Supporting Emergency Medical Care Teams with an Integrated Status Display Providing Real-Time Access to Medical Best Practices, Workflow Tracking, and Patient Data.

The work of a hospital's medical staff is safety critical and often occurs under severe time constraints. To provide timely and effective cognitive support to medical teams working in such contexts, guidelines in the form of best practice workflows for healthcare have been developed by medical organizations. However, the high cognitive load imposed in such stressful and rapidly changing environments poses significant challenges to the medical staff or team in adhering to these workflows. In collaboration with physicians and nurses from Carle Foundation Hospital, we first studied and modeled medical team's individual responsibilities and interactions in cardiac arrest resuscitation and decomposed their overall task into a set of distinct cognitive tasks that must be specifically supported to achieve successful human-centered system design. We then developed a medical Best Practice Guidance (BPG) system for reducing medical teams' cognitive load, thus fostering real-time adherence to best practices. We evaluated the resulting system with physicians and nurses using a professional patient simulator used for medical training and certification. The evaluation results point to a reduction of cognitive load and enhanced adherence to medical best practices.

Preventable Medical Errors Driven Modeling of Medical Best Practice Guidance Systems.

In a medical environment such as Intensive Care Unit, there are many possible reasons to cause errors, and one important reason is the effect of human intellectual tasks. When designing an interactive healthcare system such as medical Cyber-Physical-Human Systems (CPHSystems), it is important to consider whether the system design can mitigate the errors caused by these tasks or not. In this paper, we first introduce five categories of generic intellectual tasks of humans, where tasks among each category may lead to potential medical errors. Then, we present an integrated modeling framework to model a medical CPHSystem and use UPPAAL as the foundation to integrate and verify the whole medical CPHSystem design models. With a verified and comprehensive model capturing the human intellectual tasks effects, we can design a more accurate and acceptable system. We use a cardiac arrest resuscitation guidance and navigation system (CAR-GNSystem) for such medical CPHSystem modeling. Experimental results show that the CPHSystem models help determine system design flaws and can mitigate the potential medical errors caused by the human intellectual tasks.

A Pathophysiological Model-Driven Communication for Dynamic Distributed Medical Best Practice Guidance Systems.

There is a great divide between rural and urban areas, particularly in medical emergency care. Although medical best practice guidelines exist and are in hospital handbooks, they are often lengthy and difficult to apply clinically. The challenges are exaggerated for doctors in rural areas and emergency medical technicians (EMT) during patient transport. In this paper, we propose the concept of distributed executable medical best practice guidance systems to assist adherence to best practice from the time that a patient first presents at a rural hospital, through diagnosis and ambulance transfer to arrival and treatment at a regional tertiary hospital center. We codify complex medical knowledge in the form of simplified distributed executable disease automata, from the thin automata at rural hospitals to the rich automata in the regional center hospitals. However, a main challenge is how to efficiently and safely synchronize distributed best practice models as the communication among medical facilities, devices, and professionals generates a large number of messages. This complex problem of patient diagnosis and transport from rural to center facility is also fraught with many uncertainties and changes resulting in a high degree of dynamism. A critically ill patient's medical conditions can change abruptly in addition to changes in the wireless bandwidth during the ambulance transfer. Such dynamics have yet to be addressed in existing literature on telemedicine. To address this situation, we propose a pathophysiological model-driven message exchange communication architecture that ensures the real-time and dynamic requirements of synchronization among distributed emergency best practice models are met in a reliable and safe manner. Taking the signs, symptoms, and progress of stroke patients transported across a geographically distributed healthcare network as the motivating use case, we implement our communication system and apply it to our developed best practice automata using laboratory simulations. Our proof-of-concept experiments shows there is potential for the use of our system in a wide variety of domains.

Sepsis Patient Detection and Monitor Based on Auto-BN.

Sepsis is a life-threatening condition caused by an inappropriate immune response to infection, and is a leading cause of elderly death globally. Early recognition of patients and timely antibiotic therapy based on guidelines improve survival rate. Unfortunately, for those patients, it is often detected late because it is too expensive and impractical to perform frequent monitoring for all the elderly. In this paper, we present a risk driven sepsis screening and monitoring framework to shorten the time of onset detection without frequent monitoring of all the elderly. Within this framework, the sepsis ultimate risk of onset probability and mortality is calculated based on a novel temporal probabilistic model named Auto-BN, which consists of time dependent state, state dependent property, and state dependent inference structures. Then, different stages of a patient are encoded into different states, monitoring frequency is encoded into the state dependent property, and screening content is encoded into different state dependent inference structures. In this way, the screening and monitoring frequency and content can be automatically adjusted when encoding the sepsis ultimate risk into the guard of state transition. This allows for flexible manipulation of the tradeoff between screening accuracy and frequency. We evaluate its effectiveness through empirical study, and incorporate it into existing medical guidance system to improve medical healthcare.

The Design of Safe Networked Supervisory Medical Systems Using Organ-Centric Hierarchical Control Architecture.

There are growing demands to leverage network connectivity and interoperability of medical devices in order to improve patient safety and the effectiveness of medical services. However, if not properly designed, the integration of medical devices through networking could significantly increase the complexity of the system and make the system more vulnerable to potential errors, jeopardizing patient safety. The system must be designed and verified to guarantee the safety of patients and the effectiveness of medical services in the face of potential problems such as network failures. In this paper, we propose organ-centric hierarchical control architecture as a viable solution that reduces the complexity in system design and verification. In our approach, medical devices are grouped into clusters according to organ-specific human physiology. Each cluster captures common patterns arising out of medical device interactions and becomes a survivable semiautonomous unit during network failures. Further, safety verification and runtime enforcement can be modularized along organ-centric hierarchical control structure. We show the feasibility of the proposed approach under Simulink's model-based development framework. A simplified scenario for airway laser surgery is used as a case study.

Designing and evaluating a clustering system for organizing and integrating patient drug outcomes in personal health messages.

Patient outcomes to drugs vary, but physicians currently have little data about individual responses. We designed a comprehensive system to organize and integrate patient outcomes utilizing semantic analysis, which groups large collections of personal comments into a series of topics. A prototype implementation was built to extract situational evidences by filtering and digesting user comments provided by patients. Our methods do not require extensive training or dictionaries, while categorizing comments based on expert opinions from standard source, or patient-specified categories. This system has been tested with sample health messages from our unique dataset from Yahoo! Groups, containing 12M personal messages from 27K public groups in Health and Wellness. We have performed an extensive evaluation of the clustering results with medical students. Evaluated results show high quality of labeled clustering, promising an effective automatic system for discovering patient outcomes from large volumes of health information.