that adding more predictor variables would have improved the accuracy of the model. This study aims to analyze the effect of the number of predictor variables on household load forecasting performance based on Tanzania’s data. Nonlinear regression based on a Weibull function and multivariate adaptive regression splines approaches are used for this purpose. Our findings indicate that income, household size, and number of appliances are common predictor variables of household consumption in developing countries. The measured forecasting root-mean-square error (RMSE) when using income, household size, and the number of appliances is 0.8244, 1.2314, and 0.9868, respectively. Finally, we forecasted load using all three determinants and the RMSE dropped to 0.7031. Having obtained the smaller value of RMSE when all predictors are used reveals that the inclusion of all three predictor variables in load forecasting leads to a significant decrease in RMSE by 14.73%. Therefore, the study recommends using multiple predictor variables in load forecasting models to increase accuracy.

How Investment, Wage Rates, and Output Impact Screen Printers Need for Workers in Palangka Raya

This study aims to examine the impact of Capital, Wage Level, and Production Amount on Labor Absorption in the Screen Printing Industry in Palangka Raya City. The present study used the technique of multiple linear regression analysis. Multiple linear regression analysis is a statistical technique employed to assess the impact of multiple predictor variables (independent variables) on a given dependent variable. This study employs a quantitative research methodology intending to substantiate a hypothesis. Data was collected using observation, interviews, questionnaires, and documentation. A simple random selection procedure was employed to choose a sample of 38 respondents from the screen printing sector for this study. The findings derived from the data analysis indicate that the variables of wage rate and productivity exhibit a statistically significant and favorable impact on employment within the screen printing industry. In the context of the screen printing sector, it is seen that capital exerts a detrimental and statistically negligible effect on work

Declarations of Independence: How Embedded Multicollinearity Errors Affect Dosimetric and Other Complex Analyses in Radiation Oncology

The statistical technique of multiple regression, commonly referred to as “multivariable regression,” is often used in clinical research to quantify the relationships between multiple predictor variables and a single outcome variable of interest. The foundational theory underpinning multivariable regression assumes that all predictor variables are independent of one another. In other words, the effect of each independent variable is measured by its contribution to the regression equation while all other variables remain unchanged. In the presence of correlations between two or more variables, however, it is impossible to change one variable without a consequent change in the variable(s) it is linked to. This condition, known as “multicollinearity,” can introduce errors into multivariable regression models by affecting estimates of the regression coefficients that quantify the relationship between individual predictor variables and the outcome variable. Errors that arise due to violations of the multicollinearity assumption are of special interest to radiation oncology researchers. Because of high levels of correlation among variables derived from points along individual organ dose-volume histogram (DVH) curves, as well as strong intercorrelations among dose-volume parameters in neighboring organs, dosimetric analyses are particularly subject to multicollinearity errors. For example, dose-volume parameters for the heart are strongly correlated not only with other points along the heart DVH curve but are likely also correlated with dose-volume parameters in neighboring organs such as the lung. In this paper, we describe the problem of multicollinearity in accessible terms and discuss examples of violations of the multicollinearity assumption within the radiation oncology literature. Finally, we provide recommendations regarding best practices for identifying and managing multicollinearity in complex data sets.

Fine‐scale variation in the effect of the cushion plantAzorella selagoon vascular plants, mosses, hepatics and lichens in the sub‐Antarctic

AbstractQuestionPlant–plant interactions can strongly influence community structure and composition. The outcome of these interactions can vary considerably across space and is often linked to environmental conditions, with, for example, a higher prevalence of facilitative interactions typically being observed under greater environmental severity. To date, most studies have documented shifts from competitive to facilitative (or neutral) plant–plant and plant–lichen interactions along gradients of increasing environmental severity from pairwise interspecific interactions. However, few studies have examined if the outcome of these interactions for different taxonomic groups is dependent on environmental conditions across multiple environmental stress gradients.LocationSub‐Antarctic Marion Island.MethodsWe examine community‐level variation in the response of four taxa (i.e., vascular plants, hepatics, mosses, and lichens) to an interaction with a long‐lived cushion plant species (Azorella selago) that ameliorates microenvironmental conditions, testing how the effect of the cushion plant on the taxa varies along multiple stress gradients at the scale of a landform.ResultsContrary to expectations, even when considering multiple proximate predictor variables, fine‐scale spatial variation in the effect ofA. selagoon the taxa could not be explained. However, the outcome of the interaction withA. selagodiffered between taxonomic groups, with vascular plants benefitting and the non‐vascular taxa experiencing neutral or negative impacts.ConclusionsThis study highlights that the impacts of biotic interactions cannot always be generalized across plant groups, and that it is necessary to consider taxon‐specific responses when predicting community‐level impacts of biotic interactions. More generally, we demonstrate how complex spatial variation in environmental stressors can be explicitly considered when modelling variation in the outcome of plant–plant interactions.

