sigFeature: an R-package for significant feature selection using SVM-RFE and t-statistic
Bibliographic record
Abstract
Depending on the sub-site of the primary tumour, up to thirty percent of the patients with clinical and radiological node negative HNSCC may have occult metastases. Therefore, currently, up to seventy percent patients with node negative neck disease receive unnecessary therapy to ensure a minority who are truly at risk [1]. The treatment of HNSCC involves surgery, radiotherapy or multimodality therapy like surgery together with adjuvant radiotherapy or chemo radiotherapy. HNSCC is typically considered as a homogeneous tumour group, i.e., histopathologically identical, but they are often genetically disparate and exhibit variable biological behaviour and response to treatment between and within anatomical sub-sites [2]. Currently, treatment decisions for patients with HNSCC are still based on clinical, radiological and pathologic parameters. No molecular markers are used for treatment decision, except in ongoing research protocols. To identify those patients who are truly at risk, a novel feature selection method has been introduced based on expressional genomic data in this study. In data mining, feature selection is an extremely dynamic field of research for classification in the field of machine learning technology. The aim of feature selection is to select a small subset of a feature from a larger pool, rendering not only a good performance of classification but also biologically meaningful insights. Filter methods e.g. the support vector machine recursive feature elimination (SVM-RFE) is recognised as one of the most effective methods. The RFE-SVM algorithm is a greedy method that only hopes to find the best possible combination for classification without considering the differentially significant feature between the classes. To overcome this limitation of SVM-RFE, our proposed approach which is based on RFE-SVM and t-statistic is to find out differentially significant features along with the good performance of classification. The experimental results which we obtained after analysing six publicly available micro array datasets are very promising and show the contribution in feature selection in machine learning technology. The main conclusion is that the selected features are differentially significant between the classes and able to produce good classification accuracy which will help further downstream analysis for strengthening the biological aspect.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.007 | 0.026 |
| Meta-epidemiology (narrow) | 0.004 | 0.002 |
| Meta-epidemiology (broad) | 0.004 | 0.003 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.004 | 0.003 |
| Research integrity | 0.001 | 0.004 |
| Insufficient payload (model declined to judge) | 0.111 | 0.051 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".