Cluster Analysis of Laboratory Tests Used for the Evaluation of Hand-Arm Vibration Syndrome
Three hundred and sixty-four patients exposed to hand-arm vibration at work were assessed in a clinical laboratory designated for this purpose in Toronto, Canada during the period 1989–92. The assessment included completion of a subjective history questionnaire; a medical examination of the upper torso, cardiovascular and central nervous systems; and multiple vascular, sensorineural and laboratory tests. The test results were used to assess the severity of Hand-arm Vibration Syndrome (HAVS) and grade the subjects according to the Stockholm stages. A statistical clustering algorithm was used to categorise the subjects according to the results of their diagnostic tests. One set of clusters was made from the vascular test results and another from the sensory test results. These clusters were compared with the Stockholm history (SH) and diagnostic (SD) stages. The clusters based upon the vascular test results (the vascular clusters) agreed well with the SD vascular stages (P= 1×10−9), and less well with the SD sensorineural stages (P=0.04). The clusters based upon the sensory test results (the sensory clusters) agreed well with the SD sensorineural stages (P=0.0003), and less well with the SD vascular stages (P=0.03). The mean values for the diagnostic tests within the clusters were compared. The sensory test results differed between the sensory clusters while most vascular test results did not. Likewise, the vascular test results differed between the vascular clusters while most sensory tests did not. A comparison of the vascular and sensory clusters showed that while some men suffered severe sensory effects and others suffered severe vascular effects, few suffered both. Hence this analysis confirms that the severity grading of sensory and vascular components of HAVS must be evaluated separately as now practised. This cluster analysis technique (SAS'S FASTCLUS procedure) has proved to be useful for the objective analysis of the results from many diagnostic tests on a large group of individuals. The reference data of the tests within the cluster groupings provides a basis for the objective classification of the severity of HAVS in individual patients.