Marion Lee Blount

Remote health-care monitoring using personal care connect

Caring for patients with chronic illnesses is costly-nearly

Opportunities for Pervasive Computing in Chronic Cancer Care

1.27 trillion today and predicted to grow much larger. To address this trend, we have designed and built a platform, called Personal Care Connect (PCC), to facilitate the remote monitoring of patients. By providing caregivers with timely access to a patients health status, they can provide patients with appropriate preventive interventions, helping to avoid hospitalization and to improve the patients quality of care and quality of life. PCC may reduce health-care costs by focusing on preventive measures and monitoring instead of emergency care and hospital admissions. Although PCC may have features in common with other remote monitoring systems, it differs from them in that it is a standards-based, open platform designed to integrate with devices from device vendors and applications from independent software vendors. One of the motivations for PCC is to create and propagate a working environment of medical devices and applications that results in innovative solutions. In this paper, we describe the PCC remote monitoring system, including our pilot tests of the system.

DataX: an approach to ubiquitous database access

While changing from a predominantly terminal to an increasingly chronic condition, cancer is still a growing concern. Accompanying this change are new opportunities for technologies to support patients, their caregivers, and clinicians. In this paper, we present an in-depth study of cancer communities. From this exploration, we define and describe the concept of a personal cancer journey. We examine lessons and design opportunities across this journey for sensing and context-awareness and capture and access applications.

Advances and Challenges for Scalable Provenance in Stream Processing Systems

The paper describes an approach for enabling remote database access from heterogeneous thin clients. DataX is a proxy based architecture that supports disconnected operation by replicating a subset of the database on the mobile client, using a weak consistency criterion. It adapts data replication to device characteristics, link attributes and user preferences. It employs a per-device renderer to present data in a form layout, making the application logic separate from user interface logic and independent of the device type. It offers small footprint of client-side software, rapid development of end-to-end solutions, and portability across multiple server platforms.

A time-and-value centric provenance model and architecture for medical event streams

While data provenance is a well-studied topic in both database and workflow systems, its support within stream processing systems presents a new set of challenges. Part of the challenge is the high stream event rate and the low processing latency requirements imposed by many streaming applications. For example, emerging streaming applications in healthcare or finance call for data provenance, as illustrated in the Century stream processing infrastructure that we are building for supporting online healthcare analytics. At anytime, given an output data element (e.g., a medical alert) generated by Century, the system must be able to retrieve the input and intermediate data elements that led to its generation. In this paper, we describe the requirements behind our initial implementation of Centurys provenance subsystem. We then analyze its strengths and limitations and propose a new provenance architecture to address some of these limitations. The paper also includes a discussion on the open challenges in this area.

Century: Automated Aspects of Patient Care

Provenance becomes a critical requirement for healthcare IT infrastructures, especially when pervasive biomedical sensors act as a source of raw medical streams for large-scale, automated clinical decision support systems. Medical and legal requirements will make it obligatory for such systems to answer queries regarding the underlying data samples from which output alerts are derived, the IDs of the processing components used and the privileges of the individuals and software components accessing the medical data. Unfortunately, existing models of either annotation or process based provenance are designed for transaction-oriented systems and do not satisfy the unique requirements for systems processing high-volume, continuous medical streams. This paper proposes a simple, but useful, hybrid provenance model called Time-Value Centric (TVC) provenance.

Body sensor data processing using stream computing

Remote health monitoring affords the possibility of improving the quality of health care by enabling relatively inexpensive out-patient care. However, remote health monitoring raises new a problem: the potential for data explosion in health care systems. To address this problem, the remote health monitoring systems must be integrated with analysis tools that provide automated trend analysis and event detection in real time. In this paper, we propose an overview of Century, an extensible framework for analysis of large numbers of remote sensor-based medical data streams.

Automatic administration of the get up and go test

Advances in sensor technologies have accelerated the instrumentation of medical institutions. Today, modern intensive care units use sophisticated patient monitoring systems able to produce massive amounts of physiological streaming data. While these monitoring systems aim at improving patient care and staff productivity, they have the potential of introducing a data explosion problem. We address this problem by developing an open infrastructure upon which healthcare analytics can be built, managed, and deployed to analyze in real time physiological streaming data and turn this data into meaningful information for medical professionals. This infrastructure incorporates feature extraction and data mining functionalities for the discovery of clinical rules capable of identifying medically significant events. The system is based on a state of the art stream computing middleware. This paper presents this infrastructure from a programming model perspective. An exemplar application for arrhythmia detection is also described to illustrate its capabilities.

Real-time analysis for short-term prognosis in intensive care

In-home monitoring using sensors has the potential to improve the life of elderly and chronically ill persons, assist their family and friends in supervising their status, and provide early warning signs to the persons clinicians. The Get Up and Go test is a clinical test used to assess the balance and gait of a patient. We propose a way to automatically apply an abbreviated version of this test to patients in their residence using video data without body-worn sensors or markers.

On the integration of an artifact system and a real-time healthcare analytics system

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 patients own live data streams. The other technique is based on comparing the patients 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.