다중혈관 관상동맥 환자에서 y-문합을 이용하여 양쪽 내흉동맥만을 사용한 우회술의 조기 성적

Many high quality studies have emerged from public databases, such as Surveillance, Epidemiology, and End Results (SEER), National Health and Nutrition Examination Survey (NHANES), The Cancer Genome Atlas (TCGA), and Medical Information Mart for Intensive Care (MIMIC); however, these data are often characterized by a high degree of dimensional heterogeneity, timeliness, scarcity, irregularity, and other characteristics, resulting in the value of these data not being fully utilized. Data-mining technology has been a frontier field in medical research, as it demonstrates excellent performance in evaluating patient risks and assisting clinical decision-making in building disease-prediction models. Therefore, data mining has unique advantages in clinical big-data research, especially in large-scale medical public databases. This article introduced the main medical public database and described the steps, tasks, and models of data mining in simple language. Additionally, we described data-mining methods along with their practical applications. The goal of this work was to aid clinical researchers in gaining a clear and intuitive understanding of the application of data-mining technology on clinical big-data in order to promote the production of research results that are beneficial to doctors and patients.

/pdf/data-mining-in-clinical-big-data-the-frequently-used-1dzr75xywz.pdf

Data mining in clinical big data: the frequently used databases, steps, and methodological models.

Reviewing ensemble classification methods in breast cancer.

Dataset size is considered a major concern in the medical domain, where lack of data is a common occurrence. This study aims to investigate the impact of dataset size on the overall performance of supervised classification models. We examined the performance of six widely-used models in the medical field, including support vector machine (SVM), neural networks (NN), C4.5 decision tree (DT), random forest (RF), adaboost (AB), and naive Bayes (NB) on eighteen small medical UCI datasets. We further implemented three dataset size reduction scenarios on two large datasets and analyze the performance of the models when trained on each resulting dataset with respect to accuracy, precision, recall, f-score, specificity, and area under the ROC curve (AUC). Our results indicated that the overall performance of classifiers depend on how much a dataset represents the original distribution rather than its size. Moreover, we found that the most robust model for limited medical data is AB and NB, followed by SVM, and then RF and NN, while the least robust model is DT. Furthermore, an interesting observation is that a robust machine learning model to limited dataset does not necessary imply that it provides the best performance compared to other models.

Impact of Dataset Size on Classification Performance: An Empirical Evaluation in the Medical Domain

Epilepsy, a fatal neurological disorder, has been emerged as a worldwide problem and is one of the major risks to human lives. There exists an urgent need for an efficient technique for early detection of epileptic seizures at its initial stage in order to save the lives of thousands of epileptic patients annually. Now a days, internet of things in combination with machine learning techniques and cloud computing services has emerged as a powerful technology to resolve many problems in healthcare sector. This paper also presents an automatic epileptic seizure detection system and its layered architecture for early detection of epileptic seizures using existing communication technologies in collaboration with machine learning and cloud computing. This model transmits sensed EEG signals from patient’s scalp to cloud through 4G cellular network or Wi-Fi network. At cloud, EEG signals are processed using Fast Walsh Hadamard transform and higher order spectra (HOS) based feature extraction for extracting higher order statistics and entropy-based features. The correlation-based feature selection algorithm has been employed for reducing the dimensionality of EEG datasets so as to tackle the problem of large volume of data and to reduce delays in service offered to the end user. Random Forest algorithm has been employed for classification of EEG signals into three different seizure stages, viz., normal, preictal and ictal. For performance analysis, other well-known machine learning algorithms like Bayes Net, Naive Bayes, Multilayer Perceptron, Radial Basis function neural network and C4.5 Decision Tree are also considered. The simulation and testing results show that Random Forest classifier provides maximum values of classification accuracy of 99.40%, sensitivity of 99.40% and specificity of 99.66%, minimum mean square error of 0.0871 along with optimum training time of 20 ms, which makes this model more real time compatible, thereby making HOS features based Random Forest algorithm’s cloud model an efficient technique for early and automatic detection of epileptic seizures in real time.

IoT and cloud computing based automatic epileptic seizure detection using HOS features based random forest classification

Various kinds of data mining algorithms are continuously raised with the development of related disciplines. The applicable scopes and their performances of these algorithms are different. Hence, finding a suitable algorithm for a dataset is becoming an important emphasis for biomedical researchers to solve practical problems promptly. In this paper, seven kinds of sophisticated active algorithms, namely, C4.5, support vector machine, AdaBoost, k-nearest neighbor, naive Bayes, random forest, and logistic regression, were selected as the research objects. The seven algorithms were applied to the 12 top-click UCI public datasets with the task of classification, and their performances were compared through induction and analysis. The sample size, number of attributes, number of missing values, and the sample size of each class, correlation coefficients between variables, class entropy of task variable, and the ratio of the sample size of the largest class to the least class were calculated to character the 12 research datasets. The two ensemble algorithms reach high accuracy of classification on most datasets. Moreover, random forest performs better than AdaBoost on the unbalanced dataset of the multi-class task. Simple algorithms, such as the naive Bayes and logistic regression model are suitable for a small dataset with high correlation between the task and other non-task attribute variables. K-nearest neighbor and C4.5 decision tree algorithms perform well on binary- and multi-class task datasets. Support vector machine is more adept on the balanced small dataset of the binary-class task. No algorithm can maintain the best performance in all datasets. The applicability of the seven data mining algorithms on the datasets with different characteristics was summarized to provide a reference for biomedical researchers or beginners in different fields.