Credit Management Practices and Financial Performance of Commercial Banks in Rwanda: A Case of Access Bank Plc

This paper examined the effect of credit management practices on financial performance of commercial banks in Rwanda with reference of Access Bank Plc. The specific objectives are to assess the effect of credit rating on performance of Access Bank Plc, to determine the effect of credit monitoring on performance of Access Bank Plc and to examine the effect of credit recovery on performance of Access Bank Plc. The researcher used liquidity theory of credit and the information theory of credit. The study used descriptive and correlational research design. The target population was 164 employees of Access Bank Plc. The study collected data from a sample size of 116 employees of Access Bank Plc at Head office in Kigali City. It used questionnaire and financial statements of Access Bank Plc to collect data and descriptive statistics and multiple regression model to analyse data. Descriptive statistics such as mean, frequency and standard deviation was used. The multiple regression analysis was use to assess the effects of multiple predictor variables on the dependent measure. Results from the first objective show that that access bank assessment of the capacity to pay loan was strongly agreed by 44.7% was used as a credit rating component at Access Bank Plc. Access Bank has used credit reference report as strongly agreed by 30.1% .Results from the second objective indicated that credit term was adopted as strongly agreed by 54.4%, credit standards as strongly agreed by 36.9 %, 40.8%, credit limits, 30.1% strongly agreed. Results to the third objective show models of loan repayment platform demonstrated that 53.4% of respondents strongly agreed with the statements. Therefore, 44.7 strongly agreed that the Access bank is continually assessment as 33.0%. Results 54.9% strongly agreed with legal enforcements. The study recommended that researcher’s asses this factors impact on credit management practices, its execution and financial performance. Keywords: Credit management, Credit Policies, Credit monitoring, debt recovery, financial performance

Estimating the daily average concentration variations of PCDD/Fs in Taiwan using a novel Geo-AI based ensemble mixed spatial model

It is generally established that PCDD/Fs is harmful to human health and therefore extensive field research is necessary. This study is the first to use a novel geospatial-artificial intelligence (Geo-AI) based ensemble mixed spatial model (EMSM) that integrates multiple machine learning algorithms and geographic predictor variables selected using SHapley Additive exPlanations (SHAP) values to predict spatial-temporal fluctuations in PCDD/Fs concentrations across the entire island of Taiwan. Daily PCDD/F I-TEQ levels from 2006 to 2016 were used for model construction, while external data was used for validating model dependability. We utilized Geo-AI, incorporating kriging, five machine learning, and ensemble methods (combinations of the aforementioned five models) to develop EMSMs. The EMSMs were used to estimate long-term spatiotemporal variations in PCDD/F I-TEQ levels, considering in-situ measurements, meteorological factors, geospatial predictors, social and seasonal influences over a 10-year period. The findings demonstrated that the EMSM was superior to all other models, with an increase in explanatory power reaching 87 %. The results of spatial-temporal resolution show that the temporal fluctuation of PCDD/F concentrations can be a result of weather circumstances, while geographical variance can be the result of urbanization and industrialization. These results provide accurate estimates that support pollution control measures and epidemiological studies.

Outcomes in dogs with congenital extrahepatic portosystemic shunts treated with surgical ligation or medical management.

The objective of this study was to evaluate differences in outcomes in dogs treated for extrahepatic portosystemic shunts (EHPSS) by either complete suture ligation, partial suture ligation or medical management. This wasa retrospective, single institutional study. Dogs (n = 152) with EHPSS treated with suture ligation (n = 62), surgery with no ligation (n = 2), or medical management (n = 88). Medical records were reviewed for data on signalment, treatment variables, complications, and outcome. Kaplan-Meier plots were generated to assess survival across groups. Cox's proportional hazard models were used to assess the relationship between survival times and multiple predictor variables. For outcomes of interest, backwards, stepwise regression was performed (p < 0.05). Complete suture ligation was possible in 46/64 (71.9%) of dogs where surgical attenuation was attempted. One dog was euthanized following partial suture ligation due to suspected portal hypertension. Dogs with complete suture ligation of the EHPSS had a significantly longer median survival time (MST) compared to the medical management group (MST not reached vs. 1730 days [p < 0.001]). Complete resolution of clinical signs (without the need for further medical treatment or dietary changes) was achieved in 16/20 (80.0%) dogs with complete suture ligation and 4/10 (40.0%) dogs with partial suture ligation of their EHPSS. Suture ligation (complete or partial) for the treatment of EHPSS, where clinically possible, yielded the best clinical outcome and increased longevity compared to medical management in this study. While medical management for the treatment of EHPSS in dogs is a valid treatment option, better clinical outcomes are achieved with surgical intervention.

