Mean Matching Method Research Articles

309. COMPARATIVE OUTCOMES OF OPEN VS. MINIMALLY INVASIVE ESOPHAGECTOMY FOR ESOPHAGEAL AND GASTRO-ESOPHAGEAL JUNCTION TUMORS: INSIGHTS FROM A THORACO-ABDOMINAL STRATIFICATION MODEL

Abstract Background Minimally invasive esophagectomy (MIE) has demonstrated improved outcomes for fit patients with esophageal/gastro-esophageal junction tumors. However, challenges arise in patients less tolerant of prolonged anesthesia or harboring extensive advanced-stage tumors, which limit the utilization of MIE, increasing the risk of referral to nonsurgical strategies. To date, the criteria for considering left thoraco-abdominal esophagectomy (TAE) and the corresponding outcomes in this specific patient population remain unclear. Therefore, our institutional study aimed to identify clinical characteristics for the consideration of TAE, offering insights into treatment selection strategies for esophageal cancer patients. Additionally, we compared the short-term outcomes between TAE and MIE. Methods We included all consecutive patients who underwent esophagectomy with gastric conduit reconstruction for stage I-IVa esophageal and gastro-esophageal junction tumors at a tertiary referral center from 2015 to 2023. Predictors for considering TAE were identified through a multivariable regression model utilizing multivariate imputation by chain equation for missing data of pulmonary and cardiac function, using the predicted mean matching method. Significant variables were used to develop a stratification model, evaluated through the receiver-operating curve. Differences in outcome were assessed using the Kruskal-Wallis rank sum for continuous and Pearson’s chi-squared or Fischer’s exact test for categorical variables. Results This study included 744 patients; 317 (43%) underwent TAE and 427 (57%) had MIE. Patient characteristics were significantly different. Following multivariable analysis, age (1.04 [1.02-1.06]; p<0.001), ECOG-status (1.43 [1.09-1.87]; p=0.009), comorbidity index (1.26 [1.10-1.46]; p<0.001), DLCO (0.98 [0.97-0.99]; p<0.001), ejection fraction (0.97 [0.94-1.00]; p=0.021), tumor location (GEJ: 1.58 [1.10-2.27], Middle: 0.38 [0.18-0.79]; p<0.001), cStage (II: 2.03 [1.02-4.19], III: 3.29 [1.78-6.33], IVa: 3.42 [1.74-6.97]; p<0.001) and adenocarcinoma (2.44 [1.39-4.55]; p=0.002) were identified as predictors for TAE. The stratification model demonstrated an area-under-the-curve of 0.76 [0.73-0.80]. Leave-one-out-cross-validation demonstrated a 70% accuracy. The short-term outcomes were comparable between TAE and MIE (Table 1). Conclusion Our study demonstrated that age, ECOG status, comorbidity index, diffusion capacity, ejection fraction, tumor location, stage and histology were independent predictors for the consideration of thoraco-abdominal esophagectomy. In this context, our stratification model demonstrated a robust predictive value. Moreover, our model suggests considering MIE below a probability threshold of 30% and TAE above 60%, demonstrating an 85% sensitivity and 90% specificity at these thresholds, respectively. Decisions within the 30% to 60% range should be individualized and based on specific patient and tumor characteristics. Short-term outcomes were comparable between TAE and MIE, emphasizing the significance of adequate stratification before surgery.

초등교사의 기대에 영향을 미치는 학생 특성 탐색

Objectives The purpose of this study is to examine student characteristics that affect elementary teachers' ex-pectations in terms of students' academic performance, peer relationship, and attitude. Methods For this purpose, the panel data of the Korea Education Longitudinal Study (KELS) 2013 from elementary school students were used. For this data, the predicted mean matching method was applied to handle missing values, multicollinearity was checked, and multiple regression analyses were conducted. Results It was found that variables affecting teachers' expectations were students' previous academic perform-ance, class attitude, gender, parental support, monthly income, physical self-concept, and single-parent family status. The effect size and direction of the variables varied by the sub-component of teacher expectations. Conclusions Based on these findings, this study proposed a teacher training program to prevent teachers' biases against students and called for the establishment of longitudinal data to conduct research on teachers' evaluations and expectations of students.

Assessment of the effect of constraints in a new multivariate mixed method for statistical matching

A Multivariate Mixed method for Statistical Matching (MMSM) is proposed. The MMSM is a predictive mean matching method to impute values when integrating two datasets from the same population without overlapping units measuring several common and non-common variables. It considers the multivariate structure of the data by using multivariate Bayesian regression. The MMSM can also include auxiliary information from an additional dataset to improve the computation of intermediate values, and constraints to improve the selection of the donors. The results from a simulation study show that including information from an auxiliary dataset leads to far better results, especially in terms of bias and percentage of correct imputations. The inclusion of constraints also increases the quality of the imputations, and hence of the statistical matching.

