Predicting dire outcomes of patients with community acquired pneumonia.

Community-acquired pneumonia (CAP) is an important clinical condition with regard to patient mortality, patient morbidity, and healthcare resource utilization. The assessment of the likely clinical course of a CAP patient can significantly influence decision making about whether to treat the patient as an inpatient or as an outpatient. That decision can in turn influence resource utilization, as well as patient well being. Predicting dire outcomes, such as mortality or severe clinical complications, is a particularly important component in assessing the clinical course of patients. We used a training set of 1601 CAP patient cases to construct 11 statistical and machine-learning models that predict dire outcomes. We evaluated the resulting models on 686 additional CAP-patient cases. The primary goal was not to compare these learning algorithms as a study end point; rather, it was to develop the best model possible to predict dire outcomes. A special version of an artificial neural network (NN) model predicted dire outcomes the best. Using the 686 test cases, we estimated the expected healthcare quality and cost impact of applying the NN model in practice. The particular, quantitative results of this analysis are based on a number of assumptions that we make explicit; they will require further study and validation. Nonetheless, the general implication of the analysis seems robust, namely, that even small improvements in predictive performance for prevalent and costly diseases, such as CAP, are likely to result in significant improvements in the quality and efficiency of healthcare delivery. Therefore, seeking models with the highest possible level of predictive performance is important. Consequently, seeking ever better machine-learning and statistical modeling methods is of great practical significance.

Automatic annotation of protein motif function with Gene Ontology terms.

BACKGROUND: Conserved protein sequence motifs are short stretches of amino acid sequence patterns that potentially encode the function of proteins. Several sequence pattern searching algorithms and programs exist foridentifying candidate protein motifs at the whole genome level. However, a much needed and important task is to determine the functions of the newly identified protein motifs. The Gene Ontology (GO) project is an endeavor to annotate the function of genes or protein sequences with terms from a dynamic, controlled vocabulary and these annotations serve well as a knowledge base. RESULTS: This paper presents methods to mine the GO knowledge base and use the association between the GO terms assigned to a sequence and the motifs matched by the same sequence as evidence for predicting the functions of novel protein motifs automatically. The task of assigning GO terms to protein motifs is viewed as both a binary classification and information retrieval problem, where PROSITE motifs are used as samples for mode training and functional prediction. The mutual information of a motif and aGO term association is found to be a very useful feature. We take advantage of the known motifs to train a logistic regression classifier, which allows us to combine mutual information with other frequency-based features and obtain a probability of correct association. The trained logistic regression model has intuitively meaningful and logically plausible parameter values, and performs very well empirically according to our evaluation criteria. CONCLUSIONS: In this research, different methods for automatic annotation of protein motifs have been investigated. Empirical result demonstrated that the methods have a great potential for detecting and augmenting information about the functions of newly discovered candidate protein motifs.