Journal - Studies in health technology and informatics (Netherlands )

Abstract :

A medical terminological system (TS) is essentially a representation of concepts, attributes and relationships pertaining to medical terms. Although the requirements and structures of TSs have enjoyed some attention in the literature, the actual implementation of TSs consisted so far of ad-hoc approaches starting from scratch. Recently, Protégé has been suggested as a software environment for the development of knowledge-based systems. In Protégé various component types interact, and knowledge can be represented at various levels. This paper investigates how to specify a frame-based TS in Protégé and demonstrates this in a specific application in the intensive care. Our approach is characterized by the utilization of a conceptual framework for understanding TSs and mapping its components onto Protégé constructs. This results in specifications of knowledge components for the implementation of terminological systems. The significance of the work stems from the generality of the specifications, thus facilitating the principled design and development of terminological systems in various medical domains

Journal - Artificial intelligence in medicine (Netherlands )

Abstract :

Health care effectiveness and efficiency are under constant scrutiny especially when treatment is quite costly as in the Intensive Care (IC). Currently there are various international quality of care programs for the evaluation of IC. At the heart of such quality of care programs lie prognostic models whose prediction of patient mortality can be used as a norm to which actual mortality is compared. The current generation of prognostic models in IC are statistical parametric models based on logistic regression. Given a description of a patient at admission, these models predict the probability of his or her survival. Typically, this patient description relies on an aggregate variable, called a score, that quantifies the severity of illness of the patient. The use of a parametric model and an aggregate score form adequate means to develop models when data is relatively scarce but it introduces the risk of bias. This paper motivates and suggests a method for studying and improving the performance behavior of current state-of-the-art IC prognostic models. Our method is based on machine learning and statistical ideas and relies on exploiting information that underlies a score variable. In particular, this underlying information is used to construct a classification tree whose nodes denote patient sub-populations. For these sub-populations, local models, most notably logistic regression ones, are developed using only the total score variable. We compare the performance of this hybrid model to that of a traditional global logistic regression model. We show that the hybrid model not only provides more insight into the data but also has a better performance. We pay special attention to the precision aspect of model performance and argue why precision is more important than discrimination ability.

Journal - Critical Care

Journal - Critical Care

Abstract :

IntroductionTo systematically review studies evaluating the performance of Sequential Organ Failure Assessment (SOFA)-based models for predicting mortality in patients in the intensive care unit (ICU).MethodsMedline, EMBASE and other databases were searched for English-language articles with the major objective of evaluating the prognostic performance of SOFA-based models in predicting mortality in surgical and/or medical ICU admissions. The quality of each study was assessed based on a quality framework for prognostic models.ResultsEighteen articles met all inclusion criteria. The studies differed widely in the SOFA derivatives used and in their methods of evaluation. Ten studies reported about developing a probabilistic prognostic model, only five of which used an independent validation data set. The other studies used the SOFA-based score directly to discriminate between survivors and non-survivors without fitting a probabilistic model. In five of the six studies, admission-based models (Acute Physiology and Chronic Health Evaluation (APACHE) II/III) were reported to have a slightly better discrimination ability than SOFA-based models at admission (the receiver operating characteristic curve (AUC) of SOFA-based models ranged between 0.61 and 0.88), and in one study a SOFA model had higher AUC than the Simplified Acute Physiology Score (SAPS) II model. Four of these studies used the Hosmer-Lemeshow tests for calibration, none of which reported a lack of fit for the SOFA models. Models based on sequential SOFA scores were described in 11 studies including maximum SOFA scores and maximum sum of individual components of the SOFA score (AUC range: 0.69 to 0.92) and delta SOFA (AUC range: 0.51 to 0.83). Studies comparing SOFA with other organ failure scores did not consistently show superiority of one scoring system to another. Four studies combined SOFA-based derivatives with admission severity of illness scores, and they all reported on improved predictions for the combination. Quality of studies ranged from 11.5 to 19.5 points on a 20-point scale.ConclusionsModels based on SOFA scores at admission had only slightly worse performance than APACHE II/III and were competitive with SAPS II models in predicting mortality in patients in the general medical and/or surgical ICU. Models with sequential SOFA scores seem to have a comparable performance with other organ failure scores. The combination of sequential SOFA derivatives with APACHE II/III and SAPS II models clearly improved prognostic performance of either model alone. Due to the heterogeneity of the studies, it is impossible to draw general conclusions on the optimal mathematical model and optimal derivatives of SOFA scores. Future studies should use a standard evaluation methodology with a standard set of outcome measures covering discrimination, calibration and accuracy.

Journal - Critical Care

Abstract :

IntroductionThe objectives of this study were to systematically identify and summarize quality indicators of tight glycaemic control in critically ill patients, and to inspect the applicability of their definitions.MethodsWe searched in MEDLINE® for all studies evaluating a tight glycaemic control protocol and/or quality of glucose control that reported original data from a clinical trial or observational study on critically ill adult patients.ResultsForty-nine studies met the inclusion criteria; 30 different indicators were extracted and categorized into four nonorthogonal categories: blood glucose zones (for example, 'hypoglycaemia'); blood glucose levels (for example, 'mean blood glucose level'); time intervals (for example, 'time to occurrence of an event'); and protocol characteristics (for example, 'blood glucose sampling frequency'). Hypoglycaemia-related indicators were used in 43 out of 49 studies, acting as a proxy for safety, but they employed many different definitions. Blood glucose level summaries were used in 41 out of 49 studies, reported as means and/or medians during the study period or at a certain time point (for example, the morning blood glucose level or blood glucose level upon starting insulin therapy). Time spent in the predefined blood glucose level range, time needed to reach the defined blood glucose level target, hyperglycaemia-related indicators and protocol-related indicators were other frequently used indicators. Most indicators differ in their definitions even when they are meant to measure the same underlying concept. More importantly, many definitions are not precise, prohibiting their applicability and hence the reproducibility and comparability of research results.ConclusionsAn unambiguous indicator reference subset is necessary. The result of this systematic review can be used as a starting point from which to develop a standard list of well defined indicators that are associated with clinical outcomes or that concur with clinicians' subjective views on the quality of the regulatory process.

Journal - Critical Care

Abstract :

IntroductionAdvanced age is thought to be associated with increased mortality in critically ill patients. This report reviews available data on factors that determine outcome, on the value of prognostic models, and on preferences regarding life-sustaining treatments in (very) elderly intensive care unit (ICU) patients.MethodsWe searched the Medline database (January 1966 to January 2005) for English language articles. Selected articles were cross-checked for other relevant publications.ResultsMortality rates are higher in elderly ICU patients than in younger patients. However, it is not age per se but associated factors, such as severity of illness and premorbid functional status, that appear to be responsible for the poorer prognosis. Patients' preferences regarding life-sustaining treatments are importantly influenced by the likelihood of a beneficial outcome. Commonly used prognostic models have not been calibrated for use in the very elderly. Furthermore, they do not address long-term survival and functional outcome.ConclusionWe advocate the development of new prognostic models, validated in elderly ICU patients, that predict not only survival but also functional and cognitive status after discharge. Such a model may support informed decision making with respect to patients' preferences.