Imputation methods on retrospective breast cancer data in Tanzania: A comparative study

Background: Clinical datasets are at risk of having missing data for several reasons including patients’ failure to attend clinical measurements and measurement recorder’s defects. Missing data can significantly affect the analysis and results might be doubtful due to bias caused by omission incomplete records during analysis especially if a dataset is small. This study aims to compare several imputation methods in terms of efficiency in filling-in missing data so as to increase prediction and classification accuracy in breast cancer dataset. Methodology: Five imputation methods namely series mean, k-nearest neighbour, hot deck, predictive mean matching, expected maximisation via bootstrapping, and multiple imputation by chained equations were applied to replace the missing values to the real breast cancer dataset. The efficiency of imputation methods was compared by using the Root Mean Square Errors and Mean Absolute Errors to obtain a suitable complete dataset. Binary logistic regression and linear discrimination classifiers were applied to the imputed dataset to compare their efficacy on classification and discrimination. Results: The evaluation of imputation methods revealed that the predictive mean matching method was better off compared to other imputation methods. In addition, the binary logistic regression and linear discriminant analyses yield almost similar values on overall classification rates, sensitivity and specificity. Conclusion: The predictive mean matching imputation showed higher accuracy in estimating and replacing missing data values in a real breast cancer dataset under the study. It is a more effective and good approach to handle missing data. We recommend replacing missing data by using predictive mean matching since it is a plausible approach toward multiple imputations for numerical variables. It improves estimation and prediction accuracy over the use complete-case analysis especially when percentage of missing data is not very small.

Self-reported alcohol consumption of pregnant women and their partners correlates both before and during pregnancy: Acohort study with 21,472 singleton pregnancies.

BackgroundThe partners’ role in determining the alcohol consumption behavior of pregnant women is not well studied. We measured alcohol use before and during pregnancy in pregnant women and their partners to evaluate the correlation in their levels of consumption.MethodsWe evaluated the self‐reported alcohol use of 14,822 women and their partners during 21,472 singleton pregnancies delivered in Kuopio University Hospital, Finland during the period 2009‒2018. The information was gathered during pregnancy and at the time of childbirth and recorded in two databases that were merged to yield a single cohort. Missing data were accounted for by multiple imputation using the predictive mean matching method.ResultsIn 86% of the pregnancies, women reported alcohol use before pregnancy, whereas in 4.5% of the pregnancies women reported alcohol use during pregnancy. In contrast, no decrease was detected in their partners’ alcohol use before or during pregnancy. In 26% of the pregnancies, the woman reported stopping alcohol use only after recognizing that she was pregnant. Before pregnancy, there were strong correlations between the pregnant women and their partners in the total Alcohol Use Disorders Identification Test score (r s = 0.69, p < 0.0001) and the self‐reported average weekly amount of alcohol consumed (r s = 0.56, p < 0.0001). During pregnancy, there were weak correlations between the pregnant women and their partners in the frequency of drinking (r s = 0.20, p < 0.0001) and the average weekly amount of alcohol consumed (r s = 0.18, p < 0.0001).ConclusionsThe self‐reported alcohol consumption of pregnant women and their partners was positively correlated both before and during pregnancy, though the correlation declined substantially during pregnancy. Evaluating the alcohol consumption of both parents before pregnancy could assist in identifying women at risk of prenatal alcohol exposure. Supporting a reduction in partners' alcohol use could help to reduce pregnant women's alcohol consumption and prevent its associated harms.

Cancer Patients Missing Pain Score Information:- Application with Imputation Techniques

Background: Methods for handling missing data in clinical research have been getting more attentions over last few years. Contemplation of missing data in any study is vital as they may lead to considerable biases and can have an impact on the power of the study.&#x0D; Objective: This manuscript is dedicated to present different techniques to handle missing observations obtained from repeatedly measured pain score data on palliative cancer.&#x0D; Methods: This problem caused by subjects drop out before completion of the study. The reason for dropout or withdrawal may be related to study (e.g., adverse event, death, unpleasant study procedures, lack of improvement) or unrelated to the study (e.g., moving away, unrelated disease). The dropout might be very common on studies on palliative cancer patients. The Palliative treatment is designed to relieve symptoms, and improve the quality of life and can be used at any stage of an illness if there are troubling symptoms, such as pain or sickness.&#x0D; Results: The mean(SD) of observed pain score was 3.638(3.156) whereas the imputed mean values were 3.615(2.980), 3.618(2.954), 3.577(2.892), 3.560(2.999) and 3.627(2.949) respectively for the imputation methods regression, predictive mean matching, propensity score, EM algorithm and MCMC methods for pain score values at visit3. &#x0D; Interpretation and Conclusion: The EM algorithm shows the least percentage change from observed values in both visits followed by predictive mean matching method and MCMC methods. The multiple imputation techniques have few advantages; the imputed values are drawsfrom a distribution, so they inherently contain some variation by introducing an additional form of error in the parameter estimates across the imputation&#x0D;

