1. What are the contributions mentioned in the paper "A kernel-based framework for medical big-data analytics" ?
Holzinger et al. this paper proposed a kernel-based framework for medical big data analytics, which employs a neutral point substitution method to address the missing data problem presented by patients with sparse or absent data modalities.
read more
2. What future works have the authors mentioned in the paper "A kernel-based framework for medical big-data analytics" ?
In terms of the second open problem Data Mining/Unsupervised Clustering Analysis, the authors might wish to explore rule-mining type approaches, since the resulting logical clauses most closely resemble the diagnostic criteria used by medical professionals in evaluation disease conditions.. Another possibility would be Structured Output Learning [ 31 ], a variant of the Support Vector Machine that incorporates a loss-function capable of measuring the distance between two structured outputs ( for example, two temporal series of labels ).. The means of such partitioned clusters would then correspond to prototypes within the data, which may be used for e. g. efficient indexing and kernel based characterization of novel data.. However, it will invariably be the case that each novel EHR dataset will involve characteristics that are more suited to one particular form of machine learning approach over another -it is not generally the case that this can be specified a priori, thereby necessitating a flexible research programme with the potential to leverage the full range of available kernel-based machine-learning techniques.
read more