Real-world clinical outcomes in a U.S. Asian population with stage IV NSCLC treated with osimertinib (Osi) stratified by EGFR subtype.

e21128 Background: EGFR mutations are observed in 40-50% of Asian populations with NSCLC compared to 10-15% in Caucasian populations, with EGFR exon 19 deletion (ex19del) and exon 21 L858R as the most common activating mutations. The FLAURA trial demonstrated PFS and OS benefit of osi, a 3rd generation tyrosine kinase inhibitor (TKI), compared to earlier generation TKIs with a median PFS (mPFS) of 19 months (mos) and overall survival (OS) of 38.6 mos. Subgroup analysis, however, suggested this survival benefit was not seen in Asian patients (pts) or in pts with the L858R mutation. Further analysis of the 322 Asian pts enrolled at Asian sites demonstrated a mPFS of 16.5 mos (HR 0.54, p &lt; 0.0001) with osi compared to 11.0 mos with SOC EGFR TKI, but no difference on two-year OS (2y OS) (HR 0.65, 95% CI 0.42-1.02). We evaluated the 2y OS in Asian pts treated in the U.S. with stage IV NSCLC with first-line (1L) osi. We further explored the 2y OS of Asian pts who received an earlier generation EGFR TKI prior to osi. Methods: We conducted a single institution IRB-approved retrospective study of Asian pts treated at NYU Perlmutter Cancer Center with stage IV NSCLC with EGFR ex19del or L858R mutations treated with osi from 1/1/2010 – 2/1/2021. 2y OS was compared based on EGFR mutations and receipt of 1L osi vs an earlier generation EGFR TKI prior to osi (TKI-pretreated). Log-rank test was used to calculate the P values of Kaplan-Meier curves subgroups. Cox proportional-hazards model was used to investigate the association between the survival time of pts and multiple predictor variables including age, sex, EGFR subtypes (L858R or ex19del) and smoking status. Results: Of 117 total cases: 85 (73%) were female, 32 (36%) were male. 57 (49%) had ex19del and 60 (51%) had L858R. 94 (80%) were nonsmokers. Age range at diagnosis with stage IV disease was 31-96 years. The analysis revealed no significant difference in 2y OS observed between the 1L osi vs. TKI-pretreated groups (HR 1.90, 95%CI 0.93-3.89). However, the subgroup analysis showed that the 2y OS was inferior in the 1L osi group compared to the TKI-pretreated group in pts with ex19del (HR 2.99, 95%CI 1.12 -7.96), but not in those with L858R (HR 1.29, 95%CI 0.43-3.86). No significant effect on 2y OS was observed from age (p = 0.19), sex (p = 0.50), EGFR subtype (p = 0.19) or smoking status (p = 0.67). Conclusions: In accordance with the FLAURA data, our real-world analysis revealed that Asian pts treated with 1L osi was comparable to pts treated with 1st- or 2nd- generation TKIs. Furthermore, our data showed that the use of 1L osi had a lower 2y OS in Asian pts with ex19del compared to those pre-treated with TKIs, but this was not the case with L858R. Although small numbers, the results suggest that ex19del and L858R should be considered differently when considering 1L treatment options and further investigation into alternative options, such as combination therapies, warrants exploration.

Comparison of Caregivers' Burden among Family Members of Patients with Severe Mental Disorders and Patients with Substance Use Disorder.

Objective: The burden on caregivers of patients with severe mental disorders is significantly higher than the care burden of patients with other medical conditions. Substance use disorder is also one of the most common psychiatric disorders that has negative effects on people's quality of life. This study was designed to investigate caregiver burden in severe mental disorders versus substance use disorder. Method : First-degree relatives of patients admitted to the Razi Psychiatric Hospital of Tehran with a diagnosis of schizophrenia, bipolar disorder type1, schizoaffective disorder, or substance use disorder entered this study. They completed the sociodemographic questionnaire for patients and caregivers and the Zarit burden interview for caregivers. Results: Our study shows that caregiver burden in substance use disorder has no significant difference with that in severe mental disorders (P > 0.05). In both groups, the highest spectrum of burden was moderate to severe. To find caregiver burden related factors, a general linear regression model with multiple predictor variables was fitted. In this model, caregivers' burden was significantly higher in patients with comorbidity (P = 0.007), poor compliance (P < 0.001), and in female caregivers (P = 0.013). Conclusion: Statistically speaking, the caregiver burden in substance use disorders is as severe as other mental disorders. The considerable burden on both groups necessitates serious efforts to minimize its negative effects.

