Data Mining In Healthcare Research Articles

2015, big data in healthcare: for whom the bell tolls?

The health care sector generates bountiful data around the clock, which can paradoxically complicate our quest for information, knowledge, and ‘wisdom’ [1]. It may be prudent that medical end-users consider seriously a fundamental change that would allow us to gain full value from the ‘big data’ that the health care section is generating [2]. Proponents of the big data revolution suggest that the value for physicians rests on the added information provided by big data analysis. Indeed, supplementary information could clarify areas for improvement, such as optimization of treatments, reduced adverse events and readmission rates, earlier identification of those patients whose health is worsening, and more efficient identification of populations in need. Recent cloud computing has even turned computing and software into commodity services, and such big data processing seems to be forging a technology revolution [3,4]. However, opponents of the big data revolution speculate that validation and impact analyses of big data in health care are still in their infancy, and approaches such as Google’s baseline study may thus not be effective in preventing disease, and possibly even lead to unnecessary, if not harmful, interventions [5]. The value of any kind of data is greatly enhanced when it exists in a form that allows for integration with other data [6]. One problem with large data sets in general is the risk for ‘GIGO’ - garbage in, garbage out - that requires very careful and thoughtful investigation to rule out the many errors of large-scale data capture before any of it can be used. Thus, an essential step for data integration is the annotation of multiple bodies of data using common controlled vocabularies or ‘ontologies’ that incorporate accurate representations of biological reality [7]. Data mining in health care is not new, and initiatives for data acquisition and analysis, storage and retrieval have all been presented before [8,9]. Yet, to our knowledge, subcommittees addressing ontology have not been established by any medical specialty. As clinicians, we apply general principles of risk stratification and risk modification to individual patients based on our education and experience. The proliferation of biomedical research makes it difficult to keep abreast of current knowledge, so clinical decision support technologies that are based on data mining techniques are knocking at our doors. Although their implementation seems inevitable, the lack of standardization continues [9]. A dramatic paradigm shift toward controlled ontologies is needed in order to optimize the technologies that integrate big data into medical decision making and practice.

Data Mining in Healthcare using Hybrid Approach

Modern medicine generates a great deal of information stored in the medical database. Extracting useful data and making scientific decision for diagnosis and treatment of disease from the database increasingly becomes necessary. We propose a Heart diseases Prediction System for the society to prevent the cause of the death. So we are analyzing heart disease patient to identify which treatment is most effective one and provide better result.

Improving Personalized Clinical Risk Prediction Based on Causality-Based Association Rules.

Developing clinical risk prediction models is one of the main tasks of healthcare data mining. Advanced data collection techniques in current Big Data era have created an emerging and urgent need for scalable, computer-based data mining methods. These methods can turn data into useful, personalized decision support knowledge in a flexible, cost-effective, and productive way. In our previous study, we developed a tool, called icuARM- II, that can generate personalized clinical risk prediction evidence using a temporal rule mining framework. However, the generation of final risk prediction possibility with icuARM-II still relied on human interpretation, which was subjective and, most of time, biased. In this study, we propose a new mechanism to improve icuARM-II's rule selection by including the concept of causal analysis. The generated risk prediction is quantitatively assessed using calibration statistics. To evaluate the performance of the new rule selection mechanism, we conducted a case study to predict short-term intensive care unit mortality based on personalized lab testing abnormalities. Our results demonstrated a better-calibrated ICU risk prediction using the new causality-base rule selection solution by comparing with conventional confidence-only rule selection methods.

Guest editorial: Special issue on data mining for medicine and healthcare

Guest editorial: Special issue on data mining for medicine and healthcare

Data Mining in Healthcare – A Review

Abstract The knowledge discovery in database (KDD) is alarmed with development of methods and techniques for making use of data. One of the most important step of the KDD is the data mining. Data mining is the process of pattern discovery and extraction where huge amount of data is involved. Both the data mining and healthcare industry have emerged some of reliable early detection systems and other various healthcare related systems from the clinical and diagnosis data. In regard to this emerge, we have reviewed the various paper involved in this field in terms of method, algorithms and results. This review paper has consolidated the papers reviewed inline to the disciplines, model, tasks and methods. Results and evaluation methods are discussed for selected papers and a summary of the finding is presented to conclude the paper.

