Filipe Portela

Pervasive and Intelligent Decision Support in Intensive Medicine – The Complete Picture

In the Intensive Care Units (ICU) it is notorious the high number of data sources available. This situation brings more complexity to the way of how a professional makes a decision based on information provided by those data sources. Normally, the decisions are based on empirical knowledge and common sense. Often, they don’t make use of the information provided by the ICU data sources, due to the difficulty in understanding them. To overcome these constraints an integrated and pervasive system called INTCare has been deployed. This paper is focused in presenting the system architecture and the knowledge obtained by each one of the decision modules: Patient Vital Signs, Critical Events, ICU Medical Scores and Ensemble Data Mining. This system is able to make hourly predictions in terms of organ failure and outcome. High values of sensitivity where reached, e.g. 97.95% for the cardiovascular system, 99.77% for the outcome. In addition, the system is prepared for tracking patients’ critical events and for evaluating medical scores automatically and in real-time.

The next generation of interoperability agents in healthcare

Interoperability in health information systems is increasingly a requirement rather than an option. Standards and technologies, such as multi-agent systems, have proven to be powerful tools in interoperability issues. In the last few years, the authors have worked on developing the Agency for Integration, Diffusion and Archive of Medical Information (AIDA), which is an intelligent, agent-based platform to ensure interoperability in healthcare units. It is increasingly important to ensure the high availability and reliability of systems. The functions provided by the systems that treat interoperability cannot fail. This paper shows the importance of monitoring and controlling intelligent agents as a tool to anticipate problems in health information systems. The interaction between humans and agents through an interface that allows the user to create new agents easily and to monitor their activities in real time is also an important feature, as health systems evolve by adopting more features and solving new problems. A module was installed in Centro Hospitalar do Porto, increasing the functionality and the overall usability of AIDA.

A pervasive approach to a real-time intelligent decision support system in intensive medicine

The decision on the most appropriate procedure to provide to the patients the best healthcare possible is a critical and complex task in Intensive Care Units (ICU). Clinical Decision Support Systems (CDSS) should deal with huge amounts of data and online monitoring, analyzing numerous parameters and providing outputs in a short real-time. Although the advances attained in this area of knowledge new challenges should be taken into account in future CDSS developments, principally in ICUs environments. The next generation of CDSS will be pervasive and ubiquitous providing the doctors with the appropriate services and information in order to support decisions regardless the time or the local where they are. Consequently new requirements arise namely the privacy of data and the security in data access. This paper will present a pervasive perspective of the decision making process in the context of INTCare system, an intelligent decision support system for intensive medicine. Three scenarios are explored using data mining models continuously assessed and optimized. Some preliminary results are depicted and discussed.

Pervasive and intelligent decision support in critical health care using ensembles

Critical health care is one of the most difficult areas to make decisions. Every day new situations appear and doctors need to decide very quickly. Moreover, it is difficult to have an exact perception of the patient situation and a precise prediction on the future condition. The introduction of Intelligent Decision Support Systems (IDSS) in this area can help the doctors in the decision making process, giving them an important support based in new knowledge. Previous work has demonstrated that is possible to use data mining models to predict future situations of patients. Even so, two other problems arise: i) how fast; and ii) how accurate? To answer these questions, an ensemble strategy was experimented in the context of INTCare system, a pervasive IDSS to automatically predict the organ failure and the outcome of the patients throughout next 24 hours. This paper presents the results obtained combining real-time data processing with ensemble approach in the intensive care unit of the Centro Hospitalar do Porto, Porto, Portugal.

Pervasive Intelligent Decision Support System – Technology Acceptance in Intensive Care Units

Intensive Care Units are considered a critical environment where the decision needs to be carefully taken. The real-time recognition of the condition of the patient is important to drive the decision process efficiently. In order to help the decision process, a Pervasive Intelligent Decision Support System (PIDSS) was developed. To provide a better comprehension of the acceptance of the PIDSS it is very important to assess how the users accept the system at level of usability and their importance in the Decision Making Process. This assessment was made using the four constructs proposed by the Technology Acceptance Methodology and a questionnaire-based approach guided by the Delphi Methodology. The results obtained so far show that although the users are satisfied with the offered information recognizing its importance, they demand for a faster system.

Improving High Availability and Reliability of Health Interoperability Systems

The accessibility and availability of patient clinical information are a constant need. The Agency for Interoperation, Diffusion and Archive of Medical Information (AIDA) was then developed to ensure the interoperability among healthcare information systems successfully. AIDA has demonstrated over time the need for greater control over its agents and their activities as the need for monitoring and preventing its machines and agents.

Pervasive Business Intelligence

In the field of intensive medicine, presentation of medical information is identified as a major concern for the health professionals, since it can be a great aid when it is necessary to make decisions, of varying gravity, for the patients state. The way in which this information is presented, and especially when it is presented, may make it difficult for the intensivists within intense healthcare units to understand a patients state in a timely fashion. Should there be a need to cross various types of clinical data from various sources, the situation worsens considerably. To support the health professionals decision-making process, the Pervasive Business Intelligence (PBI) Systems are a forthcoming field. Based on this principle, the current study approaches the way to present information about the patients, after they are received in a BI system, making them available at any place and at any time for the intensivists that may need it for the decision-making. The patients history will, therefore, be available, allowing examination of the vital signs data, what medicine that they might need, health checks performed, among others. Then, it is of vital importance, to make these conclusions available to the health professionals every time they might need, so as to aid them in the decision-making. This study aims to make a stance by approaching the theme of PBI in Critical Healthcare. The main objective is to understand the underlying concepts and the assets of BI solutions with Pervasive characteristics. Perhaps consider it a sort of guide or a path to follow for those who wish to insert Pervasive into Business Intelligence in Healthcare area.

Intelligent data acquisition and scoring system for intensive medicine

In a critical area as is Intensive Medicine, the existence of systems to support the clinical decision is mandatory. These systems should ensure a set of data to evaluate medical scores like is SAPS, SOFA and GLASGOW. The value of these scores gives the doctors the ability to understand the real condition of the patient and provides a mean to improve their decisions in order to choose the best therapy for the patient. Unfortunately, almost all of the required data to obtain these scores are recorded on paper and rarely are stored electronically. Doctors recognize this as an important limitation in the Intensive Care Units. This paper presents an intelligent system to obtain the data, calculate the scores and disseminate the results in an online, automatic, continuous and pervasive way. The major features of the system are detailed and discussed. A preliminary assessment of the system is also provided.

Preventing patient Cardiac Arrhythmias by using data mining techniques

Cardiac Arrhythmia (CA) is very dangerous and can significantly undermine patient condition. New tools are fundamental to forecast and to prevent possible critical situations. In order to help clinicians acting proactively, predictive data mining real-time models were induced using online-learning. As input variables were considered those acquired at the patient admission and complementary variables (vital signs, laboratory results, therapeutics) hourly collected. The results are very motivating; sensitivity near to 95% was obtained when using Support Vector Machines. The approach explored in this work reveals to be an interesting contribution to the healthcare in terms of predicting CA and a good direction to be further explored.

Improvements in Data Quality for Decision Support in Intensive Care

Nowadays, there is a plethora of technology in hospitals and, in particular, in intensive care units. The clinical data produced everyday can be integrated in a decision support system in real-time to improve quality of care of the critically ill patients. However, there are many sensitive aspects that must be taken into account, mainly the data quality and the integration of heterogeneous data sources. This paper presents INTCare, an Intelligent Decision Support System for Intensive Care in real-time and addresses the previous aspects, in particular, the development of an Electronic Nursing Record and the improvements in the quality of monitored data.