Logistic regression was used to analyze the clinical findings (attributes) which predicted coliform mastitis in 113 dairy cattle, 36 of which had coliforms cultured from milk. Weakness of the cow, swelling of the udder, decreased body temperature and watery consistency of the milk were selected for the model. An analysis was then done to find the attributes which clinicians used when predicting that a cow would have a coliform cultured. Clinicians appeared to use water consistency of the milk, shivering, firmness of the udder, pulse rate, elevated body temperature, and respiratory rate. In a final analysis the clinicians' predictions were forced into the model to determine which attributes might be used by clinicians to increase diagnostic accuracy. Inclusion of weakness of the cow, swelling of the udder, decreased temperature of the cow, and duration of mastitis of less than 24 hours increased accuracy over clinical prediction alone. Accuracy of cowside diagnosis might be increased if more attention were paid to these attributes when making a diagnosis of coliform mastitis.