A deep learning model based on multi-source data for daily tourist volume forecasting

ABSTRACT Demand forecasting is important for management and decision making in the tourism sector. However, research on deep learning forecasting, which combines multiple data sources, is still in the development phase. This study proposes a bidirectional long short-term memory (BiLSTM) forecasting method incorporating an attention mechanism (ATT-BiLSTM) that can better extract data features from a set of predictor variables consisting of multiple predictor variables (generated from historical tourist volume, search engine data, weather data and day off data). The research experimentally validates the effectiveness of the method using the famous Chinese tourist attraction Jiuzhaigou as a case study. The results show that the proposed model not only has better generalization ability but also significantly outperforms the four benchmark models, convolutional neural network (CNN), SVR, LSTM, and BiLSTM, in terms of prediction accuracy. In addition, we analyse the importance of the different predictor variables in the prediction model characteristics.

Smartphone prediction of skeletal muscle mass: model development and validation in adults

BackgroundSkeletal muscle is a large and clinically relevant body component that has been difficult and impractical to quantify outside of specialized facilities. Advances in smartphone technology now provide the opportunity to quantify multiple body surface dimensions such as circumferences, lengths, surface areas, and volumes. ObjectivesThis study aimed to test the hypothesis that anthropometric body measurements acquired with a smartphone application can be used to accurately estimate an adult’s level of muscularity. MethodsAppendicular lean mass (ALM) measured by DXA served as the reference for muscularity in a sample of 322 adults. Participants also had digital anthropometric dimensions (circumferences, lengths, and regional and total body surface areas and volumes) quantified with a 20-camera 3D imaging system. Least absolute shrinkage and selection operator (LASSO) regression procedures were used to develop the ALM prediction equations in a portion of the sample, and these models were tested in the remainder of the sample. Then, the accuracy of the prediction models was cross-validated in a second independent sample of 53 adults who underwent ALM estimation by DXA and the same digital anthropometric estimates acquired with a smartphone application. ResultsLASSO models included multiple significant demographic and 3D digital anthropometric predictor variables. Evaluation of the models in the testing sample indicated respective RMSEs in women and men of 1.56 kg and 1.53 kg and R2’s of 0.74 and 0.90, respectively. Cross-validation of the LASSO models in the smartphone application group yielded RMSEs in women and men of 1.78 kg and 1.50 kg and R2’s of 0.79 and 0.95; no significant differences or bias between measured and predicted ALM values were observed. ConclusionsSmartphone image capture capabilities combined with device software applications can now provide accurate renditions of the adult muscularity phenotype outside of specialized laboratory facilities. Am J Clin Nutr 2023;x:xx.This trial was registered at clinicaltrials.gov as NCT03637855 (https://clinicaltrials.gov/ct2/show/NCT03637855), NCT05217524 (https://clinicaltrials.gov/ct2/show/NCT05217524), and NCT03771417 (https://clinicaltrials.gov/ct2/show/NCT03771417).

Viscoelastic or Viscoplastic Glucose Theory (VGT #63): A Summary Report on the Annual Relative Risks of Developing Pancreatic, Liver, And Various Cancers Using Various Influential Factors Such As HbA1C, Glucose, Insulin Resistance, Lipids, Weight, Diet, Walking Steps and Metabolism Index from the Collected Data of a Type 2 Diabetes Patient Over an ~12+ Years Period Based on GH-Method: Math-Physical Medicine

HR+ HER2- T1 N0 M0 breast cancer has very low 5-year postoperative risk of relapse (&lt;5%) with current SoC treat- ment regimens: endocrine monotherapy or chemoendocrine com- bination therapy. Minimally aggressive treatment is ideal. Absent gene-profiling, histopathological features of the tumor are examined to predict risk of relapse. This paper establishes statistical evidence for use of an empirical prognostic index as a risk-based clinical decision aid where gene profiles are unavailable. Methods: A retrospective cohort (n=965) observed for 5 years was propensity score (PS) matched to correct baseline risk differences between chemoendocrine therapy and endocrine monotherapy treatment groups. PS were generated from logistic regression of pertinent histopathological covariates available to a clinician at the time of diagnosis onto treatment designation. Comparator groups were fur- ther equilibrated using Synthetic Minority Over-Sampling (SMOTE). Estimated treatment effects were assessed after propensity score- matching (PSM) and after SMOTE-normalized re-sampling. Results: Propensity score-matched groups (n=262) showed no difference in relapse rates between groups. Significant differences in histopatho- logical covariates remained between groups after PSM. SMOTE further minimized inter-group differences. Corresponding propen- sity score quartiles of the SMOTE groups (n=1000) were tested for proportional differences in relapse. No proportional differences in relapses were observed between groups in Q1-Q3. Proportionally, significantly more relapses occurred in the Q4 endocrine therapy group than in the Q4 chemoendocrine group. Conclusion: After matching, the PSM sample failed to produce generalizable results due to significant group imbalance for multiple predictor variables, whereas SMOTE re-sampling provided adequately risk-matched groups (standardized differences&lt;0.2) for treatment effect anal- ysis. Individuals with HR+ HER2- T1 N0 M0 breast cancer are over-treated if they have PS&lt;0.75, and are prescribed chemoen- docrine therapy, as no additional benefit was observed from this more aggressive treatment regimen. Conversely, individuals are under-treated, and at a significantly higher risk of relapse, if they have PS&gt;0.75 and are not prescribed chemotherapy

