Search PubMed⌕ Search

Biomedical subjects

B A Metfessel

Publications and source records attributed to B A Metfessel.

3 recordsLinked to original sources

An automated tool for an analysis of compliance to evidence-based clinical guidelines.

Evidence-based clinical guidelines have been developed in an attempt to decrease practice variation and improve patient outcomes. Although a number of studies and a few commercial products have attempted to measure guideline compliance, there still exists a strong need for an automated product that can take as input large amounts of data and create systematic and detailed profiles of compliance to evidence-based guidelines. The Guideline Compliance Assessment Tool is a product presently under development in our group that will accept as input medical and pharmacy claims data and create a guideline compliance profile that assesses provider practice patterns as compared to evidence-based standards. The system components include an episode of care grouper to standardize classifications of illnesses, an evidence-based guideline knowledge base that potentially contains information on several hundred distinct conditions, a guideline compliance scoring system that emphasizes systematic guideline variance rather than random variances, and an advanced data warehouse that would allow drilling into specific areas of interest. As provider profiling begins to shift away from a primary emphasis on cost to an emphasis on quality, automated methods for measuring guideline compliance will become important in measuring provider performance and increasing guideline usage, consequently improving the standard of care and the potential for better patient outcomes.

Computing Methodologies↗

Cross-validation of protein structural class prediction using statistical clustering and neural networks.

We present an approach to predicting protein structural class that uses amino acid composition and hydrophobic pattern frequency information as input to two types of neural networks: (1) a three-layer back-propagation network and (2) a learning vector quantization network. The results of these methods are compared to those obtained from a modified Euclidean statistical clustering algorithm. The protein sequence data used to drive these algorithms consist of the normalized frequency of up to 20 amino acid types and six hydrophobic amino acid patterns. From these frequency values the structural class predictions for each protein (all-alpha, all-beta, or alpha-beta classes) are derived. Examples consisting of 64 previously classified proteins were randomly divided into multiple training (56 proteins) and test (8 proteins) sets. The best performing algorithm on the test sets was the learning vector quantization network using 17 inputs, obtaining a prediction accuracy of 80.2%. The Matthews correlation coefficients are statistically significant for all algorithms and all structural classes. The differences between algorithms are in general not statistically significant. These results show that information exists in protein primary sequences that is easily obtainable and useful for the prediction of protein structural class by neural networks as well as by standard statistical clustering algorithms.

Algorithms↗

Patterns in protein primary sequences: classification, display and analysis.

The protein folding code, which is contained in the amino acid chain of a protein, has so far eluded elucidation. However, patterns of hydrophobic residues have previously been identified which show a specificity towards certain secondary structural elements. We are developing an analysis toolkit to find, visualize, and analyze patterns in primary sequences. Preliminary results show that there exist patterns in primary sequences which are useful for predicting the structural class of amino acid chains, performing especially well for the all-alpha helix and all-beta sheet classes.

Algorithms↗