Significant patterns for oral cancer detection: association rule on clinical examination and history data

This paper presents an application of data mining in healthcare and discusses how the generated patterns can be used by physicians for early detection and hence prevention of oral cancer. One of the popular association rule mining algorithms, Apriori is used to extract a set of significant rules from the data pertaining to clinical examination, history, and survivability of the cancer patients. These rules suggest various investigations and also help predicting distribution of cancer in oral cavity. In spite of the fact that the clinical judgment happens by means of examination of the oral cavity and tongue using various diagnostic tools, the majority of cases present to a healthcare setups at later stages of tumor subtypes, thereby lessening the chances of survival due to delay in diagnosis. Nevertheless, the data mining rules would certainly assist the practitioners in early detection of oral cancer and prediction of distribution of cancer in the oral cavity that can be helpful preventing the disease. The experimental results demonstrate that all the generated rules hold the highest confidence level, thereby making them useful for early detection and prevention of the oral cancer.

Building Weighted Associative Classifiers using Maximum Likelihood Estimation to Improve Prediction Accuracy in Health Care Data Mining

Associative classifiers are new classification approach that use association rules for classification. An important advantage of these classification systems is that, using association rule mining (ARM) they are able to examine several features at a time. Many applications can benefit from good classification model. Associative classifiers are especially fit to applications where the model may assist the domain experts in their decisions. Medical diagnosis is a domain where the maximum accuracy of the model is desired. In this paper, we propose a framework weighted associative classifier (WAC) that assigns different weights to different attributes according to their predicting capability. We are using maximum likelihood estimation (MLE) theory to calculate weight of each attribute using training data. We also show how existing Apriori algorithm can be modified in weighted environment to infer association rule from medical dataset having numeric valued attributes as the conventional ARM usually deals with the transaction database with categorical values. Experiments have been performed on benchmark data set to evaluate the performance of WAC in terms of accuracy, number of rules generating and impact of minimum support threshold on WAC outcomes. The result reveals that WAC is a promising alternative in medical prediction and certainly deserves further attention.

Association of Data Mining and Biomedical Domain: Choosing the Best Algorithm for Analysis

Data mining has been used prosperously in the favourably perceived areas, such as e-business, marketing, health domain and retail, because of which it is now applicable in knowledge discovery in databases (KDD). While data mining has become a much-lauded tool in medical-related fields, its role in the healthcare arena is still being explored. Data mining is mainly gaining its importance and usage in the areas of medicine and public health. Currently, most applications of data mining in healthcare can be categorised into two areas: decision support for clinical practice and decision making. In this paper, we studied and analysed the performance of the popular clustering methods like k-mean, Self Organized Maps and EM methods by using the bio medical data extracted from UCI Machine leaning repository. We made a comparative analysis between Entropy based mean (EBM) clustering approach and traditional clustering methods through accuracy, return on investment, reliability, time complexity and fitness. With this paper, we discussed the various issues to explore the strength of the data mining methodology.

Prediction and decision making in Health Care using Data Mining

Tendency for data mining application in healthcare today is great, because healthcare sector is rich with information, and data mining is becoming a necessity. Healthcare organizations produce and collect large volumes of information on daily basis. Use of information technologies allows automatization of processes for extraction of data that help to get interesting knowledge and regularities, which means the elimination of manual tasks and easier extraction of data directly from electronic records, transferring onto secure electronic system of medical records which will save lives and reduce the cost of the healthcare services, as well and early discovery of contagious diseases with the advanced collection of data. Data mining can enable healthcare organizations to predict trends in the patient conditions and their behaviors, which is accomplished by data analysis from different perspectives and discovering connections and relations from seemingly unrelated information. Raw data from healthcare organizations are voluminous and heterogeneous. They need to be collected and stored in the organized forms, and their integration enables forming of hospital information system. Healthcare data mining provides countless possibilities for hidden pattern investigation from these data sets. These patterns can be used by physicians to determine diagnoses, prognoses and treatments for patients in healthcare organizations.

