By Topic

IBM Journal of Research and Development

Issue 5 • Date Sept.-Oct. 2012

Technologies for Healthcare Transformation

The healthcare industry worldwide is undergoing a profound transformation to improve quality of care and reduce cost. At the center of this transformation are efforts toward the creation of an evidence-centric ecosystem that enables the generation of patient-centered medical insight from aggregated medical data. Such evidence must be delivered at the point of care in a highly consumable manner, and the evidence must be incorporated into models for policy decision-making. This special issue presents state-of-the-art applications of advanced analytics, visualizations, and medical records to enable such transformation.

Nontopical Papers

Two nontopical papers are included at the end of this issue. Topics include the assessment of "technical debt" by identifying design flaws in software systems and discussions on problem-oriented system architectures.

Filter Results

Displaying Results 1 - 15 of 15
  • Front Cover

    Page(s): C1
    Save to Project icon | PDF file iconPDF (757 KB)  
    Freely Available from IEEE
  • Cover 2

    Page(s): C2
    Save to Project icon | PDF file iconPDF (7 KB)  
    Freely Available from IEEE
  • Table of Contents

    Page(s): 1 - 2
    Save to Project icon | PDF file iconPDF (51 KB)  
    Freely Available from IEEE
  • Preface: Technologies for healthcare transformation

    Page(s): 0:1 - 0:2
    Save to Project icon | PDF file iconPDF (48 KB)  
    Freely Available from IEEE
  • Meaningful use of patient-centric health records for healthcare transformation

    Page(s): 1:1 - 1:7
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (98 KB) |  | HTML iconHTML  

    Healthcare transformation through the use of information technologies is partly dependent on effectively applying the most up-to-date knowledge to the complete representation of the patient's past medical history at the point of care. In order for health knowledge to be effectively used, patient information should be sufficiently detailed, and more importantly, the semantics of the data should be made explicit and machine processable. Often, the semantics of data are represented implicitly and are hidden in unstructured and disconnected descriptions of the data. Alternatively, they may be known to human experts, such as the researchers or caregivers involved in the generation of that data. Predefined schemas of health information systems are insufficient; it is extremely important to explicitly represent the patient-specific context of each discrete data item and how it relates to other data items (e.g., indications and outcomes of an operation), as well as how it fits into the entire health history of an individual. Dispersed and disparate medical records of a patient are often inconsistent and incoherent. An independent patient-centric electronic health record may provide an explicit, coherent, and complete representation of contextual data. This paper reviews healthcare transformations, with consideration of an independent health record. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An infrastructure for real-time population health assessment and monitoring

    Page(s): 2:1 - 2:11
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (2392 KB) |  | HTML iconHTML  

    The fragmented nature of population health information is a barrier to public health practice. Despite repeated demands by policymakers, administrators, and practitioners to develop information systems that provide a coherent view of population health status, there has been limited progress toward developing such an infrastructure. We are creating an informatics platform for describing and monitoring the health status of a defined population by integrating multiple clinical and administrative data sources. This infrastructure, which involves a population health record, is designed to enable development of detailed portraits of population health, facilitate monitoring of population health indicators, enable evaluation of interventions, and provide clinicians and patients with population context to assist diagnostic and therapeutic decision-making. In addition to supporting public health professionals, clinicians, and the public, we are designing the infrastructure to provide a platform for public health informatics research. This early report presents the requirements and architecture for the infrastructure and describes the initial implementation of the population health record, focusing on indicators of chronic diseases related to obesity. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Real-time analysis for short-term prognosis in intensive care

    Page(s): 3:1 - 3:10
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (1045 KB) |  | HTML iconHTML  

