Swarm learning for decentralized healthcare

Excerpt

Machine learning is revolutionizing medicine by enabling novel applications as well as supporting physicians in routine tasks. These techniques rely on large datasets and collections for development, which are hard to acquire in the decentralized world of healthcare. Privacy and data safety are challenges which slow development in the medical field in comparison to others. Even if a sufficiently large dataset can be created, it is only a static snapshot and cannot reflect upcoming diseases. Machine learning is playing a growing role in dermatology [1, 2] and will become a major technology to assist (and not replace) physicians to improve the quality of care and reduce workload. Medicine itself is inherently based on learning from each other. The long-established mentor principle during training is a good example. Similarly, tools that support physicians in using machine learning techniques need to be trained as well. Unlike humans, these tools do not have a general understanding of the world (like a strong artificial intelligence) and need to compensate that by learning from a large number of training datasets. The performance of a machine learning model correlates with the amount of training data. Therefore, acquiring ever-growing training datasets is crucial. However, data privacy laws and patient consent limit the data collection and impact model performance. …