Near-infrared spectroscopic applications for diagnosis of endometrial carcinoma

Spectral Differentiation of Esophageal Precancerous Lesion Staging and an Improved Feature Wavelength Selection Method Based on Enhanced Fox Algorithm

Near-infrared (NIR) spectroscopy, known for its non-destructive, rapid, and precise nature, captures spectral responses to chemical bond changes in cancerous tissues. This provides a promising approach for accurate cancer staging and identifying spectral differences between cancerous and healthy tissues. In this study, NIR data from esophageal lesions excised via endoscopic submucosal dissection were analyzed using partial least squares discriminant analysis (PLS-DA) to classify normal tissues, low-grade, and high-grade intraepithelial neoplasia, confirming its feasibility for staging diagnosis. To enhance wavelength selection, the FOX algorithm, a swarm intelligence optimization method, is improved with two modifications: a nonlinear time-varying sigmoid transfer function and mirror selection. These enhancements are combined to form an improved FOX algorithm (iFOX) for wavelength selection. iFOX effectively enhances the algorithm's stability while enhancing classification performance.

Evaluating the use of machine learning in endometrial cancer: a systematic review

OBJECTIVE

To review the literature on machine learning in endometrial cancer, report the most commonly used algorithms, and compare performance with traditional prediction models.

METHODS

This is a systematic review of the literature from January 1985 to March 2021 on the use of machine learning in endometrial cancer. An extensive search of electronic databases was conducted. Four independent reviewers screened studies initially by title then full text. Quality was assessed using the MINORS (Methodological Index for Non-Randomized Studies) criteria. P values were derived using the Pearson's Χ2 test in JMP 15.0.

RESULTS

Among 4295 articles screened, 30 studies on machine learning in endometrial cancer were included. The most frequent applications were in patient datasets (33.3%, n=10), pre-operative diagnostics (30%, n=9), genomics (23.3%, n=7), and serum biomarkers (13.3%, n=4). The most commonly used models were neural networks (n=10, 33.3%) and support vector machine (n=6, 20%).The number of publications on machine learning in endometrial cancer increased from 1 in 2010 to 29 in 2021.Eight studies compared machine learning with traditional statistics. Among patient dataset studies, two machine learning models (20%) performed similarly to logistic regression (accuracy: 0.85 vs 0.82, p=0.16). Machine learning algorithms performed similarly to detect endometrial cancer based on MRI (accuracy: 0.87 vs 0.82, p=0.24) while outperforming traditional methods in predicting extra-uterine disease in one serum biomarker study (accuracy: 0.81 vs 0.61). For survival outcomes, one study compared machine learning with Kaplan-Meier and reported no difference in concordance index (83.8% vs 83.1%).

CONCLUSION

Although machine learning is an innovative and emerging technology, performance is similar to that of traditional regression models in endometrial cancer. More studies are needed to assess its role in endometrial cancer.

PROSPERO REGISTRATION NUMBER

CRD42021269565.

Support Vector Machine Classification Trees

Proteomic and metabolomic studies based on chemical profiling require powerful classifiers to model accurately complex collections of data. Support vector machines (SVMs) are advantageous in that they provide a maximum margin of separation for the classification hyperplane. A new method for constructing classification trees, for which the branches comprise SVMs, has been devised. The novel feature is that the distribution of the data objects is used to determine the SVM encoding. The variance and covariance of the data objects are used for determining the bipolar encoding required for the SVM. The SVM that yields the lowest entropy of classification becomes the branch of the tree. The SVM-tree classifier has the added advantage that nonlinearly separable data may be accurately classified without optimization of the cost parameter C or searching for a correct higher dimensional kernel transform. It compares favorably to a regularized linear discriminant analysis, SVMs in a one against all multiple classifier, and a fuzzy rule-building expert system, a tree classifier with a fuzzy margin of separation. SVMs offer a speed advantage, especially for data sets that have more measurements than objects.