Medical Outcome Prediction for Intensive Care Unit Patients

The rate of people dying from medical errors in hospitals each year is very high. Errors that frequently occur during the course of providing health care are adverse drug events and improper transfusions, surgical injuries and wrong-site surgery, suicides, restraint-related injuries or death, falls, burns, pressure ulcers, and mistaken patient identities. Medical decision support systems play an increasingly important role in medical practice. By assisting physicians in making clinical decisions, medical decision support systems improve the quality of medical care. Two approaches have been investigated for the prediction of medical outcomes: “hours of ventilation” and the “mortality rate” in the adult intensive care unit. The first approach is based on neural networks with the weight-elimination algorithm, and the second is based on genetic programming. Both approaches are compared to commonly used machine learning algorithms. Results show that both algorithms developed score well for the outcomes selected.

Evaluation of Clustering Patterns using Singular Value Decomposition (SVD)

Computational techniques, such as Simple K, have been used for exploratory analysis in applications ranging from data mining research, machine learning, and computational biology. The medical domain has benefitted from these applications, and in this regard, the authors analyze patterns in individuals of selected age groups linked with the possibility of Metabolic Syndrome (MetS), a disorder affecting approximately 45% of the elderly. The study identifies groups of individuals behaving in two defined categories, that is, those diagnosed with MetS (MetS Positive) and those who are not (MetS Negative), comparing the pattern definition. The paper compares the cluster formation in patterns when using a data reduction technique referred to as Singular Value Decomposition (SVD) versus eliminating its application in clustering. Data reduction techniques like SVD have proved to be very useful in projecting only what is considered to be key relations in the data by suppressing the less important ones. With the existence of high dimensionality, the importance of SVD can be highly effective. By applying two internal measures to validate the cluster quality, findings in this study prove interesting in context to both approaches.

Privacy Preserving Integration of Health Care Data

For health care related research studies the medical records of patients may need to be retrieved from multiple sites with different regulations on the disclosure of health information. Given the sensitive nature of health care information, privacy is a major concern when patients’ health care data is used for research purposes. In this paper, the authors propose approaches for integration and querying of health care data from multiple sources in a secure and privacy preserving manner. In particular, the first approach ensures secure data integration based on unique identifiers, and the second one considers data integration based on quasi identifiers, for which a rule-based framework is proposed for cross-linking data records, including secure character matching.

A Formal Approach to Evaluating Medical Ontology Systems using Naturalness

Ontologies, terminologies and vocabularies are popular repositories for collecting the terms used in a domain. It may be expected that in the future more such ontologies will be created for domain experts. However, there is increasing interest in making the language of experts understandable to casual users. For example, cancer patients often research their cases on the Web. The authors consider the problem of objectively evaluating the quality of ontologies (QoO). This article formalizes the notion of naturalness as a component of QoO and quantitatively measures naturalness for well-known ontologies (UMLS, WordNet, OpenCyc) based on their concepts, IS-A relationships and semantic relationships. To compute numeric values characterizing the naturalness of an ontology, this article defines appropriate metrics. As absolute numbers in such a pursuit are often meaningless, we concentrate on using relative naturalness metrics. That allows us to say that a certain ontology is relatively more natural than another one.

A Partial Optimization Approach for Privacy Preserving Frequent Itemset Mining

While data mining has been widely acclaimed as a technology that can bring potential benefits to organizations, such efforts may be negatively impacted by the possibility of discovering sensitive patterns, particularly in patient data. In this article the authors present an approach to identify the optimal set of transactions that, if sanitized, would result in hiding sensitive patterns while reducing the accidental hiding of legitimate patterns and the damage done to the database as much as possible. Their methodology allows the user to adjust their preference on the weights assigned to benefits in terms of the number of restrictive patterns hidden, cost in terms of the number of legitimate patterns hidden, and damage to the database in terms of the difference between marginal frequencies of items for the original and sanitized databases. Most approaches in solving the given problem found in literature are all-heuristic based without formal treatment for optimality. While in a few work, ILP has been used previously as a formal optimization approach, the novelty of this method is the extremely low cost-complexity model in contrast to the others. They implement our methodology in C and C++ and ran several experiments with synthetic data generated with the IBM synthetic data generator. The experiments show excellent results when compared to those in the literature.

