Mohammad-Reza Siadat

Unstructured medical image query using big data - An epilepsy case study

Big data technologies are critical to the medical field which requires new frameworks to leverage them. Such frameworks would benefit medical experts to test hypotheses by querying huge volumes of unstructured medical data to provide better patient care. The objective of this work is to implement and examine the feasibility of having such a framework to provide efficient querying of unstructured data in unlimited ways. The feasibility study was conducted specifically in the epilepsy field. The proposed framework evaluates a query in two phases. In phase 1, structured data is used to filter the clinical data warehouse. In phase 2, feature extraction modules are executed on the unstructured data in a distributed manner via Hadoop to complete the query. Three modules have been created, volume comparer, surface to volume conversion and average intensity. The framework allows for user-defined modules to be imported to provide unlimited ways to process the unstructured data hence potentially extending the application of this framework beyond epilepsy field. Two types of criteria were used to validate the feasibility of the proposed framework - the ability/accuracy of fulfilling an advanced medical query and the efficiency that Hadoop provides. For the first criterion, the framework executed an advanced medical query that spanned both structured and unstructured data with accurate results. For the second criterion, different architectures were explored to evaluate the performance of various Hadoop configurations and were compared to a traditional Single Server Architecture (SSA). The surface to volume conversion module performed up to 40 times faster than the SSA (using a 20 node Hadoop cluster) and the average intensity module performed up to 85 times faster than the SSA (using a 40 node Hadoop cluster). Furthermore, the 40 node Hadoop cluster executed the average intensity module on 10,000 models in 3h which was not even practical for the SSA. The current study is limited to epilepsy field and further research and more feature extraction modules are required to show its applicability in other medical domains. The proposed framework advances data-driven medicine by unleashing the content of unstructured medical data in an efficient and unlimited way to be harnessed by medical experts.

Novel Application of Statistical Methods to Identify New Urinary Incontinence Risk Factors

Longitudinal data for studying urinary incontinence (UI) risk factors are rare. Data from one study, the hallmark Medical, Epidemiological, and Social Aspects of Aging (MESA), have been analyzed in the past; however, repeated measures analyses that are crucial for analyzing longitudinal data have not been applied. We tested a novel application of statistical methods to identify UI risk factors in older women. MESA data were collected at baseline and yearly from a sample of 1955 men and women in the community. Only women responding to the 762 baseline and 559 follow-up questions at one year in each respective survey were examined. To test their utility in mining large data sets, and as a preliminary step to creating a predictive index for developing UI, logistic regression, generalized estimating equations (GEEs), and proportional hazard regression (PHREG) methods were used on the existing MESA data. The GEE and PHREG combination identified 15 significant risk factors associated with developing UI out of which six of them, namely, urinary frequency, urgency, any urine loss, urine loss after emptying, subjects anticipation, and doctors proactivity, are found most highly significant by both methods. These six factors are potential candidates for constructing a future UI predictive index.

Extensible Query Framework for Unstructured Medical Data -- A Big Data Approach

With the ever increasing amount of medical image scans, it is critical to have an extensible framework that allows for mining such unstructured data. Such a framework would provide a medical researcher the flexibility in validating and testing hypotheses. Important characteristics of this type of framework include accuracy, efficiency and extensibility. The objective of this work is to build an initial implementation of such a framework within a big data paradigm. To this end, a clinical data warehouse was built for the structured data and a set of modules were created to analyze the unstructured content. The framework contains built-in modules but is flexible in allowing the user to import their own, making it extensible. Furthermore, the framework runs the modules in a Hadoop cluster making it efficient by utilizing the distributed computing capability of big data approach. To test the framework, simulated data of 1,000 patients along with their hippocampi images were created. The results show that the framework accurately returned all 15 patients who had hippocampal resection with hippocampus ipsilateral to surgery being less than 20% the size of the hippocampus contralateral to surgery, using a built-in module. In addition, the framework allowed the user to run a different module using the previous output to further analyze the unstructured data. Finally, the framework also enabled the user to import a new module. This study paves the way towards showing the feasibility of such a framework to handle unstructured medical data in an accurate, efficient and extensible manner.

Improved Feature Selection by Incorporating Gene Similarity Into the LASSO

Personalized medicine is customizing treatments to a patientâs genetic profile, and it has the potential to revolutionize medical practice. An important process used in personalized medicine is gene expression profiling. Analyzing gene expression profiles is difficult, because there are usually few patients and thousands of genes. This leads to the curse of dimensionality. In order to combat this problem, some researchers suggest using prior knowledge to enhance feature selection for supervised learning algorithms. We propose an enhancement to the LASSO, a shrinkage and selection technique that induces parameter sparsity by penalizing a modelâs objective function. Our enhancement gives preference to the selection of genes that are involved in similar biological processes. We expect this to be the case because co-expressed genes are likely to be involved in related pathways. Our modified LASSO selects similar genes by penalizing interaction terms between genes. We devised a coordinate descent algorithm to minimize the corresponding objective function. To evaluate our method, we created simulation data where we compared our model to the standard LASSO model and an interaction LASSO model. Our model outperformed both the standard LASSO and the interaction model in terms of detecting important genes and gene interactions for a reasonable number of training samples. This preliminary study leads us to believe that our method has the potential compete with state of the art methods in gene expression analysis.