Applying Machine Learning Methods in Diagnosing Heart Disease for Diabetic Patients

Classifying data is a common task in Machine learning. Data mining plays an essential role for extracting knowledge from large databases from enterprises operational databases. Data mining in health care is an emerging field of high importance for providing prognosis and a deeper understanding of medical data. Most data mining methods depend on a set of features that define the behaviour of the learning algorithm and directly or indirectly influence the complexity of resulting models. Heart disease is the leading cause of death in the world over the past 10 years. Researches have been using several data mining techniques in the diagnosis of heart disease. Diabetes is a chronic disease that occurs when the pancreas does not produce enough insulin, or when the body cannot effectively use the insulin it produces. Most of these systems have successfully employed Machine learning methods such as Naive Bayes and Support Vector Machines for the classification purpose. Support vector machines are a modern technique in the field of machine learning and have been successfully used in different fields of application. Using diabetics’ diagnosis, the system exhibited good accuracy and predicts attributes such as age, sex, blood pressure and blood sugar and the chances of a diabetic patient getting a heart disease.

Healthcare Data Mining

A model to predict the Length of Stay (LOS) for hospitalized patients can be an effective tool for measuring the consumption of hospital resources. Such a model will enable early interventions to prevent complications and prolonged LOS and also enable more efficient utilization of manpower and facilities in hospitals. In this paper, the authors propose an approach for Predicting Hospital Length of Stay (PHLOS) using a multi-tiered data mining approach. In their aproach, the authors form training sets, using groups of similar claims identified by k-means clustering and perfom classification using ten different classifiers. The authors provide a combined measure of performance to statistically evaluate and rank the classifiers for different levels of clustering. They consistently found that using clustering as a precursor to form the training set gives better prediction results as compared to non-clustering based training sets. The authors have also found the accuracies to be consistently higher than some reported in the current literature for predicting individual patient LOS. Binning the LOS to three groups of short, medium and long stays, their method identifies patients who need aggressive or moderate early interventions to prevent prolonged stays. The classification techniques used in this study are interpretable, enabling them to examine the details of the classification rules learned from the data. As a result, this study provides insight into the underlying factors that influence hospital length of stay. They also examine the authors’ prediction results for three randomly selected conditions with domain expert insights.

Fuzzy Weighted Associative Classifier : A Predictive Technique for Health Care Data Mining

In this paper we extend the problem of classification using Fuzzy Association Rule Mining and propose the concept of Fuzzy Weighted Associative Classifier (FWAC). Classification based on Association rules is considered to be effective and advantageous in many cases. Associative classifiers are especially fit to applications where the model may assist the domain experts in their decisions. Weighted Associative Classifiers that takes advantage of weighted Association Rule Mining is already being proposed. However, there is a so-called sharp boundary problem in association rules mining with quantitative attribute domains. This paper proposes a new Fuzzy Weighted Associative Classifier (FWAC) that generates classification rules using Fuzzy Weighted Support and Confidence framework. The naive approach can be used to generating strong rules instead of weak irrelevant rules. where fuzzy logic is used in partitioning the domains. The problem of Invalidation of Downward Closure property is solved and the concept of Fuzzy Weighted Support and Fuzzy Weighted Confidence frame work for Boolean and quantitative item with weighted setting is generalized. We propose a theoretical model to introduce new associative classifier that takes advantage of Fuzzy Weighted Association rule mining.

Data Mining in Healthcare and Biomedicine: A Survey of the Literature

As a new concept that emerged in the middle of 1990's, data mining can help researchers gain both novel and deep insights and can facilitate unprecedented understanding of large biomedical datasets. Data mining can uncover new biomedical and healthcare knowledge for clinical and administrative decision making as well as generate scientific hypotheses from large experimental data, clinical databases, and/or biomedical literature. This review first introduces data mining in general (e.g., the background, definition, and process of data mining), discusses the major differences between statistics and data mining and then speaks to the uniqueness of data mining in the biomedical and healthcare fields. A brief summarization of various data mining algorithms used for classification, clustering, and association as well as their respective advantages and drawbacks is also presented. Suggested guidelines on how to use data mining algorithms in each area of classification, clustering, and association are offered along with three examples of how data mining has been used in the healthcare industry. Given the successful application of data mining by health related organizations that has helped to predict health insurance fraud and under-diagnosed patients, and identify and classify at-risk people in terms of health with the goal of reducing healthcare cost, we introduce how data mining technologies (in each area of classification, clustering, and association) have been used for a multitude of purposes, including research in the biomedical and healthcare fields. A discussion of the technologies available to enable the prediction of healthcare costs (including length of hospital stay), disease diagnosis and prognosis, and the discovery of hidden biomedical and healthcare patterns from related databases is offered along with a discussion of the use of data mining to discover such relationships as those between health conditions and a disease, relationships among diseases, and relationships among drugs. The article concludes with a discussion of the problems that hamper the clinical use of data mining by health professionals.

