Siow-Wee Chang

Oral cancer prognosis based on clinicopathologic and genomic markers using a hybrid of feature selection and machine learning methods

BackgroundMachine learning techniques are becoming useful as an alternative approach to conventional medical diagnosis or prognosis as they are good for handling noisy and incomplete data, and significant results can be attained despite a small sample size. Traditionally, clinicians make prognostic decisions based on clinicopathologic markers. However, it is not easy for the most skilful clinician to come out with an accurate prognosis by using these markers alone. Thus, there is a need to use genomic markers to improve the accuracy of prognosis. The main aim of this research is to apply a hybrid of feature selection and machine learning methods in oral cancer prognosis based on the parameters of the correlation of clinicopathologic and genomic markers.ResultsIn the first stage of this research, five feature selection methods have been proposed and experimented on the oral cancer prognosis dataset. In the second stage, the model with the features selected from each feature selection methods are tested on the proposed classifiers. Four types of classifiers are chosen; these are namely, ANFIS, artificial neural network, support vector machine and logistic regression. A k-fold cross-validation is implemented on all types of classifiers due to the small sample size. The hybrid model of ReliefF-GA-ANFIS with 3-input features of drink, invasion and p63 achieved the best accuracy (accuracy = 93.81%; AUC = 0.90) for the oral cancer prognosis.ConclusionsThe results revealed that the prognosis is superior with the presence of both clinicopathologic and genomic markers. The selected features can be investigated further to validate the potential of becoming as significant prognostic signature in the oral cancer studies.

Virtual reality based support system for layout planning and programming of an industrial robotic work cell.

Traditional robotic work cell design and programming are considered inefficient and outdated in current industrial and market demands. In this research, virtual reality (VR) technology is used to improve human-robot interface, whereby complicated commands or programming knowledge is not required. The proposed solution, known as VR-based Programming of a Robotic Work Cell (VR-Rocell), consists of two sub-programmes, which are VR-Robotic Work Cell Layout (VR-RoWL) and VR-based Robot Teaching System (VR-RoT). VR-RoWL is developed to assign the layout design for an industrial robotic work cell, whereby VR-RoT is developed to overcome safety issues and lack of trained personnel in robot programming. Simple and user-friendly interfaces are designed for inexperienced users to generate robot commands without damaging the robot or interrupting the production line. The user is able to attempt numerous times to attain an optimum solution. A case study is conducted in the Robotics Laboratory to assemble an electronics casing and it is found that the output models are compatible with commercial software without loss of information. Furthermore, the generated KUKA commands are workable when loaded into a commercial simulator. The operation of the actual robotic work cell shows that the errors may be due to the dynamics of the KUKA robot rather than the accuracy of the generated programme. Therefore, it is concluded that the virtual reality based solution approach can be implemented in an industrial robotic work cell.

A Bootstrap-ANFIS framework for oral cancer prognosis based on clinical and genomic markers

The incidence of oral cancer is high in Malaysia especially for those of Indian ethnic origin. In this research, an oral cancer prognosis prediction model will be developed by using Bootstrap-ANFIS techniques. The aim of this research is to improve the prediction of oral cancer survival and to identify the key clinical and genomic markers for the survival prediction of oral cancer. The proposed model is designed to handle small medical dataset with limitations in terms of time, cost and tissue samples.

Plant data visualisation using network graphs

Background The amount of plant data such as taxonomical classification, morphological characteristics, ecological attributes and geological distribution in textual and image forms has increased rapidly due to emerging research and technologies. Therefore, it is crucial for experts as well as the public to discern meaningful relationships from this vast amount of data using appropriate methods. The data are often presented in lengthy texts and tables, which make gaining new insights difficult. The study proposes a visual-based representation to display data to users in a meaningful way. This method emphasises the relationships between different data sets. Method This study involves four main steps which translate text-based results from Extensible Markup Language (XML) serialisation format into graphs. The four steps include: (1) conversion of ontological dataset as graph model data; (2) query from graph model data; (3) transformation of text-based results in XML serialisation format into a graphical form; and (4) display of results to the user via a graphical user interface (GUI). Ontological data for plants and samples of trees and shrubs were used as the dataset to demonstrate how plant-based data could be integrated into the proposed data visualisation. Results A visualisation system named plant visualisation system was developed. This system provides a GUI that enables users to perform the query process, as well as a graphical viewer to display the results of the query in the form of a network graph. The efficiency of the developed visualisation system was measured by performing two types of user evaluations: a usability heuristics evaluation, and a query and visualisation evaluation. Discussion The relationships between the data were visualised, enabling the users to easily infer the knowledge and correlations between data. The results from the user evaluation show that the proposed visualisation system is suitable for both expert and novice users, with or without computer skills. This technique demonstrates the practicability of using a computer assisted-tool by providing cognitive analysis for understanding relationships between data. Therefore, the results benefit not only botanists, but also novice users, especially those that are interested to know more about plants.

