Abstract: A method is presented for evaluating data to predict the future occurrence of a medical condition that is presently clinically occult or which has not yet occurred. Specifically, the method uses a neural network to analyze and interpret DNA flow cytometric histograms. A first set of DNA histograms taken from tumors from patients having known relapse rates are used to train the neural network, an then the trained network is applied to predict the relapse rates of patients using DNA histograms of tumors from those patients. Prognosis according to this method can be performed using only diploid histograms, using only aneuploid histograms, or using a combination of diploid and aneuploid histograms.

Abstract: The invention relates to a method of predicting disease-free survival in cancer patients by relating the number and amount of stress response proteins in cancer tissue to the probability of tumor recurrence. Particular heat shock/stress response proteins useful in the determination of tumor recurrence are the stress response proteins, hsp70, hsp90, hsp27, and glucose regulated protein grp94. Specific levels of the stress response proteins relative to an internal standard are identified, above which the probability of tumor recurrence is highly significant. Kit methods are disclosed which could enable determination of the stress proteins by an antibody assay.

Abstract: The invention relates to a method of predicting disease-free survival in cancer patients by relating the number and amount of stress response proteins in the cancer tissue to the probability of tumor recurrence. Particular heat shock/stress response proteins useful in the determination of tumor recurrence are the stress response proteins, hsp70, hsp90, hsp27, and glucose regulated protein grp94. Specific levels of the stress response proteins are identified, above which the probability of tumor recurrence is highly signficant. Kit methods are disclosed which could enable determination of the stress proteins by an antibody assay.