Using Associative Classifiers for Predictive Analysis in Health Care Data Mining

Association rule mining is one of the most important and well researched techniques of data mining for descriptive task, initially used for market basket analysis. It finds all the rules existing in the transactional database that satisfy some minimum support and minimum confidence constraints. Classification using Association rule mining is another major Predictive analysis technique that aims to discover a small set of rule in the database that forms an accurate classifier. In this paper, we introduce the combined approach that integrates association rule mining and classification rule mining called Associative Classification (AC). This is new classification approach. The integration is done by focusing on mining a special subset of association rules called classification association rule (CAR). And then classification is being performed using these CAR. Using association rule mining for constructing classification systems is a promising approach. Given the readability of the associative classifiers, they are especially fit to applications were the model may assist domain experts in their decisions. Medical field is a good example was such applications may appear. Consider an example were a physician has to examine a patient. There is a considerable amount of information associated with the patient (e.g. personal data, medical tests, etc.). A classification system can assist the physician in this process. The system can predict if the patient is likely to have a certain disease or present incompatibility with some treatments. Considering the output of the classification model, the physician can make a better decision on the treatment to be applied to this patient. There are many associative classification approaches that have been proposed recently such as CBA, CMAR, CPAR and MCAR and MMAC. Also Combining the Advanced association rule mining with classifiers gives a new type of Associative classifiers with small refinement in the definition of support and confidence that satisfies the validation of downward closure property. We will discuss advanced associative classifiers being proposed in recent years to provide better accuracy as compare to traditional Classifiers.

Development of Application Service Provider System with Healthcare Data Mining

Development of Application Service Provider System with Healthcare Data Mining

A scalable mobile phone‐based system for multiple vital signs monitoring and healthcare

To meet the increasing needs for ubiquitous healthcare, a mobile phone‐based system for monitoring multiple vital signs is under development. In this paper, design and implementation of the system architecture are described. The hierarchy of this system comprises three layers, which respectively handle multiple vital signs sensing, data/command communication via either wireless or wired means, and healthcare management. The fundamental basis of the sensing layer is a wearable cordless sensor device for monitoring vital signs without discomfort to the user during daily activities. The data communication layer performs bi‐directional information exchange between the sensing layer and the management layer. The uppermost management layer conducts data mining and analysis for risk factors assessment and healthcare. Overall considerations of implementation method and prototype fabrication are outlined. Finally, applicability to a variety of real‐world situations, and provision of customizable solutions not only for home healthcare but also for other vital signs‐related domains (such as emergency rescue and safety guarantee) are discussed. Three of the most promising applications based upon this system are described.

Bayesian analysis, pattern analysis, and data mining in health care.

To discuss the current role of data mining and Bayesian methods in biomedicine and heath care, in particular critical care. Bayesian networks and other probabilistic graphical models are beginning to emerge as methods for discovering patterns in biomedical data and also as a basis for the representation of the uncertainties underlying clinical decision-making. At the same time, techniques from machine learning are being used to solve biomedical and health-care problems. With the increasing availability of biomedical and health-care data with a wide range of characteristics there is an increasing need to use methods which allow modeling the uncertainties that come with the problem, are capable of dealing with missing data, allow integrating data from various sources, explicitly indicate statistical dependence and independence, and allow integrating biomedical and clinical background knowledge. These requirements have given rise to an influx of new methods into the field of data analysis in health care, in particular from the fields of machine learning and probabilistic graphical models.