An algorithm is proposed to classify the regional cerebral blood flow (RCBF) of two groups of subjects. A 32-tuple training vector is defined corresponding to 32 detectors used to measure 133Xe washout following inhalation. For any index of 133Xe washout, each detector is associated with two cumulative distributions (cds) each corresponding to a population. The 32 index values at which the differences between cds are maximum are defined as partition values. All index values are then compared to their partitions and are designated binary values of 1 or 0 for being above or below the partitions. A representative sum of the binary numbers (0 to 16) indicates the number of detectors in each hemisphere which exceed their respective threshold. In the example, a normal group of subjects (n = 40) is compared to an abnormal group (n = 82). The abnormal group was identified independently of RCBF by clinical testing as having Alzheimer's disease, a subcategory of dementing diseases. The classification algorithm defined a training vector to which the two populations were compared. The normal subjects had higher representative scores than the abnormals with a tight clustering of these scores. Although some abnormals scored well, the great majority had representative scores well below 12 for each cerebral hemisphere. The training vector can be used to classify new studies or can be updated by new studies until no significant changes result. At this point, the new tracing vector is used as a reference set of partition values.