Search

Quality reporting that relies on coded administrative data alone may not completely and accurately depict providers' performance. To assess this concern with a test case, we developed and evaluated a natural language processing (NLP) approach to identify falls risk screenings documented in clinical notes of patients without coded falls risk screening data. Extracting information from 1,558 clinical notes (mainly progress notes) from 144 eligible patients, we generated a lexicon of 38 keywords relevant to falls risk screening, 26 terms for pre-negation, and 35 terms for post-negation. The NLP algorithm identified 62 (out of the 144) patients who falls risk screening documented only in clinical notes and not coded. Manual review confirmed 59 patients as true positives and 77 patients as true negatives. Our NLP approach scored 0.92 for precision, 0.95 for recall, and 0.93 for F-measure. These results support the concept of utilizing NLP to enhance healthcare quality reporting.

The purpose of writing medical notes in a computer system goes beyond documentation for medical-legal purposes or billing. The structure of documentation is a checklist that serves as a cognitive aid and a potential index to retrieve information for learning from the record. For the past 50 years, one of the primary organizing structures for physicians' clinical documentation have been the SOAP note (Subjective, Objective, Assessment, Plan). The cognitive check list is well-suited to differential diagnosis but may not support detection of changes in systems and/or learning from cases. We describe an alternative cognitive checklist called the OODA Loop (Observe, Orient, Decide, Act. Through incorporation of projections of anticipated course events with and without treatment and by making "Decisions" an explicit category of documentation in the medical record in the context of a variable temporal cycle for observations, OODA may enhance opportunities to learn from clinical care.

Discharge summaries (DCS) frequently fail to improve the continuity of care. A chart review of 188 DCS was performed to identify specific components that could be improved through health information technology. Medication reconciliations were analyzed for completeness and for medical reasoning. Documentation of pending results and follow-up details were analyzed. Patient preferences, patient goals, and the handover tone were noted. Patients were discharged on an average of 9.8 medications, only 3% of medication reconciliations were complete and medical reasoning was frequently absent. There were 358 pending results in 188 hospital discharges though only 14% were mentioned in the DCS. Documentation of clear, timely follow-up was present for less than 50% of patients. Patient preferences, patient goals, and lessons learned were rarely included. A handover tone was in only 17% of the DCS. Evaluating the DCS as a clinical handover is novel but information for safe handovers is frequently missing.

We conducted an unblinded experimental comparative trial during a disaster drill involving DMATs using the WIISARD system and traditional paper tracking of casualties. We shadowed the paper work flow to collect data on 40 victims tracked by both systems. WIISARD captured patients as well as the paper system. However, WIISARDwas superior at tracking patient destinations and transporting units. WIISARD proved to be an effective victim tracking system.

Incident Command systems often achieve situational awareness through manual paper-tracking systems. Such systems often produce high latencies and in-complete data, resulting in inefficient and ineffective resource deployment. WIISARD (Wireless Internet Information System for Medical Response in Disasters) collects much more data than a paper-based system, dramatically reducing latency while increasing the kinds and quality of information available to incident commanders. Yet, the introduction of IT into a disaster setting is not problem-free. Notably, system component failures can delay the delivery of data. The type and extent of a failure can have varying effects on the usefulness of information displays. We describe a small, coherent set of customizble information overlays to address this problem, and we discuss reactions to these displays by medical commanders.

WIISARD (Wireless Internet Information System for Medical Response to Disasters) utilizes wireless technology to improve medical care at mass casualty disasters. An important component of WIISARD is geolocation tracking of field personnel at the disaster site. Accurate, real-time information on personnel has the potential to improve resource utilization at the disaster site, as well as increase the safety of first responders caring for victims at a hazardous scene.

The study aims to determine information overlap in the admission and summary notes by physicians and nurses to decrease redundancy and time spent on the documentation process and increase the accessibility of the notes. The population in this study is aggregated data from 50 randomly selected inpatient orthopaedic CPR's at the Veterans Health Care System San Diego. Analysis is still in progress but preliminary results indicates substantial information overlap and redundancy between nurses and physicians notes in the CPR and delays in accessibility of voice recorded notes.

Assessment of how well a multiple client server system is functioning is a difficult task. In this poster we present visualization tools for such assessments. Arranged on a timeline, UDP client connection events are point-like. TCP client events are structured into intervals. Informative patterns and correlations are revealed by both sets. For the latter, comparison of two visualization schemes on the same timeline yields additional insights.

The WIISARD disaster response patient tracking program that allows for improved process flow, communication, and patient care using sophisticated wireless technology to coordinate and enhance the care of mass casualties in terrorist attacks or natural disasters. The MICN device has been developed as the link between the Base Station Mobile Intensive Care Nurse and Incident Command in the field. This tool allows the MICN coordinating the incident from the hospital side to more effectively and efficiently communicate with the Incident Command for the accurate and rapid distribution of patients from the scene to the hospitals.