/pdf/empirical-study-of-seven-data-mining-algorithms-on-different-2z4kw0b7s8.pdf

Empirical study of seven data mining algorithms on different characteristics of datasets for biomedical classification applications

Background Stroke is a frequently-occurring disease and is a severe threat to human health. Objective We aimed to explore the associations between stroke risk factors. Methods Subjects who were aged 40 or above were requested to do surveys with a unified questionnaire as well as laboratory examinations. The Apriori algorithm was applied to find out the meaningful association rules. Selected association rules were divided into 8 groups by the number of former items. The rules with higher confidence degree in every group were viewed as the meaningful rules. Results The training set used in association analysis consists of a total of 985,325 samples, with 15,835 stroke patients (1.65%) and 941,490 without stroke (98.35%). Based on the threshold we set for the Apriori algorithm, eight meaningful association rules were obtained between stroke and its high risk factors. While between high risk factors, there are 25 meaningful association rules. Conclusions Based on the Apriori algorithm, meaningful association rules between the high risk factors of stroke were found, proving a feasible way to reduce the risk of stroke with early intervention.

Mining association rules between stroke risk factors based on the Apriori algorithm

Background Magnesium ion, as important cation in the human body, involved in various enzymatic reactions, glucose transport and insulin release. Now diabetes mellitus and diabetic complications have become important public health problems around the world. Objective This paper explores the association between concentration levels of serum magnesium and common complications and comorbidities of diabetes mellitus and other biochemical indexes. Methods There are 1217 eligible patients selected from 14,317 cases of diabetic hospitalization patients from January 2010 to December 2011. Random forest algorithm was applied to assess the importance of various biochemical indexes and to perform diabetic complications prediction. Results The research results showed that low concentration of serum magnesium and four common diabetic complications - diabetic retinopathy, diabetic nephropathy, diabetic neuropathy and diabetic macroangiopathy - exists association, but no obvious correlation with other comorbidities like hypertension. Conclusions The specific factors of four common diabetic complications were selected from the biochemical indexes to provide a reference direction for further research.

Association between serum magnesium and common complications of diabetes mellitus.

The incidence of prostate cancer increases annually. Prostate cancer is an underreported and emerging problem in China. We conducted a cross-sectional study of 392 eligible patients from 710 men with prostate cancer or benign prostatic hyperplasia between 2000 and 2003. For total prostate-specific antigen, age, three diameters of prostate, prostate volume and prostate-specific antigen density seven indices, analysis of variance, and t test were used to analyze the difference between the groups. A decision tree with pruning was established using the prostate-specific antigen density, age, and transversal diameter of the prostate to screen the patient with prostate cancer. According to the established decision tree model, prostate-specific antigen density was the most important factor affecting the occurrence of prostate cancer. In elderly people over the age of 83 years, the transverse diameter of prostate cancer was smaller than that of benign prostatic hyperplasia, with prostate-specific antigen density less than 0.49 ng/L2. No additional index was introduced, and the detection rate of prostate cancer was 86.6 percent. The specificity was enhanced to 78.1 percent.

Differentiating Prostate Cancer from Benign Prostatic Hyperplasia Using PSAD Based on Machine Learning: Single-Center Retrospective Study in China

Stroke is a common disease that seriously endangers human health and life. According to the number of eight traditional risk factors of stroke to determine the stroke high-risk group, there are still some limitations. The study aims to explore the risk weights of different stroke risk factors. The research data used in this study was collected by the stroke prevention and control project. The study population included adults aged ≥40 years residing in 16 provinces, municipalities and autonomous regions throughout China. 985, 325 subjects were included in the study, 15,835 stroke patients (1.65%) and 941,490 without stroke (98.35%). The Cumulative score model was applied to explore the stroke risk factors and their risk weights based on Logistic regression. From high to low, the risk of eight traditional factors is hypertension, family history of stroke, atrial fibrillation, diabetes mellitus, dyslipidemia, obvious weight, lack of physical activity and smoking. The weight coefficient of hypertension is about 7.7 times that of smoking.

/pdf/study-on-risk-weights-of-different-stroke-risk-factors-2yunycz0hu.pdf

Yiyan Zhang

Papers

Empirical study of seven data mining algorithms on different characteristics of datasets for biomedical classification applications

Mining association rules between stroke risk factors based on the Apriori algorithm

Association between serum magnesium and common complications of diabetes mellitus.

Differentiating Prostate Cancer from Benign Prostatic Hyperplasia Using PSAD Based on Machine Learning: Single-Center Retrospective Study in China

Study on risk weights of different stroke risk factors