Combining Item Response Theory with Multiple Imputation to Equate Health Assessment Questionnaires

The assessment of patients' functional status across the continuum of care requires a common patient assessment tool. However, assessment tools that are used in various health care settings differ and cannot be easily contrasted. For example, the Functional Independence Measure (FIM) is used to evaluate the functional status of patients who stay in inpatient rehabilitation facilities, the Minimum Data Set (MDS) is collected for all patients who stay in skilled nursing facilities, and the Outcome and Assessment Information Set (OASIS) is collected if they choose home health care provided by home health agencies. All three instruments or questionnaires include functional status items, but the specific items, rating scales, and instructions for scoring different activities vary between the different settings. We consider equating different health assessment questionnaires as a missing data problem, and propose a variant of predictive mean matching method that relies on Item Response Theory (IRT) models to impute unmeasured item responses. Using real data sets, we simulated missing measurements and compared our proposed approach to existing methods for missing data imputation. We show that, for all of the estimands considered, and in most of the experimental conditions that were examined, the proposed approach provides valid inferences, and generally has better coverages, relatively smaller biases, and shorter interval estimates. The proposed method is further illustrated using a real data set.

A comparison study on fusion methods using evaluation indicators

Various fusion methods have been developed for improving data spatial resolution. The methods most encountered in the literature are the intensity‐hue‐saturation (IHS) transform, the Brovey transform, the principal components algorithm (PCA) fusion method, the Gram–Schmidt fusion method, the local mean matching method, the local mean and variance matching method, the least square fusion method, the discrete wavelet fusion method including Daubechies, Symlet, Coiflet, biorthogonal spline, reverse biorthogonal spline, and Meyer wavelets, the wavelet‐PCA fusion method, and the crossbred IHS and wavelet fusion method. Using various evaluation indicators such as two‐dimensional correlation, relative difference of means, relative variation, deviation index, entropy difference, peak signal‐to‐noise ratio index and universal image quality index, as well as photo‐interpretation methods and techniques, results of the above fusion methods were compared and comments on the fusion methods and potential of evaluation indicators were made. Among data fusion methods and indicators the local mean and variance matching methods proved the most efficient and the peak signal‐to‐noise ratio indicator proved the most appropriate for the evaluation of data fusion results.

A comparison of imputation methods in a longitudinal randomized clinical trial

It is common for longitudinal clinical trials to face problems of item non-response, unit non-response, and drop-out. In this paper, we compare two alternative methods of handling multivariate incomplete data across a baseline assessment and three follow-up time points in a multi-centre randomized controlled trial of a disease management programme for late-life depression. One approach combines hot-deck (HD) multiple imputation using a predictive mean matching method for item non-response and the approximate Bayesian bootstrap for unit non-response. A second method is based on a multivariate normal (MVN) model using PROC MI in SAS software V8.2. These two methods are contrasted with a last observation carried forward (LOCF) technique and available-case (AC) analysis in a simulation study where replicate analyses are performed on subsets of the originally complete cases. Missing-data patterns were simulated to be consistent with missing-data patterns found in the originally incomplete cases, and observed complete data means were taken to be the targets of estimation. Not surprisingly, the LOCF and AC methods had poor coverage properties for many of the variables evaluated. Multiple imputation under the MVN model performed well for most variables but produced less than nominal coverage for variables with highly skewed distributions. The HD method consistently produced close to nominal coverage, with interval widths that were roughly 7 per cent larger on average than those produced from the MVN model.

An Empirical Evaluation of the Predictive Mean Matching Method for Imputing Missing Values

This article reports empirical explorations of how well the predictive mean matching method for imputing missing data works for an often problematic variable—income—when income is used as an explanatory variable in a substantive regression model. It is found that the performance of the predictive mean method varies considerably with the predictive power of the imputation regression model and the percentage of cases with missing data on income. In comparisons of single-value with multiple-imputation methods, it also is found that the amount of bias and the loss of precision associated with single-value methods is considerably less than that associated with a weak imputation model. Situations in which using imputed data can lead to seriously biased estimates of regression coefficients (and related statistics) and situations in which the bias is so minimal as to be nonproblematic are identified.