>
Patent abstract
The invention concerns a method for predicting the lifespan of an individual, which includes i. the provision of biological input data of the subject, ii. the provision of a list of determining variables, iii. predict age-related mortality or disease, preferably time to death and/or mortality risk and/or age-related disease risk, for the subject by analyzing the data with an algorithm, wherein the algorithm comprises a neural network, trained on at least one reference data set comprising the biological data of at least one reference subject by applying: a) a selector layer to filter the input data of i., and b) an adversarial learning structure, which removes from the data of input the information relating to the confounding variables, where preferably the adversarial learning structure is a neural network comprising three elements: a feature extractor (FE), a predictor (P) and a confounders predictor (C). The invention further concerns a device or system comprising means for carrying out the steps of the method according to the invention, a computer program [product] and a computer-readable reading medium.