Mobile information technology can help first responders assist patients more quickly, reliably, and safely, while focusing resources on those most in need. Yet the disaster setting complicates reliable networked computing. The WIISARD client-server architecture provides mobile IT support for medical response in disasters. Cached remote objects (CROs) are shared via publish/subscribe, enabling disconnected operation when out of network range and ensuring data consistency across clients with rollback/replay. CROs also provide a flexible, familiar, and performant programming model for client programmers. A drill with the San Diego MMST showed that a basic client-server architecture, even with CRO's, is insufficient, because prolonged network failures-to be expected in disaster reponse-inhibit group work. We describe an extension of the CRO model to clusters of computers that supports group work during network failures.

In existing Incident Command systems, situational awareness is achieved manually through paper tracking systems. Such systems often produce high latencies and incomplete data, resulting in inefficient and ineffective resource deployment. The WIISARD system collects much more data than a paper-based system, dramatically reducing latency while increasing the kinds and quality of information available to Incident Commanders. The WIISARD Command Center solves the problem of data over-load and uncertainty through the careful use of limited screen area and novel visualization techniques.

WIISARD utilizes wireless technology to improve the care of victims following a mass casualty disaster. The WIISARD Scene Manager device (WSM) is designed to enhance the collection and accessibility of real-time data on victims, ambulances and hospitals for disaster supervisors and managers. We recently deployed WSM during a large-scale disaster exercise. The WSM performed well logging and tracking victims and ambulances. Scene managers had access to data and utilized the WSM to coordinate patient care and disposition.

Medical care at mass casualty incidents and disasters requires rapid patient triage and assessment, acute care and disposition often in the setting of overwhelming numbers of victims, limited time, and little resources. Current systems rely on a paper triage tag on which rescuers and medical providers mark the patient's triage status and record limited information on injuries and treatments administered in the field. In this manuscript, we describe the design, development and deployment of a wireless handheld device with an electronic medical record (EMR) for use by rescuers responding to mass casualty incidents (MCIs) and disasters. The components of this device, the WIISARD First Responder (WFR), includes a personal digital assistant (PDA) with 802.11 wireless transmission capabilities, microprocessor and non-volatile memory, and a unique EMR software that replicates the rapidity and ease of use of the standard paper triage tag. WFR also expands its functionality by recording real-time medical data electronically for simultaneous access by rescuers, mid-level providers and incident commanders on and off the disaster site. WFR is a part of the Wireless Information System for Medical Response in Disasters (WIISARD) architecture.

Achieving reliable, efficient data communications networks at disaster site is a difficult task. Network paradigms such as Wireless Mesh Network (WMN) architectures are one paradigm for providing high bandwidth scalable data communication. WMNs are formed by self-organized wireless nodes that use multi-hop wireless relaying for data communications. In this paper describe our experience using mesh network architecture broadband network developed for homeland security and medical emergency applications. We briefly discuss the architecture and present the traffic behavioral observations made by a client server applications tested during a large scale homeland security drill. The results suggest that 802.11 mesh networks are feasible and scalable systems for field communications. We also present our traffic measurements based on which we make essential requirements for such medical emergency response networks.

Much of the clinical care of sleep apnea patients is focused on case identification, diagnosis, and treatment prescription, while follow-up care tends to be intermittent and patient-initiated. There is a clear need for an alternative, cost-effective way to examine sleep apnea treatment efficacy. As part of our research program to improve the clinical care of sleep apnea patients using Internet enabled systems, we have developed a prototype Wireless Blood Pulse-Oximeter System that patients can use in their homes. The oximeter system can be applied by the patient and is based on a data-push mechanism to a secure server that is designed for both patient and provider access.

The WiFi Bullhorn is designed to assist emergency workers in the event of a disaster situation by offering a rapidly configurable wireless of public address system for disaster sites. The current configuration plays either pre recorded or custom recorded messages and utilizes 802.11b networks for communication. Units can be position anywhere wireless coverage exists to help manage crowds or to recall first responders from dangerous areas.

In a mass casualty situation, medical personnel at the disaster site and other field treatment settings may need to monitor the vital signs of hundreds of seriously injured patients with minimal staffing. The conditions may be primitive and personnel may have to improvise infrastructure. As part of our research to enhance medical response to disasters with Internet-enabled systems, we have developed a prototype Wireless Blood Pulse Oximeter system for mass casualty events designed to operate in WiFi hotspots. Pulse ox units were designed using low-cost embedded system technologies to operate in integrated or stand alone environments. Units can report data to a command post on the scene or any remote location with Internet access. The entire system is potentially capable of tracking and monitoring several hundred patients.

To support mobile computing systems for first responders at mass casualty sites, as part of the WIISARD (Wireless Internet Information System for Medical Response in Disasters) project, we have developed a data architecture to gracefully handle an environment with frequent network failure and, multiple writers that also supports rapid dissemination of updates that could be critical to the safety of responders. This is accomplished by allowing for a subset of the overall information available in a disaster scene to be cached locally on a responder's device and locally modified with or without network access. When the network is available, the local subset of the model is automatically synchronized with a server that contains the full model, and conflicts are resolved. When changes from a device are committed, the changes are instantly sent to any connected devices where the local subset would be modified by the changes.