Regulatory Compliance and the Correlation to Privacy Protection in Healthcare

Recent government-led efforts and industry-sponsored privacy initiatives in the healthcare sector have received heightened publicity. The current set of privacy legislation mandates that all parties involved in the delivery of care specify and publish privacy policies regarding the use and disclosure of personal health information. The authors’ study of actual healthcare privacy policies indicates that the vague representations in published privacy policies are not strongly correlated with adequate privacy protection for the patient. This phenomenon is not due to a lack of available technology to enforce privacy policies, but rather to the will of the healthcare entities to enforce strong privacy protections and their interpretation of minimum compliance obligations. Using available information systems and data mining techniques, this article describes an infrastructure for privacy protection based on the idea of policy refinement to allow the transition from the current state of perceived to be privacy-preserving systems to actually privacy-preserving systems.

Modeling a Classification Scheme of Epileptic Seizures Using Ontology Web Language

Ontology-based disease classification offers a way to rigorously assign disease types and to reuse diagnostic knowledge. However, ontology itself is not sufficient for fully representing the complex knowledge needed in classification schemes which are continuously evolving. This article describes the application of SWRL/OWL-DL to the representation of knowledge intended for proper classification of a complex neurological condition, namely epilepsy. The authors present a rigorous and expandable approach to the ontological classification of epileptic seizures based on the 1981ILAE classification. It provides a classification knowledge base that can be extended with rules that describe constraints in SWRL. Moreover, by transforming an OWL classification scheme into JESS (rule engine in Java platform) facts and by transforming SWRL constraints into JESS, logical inferences and reasoning provide a mechanism to discover new knowledge and facts. The logic representation of epileptic classification amounts to greater community understanding among practitioners, knowledge reuse and interoperability.

Relevance of Mesh Dimension Optimization, Geometry Simplification and Discretization Accuracy in the Study of Mechanical Behaviour of Bare Metal Stents

In this paper, a set of analyses on the deployment of coronary stents by using a nonlinear finite element method is proposed. The author proposes a convergence test able to select the appropriate mesh dimension and a methodology to perform the simplification of structures composed of cyclically repeated units to reduce the number of degree of freedom and the analysis run time. A systematic study, based on the analysis of seven meshes for each model, is performed, gradually reducing the element dimension. In addition, geometric models are simplified considering symmetries; adequate boundary conditions are applied and verified based on the results obtained from analysis of the whole model.

Optimization Model and Algorithm Help to Screen and Treat Sexually Transmitted Diseases

Chlamydia trachomatis (CT) and Neisseria gonorrhoeae (GC) are two common sexually transmitted diseases among women in the United States. Publicly funded programs usually do not have enough money to screen and treat all patients. Therefore, the authors propose a new resource allocation model to assist clinical managers to make decisions on identifying at-risk population groups, as well as selecting a screening and treatment strategy for CT and GC patients under a fixed budget. At the same time, the authors also develop a two-step branch-and-bound algorithm tailor-made for our model. Running on real-life data, the algorithm calculates the optimal solution within a very short time. The new algorithm also improves the accuracy of an approximate solution obtained by Excel Solver. This study has shown that a resource allocation model and algorithm might have a significant impact on real clinical issues.

Upper GI Bleed, Etiology, Role of Endoscopy in Rural Population of Punjab

Haematemesis and malena are the two most important symptoms of upper gastrointestinal bleeding . The most common cause of upper gastrointestinal bleeding is due to a peptic ulcer. In this paper, the authors research the cause of bleeding. Contrary to previous studies, results favor esophageal varices, e.g., alcoholism or cirrhosis liver post necrotic, as the most common cause of bleeding rather than a peptic ulcer. The authors’ study is based on an observational retrospective protocol with records of 50 consecutive patients with GI bleeding, attending the emergency room from February 2007 until September 2009. Results show that the treatment of UGI bleeding has made important progress since the introduction of emergency endoscopy and endoscopic techniques for haemostasis. The application of specific protocols significantly decreases rebleeding and the need for surgery, whereas mortality is still high. The data highlight the decreasing trend of peptic ulcer as the sole cause of bleeding, as shown in previous literature, ascertaining that varices are now the most common variable.