Dynamic child growth prediction: A comparative methods approach

BackgroundThe wide adoption of electronic health records (EHR) system has provided vast opportunities to advance health care services. However, the prevalence of missing values in EHR system poses a great challenge on data analysis to support clinical decision-making. The objective of this study is to develop a new methodological framework that can address the missing data challenge and provide a reliable tool to predict the hospital readmission among Heart Failure patients.MethodsWe used Gaussian Process Latent Variable Model (GPLVM) to impute the missing values. Specifically, a lower dimensional embedding was learned from a small complete dataset and then used to impute the missing values in the incomplete dataset. The GPLVM-based missing data imputation can provide both the mean estimate and the uncertainty associated with the mean estimate. To incorporate the uncertainty in prediction, a constrained support vector machine (cSVM) was developed to obtain robust predictions. We first sampled multiple datasets from the distributions of input uncertainty and trained a support vector machine for each dataset. Then an optimal classifier was identified by selecting the support vectors that maximize the separation margin of a newly sampled dataset and minimize the similarity with the pre-trained support vectors.ResultsThe proposed model was derived and validated using Physionet MIMIC-III clinical database. The GPLVM imputation provided normalized mean absolute errors of 0.11 and 0.12 respectively when 20% and 30% of instances contained missing values, and the confidence bounds of the estimations captures 97% of the true values. The cSVM model provided an average Area Under Curve of 0.68, which improves the prediction accuracy by 7% as compared to some existing classifiers.ConclusionsThe proposed method provides accurate imputation of missing values and has a better prediction performance as compared to existing models that can only deal with deterministic inputs.

The University of California Irvine Heart disease dataset had missing data on several attributes. The missing data can loss the important information of the attributes, but it cannot be deleted immediately on dataset. To handle missing data, there are several ways including deletion, imputation by mean, mode, or with prediction methods. In this study, the missing data were handled by deletion technique if the attribute had more than 70% missing data. Otherwise, it were handled by mean and mode method to impute missing data that had missing data less or equal 1%. The artificial neural network was used to handle the attribute that had missing data more than 1%. The results of the techniques and methods used to handle missing data were measured based on the performance results of the classification method on data that has been handled the problem of missing data. In this study the classification method used is Artificial Neural Network, Naïve Bayes, Support Vector Machine, and K-Nearest Neighbor. The performance results of classification methods without handling missing data were compared with the performance results of classification methods after imputation missing data on dataset for accuracy, sensitivity, specificity and ROC. In addition, the comparison of the Mean Squared Error results was also used to see how close the predicted label in the classification was to the original label. The lowest Mean Squared Error wasobtained by Artificial Neural Network, which means that the Artificial Neural Network worked very well on dataset that has been handled missing data compared to other methods. The result of accuracy, specificity, sensitivity in each classification method showed that imputation missing data could increase the performance of classification, especially for the Artificial Neural Network method.

Prediction model is used to forecast or predict value from dataset. But one of the most common problems in training prediction model is there are missing values in datasets. Problem is usually managed by two methods for solving this problem. First is ignoring, but it reduces the predictive model's performance because of the data that was cut off may be important. Another method is replacing the missing values or data imputation. Benefit of imputation is it still keep all of data. It means an important data will not loss. Therefore, most researchers offer an imputation method for solving this problem. In the past most researches are proposed algorithm that trying to recover the original data, but main object of using prediction model is accuracy of prediction. Algorithm is based on Genetics Algorithm and Multiple Linear Regression is create for improving performance of prediction model.

Background . Properly constructed decision support systems (DSS) for modelling and forecasting behaviour of dynamic systems provide a possibility for taking into consideration uncertainties of probabilistic, statistical and structural types what results in higher quality of developed models and estimated forecasts. Objective . To consider general reasons for loosing (missing) data in statistical data analysis; to provide categorization of missing data into several groups, and identify the reasons for missing measurements; to provide stepwise system methodology for uncertainty analysis and selection of data imputation techniques; to give an insight into some popular missing values imputation techniques regarding their possible applications. Methods . To solve the problems mentioned the following methods have been used: data categorization approach from business or practical point of view that is necessary for discovering the reasons for availability of systemic and/or random missing values; the modern systemic methodology was hired for analysis of uncertainty causes and missing values imputation; the decision tree based imputation procedures; EM algorithm and regression model approach to forecasting missing data using forecasting functions. Results . The main results of the study are in categorization of the missing data into groups; development of systemic methodology for analysis of uncertainty causes and missing values imputation; providing an analysis for possibilities of missing values imputation with decision trees, EM algorithm and regression models; development of multistep forecasting functions on the basis of autoregression models; illustration of application of some selected perspective methods for missing data imputation. Conclusions . We proposed the six steps system methodology for data imputation which stresses that selection of correct method for imputation is tightly connected with the step-by-step analysis of the gaps causes and finding an appropriate technique for their imputation. The results of imputation sometimes are rather far from the existing data and should be smoothed or even broken from the sample due to their incorrectness. For such cases it should be proposed a new probabilistic-regression method which allows define parameters of the probability interval for the regression aiming missing data imputation. A series of computing experiments performed with EM algorithm, forecast regression based imputation technique and some other approaches shows that it is possible to reach high quality results regarding correct processing of data with missing values.