802.11 (WiFi) is a well established network communications protocol that has wide applicability in civil infrastructure. This paper describes research that explores the design of 802.11 networks enhanced to support data communications in disaster environments. The focus of these efforts is to create network infrastructure to support operations by Metropolitan Medical Response System (MMRS) units and Federally-sponsored regional teams that respond to mass casualty events caused by a terrorist attack with chemical, biological, nuclear or radiological weapons or by a hazardous materials spill. In this paper, we describe an advanced WiFi-based network architecture designed to meet the needs of MMRS operations. This architecture combines a Wireless Distribution Systems for peer-to-peer multihop connectivity between access points with flexible and shared access to multiple cellular backhauls for robust connectivity to the Internet. The architecture offers a high bandwidth data communications infrastructure that can penetrate into buildings and structures while also supporting commercial off-the-shelf end-user equipment such as PDAs. It is self-configuring and is self-healing in the event of a loss of a portion of the infrastructure. Testing of prototype units is ongoing.

We study how Metropolitan Medical Response System units conceptualize the physical space of a disaster and their organized response. Using a variety of ethnographic methods before, during, and after a disaster drill, we have developed an initial ontology for geospatial and context-aware technology. The conceptual map of first responders is far more complex than a geographical map. Zones and Areas are used to describe documented concepts critical to MMRS operations. Ad hoc locations also play a critical role, helping first responders communicate tactics in spatial terms. Such distinctions play an important role in the way our experts think about their activity. Successful geoaware alerting systems must incorporate these notions if they are to seamlessly fit into the work flow of first responders.

When medical care is initiated at a mass casualty event, the first activity is the triage of victims, which is the grouping by victims severity of injury. Paper triage tags are often used to mark victims' triage status and to record information on injuries and treatments administered in the field. In this paper we describe the design and development of an"Intelligent Triage Tag" (ITT), an electronic device to coordinate patient field care. ITTs combine the basic functionality of a paper triage tag with sensors, nonvolatile memory, a microprocessor and 802.11 wireless transmission capabilities. ITTs not only display victims' triage status but also signal alerts, and mark patients for transport or immediate medical attention. ITTs record medical data for later access offsite and help organize care by relaying information on the location of the victims during field treatment. ITTs are a part of the Wireless Information System for Medical Response in Disasters (WIISARD) architecture.

Most medical facilities practice managing the large numbers of seriously injured patients expected during catastrophic events. During mass casualty events, as the demands on the healthcare team increase, and the challenges faced by managers escalate, workflow bottlenecks begin to develop and system capacity decreases. This paper describes MASCAL, an integrated software-hardware system designed to enhance management of resources at a hospital during a mass casualty situation. MASCAL uses active 802.11b asset tags to track patients, equipment and staff during the response to a disaster. The system integrates tag position information with data from personnel databases, medical information systems, registration applications and the US Navy's TACMEDCS triage application in a custom visual disaster management environment. MASCAL includes interfaces for a hospital command center, local area managers (emergency room, operating suites, radiology, etc.) and registration personnel. MASCAL is an operational system undergoing functional evaluation at the Naval Medical Center, San Diego, CA.

WIISARD (Wireless Internet Information System for Medical Response in Disasters) is developing wireless technology to coordinate and enhance the care of mass casualties at disaster sites. Mid-tier personnel (area supervisors) play a critical role in disaster response, supervising care processes in the triage, Treatment and Transport areas of the attack site. The design of a software tool to support mid-tier activities focuses on providing supervisors aggregate information on patient conditions and needs, real-time data on ambulance availability and location, and hospital status and on coordinating care delivery among triage, treatment and transport areas.

We discuss the design of multi-hop access networks with multiple gateways that supports medical response to disasters. We examine and implement protocols to ensure high bandwidth, robust, self-healing and secure wireless multi-hop access networks for extreme conditions. Address management, path setup, gateway discovery and selection protocols are described. Future directions and plans are also considered.

The first moments at a disaster scene are chaotic. The command center initially operates with little knowledge of hazards, geography and casualties, building up knowledge of the event slowly as information trickles in by voice radio channels. RealityFlythrough is a tele-presence system that stitches together live video feeds in real-time, using the principle of visual closure, to give command center personnel the illusion of being able to explore the scene interactively by moving smoothly between the video feeds. Using RealityFlythrough, medical, fire, law enforcement, hazardous materials, and engineering experts may be able to achieve situational awareness earlier, and better manage scarce resources. The RealityFlythrough system is composed of camera units with off-the-shelf GPS and orientation systems and a server/viewing station that offers access to images collected by the camera units in real time by position/orientation. In initial field testing using an experimental mesh 802.11 wireless network, two camera unit operators were able to create an interactive image of a simulated disaster scene in about five minutes.

Provider Link is a system designed to enhance the efficacy of a web-based intervention for smoking cessation by helping health care providers support their patients via e-mail. The system is designed to maintain confidentiality while allowing providers rapid access to patient data collected over the web. A trial of Provider Link is currently underway.