Integrative machine learning analysis of multiple gene expression profiles in cervical cancer

Although most of the cervical cancer cases are reported to be closely related to the Human Papillomavirus (HPV) infection, there is a need to study genes that stand up differentially in the final actualization of cervical cancers following HPV infection. In this study, we proposed an integrative machine learning approach to analyse multiple gene expression profiles in cervical cancer in order to identify a set of genetic markers that are associated with and may eventually aid in the diagnosis or prognosis of cervical cancers. The proposed integrative analysis is composed of three steps: namely, (i) gene expression analysis of individual dataset; (ii) meta-analysis of multiple datasets; and (iii) feature selection and machine learning analysis. As a result, 21 gene expressions were identified through the integrative machine learning analysis which including seven supervised and one unsupervised methods. A functional analysis with GSEA (Gene Set Enrichment Analysis) was performed on the selected 21-gene expression set and showed significant enrichment in a nine-potential gene expression signature, namely PEG3, SPON1, BTD and RPLP2 (upregulated genes) and PRDX3, COPB2, LSM3, SLC5A3 and AS1B (downregulated genes).

Automated classification of tropical shrub species: a hybrid of leaf shape and machine learning approach

Plants play a crucial role in foodstuff, medicine, industry, and environmental protection. The skill of recognising plants is very important in some applications, including conservation of endangered species and rehabilitation of lands after mining activities. However, it is a difficult task to identify plant species because it requires specialized knowledge. Developing an automated classification system for plant species is necessary and valuable since it can help specialists as well as the public in identifying plant species easily. Shape descriptors were applied on the myDAUN dataset that contains 45 tropical shrub species collected from the University of Malaya (UM), Malaysia. Based on literature review, this is the first study in the development of tropical shrub species image dataset and classification using a hybrid of leaf shape and machine learning approach. Four types of shape descriptors were used in this study namely morphological shape descriptors (MSD), Histogram of Oriented Gradients (HOG), Hu invariant moments (Hu) and Zernike moments (ZM). Single descriptor, as well as the combination of hybrid descriptors were tested and compared. The tropical shrub species are classified using six different classifiers, which are artificial neural network (ANN), random forest (RF), support vector machine (SVM), k-nearest neighbour (k-NN), linear discriminant analysis (LDA) and directed acyclic graph multiclass least squares twin support vector machine (DAG MLSTSVM). In addition, three types of feature selection methods were tested in the myDAUN dataset, Relief, Correlation-based feature selection (CFS) and Pearson’s coefficient correlation (PCC). The well-known Flavia dataset and Swedish Leaf dataset were used as the validation dataset on the proposed methods. The results showed that the hybrid of all descriptors of ANN outperformed the other classifiers with an average classification accuracy of 98.23% for the myDAUN dataset, 95.25% for the Flavia dataset and 99.89% for the Swedish Leaf dataset. In addition, the Relief feature selection method achieved the highest classification accuracy of 98.13% after 80 (or 60%) of the original features were reduced, from 133 to 53 descriptors in the myDAUN dataset with the reduction in computational time. Subsequently, the hybridisation of four descriptors gave the best results compared to others. It is proven that the combination MSD and HOG were good enough for tropical shrubs species classification. Hu and ZM descriptors also improved the accuracy in tropical shrubs species classification in terms of invariant to translation, rotation and scale. ANN outperformed the others for tropical shrub species classification in this study. Feature selection methods can be used in the classification of tropical shrub species, as the comparable results could be obtained with the reduced descriptors and reduced in computational time and cost.

A genetic programming approach to oral cancer prognosis

Background The potential of genetic programming (GP) on various fields has been attained in recent years. In bio-medical field, many researches in GP are focused on the recognition of cancerous cells and also on gene expression profiling data. In this research, the aim is to study the performance of GP on the survival prediction of a small sample size of oral cancer prognosis dataset, which is the first study in the field of oral cancer prognosis. Method GP is applied on an oral cancer dataset that contains 31 cases collected from the Malaysia Oral Cancer Database and Tissue Bank System (MOCDTBS). The feature subsets that is automatically selected through GP were noted and the influences of this subset on the results of GP were recorded. In addition, a comparison between the GP performance and that of the Support Vector Machine (SVM) and logistic regression (LR) are also done in order to verify the predictive capabilities of the GP. Result The result shows that GP performed the best (average accuracy of 83.87% and average AUROC of 0.8341) when the features selected are smoking, drinking, chewing, histological differentiation of SCC, and oncogene p63. In addition, based on the comparison results, we found that the GP outperformed the SVM and LR in oral cancer prognosis. Discussion Some of the features in the dataset are found to be statistically co-related. This is because the accuracy of the GP prediction drops when one of the feature in the best feature subset is excluded. Thus, GP provides an automatic feature selection function, which chooses features that are highly correlated to the prognosis of oral cancer. This makes GP an ideal prediction model for cancer clinical and genomic data that can be used to aid physicians in their decision making stage of diagnosis or prognosis.