In survival analyses that include a time-dependent covariate, the standard partial likelihood approach is often complicated by the fact that the necessary observations of the time-dependent covariate are not always available for the subjects in each risk set. In this article, we consider the situation of a binary time-dependent covariate. We specify a longitudinal model for the binary covariate with missing observations and a proportional hazards model for survival time conditional on fixed covariates and the completed time-dependent covariate history. The joint posterior distribution of the missing covariates and the parameters in the covariate and hazard models is simulated using Gibbs sampling. The joint modeling approach allows the missing covariates to be generated using all of the observed covariates as well as the disease outcome and failure time information. Simulation studies show that this approach often leads to lower bias of relative risk estimates associated with the time-dependent covariate and superior coverage of interval estimates as compared to variations of approaches based on imputing missing covariate values using previous values and then performing partial likelihood analysis. Our research is motivated by a study of survival of lung cancer patients after surgery in which current smoking status is a binary time-dependent covariate. We apply the methods to data from this study and explore the advantages of the joint modeling approach. The application demonstrates that the joint modeling approach can have improved efficiency in estimating the coefficients of both the fixed and the time-dependent covariates. Moreover, it can facilitate analyses using more complicated functions of the time-dependent covariate, such as cumulative smoking, that are difficult or inappropriate to use with the comparison methods.

Missing data is a common problem in palliative care research due to the special characteristics (deteriorating condition, fatigue and cachexia) of the population. Using data from a palliative study, we illustrate the problems that missing data can cause and show some approaches for dealing with it. Reasons for missing data and ways to deal with missing data (including complete case analysis, imputation and modelling procedures) are explored. Possible mechanisms behind the missing data are: missing completely at random, missing at random or missing not at random. In the example study, data are shown to be missing at random. Imputation of missing data is commonly used (including last value carried forward, regression procedures and simple mean). Imputation affects subsequent summary statistics and analyses, and can have a substantial impact on estimated group means and standard deviations. The choice of imputation method should be carried out with caution and the effects reported.

Most previous studies of the relationship between birth weight and childhood growth have concentrated on the growth of low birth weight infants. To examine this relationship throughout the full range of birth weights, growth data for children less than 5 years of age from the Tennessee Special Supplemental Food Program for Women, Infants, and Children linked to birth certificate records for 1975 to 1985 were used. Growth status was compared for 500-g birth weight categories from 1,000 g to 4,999 g using mean Z scores and the percentage of children more than 2 SD above or less than 2 SD below the median for height for age, weight for age, and weight for height. Infants with lower birth weights were likely to remain shorter and lighter throughout childhood, especially those who were intrauterine growth retarded rather than premature. Conversely, those infants with higher birth weights were likely to remain taller and heavier and to have a higher risk of obesity. Birth weight is a strong predictor of weight and height in early childhood, not only for low birth weight children but also for those of normal and high birth weight.

