Machine Learning Models for Classification of Cushing's Syndrome Using Retrospective Data.

Accurate classification of Cushing's Syndrome (CS) plays a critical role in providing the early and correct diagnosis of CS that may facilitate treatment and improve patient outcomes. Diagnosis of CS is a complex process, which requires careful and concurrent interpretation of signs and symptoms, multiple biochemical test results, and findings of medical imaging by physicians with a high degree of specialty and knowledge to make correct judgments. In this article, we explore the state of the art machine learning algorithms to demonstrate their potential as a clinical decision support system to analyze and classify CS to facilitate the diagnosis, prognosis, and treatment of CS. Prominent algorithms are compared using nested cross-validation and various class comparison strategies including multiclass, one vs. all, and one vs. one binary classification. Our findings show that Random Forest (RF) algorithm is most suitable for the classification of CS. We demonstrate that the proposed approach can classify CS with an average accuracy of 92% and an average F1 score of 91.5%, depending on the class comparison strategy and selected features. RF-based one vs. all binary classification model achieves sensitivity of 97.6%, precision of 91.1%, and specificity of 87.1% to discriminate CS from non-CS on the test dataset. RF-based multiclass classification model achieves average per class sensitivity of 91.8%, average per class specificity of 97.1%, and average per class precision of 92.1% to classify different subtypes of CS on the test dataset. Clinical performance evaluation suggests that the developed models can help improve physicians' judgment in diagnosing CS.

Bayesian pathway analysis of cancer microarray data.

High Throughput Biological Data (HTBD) requires detailed analysis methods and from a life science perspective, these analysis results make most sense when interpreted within the context of biological pathways. Bayesian Networks (BNs) capture both linear and nonlinear interactions and handle stochastic events in a probabilistic framework accounting for noise making them viable candidates for HTBD analysis. We have recently proposed an approach, called Bayesian Pathway Analysis (BPA), for analyzing HTBD using BNs in which known biological pathways are modeled as BNs and pathways that best explain the given HTBD are found. BPA uses the fold change information to obtain an input matrix to score each pathway modeled as a BN. Scoring is achieved using the Bayesian-Dirichlet Equivalent method and significance is assessed by randomization via bootstrapping of the columns of the input matrix. In this study, we improve on the BPA system by optimizing the steps involved in "Data Preprocessing and Discretization", "Scoring", "Significance Assessment", and "Software and Web Application". We tested the improved system on synthetic data sets and achieved over 98% accuracy in identifying the active pathways. The overall approach was applied on real cancer microarray data sets in order to investigate the pathways that are commonly active in different cancer types. We compared our findings on the real data sets with a relevant approach called the Signaling Pathway Impact Analysis (SPIA).

Bayesian network prior: network analysis of biological data using external knowledge.

MOTIVATION: Reverse engineering GI networks from experimental data is a challenging task due to the complex nature of the networks and the noise inherent in the data. One way to overcome these hurdles would be incorporating the vast amounts of external biological knowledge when building interaction networks. We propose a framework where GI networks are learned from experimental data using Bayesian networks (BNs) and the incorporation of external knowledge is also done via a BN that we call Bayesian Network Prior (BNP). BNP depicts the relation between various evidence types that contribute to the event 'gene interaction' and is used to calculate the probability of a candidate graph (G) in the structure learning process. RESULTS: Our simulation results on synthetic, simulated and real biological data show that the proposed approach can identify the underlying interaction network with high accuracy even when the prior information is distorted and outperforms existing methods. AVAILABILITY: Accompanying BNP software package is freely available for academic use at http://bioe.bilgi.edu.tr/BNP. CONTACT: hasan.otu@bilgi.edu.tr SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Pathway analysis of high-throughput biological data within a Bayesian network framework.

MOTIVATION: Most current approaches to high-throughput biological data (HTBD) analysis either perform individual gene/protein analysis or, gene/protein set enrichment analysis for a list of biologically relevant molecules. Bayesian Networks (BNs) capture linear and non-linear interactions, handle stochastic events accounting for noise, and focus on local interactions, which can be related to causal inference. Here, we describe for the first time an algorithm that models biological pathways as BNs and identifies pathways that best explain given HTBD by scoring fitness of each network. RESULTS: Proposed method takes into account the connectivity and relatedness between nodes of the pathway through factoring pathway topology in its model. Our simulations using synthetic data demonstrated robustness of our approach. We tested proposed method, Bayesian Pathway Analysis (BPA), on human microarray data regarding renal cell carcinoma (RCC) and compared our results with gene set enrichment analysis. BPA was able to find broader and more specific pathways related to RCC. AVAILABILITY: Accompanying BPA software (BPAS) package is freely available for academic use at http://bumil.boun.edu.tr/bpa.

Development of a surgical diode-laser system: controlling the mode of operation.

OBJECTIVE: The aim of this study was to develop a microcontroller based surgical diode laser system and to test it at two different modes (continuous [CW] and modulated) in vitro on lamb liver tissue. BACKGROUND DATA: In laser surgery, depending on the properties of laser source (wavelength, power, application time, and mode of operation), the effects observed on the tissue may change from carbonization to hyperthermia. The aim is to remove the target tissue without giving any thermal damage to the surrounding tissue. Carbonization should be avoided, thus controlling the mode of operation is very crucial. METHODS: The system consisted of a microcontroller based control unit, 980-nm high-power diode laser source, and fiber delivery unit. This system has the capability of delivering different modes of laser energy to the target tissue ranging from CW to 20-Hz modulated beams. The surgical diode laser system was tested on liver tissue in vitro. Efficiency of laser-tissue interaction was quantified in terms of thermal alteration per unit energy and corresponding carbonization level. RESULTS: Modulated mode resulted in larger coagulated area with minimum carbonizations. Carbonized area/thermally altered area (CarbA/TAA) ratio for CW mode of operation at 16 J is 0.35; however, this ratio was found to be 0.05 at modulated mode, when even 10 times higher energy (160 J) was delivered to the target tissue. CONCLUSION: Results emphasized the significance of mode of operation as well as the other laser parameters. Modulated mode was found to be a promising regime for safer laser surgery.