    There is a tremendous amount of data available to physicians at the point of care in intensive care environments; however, physicians do not have the tools to extract relevant clinical information in a timely manner. They mostly rely on manual inspection of the data to make diagnosis and prognosis. New software technologies make it possible to automatically generate meaningful information in real-time from the physiological data streams of patients. These real-time monitoring software technologies can support multiple concurrent patients and have been developed mainly to be applied in a reactive way, for the detection of patient complications. This paper proposes ways to extend these real-time monitoring technologies to help intensive care become more proactive. We present a system design and algorithms for a prototype system that produces in real-time short-term predictions of patient physiological data from live and historical patient data. One technique is based solely on the patient's own live data streams. The other technique is based on comparing the patient's physiological data streams with data streams of similar patients that have been monitored in the past. An extensive experimental study of this system is proposed to evaluate its predictive ability. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Case-based reasoning in comparative effectiveness research

    Page(s): 4:1 - 4:12
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (160 KB) |  | HTML iconHTML  

    A medical case, as defined by the medical field, is the fundamental building block of medical knowledge. We combine the concept of medical case with indirect evidence from similar patients so as to enable the performance of CER (comparative effectiveness research) treatment comparisons for personalization of medical care. We propose that the vehicle by which this goal is achieved is provided by the integration of case-based reasoning and CER considerations. We discuss the challenges involved and propose a roadmap for creating scientifically sound real-world evidence for assisting personalized treatment decisions. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Facilitating observational study for comparative effectiveness research

    Page(s): 5:1 - 5:12
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (4063 KB) |  | HTML iconHTML  

    Comparative effectiveness research (CER) compares the benefits and harms of alternative methods to prevent, diagnose, treat, and monitor a clinical condition or to improve the delivery of care for a particular group of patients. With the advent of clinical information systems, e.g., the electronic medical record, observational studies play an increasingly important role in generating clinical evidence for CER. From an information technology perspective, we identify four challenges associated with CER: 1) compliance with recommended procedures in epidemiology, 2) efficient discovery of potentially interesting hypotheses, 3) correct use of the appropriate statistical methods in hypothesis testing, and 4) the appropriate presentation and interpretation of results. To address these challenges, we propose a new system On-demand Comparative Effectiveness Research Accelerator (OCERA). The new system can facilitate observational studies for CER and assist clinical researchers in effectively and efficiently conducting high-quality CER studies. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multifaceted visual analytics for healthcare applications

    Page(s): 6:1 - 6:12
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (5699 KB) |  | HTML iconHTML  

    A vast amount of electronic healthcare information is now available, ranging from online healthcare articles to patient electronic health records. These electronic data sets contain valuable information that can guide the decisions of both clinical professionals and patients. However, the data are often difficult to analyze, in part because they often contain multiple facets of information. For example, patient records have information on demographics, diagnoses, medications, lab results, and symptoms. To address this challenge, we have been exploring interactive visual analysis techniques that help visualize such healthcare information in an intuitive manner and enable the discovery of actionable insights. In this paper, we present a review of three different techniques. First, we describe a visual analytic system named FacetAtlas that helps users navigate a large set of disease-related documents and understand multidimensional relationships for key semantic concepts such as symptoms and treatments. We then present SolarMap, an alternative technique to FacetAtlas that adds visual representations of facet keyword clusters to expose greater information about semantic relationships. Finally, we describe the DICON (Dynamic Icon) visualization tool, which allows users to interactively view and refine similar multidimensional patient clusters. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Visualization of multivariate time-series data in a neonatal ICU

    Page(s): 7:1 - 7:12
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (4167 KB) |  | HTML iconHTML  

    Existing visualizations in the neonatal intensive care unit (NICU) frequently obscure important trends in clinical data presented to the clinician in tabular displays or stacked univariate plots of variables as a function of time. Scales and alarm limits in clinical displays are based on data that is typical for adults (i.e., adult “norm data”), resulting in confusing or misleading displays in the NICU. In premature infants, norm data differs significantly both from adult values and among infants of differing gestational ages. Interfaces designed to display adult values hinder the perception of clinical changes. We developed a visualization that provides an integrated, multivariate interface for representing laboratory and physiological data in the NICU. We present its design and evaluation and discuss potential future applications of this visualization that is interactive, animated, and personalized to an individual patient so that clinicians can quickly and efficiently recognize significant changes in the patient's condition. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A comparison of decision-maker perspectives for optimal cholesterol treatment

