Citation, DOI and article data
Generalisability in machine learning models represents how well the models can be adapted to new example datasets.
Evaluating generalisability of machine learning applications is crucial as this has profound implications for their clinical adaptability. Briefly, two main techniques are used for this purpose: internal and external validation. The disadvantage of internal validation is that this approach may overestimate the performance of the model. For a realistic assessment a truly independent external validation dataset should be used, which should also correctly represent a realistic patient population (e.g. prevalence of the pathology of interest, age, gender, etc.). For this purpose the participation of external institutions is usually warranted 1.