Overtreatment in Hormone Receptor Positive, HER2-, Axillary Node Negative, Non-Metastatic Early Breast Cancer

HR+ HER2- T1 N0 M0 breast cancer has very low 5-year postoperative risk of relapse (&lt;5%) with current SoC treat- ment regimens: endocrine monotherapy or chemoendocrine com- bination therapy. Minimally aggressive treatment is ideal. Absent gene-profiling, histopathological features of the tumor are examined to predict risk of relapse. This paper establishes statistical evidence for use of an empirical prognostic index as a risk-based clinical decision aid where gene profiles are unavailable. Methods: A retrospective cohort (n=965) observed for 5 years was propensity score (PS) matched to correct baseline risk differences between chemoendocrine therapy and endocrine monotherapy treatment groups. PS were generated from logistic regression of pertinent histopathological covariates available to a clinician at the time of diagnosis onto treatment designation. Comparator groups were fur- ther equilibrated using Synthetic Minority Over-Sampling (SMOTE). Estimated treatment effects were assessed after propensity score- matching (PSM) and after SMOTE-normalized re-sampling. Results: Propensity score-matched groups (n=262) showed no difference in relapse rates between groups. Significant differences in histopatho- logical covariates remained between groups after PSM. SMOTE further minimized inter-group differences. Corresponding propen- sity score quartiles of the SMOTE groups (n=1000) were tested for proportional differences in relapse. No proportional differences in relapses were observed between groups in Q1-Q3. Proportionally, significantly more relapses occurred in the Q4 endocrine therapy group than in the Q4 chemoendocrine group. Conclusion: After matching, the PSM sample failed to produce generalizable results due to significant group imbalance for multiple predictor variables, whereas SMOTE re-sampling provided adequately risk-matched groups (standardized differences&lt;0.2) for treatment effect anal- ysis. Individuals with HR+ HER2- T1 N0 M0 breast cancer are over-treated if they have PS&lt;0.75, and are prescribed chemoen- docrine therapy, as no additional benefit was observed from this more aggressive treatment regimen. Conversely, individuals are under-treated, and at a significantly higher risk of relapse, if they have PS&gt;0.75 and are not prescribed chemotherapy

Quantitative multi-species toxicity modeling: Does a multi-species, machine learning model provide better performance than a single-species model for the evaluation of acute aquatic toxicity by organic pollutants?

The toxicological profile of any chemical is defined by multiple endpoints and testing procedures, including representative test species from different trophic levels. While computer-aided methods play an increasingly important role in supporting ecotoxicology research and chemical hazard assessment, most of the recently developed machine learning models are directed towards a single, specific endpoint. To overcome this limitation and accelerate the process of identifying potentially hazardous environmental pollutants, we are introducing an effective approach for quantitative, multi-species modeling. The proposed approach is based on canonical correlation analysis that finds a pair(s) of uncorrelated, linear combinations of the original variables that best defines the overall variability within and between multiple biological responses and predictor variables. Its effectiveness was confirmed by the machine learning model for estimating acute toxicity of diverse organic pollutants in aquatic species from three trophic levels: algae (Pseudokirchneriella subcapitata), daphnia (Daphnia magna), and fish (Oryzias latipes). The multi-species model achieved a favorable predictive performance that were in line with predictive models derived for the aquatic organisms individually. The chemical bioavailability and reactivity parameters (n-octanol/water partition coefficient, chemical potential, and molecular size and volume) were important to accurately predict acute ecotoxicity to the three aquatic organisms. To facilitate the use of this approach, an open-source, Python-based script, named qMTM (quantitative Multi-species Toxicity Modeling) has been provided.