Steps towards Interoperability in Healthcare Environment

Information should be accessible everywhere and at any time to help with clinical decision and be available for clinical studies through data computationally interpretable. This work is based on a set of studies performed at Centro Hospitalar do Tâmega e Sousa. An Electronic Semantic Health Record was formalized and implemented which was delivered through a platform named Agency for the Integration, Diffusion and Archive, which is supported by intelligent agents. Furthermore, to strengthen the relation between the patient and the hospital, an appointment alert system was developed, which allowed the reduction of non-programmed misses and a decrease of costs. Finally to promote user's confidence on Information Systems, an open-source tool was developed that enables the scheduling of preventive actions. These tools allowed continuous improvement of systems and are currently well accepted inside the healthcare unit, proving in real clinical situation the effectiveness and usability of the model.

A New Approach to Generate Hospital Data Warehouse Schema

The healthcare industry generates huge amount of data underused for decision making needs because of the absence of specific design mastered by healthcare actors and the lack of collaboration and information exchange between the institutions. In this work, a new approach is proposed to design the schema of a Hospital Data Warehouse (HDW). It starts by generating the schemas of the Hospital Data Mart (HDM) one for each department taking into consideration the requirements of the healthcare staffs and the existing data sources. Then, it merges them to build the schema of HDW. The bottom-up approach is suitable because the healthcare departments are separately. To merge the schemas, a new schema integration methodology is used. It starts by extracting the similar elements of the schemas and the conflicts and presents them as mapping rules. Then, it transforms the rules into queries and applies them to merge the schemas.

An Approach for the Semantic Interoperability of SNOMED

The semantic and syntactic interoperability introduces the capability of two machines to communicate and understand each other improving then the quality of Electronic Health Records. In this work, is presented an independent application of the medical record, using a web service (with protocol TCP/IP) capable of provide human interaction with interfaces in different devices (web, android app., browser). SNOMED CT is a comprehensive and scientifically validated health care terminology resulting in an organized computer processable collection of medical terms. This can be mapped into other systems of codes like ICD also used in our application. A data base (SNOMED codes and relations) was created capable of answer to all sort of queries from the users using the browser or the mobile application. The first hospital unit to enjoy this system was the pathological anatomy unit of the CHAA hospital. Here after receiving a “piece” and a task, the responsible performs all kind of procedures with the purpose of performing a report (diagnosis for example). With the implementation of SNOMED CT, to produce reports a physician could search for the name of the “piece” or the code and immediately upload in that patient HER the diagnosis. The usage of this codes leads to report uniformed that could be read and understood around the world. Another important feature of the application is the incorporation within the AIDA, AIDA-PCE and AIDA-BI. Experiments with real user show a successful software implementation judging by the utilization rate and medical personal acceptance. The mobile application should suffer an upgrade allowing the patient usage for example.

A Clinical Recommendation System to Maternity Care

Nowadays in healthcare, the Clinical Decision Support Systems are used in order to help health professionals to take an evidence-based decision. An example is the Clinical Recommendation Systems. In this sense, a pre-triage system was developed and implemented in Centro Hospitalar do Porto in order to group the patients on two levels (urgent or outpatient). However, although this system is calibrated and specific to the urgency of obstetrics and gynaecology, it does not meet all clinical requirements by the general department of the Portuguese HealthCare (Direção Geral de Saúde). The main requirement is the need of having priority triage system characterized by five levels. Thus some studies have been conducted with the aim of presenting a methodology able to evolve the pre-triage system on a Clinical Recommendation System with five levels. After some tests (using data mining and simulation techniques), it has been validated the possibility of transformation the pre-triage system in a Clinical Recommendation System in the obstetric context. At the end the main indicators achieved with this system are presented in the Business Intelligence Platform already deployed. This paper presents an overview of the Clinical Recommendation System for obstetric triage, the model developed and the main results achieved.

Evolutionary Intelligence and Quality-Of-Information

The strategy of making predictions for a specific case or problem, in particular regarding scenarios with incomplete information, should follow a dynamic and formal model. This chapter presents a specific case concerning the employment of professionals for a health institution, as technicians and physicians, to demonstrate a model that requires the Quality-of-Information and the Degree-of-Confidence of the extensions of the predicates that model the universe of discourse. It is also mentioned a virtual intellect, or computational model, in order to maximize the Degree-of-Confidence that is associated with each term in the extensions of the predicates, according to the approximate representation of the universe of discourse. This model is prepared to be adopted by a Business Intelligence platform in order to increase the Quality-of-Information and the Degree-of-Confidence of the extensions in healthcare.

