Vibrations emitted from a knee joint during flexion or extension are expected to be associated with pathological conditions in the joint. Externally detected vibroarthrographic (VAG) signals may be useful indicators of roughness, softening, breakdown, or the state of lubrication of the articular cartilage surfaces of the joint. Computer-aided analysis of VAG signals could provide quantitative indices for noninvasive diagnosis of articular cartilage breakdown and staging of osteoarthritis. We propose the use of statistical parameters of VAG signals, such as the form factor involving the variance of the signal and its derivatives, skewness, kurtosis, and entropy, to classify VAG signals as normal or abnormal, that is, perform screening. With 89 VAG signals, screening efficiency of up to 0.78 was achieved, in terms of the area under the receiver operating characteristics curve, using the parameters mentioned above with a neural network classifier based on radial basis functions.