One of the biggest problems facing operators of aging aircraft is making sure that their aircraft is structurally safe. Multiple site fatigue damage (MSD) refers to the presence of multiple fatigue cracks in the same structural element. These cracks interact with each other, rapidly increasing the crack growth rate, and this can result in a more sudden loss of structural integrity. This research is intended to explore the suitability of LSTM (Long and Short Term Memory recurrent neural network) to augment current fracture mechanics-derived analytical methods in the task of accurately predicting the cycle number at which a structural element's residual strength levels have been lowered enough that it cannot sustain the loads it is required to sustain any more. Current methods still require empirically determined correction factors to account for material variability and assembly tolerance-induced scatter. The LSTM tested in this paper is intended to be a part of a larger predictive system that can predict the life of a part, with manufacturing and in-service inspection and load monitoring results as its inputs. The LSTM is trained on a combined dataset, which consists of the fatigue test data from the Federal Aviation Administration's AR-07/22 report, combined with data generated by a crack growth simulator program, with initial conditions and loading similar to that encountered in the FAA's fatigue test. This original version of the model obtained an average MSE of 0.18 and an average MAE of 0.248 on the combined dataset, with the input and the output both normalized and centered.