A nonparametric regression approach to syringe grading for quality improvement

In the biomedical products industry, measures of the quality of individual clinical specimens or manufacturing production units are often available in the form of high-dimensional data such as continuous recordings obtained from an analytical instrument. These recordings are then examined by experts in the field who extract certain features and use these to classify individuals. To formalize and quantify this procedure, an approach for extracting features from recordings based on nonparametric regression is described. These features are then used to build a classification model that incorporates the knowledge of the expert. The procedure is illustrated with the problem of grading of syringes from associated friction profile data. Features of the syringe friction profiles used in the classification are extracted via smoothing splines, and grades of the syringes are assigned by an expert tribologist. A nonlinear classification model is constructed to predict syringe grades based on the extracted features. The classification model makes it possible to grade syringes automatically without expert inspection. Using leave-one-out cross-validation, the prediction accuracy of the classification model is found to be about the same as the accuracy obtained from the expert.