The Naive Bayes can outperform more sophisticated classification methods, despite its simplicity.
To improve the diagnosis sensitivity of mediastinal lymph node NSCLC, more sophisticated classification strategy is needed and computerized machine learning algorithms could be of help.
We plan to extend this preliminary study using both more sophisticated classification schemes, such as the use of SVMs and a more comprehensive set of speech features, such as variations of our speech-rate measures, power, fundamental frequency measures, and temporal- and frequency-based rhythmic/modulation patterns.
More sophisticated classification arrangements were proposed by Pseudo-Geber (in the Geber corpus, c. 1310), Paracelsus (De Natura Rerum libri nonem, 1525 6; and later works), Basil Valentine (Conclusiones, 1624), and Boerhaave (Elementa Chemiæ, 1733).
Finally, our study shows how functional metabolomics can contribute to obtaining a more sophisticated classification of the disease as well as rational optimization of diagnostic and treatment options, as recently suggested by Bain et al. [4].
It may be possible to improve performance further by making use of a richer set of features in a more sophisticated classification framework, including, say, the primary traces for sequencing reads and the full multiple alignment of reads used by the assembler [19].
While journal impact factors may thus indeed provide a meaningful qualitative measure of impact, a fair quantitative comparison requires a more sophisticated journal classification system, together with multiple field-specific impact statistics per journal.
The Dutch cohort study used a more sophisticated dosage classification [ 21].
These initial works offered valuable insights into tumor biology and demonstrated that intrinsic gene expression patterns could be used in conjunction with histopathological characteristics for a far more sophisticated tumor classification system.
Subsequent algorithms added additional prognosticators in order to produce sequentially more sophisticated risk classifications using the following high risk classifiers: T cell immunophenotype, poor risk cytogenetics, and presence of MRD (Table 1).
However, other more sophisticated methods of classification were also used for comparison.
