A Case Based approach to assess Waiting Time Prediction at an Intensive Care Unity

Waiting time at an intensive care unity stands for a key feature in the assessment of healthcare quality. Nevertheless, its estimation is a difficult task, not only due to the different factors with intricate relations among them, but also with respect to the available data, which may be incomplete, self-contradictory or even unknown. However, its prediction not only improves the patients’ satisfaction but also enhance the quality of the healthcare being provided. To fulfill this goal, this work aims at the development of a decision support system that allows one to predict how long a patient should remain at an emergency unit, having into consideration all the remarks that were just stated above. It is built on top of a Logic Programming approach to knowledge representation and reasoning, complemented with a Case Base approach to computing.

Length of Stay in Intensive Care Units - A Case Base Evaluation

As a matter of fact, an Intensive Care Unit (ICU) stands for a hospital facility where patients require close observation and monitoring. Indeed, predicting Length-of-Stay (LoS) at ICUs is essential not only to provide them with improved Quality-of-Care, but also to help the hospital management to cope with hospital resources. Therefore, in this work one`s aim is to present an Artificial Intelligence based Decision Support System to assist on the prediction of LoS at ICUs, which will be centered on a formal framework based on a Logic Programming acquaintance for knowledge representation and reasoning, complemented with a Case Based approach to computing, and able to handle unknown, incomplete, or even contradictory data, information or knowledge.

Epidemiology of painful procedures performed in neonates: A systematic review of observational studies

Procedural pain in neonates has been a concern in the last two decades. The purpose of this review was to provide a critical appraisal and a synthesis of the published epidemiological studies about procedural pain in neonates admitted to intensive care units. The aims were to determine the frequency of painful procedures and pain management interventions as well as to identify their predictors. Academic Search, CINAHL, LILACS, Medic Latina, MEDLINE and SciELO databases were searched for observational studies on procedural pain in neonates admitted to intensive care units. Studies in which neonatal data could not be extracted from the paediatric population were excluded. Eighteen studies were included in the review. Six studies with the same study duration, the first 14 days of the neonate life or admission in the unit of care, identified 6832 to 42,413 invasive procedures, with an average of 7.5-17.3 per neonate per day. The most frequent procedures were heel lance, suctioning, venepuncture and insertion of peripheral venous catheter. Pharmacological and nonpharmacological approaches were inconsistently applied. Predictors of the frequency of procedures and analgesic use included the neonate's clinical condition, day of unit stay, type of procedure, parental presence and pain assessment. The existence of pain protocols was not a predictor of analgesia. Painful procedures were performed frequently and often with inadequate pain management. Unlike neonate clinical factors, organizational factors may be modified to promote a context of care more favourable to pain management. © 2015 European Pain Federation - EFIC®