Missing data problem is ubiquitous in many real life situations. Information Technology researchers have explored and tried to address this problem in different settings. In this thesis, we undertake research to address missing data problem associated with order book information in stock markets. This is an in-depth and large-scale study with systematic and comprehensive framework to address missing data problem in the finance literature. Orders placed by traders and the corresponding order imbalance (OIB) is informative to predict future stock returns, however, stock exchange rules do not reveal price sensitive complete order book data for traders. Hence, return prediction using the revealed, incomplete trade book data (that contains only matched buy and sell orders and deletes the unmatched orders), does not let traders to completely exploit possible short term trading opportunities. Hence, this can be considered as a classical missing data problem for predicting future returns, by using the information content of order book. This thesis addresses the missing data problem by developing an integrated theoretical framework applied in stock market trading environment. We use relational Markov networks theory and build an empirically testable Algorithm for Imputed Complete Order Book (AICOB). The thesis contributes by developing a new theoretical advancement of information technology research relating to missing data problem and applying it to financial markets. First, the thesis presents the missing data problem as a Missing at Random (MAR) data and builds a systematic framework to estimate single as well as joint log likelihood functions. The thesis demonstrates that estimating by using incomplete records, improves the accuracy of the parameter estimates. Second, the thesis proposes a Relational Markov Network Model for estimation of the joint distribution function of orders, order characteristics and their interactions. Later, the Expectation Maximization Algorithm is proposed to address the missing data problem during the joint estimation procedure. All pooled regression results follow Fama and MacBeth (1973) and Generalized Methods of Moments (GMM) methods. These methods control the cross sectional and time series correlations between the observations and across the pooled stocks. The proposed novel methodology overcomes the estimation problem in the context of missing order book data. Third, the thesis develops an objective evaluation strategy for AICOB, based on efficiency, accuracy and adaptability dimensions. The thesis uses Australian stock market data, which provides not only trade book data but also historical order book data for cross validating the results. This unique setting allows validating the accuracy of AICOB methodology by comparing with complete order book data. The main contribution of the thesis is to show that AICOB based predictions match with the complete order book data. Whereas, trade book based predictions are quite inconsistent to the complete order book data. The AICOB based results are also consistent with the theoretical predictions proposed in finance literature that OIB predicts better as the firm size increases. The results show that large firms, with higher trading activity and more competition for order flows, report more significant OIB prediction of future returns. Trade Book based OIB estimates, which suffer from missing data problem, fail to predict future returns for stock portfolios. Hence, addressing the missing data problem is important before implementing OIB based trading strategies. Overall, the thesis finds that machine learning applications, similar to AICOB, can be helpful in implementing the trading strategies in financial markets. The imputation of missing data, through systematic procedures, based on theoretical distributional properties of the financial variables, can be informative for more accurate prediction of future returns. The thesis contributes towards establishing a common ground for cross-disciplinary research in Finance and Information Technology (IT) by applying the advances in IT research to solve research and corresponding implementation problems in finance. Further, the thesis contributes towards advancing the order imbalance literature by showing that missing data can play a critical role in the predictive ability of order imbalance.

The accuracy of a knowledge extraction algorithm in a large database depends on the quality of the data preprocessing and the methods used. The massive amounts of data that we collect every day are putting storage capacity at a premium. In reality, many databases are characterized by attributes with outliers, redundant, and even more missing values. Missing data and outliers are ubiquitous in our databases, and imputation techniques will help us mitigate their influence. To solve this problem, as well as the problem of data size, this paper proposes a data preprocessing approach based on the k-nearest neighbor (KNN) completion for imputation of missing data and principal component analysis (PCA) for processing redundant data, thus reducing the data size by generating a significant quality sample after imputation of missing and outlier data. A rigorous comparison is made between our approach and two others. The dissolved gas data from Rio Tinto Alcan’s transformer T0001 were imputed by KNN, where k equals 5. For 6 imputed gases, the average percentage error is about 2%, 17.5% after average imputation, and 23.65% after multiple imputations. For data compression, 2 axes were selected based on the elbow rule and the Kaiser threshold.

Despite considerable advances in high throughput technology over the last decade, new challenges have emerged related to the analysis, interpretation, and integration of high-dimensional data. The arrival of omics datasets has contributed to the rapid improvement of systems biology, which seeks the understanding of complex biological systems. Metabolomics is an emerging omics field, where mass spectrometry technologies generate high dimensional datasets. As advances in this area are progressing, the need for better analysis methods to provide correct and adequate results are required. While in other omics sectors such as genomics or proteomics there has and continues to be critical understanding and concern in developing appropriate methods to handle missing values, handling of missing values in metabolomics has been an undervalued step. Missing data are a common issue in all types of medical research and handling missing data has always been a challenge. Since many downstream analyses such as classification methods, clustering methods, and dimension reduction methods require complete datasets, imputation of missing data is a critical and crucial step. The standard approach used is to remove features with one or more missing values or to substitute them with a value such as mean or half minimum substitution. One of the major issues from the missing data in metabolomics is due to a limit of detection, and thus sophisticated methods are needed to incorporate different origins of missingness. This dissertation contributes to the knowledge of missing value imputation methods with three separate but related research projects. The first project consists of a novel missing value imputation method based on a modification of the k nearest neighbor method which accounts for truncation at the minimum value/limit of detection. The approach assumes that the data follows a truncated normal distribution with the truncation point at the detection limit. The aim of the second project arises from the limitation in the first project. While the novel approach is useful, estimation of the truncated mean and standard deviation is problematic in small sample sizes (N < 10). In this project, we develop a Bayesian model for imputing missing values with small sample sizes. The Bayesian paradigm has generally been utilized in the omics field as it exploits the data accessible from related components to acquire data to stabilize parameter estimation. The third project is based on the motivation to determine the impact of missing value imputation on down-stream analyses and whether ranking of imputation methods

