Estudo de validação da versão portuguesa da Alarm Distress Baby Scale (ADBB)

Contexto. O comportamento de retraimento social prolongado da criança é um importante sinal de alarme, quer tenha origem orgânica, psicológica e/ou social. A. Guédeney construiu a Alarm Distress Baby Scale (ADBB), para identificar este comportamento no contexto da consulta pediátrica ou da observação psicológica. Objectivos. Validação da versão portuguesa da ADBB destinada a avaliar o comportamento de retraimento social de crianças com idades compreendidas entre 2 e 24 meses. Metodologia A ADBB e as Bayley Scales of Infant Development (BSID) foram administradas a uma amostra de 130 lactentes com 3 meses de idade, cujas mães preencheram a versão portuguesa da Edinburgh Postnatal Depression Scale (EPDS); 51 bebés foram novamente avaliados aos 12 meses de idade. Resultados. Os itens da ADBB organizam-se satisfatoriamente em duas sub-escalas. A consistência interna do instrumento é razoável (alpha de Cronbach = .587). A validade externa é elevada: a correlação entre os resultados na ADBB e nas BSID é muito significativa - os bebés que aos 3 meses apresentam um resultado igual ou superior a 5 na ADBB evidenciam menor desenvolvimento nas BSID. Os resultados testemunham ainda que bebés de mães deprimidas (EPDS ≥ 12) mostram mais sinais de retraimento social do que os bebés das mães não deprimidas. Conclusão. A escala permite detectar crianças a necessitar de ajuda no sentido de contrariar o retraimento social que encetaram em relação ao meio. Desenhada para sinalizar tão precocemente quanto possível o retraimento social do lactente, e na medida em que este é um comprovado sinal da perturbação do desenvolvimento, a ADBB pode estimular os clínicos na procura das suas causas e na intervenção junto das mesmas. Estudos em amostras de crianças com mais idade são necessários. No entanto, os resultados obtidos apontam que a Versão portuguesa da ADBB é robusta e válida.

Critical events in mechanically ventilated patients

Mechanical Ventilation is an artificial way to help a Patient to breathe. This procedure is used to support patients with respiratory diseases however in many cases it can provoke lung damages, Acute Respiratory Diseases or organ failure. With the goal to early detect possible patient breath problems a set of limit values was defined to some variables monitored by the ventilator (Average Ventilation Pressure, Compliance Dynamic, Flow, Peak, Plateau and Support Pressure, Positive end-expiratory pressure, Respiratory Rate) in order to create critical events. A critical event is verified when a patient has a value higher or lower than the normal range defined for a certain period of time. The values were defined after elaborate a literature review and meeting with physicians specialized in the area. This work uses data streaming and intelligent agents to process the values collected in real-time and classify them as critical or not. Real data provided by an Intensive Care Unit were used to design and test the solution. In this study it was possible to understand the importance of introduce critical events for Mechanically Ventilated Patients. In some cases a value is considered critical (can trigger an alarm) however it is a single event (instantaneous) and it has not a clinical significance for the patient. The introduction of critical events which crosses a range of values and a pre-defined duration contributes to improve the decision-making process by decreasing the number of false positives and having a better comprehension of the patient condition.

Towards a pervasive data mining engine: architecture overview

Current data mining engines are difficult to use, requiring optimizations by data mining experts in order to provide optimal results. To solve this problem a new concept was devised, by maintaining the functionality of current data mining tools and adding pervasive characteristics such as invisibility and ubiquity which focus on their users, providing better ease of use and usefulness, by providing autonomous and intelligent data mining processes. This article introduces an architecture to implement a data mining engine, composed by four major components: database; Middleware (control); Middleware (processing); and interface. These components are interlinked but provide independent scaling, allowing for a system that adapts to the user’s needs. A prototype has been developed in order to test the architecture. The results are very promising and showed their functionality and the need for further improvements.

A Real-Time intelligent system for tracking patient condition

Hospitals have multiple data sources, such as embedded systems, monitors and sensors. The number of data available is increasing and the information are used not only to care the patient but also to assist the decision processes. The introduction of intelligent environments in health care institutions has been adopted due their ability to provide useful information for health professionals, either in helping to identify prognosis or also to understand patient condition. Behind of this concept arises this Intelligent System to track patient condition (e.g. critic events) in health care. This system has the great advantage of being adaptable to the environment and user needs. The system is focused in identifying critic events from data streaming (e.g. vital signs and ventilation) which is particularly valuable for understanding the patient’s condition. This work aims to demonstrate the process of creating an intelligent system capable of operating in a real environment using streaming data provided by ventilators and vital signs monitors. Its development is important to the physician because becomes possible crossing multiple variables in real-time by analyzing if a value is critic or not and if their variation has or not clinical importance.