Bayesian Prediction of Incontinence among Older Women Using an Experimental Design Template

In this study, a Bayesian predictor of urinary incontinence (UI) is devised for screening older women. Risk factors identified from an epidemiological survey data as significant for UI, are utilized. The proposed Bayesian method combines an experimental design template with relevant information to construct a predictive index in terms of posterior probabilities. The computations are carried out on a longitudinal data called the Medical, Epidemiological and Social Aspects of Aging (MESA). The index is applied to the baseline and follow-up portions of the MESA data. The results show that, the percentage of the absolute relative change between the prior and posterior probabilities can be used as a decision tool to make conclusions on credibility of the class labels on continence and incontinence. The proposed index can be applied for immediate screening and for predicting future urinary incontinence in older women of comparable demographics as those presented in the MESA data.

Skip pattern analysis of the MESA data for stratification

Urinary Incontinence (UI) is a costly condition that decreases the quality of a patients life and social engagement. Identification of UI risk factors may help early prevention and treatment of the condition. In this study we revisited the Medical, Epidemiological and Social Aspects of Aging (MESA) data collected in 1983. The experiments are conducted on a longitudinal dataset pertaining to the female-only population. A methodology that identifies skip patterns in order to facilitate MESA risk factor analysis is presented. The identified skip patterns are used to stratify MESA data. Based on the stratification performed, the important risk factors are then analyzed for each group of subjects. JRip rule extraction technique is utilized to determine the UI risk factors. Consequently, taking female hormones was determined as the most important stratifying feature. The dataset is then stratified to two subsets based on this stratifying feature. Education level, hearing problems, urine loss while coughing or sneezing, physical activity, stress and cancer are risk factors specific to taking female hormones. The common risk factors among both of the stratified groups were: stress, frequent sneezing, and low physical activity. Although there were common risk factors among both of the stratified groups these preliminary results show that different group of subjects have different risk factors, and therefore they should be provided with different UI predictive indices, diagnoses and possibly treatment plans.

Skip pattern analysis for stratification and detection of undetermined and inconsistent data

Urinary Incontinence (UI) is a costly condition that decreases the quality of a patients life and social engagement. Identification of UI risk factors may help early prevention and treatment of the condition. In this study we revisited the Medical, Epidemiological and Social Aspects of Aging (MESA) data collected in 1983 by the University of Michigan. The experiments are conducted on the dataset pertaining to the female-only population. The dataset contains missing values. First, the missing values are classified into inconsistent, undetermined, genuine missing values and skip patterns. The undetermined and inconsistent values are distinguished from the skip patterns and removed from the dataset. Once the skip patterns are detected, they are used to stratify the MESA data. Based on the stratification performed, the important risk factors are then analyzed for each group of subjects. JRip rule extraction technique is utilized to determine the UI risk factors. Consequently, taking female hormones was determined as the most important stratifying feature. The dataset is then stratified to two subsets based on this stratifying feature. Education level, hearing problems, urine loss while coughing or sneezing, physical activity, stress and cancer are risk factors specific to taking female hormones. The common risk factors among both of the stratified groups were: stress, frequent sneezing, and low physical activity. Although there were common risk factors among both of the stratified groups these preliminary results show that different group of subjects have different risk factors, and therefore they should be provided with different diagnoses and possibly treatment plans.

A novel rule infusion technique for generating simulated binary data to validate data mining methods

Mathematical analysis of existing data mining methods is not straightforward and in many cases it is not possible. Therefore, simulated data plays a central role in validation of data mining results in a given situation, i.e., noise, missing value and multicollinearity levels. This paper proposes a longitudinal binary data simulation focusing on presentation of the major challenge of infusing user-defined rules. Results of applying Apriori, PRAT, Prism, and JRip rule extraction methods on these simulated data in several missing value levels are presented in this paper. This simulation proved to be essential in verifying data mining results that we have generated on Medical Epidemiological and Social Aspects of Aging (MESA) data set.

Skip pattern analysis for detection of undetermined and inconsistent data

A common problem in clinical survey trials is missing data. Skip patterns are one type of missing data in medical datasets, skipping a respondent over a group of questions that is not relevant to them. Applying any imputation technique to missing values caused by skip patterns may add misinformation. Moreover, skip pattern analysis provides detection of non-applicable data along with undetermined and inconsistent data. The Medical, Epidemiological and Social Aspects of Aging (MESA) questionnaire is responded by a large number of subjects which entails the need of an automated method. Manual methods may not provide reliable results and they are costly. A directed, acyclic graph is generated based on the questionnaire. A graph theory method is proposed to detect each missing data type. The method finds a minimal deletion set of nodes, that are the nodes once deleted, leaves a connected graph behind. The deleted nodes can be considered as noise. The experiments are conducted on a subset of the MESA data and the results show that there are 16.04% of non-applicable data, 7.09% of genuine missing data, 0.61% of undetermined data and 0.015% of inconsistent data. This method can be used for preprocessing the dataset and estimating the noise.