Introduction: Imputation of missing data and selection of appropriate risk function are of importance . Sometimes a variable with continuous nature will be offered to the regression model as an ordinal variable. Our aim is to investigate whether to offer the continuous form of the variable to the imputation phase and its ordinal from to the modeling phase, or whether to offer the ordinal version to both phases. Material and Methods: The outcome and main variable of interest was use of diet as a body change approach, and Body Mass Index (BMI). We randomly deleted 10%, 20%, and 40% of BMI values. In strategies 1 and 2, BMI was offered to the imputation phase as a continuous (BMIC) and ordinal variable (BMIO). Missing data were imputed using linear and polytomous regression respectively. In strategy 1, after imputation, BMIC was categorized (named BMICO) and offered to the modeling phase. In strategy 2, after imputation of BMIO values, this variable was offered to the logistic model (named BMIOO). We compared two strategies at Event Per Variables (EPV) of 75, 10, and 5. Result: At EPVs of 75 and 10 no remarkable difference was seen. However, at EPV of 5, strategy 2 was superior. At 20% and 40% missing rates, strategy 1 was 2.21 and 3.67 times more likely to produce Severe Relative Bias. At high missing rate, power was higher in strategy2 (90% versus 83%). Conclusions: When EPV is low and missing rate is high, categorizing of variable before imputation of missing data produces less SRB and leads to higher power.

Imputation of missing data is of paramount importance in machine learning and data mining tasks with incomplete data. In this paper, a fuzzy-neighborhood density-based clustering technique is developed for imputation of missing data. The proposed technique makes use of the density measure, in order to group the similar patterns and find the best donors for each incomplete target pattern to impute its missing values. The fuzzy neighborhood membership degrees are adjusted using an invasive weed optimization algorithm. The performance of the proposed imputation technique is evaluated using eight synthetic publicly available datasets with induced missing values and compared with the performance of other existing competitors, k-means imputation, fuzzy c-means imputation and fuzzy c-means with genetic algorithm imputation. Various types of missingness have been induced to each dataset. The attained results show the effectiveness of the proposed missing data imputation technique.

In the field of higher education, predicting students At-Risk of failing is crucial since they could then be recommended for various interventions. These predictions are made on real world datasets that most likely have various missing data. Addressing this missing data could have substantial affects on the eventual At-Risk predictions. In this study we address the missing data problem with recently developed missing data imputation techniques not currently seen in the relevant literature. These techniques include multivariate imputation by chained equations (MICE) and missForest. We found that MICE does not perform better than simple listwise-deletion. However, missForest is shown to substantially improve predictive performance. This is important since it implies that any subsequent machine learning predictions on students At-Risk of failing are potentially much better.

CRISPR/Cas9-based genome editing has yet to be reported in species of the Platyhelminthes. We tested this approach by targeting omega-1 (ω1) of Schistosoma mansoni as proof of principle. This secreted ribonuclease is crucial for Th2 polarization and granuloma formation. Schistosome eggs were exposed to Cas9 complexed with guide RNA complementary to ω1 by electroporation or by transduction with lentiviral particles. Some eggs were also transfected with a single stranded donor template. Sequences of amplicons from gene-edited parasites exhibited Cas9-catalyzed mutations including homology directed repaired alleles, and other analyses revealed depletion of ω1 transcripts and the ribonuclease. Gene-edited eggs failed to polarize Th2 cytokine responses in macrophage/T-cell co-cultures, while the volume of pulmonary granulomas surrounding ω1-mutated eggs following tail-vein injection into mice was vastly reduced. Knock-out of ω1 and the diminished levels of these cytokines following exposure showcase the novel application of programmed gene editing for functional genomics in schistosomes.

Most bacteria exist and interact within polymicrobial communities. These interactions produce unique compounds, increase virulence and augment antibiotic resistance. One community associated with negative healthcare outcomes consists of Pseudomonas aeruginosa and Staphylococcus aureus. When co-cultured, virulence factors secreted by P. aeruginosa reduce metabolism and growth in S. aureus. When grown in vitro, this allows P. aeruginosa to drive S. aureus toward extinction. However, when found in vivo, both species can co-exist. Previous work has noted that this may be due to altered gene expression or mutations. However, little is known about how the growth environment could influence the co-existence of both species. Using a combination of mathematical modeling and experimentation, we show that changes to bacterial growth and metabolism caused by differences in the growth environment can determine the final population composition. We found that changing the carbon source in growth media affects the ratio of ATP to growth rate for both species, a metric we call absolute growth. We found that as a growth environment increases the absolute growth for one species, that species will increasingly dominate the co-culture. This is due to interactions between growth, metabolism, and metabolism-altering virulence factors produced by P. aeruginosa. Finally, we show that the relationship between absolute growth and the final population composition can be perturbed by altering the spatial structure in the community. Our results demonstrate that differences in growth environment can account for conflicting observations regarding the co-existence of these bacterial species in the literature, provides support for the intermediate disturbance hypothesis, and may offer a novel mechanism to manipulate polymicrobial populations.