    Page(s): 8:1 - 8:12
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (1119 KB) |  | HTML iconHTML  

    Medical decisions often involve tradeoff among competing criteria. For example, patients with third-party health insurance are primarily concerned about maximizing their quality-adjusted lifespan, since the majority of the cost burden typically falls on the third-party payer. On the other hand, third-party payers are incented to minimize total healthcare-related costs. Therefore, third-party payers must weigh the short-term cost of treatment against the long-term benefits of avoiding more costly health outcomes associated with disease progression and adverse events. The goal of the societal perspective is to achieve a reasonable balance among these competing criteria of quality-adjusted lifespan and costs. Treatment of diabetes provides a good example of the need to apply multicriteria decision-making models to treatment decisions. Chronic diseases such as diabetes are associated with high medical costs and a large number of available treatment options. In this paper, we use a Markov decision process (MDP) to show how decision-maker perspectives can influence medical treatment decisions related to cardiovascular risk management in patients with type 2 diabetes. We compare optimal treatment decisions from three different perspectives: societal, patient, and third-party payer. We further formulate an inverse MDP model to estimate the implied monetary value of a year of life, from the societal perspective, according to current U.S. treatment guidelines. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Assessing technical debt by identifying design flaws in software systems

    Page(s): 9:1 - 9:13
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (2449 KB) |  | HTML iconHTML  

    Tough time-to-market constraints and unanticipated integration or evolution issues lead to design tradeoffs that usually cause flaws in the structure of a software system. Thus, maintenance costs grow significantly. The impact of these design decisions, which provide short-term benefits at the expense of the system’s design integrity, is usually referred to as technical debt. In this paper, I propose a novel framework for assessing technical debt using a technique for detecting design flaws, i.e., specific violations of well-established design principles and rules. To make the framework comprehensive and balanced, it is built on top of a set of metrics-based detection rules for well-known design flaws that cover all of the major aspects of design such as coupling, complexity, and encapsulation. I demonstrate the effectiveness of the framework by assessing the evolution of technical debt symptoms over a total of 63 releases of two popular Eclipse® projects. The case study shows how the framework can detect debt symptoms and past refactoring actions. The experiment also reveals that in the absence of such a framework, restructuring actions are not always coherent and systematic, not even when performed by very experienced developers. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Beyond the Zachman framework: Problem-oriented system architecture

    Page(s): 10:1 - 10:9
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (1385 KB) |  | HTML iconHTML  

    The year 2012 marks the twenty-fifth anniversary of “A framework for information systems architecture,” written by John Zachman and published in the IBM Systems Journal. The first part of this paper reviews the Zachman and similar frameworks and concludes that there are a number of limitations in the framework approach when applied to today's technology environment and business problems. These include the inability of the problem owner to properly describe a solution, the partitioning approach, and the decision-making processes in the context of uncertainty and change. The second part of this paper analyzes today's problems and allocates them to one of three classifications: tame, complex, and wicked, depending on the degree of certainty and stability of knowledge and decisions in both the problem and the solution domains. The final part outlines an approach to problem-solving and architecture development using techniques borrowed from cybernetics and control theory. It proposes that partitioning should be determined by the nature of the problem and potential solutions; that feedback loops should be implemented in order to control the process; that the architect should work across the business problem and solution spaces; and that decisions should be related to business value. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Cover 3

    Page(s): C3
    Save to Project icon | PDF file iconPDF (7 KB)  
    Freely Available from IEEE

Aims & Scope

The IBM Journal of Research and Development is a peer-reviewed technical journal, published bimonthly, which features the work of authors in the science, technology and engineering of information systems.

Full Aims & Scope

Meet Our Editors

Editor-in-Chief
Clifford A. Pickover
IBM T. J. Watson Research Center