Applying Soft Computing to Clinical Decision Support

This article aims to explain the construction process of the learing systems based on Artificial Neural Networks and Genetic Algorithms. These systems were implemented using R and Python programming languages, in order to compare results and achieve the best solution and it was used Diabetes and Parkinson datasets with the purpose of identifying the carriers of these diseases.

Monitoring Time Consumption in Complementary Diagnostic and Therapeutic Procedure Requests

Over the years, information technologies and computer applications have been widespread amongst all fields, including healthcare. The main goal of these organizations is focused on providing quality health services to their patients, ensuring the provision of quality services. Therefore, decisions have to be made quickly and effectively. Thus, the increased use of information technologies in healthcare has been helping the decision-making process, improving the quality of their services. For an example, the insertion of Business Intelligence (BI) tools in healthcare environments has been recently used to improve healthcare delivery. It is based on the analysis of data in order to provide useful information. BI tools assist managers and health professionals through decision-making, since they allow the manipulation and analysis of data in order to extract knowledge. This work aims to study and analyze the time that physicians take to prescribe medical exams in Centro Hospitalar do Porto (CHP), though BI tools. The main concern is to identify the physicians who take more time than average to prescribe complementary means of diagnosis and treatment, making it possible to identify and understand the reason why it occurs. To discover these outliners, a BI platform was developed using the Pentaho Community. This platform presents means to represent information through tables and graphs that facilitate the analysis of information and the knowledge extraction. This information will be useful to represent knowledge concerning not only the prescription system (auditing it) but also its users. The platform evaluates the time prescription, by specialty and physician, which can afterwards be applied in the decision-making process. This platform enables the identification of measures to unravel the time differences that some physicians exhibit, in order to, subsequently, improve the whole process of electronic medical prescription.

Optimizing the Use and Adoption of Healthcare Information Systems

Advancements in Information and Communication Technology (ICT) have led to the development of various forms of electronic records to support general practitioners and healthcare providers in capturing, storing, and retrieving routinely collected medical records and/or clinical information for optimal primary care and translational research. These advancements have resulted in the emergence of interoperable Healthcare Information Systems (HIS) such as Electronic Health Records (EHRs), Electronic Medical Records (EMRs) and Personal Health Records (PHRs). However, even as these systems continue to evolve, the research community is interested in understanding how the use and adoption of HIS can be optimized to support effective and efficient healthcare delivery and translational research. In this chapter, a systematic literature review methodology was used not only to explore the key benefits and technical challenges of HIS, but also to discuss the optimization approaches to maximizing the use and adoption of HIS in healthcare delivery.

Clinical Business Intelligence to Prevent Stroke Accidents

Stroke is considered the third main cause of death among all population, without distinguishing genders, led by heart diseases in first place. In other hand, despite representing a significant number of mortality, these diseases are the causes for a long-term disability in all countries with a vast recovery time going parallel with its costs. However, leaving aside this facts, stokes and heath diseases can also be easily prevented considering the outcome. This paper presents a new methodology to prevent these events to happen by using segmentation methods, which allows distinguishing and aggregating clusters of historical records, classification methods, such as Artificial Neural Networks, capable of classifying a new record according to its distribution among the clusters. A Multi-Agent Case Based Reasoning system is also proposed to evaluate solutions based in a similar case.

Evaluation of the Length of Hospital Stay through Artificial Neural Networks Based Systems

The mentality of savings and eliminating any kind of outgoing costs is undermining our society and our way of living. Cutting funds from Education to Health is at best delaying the inevitable “Crash” that is foreshadowed. Regarding Health, a major concern, can be described as jeopardize the health of Patients – Reduce of the Length of Hospital. As we all know, Human Health is very sensitive and prune to drastic changes in short spaces of time. Factors like age, sex, their ambient context – house conditions, daily lives – should all be important when deciding how long a specific patient should remain safe in a hospital. In no way, ought this be decided by the economic politics. Logic Programming was used for knowledge representation and reasoning, letting the modeling of the universe of discourse in terms of defective data, information and knowledge. Artificial Neural Networks and Genetic Algorithms were used in order to evaluate and predict how long should a patient remain in the hospital in order to minimize the collateral damage of our government approaches, not forgetting the use of Degree of Confidence to demonstrate how feasible the assessment is.