IntroductionK-nearest neighbor (k-NN) classification is conventional non-parametric classifier, which has been used as the baseline classifier in many pattern classification problems. It is based on measuring the distances between the test data and each of the training data to decide the final classification output.Case descriptionSince the Euclidean distance function is the most widely used distance metric in k-NN, no study examines the classification performance of k-NN by different distance functions, especially for various medical domain problems. Therefore, the aim of this paper is to investigate whether the distance function can affect the k-NN performance over different medical datasets. Our experiments are based on three different types of medical datasets containing categorical, numerical, and mixed types of data and four different distance functions including Euclidean, cosine, Chi square, and Minkowsky are used during k-NN classification individually.Discussion and evaluationThe experimental results show that using the Chi square distance function is the best choice for the three different types of datasets. However, using the cosine and Euclidean (and Minkowsky) distance function perform the worst over the mixed type of datasets.ConclusionsIn this paper, we demonstrate that the chosen distance function can affect the classification accuracy of the k-NN classifier. For the medical domain datasets including the categorical, numerical, and mixed types of data, K-NN based on the Chi square distance function performs the best.

Breast cancer is an all too common disease in women, making how to effectively predict it an active research problem. A number of statistical and machine learning techniques have been employed to develop various breast cancer prediction models. Among them, support vector machines (SVM) have been shown to outperform many related techniques. To construct the SVM classifier, it is first necessary to decide the kernel function, and different kernel functions can result in different prediction performance. However, there have been very few studies focused on examining the prediction performances of SVM based on different kernel functions. Moreover, it is unknown whether SVM classifier ensembles which have been proposed to improve the performance of single classifiers can outperform single SVM classifiers in terms of breast cancer prediction. Therefore, the aim of this paper is to fully assess the prediction performance of SVM and SVM ensembles over small and large scale breast cancer datasets. The classification accuracy, ROC, F-measure, and computational times of training SVM and SVM ensembles are compared. The experimental results show that linear kernel based SVM ensembles based on the bagging method and RBF kernel based SVM ensembles with the boosting method can be the better choices for a small scale dataset, where feature selection should be performed in the data pre-processing stage. For a large scale dataset, RBF kernel based SVM ensembles based on boosting perform better than the other classifiers.

BackgroundPolycystic ovary syndrome (PCOS) is one of the most common endocrine disorders among women of reproductive age. A higher prevalence of psychiatric comorbidities, including depressive disorder, anxiety disorder, and bipolar disorder has been proved in patients with PCOS. However, a clear temporal causal relationship between PCOS and psychiatric disorders has not been well established.ObjectiveWe explored the relationship between PCOS and the subsequent development of psychiatric disorders including schizophrenia, bipolar disorder, depressive disorder, anxiety disorder, and sleep disorder.MethodsWe identified patients who were diagnosed with PCOS by an obstetrician-gynecologist in the Taiwan National Health Insurance Research Database. A comparison cohort was constructed of patients without PCOS who were matched according to age and sex. The occurrence of subsequent new-onset psychiatric disorders was evaluated in both cohorts based on diagnoses made by psychiatrists.ResultsThe PCOS cohort consisted of 5431 patients, and the comparison cohort consisted of 21,724 matched control patients without PCOS. The incidence of depressive disorder (hazard ratio [HR] 1.296, 95% confidence interval [CI] 1.084–.550), anxiety disorder (HR 1.392, 95% CI 1.121–1.729), and sleep disorder (HR 1.495, 95% CI 1.176–1.899) were higher among the PCOS patients than among the patients in the comparison cohort. In addition, a higher incidence of newly diagnosed depressive disorder, anxiety disorder, and sleep disorder remained significantly increased in all of the stratified follow-up durations (0–1, 1–5, ≥5 y).ConclusionsPCOS might increase the risk of subsequent newly diagnosed depressive disorder, anxiety disorder, and sleep disorder. The risk of newly diagnosed bipolar disorder, which has often been reported in the literature to be comorbid with PCOS, was not significantly elevated.

BackgroundIrritable bowel syndrome (IBS) is the most common functional gastrointestinal (GI) disorder observed in patients who visit general practitioners for GI-related complaints. A high prevalence of psychiatric comorbidities, particularly anxiety and depressive disorders, has been reported in patients with IBS. However, a clear temporal relationship between IBS and psychiatric disorders has not been well established.ObjectiveWe explored the relationship between IBS and the subsequent development of psychiatric disorders including schizophrenia, bipolar disorder, depressive disorder, anxiety disorder, and sleep disorder.MethodsWe selected patients who were diagnosed with IBS caused by gastroenteritis, according to the data in the Taiwan National Health Insurance Research Database. A comparison cohort was formed of patients without IBS who were matched according to age and sex. The incidence rate and the hazard ratios (HRs) of subsequent new-onset psychiatric disorders were calculated for both cohorts, based on psychiatrist diagnoses.ResultsThe IBS cohort consisted of 4689 patients, and the comparison cohort comprised 18756 matched control patients without IBS. The risks of depressive disorder (HR = 2.71, 95% confidence interval [CI] = 2.30–3.19), anxiety disorder (HR = 2.89, 95% CI = 2.42–3.46), sleep disorder (HR = 2.47, 95% CI = 2.02–3.02), and bipolar disorder (HR = 2.44, 95% CI = 1.34–4.46) were higher in the IBS cohort than in the comparison cohort. In addition, the incidence of newly diagnosed depressive disorder, anxiety disorder, and sleep disorder remained significantly increased in all of the stratified follow-up durations (0–1, 1–5, ≥5 y).ConclusionsIBS may increase the risk of subsequent depressive disorder, anxiety disorder, sleep disorder, and bipolar disorder. The risk ratios are highest for these disorders within 1 year of IBS diagnosis, but the risk remains statistically significant for more than 5 years. Clinicians should pay particular attention to psychiatric comorbidities in IBS patients.