Prediction of Occurrence of Cerebral Infarction After Successful Mechanical Thrombectomy for Ischemic Stroke in the Anterior Circulation by Arterial Spin Labeling.

PURPOSE: The overall goal of our study is to create modified Alberta Stroke Program Early Computed Tomography Score (ASPECTS) determined by the findings on arterial spin labeling imaging (ASL) to predict the prognosis of patients with acute ischemic stroke after successful mechanical thrombectomy (MT). Prior to that, we examined predictive factors including the value of cerebral blood flow (CBF) measured by ASL for occurrence of cerebral infarction at the region of interest (ROI) used in the ASPECTS after successful MT. METHODS: Of the 92 consecutive patients with acute ischemic stroke treated with MT at our institution between April 2013 and April 2021, a total of 26 patients who arrived within 8 h after stroke onset and underwent MT resulting in a thrombolysis in cerebral infarction score of 2B or 3 were analyzed. Magnetic resonance imaging, including diffusion-weighted imaging (DWI) and ASL, was performed on arrival and the day after MT. The asymmetry index (AI) of CBF by ASL (ASL-CBF) before MT was calculated for 11 regions of interest using the DWI-Alberta Stroke Program Early CT Score. RESULTS: Occurrence of infarction after successful MT for ischemic stroke in the anterior circulation can be expected when the formula 0.3211â€¯× history of atrial fibrillation +0.0096â€¯× the AI of ASL-CBF before MT (%) +0.0012â€¯× the time from onset to reperfusion (min) yields a value below 1.0 or when the AI of ASL-CBF before MT is below 61.5%. CONCLUSION: The AI of ASL-CBF before MT or a combination of a history of atrial fibrillation, the AI of ASL-CBF before MT, and the time from onset to reperfusion can be used to predict the occurrence of infarction in patients arriving within 8 h after stroke onset in which reperfusion with MT was successful.

Factors affecting reasonable duration of continuous electrocardiographic monitoring to detect atrial fibrillation in acute ischemic stroke.

BACKGROUND: To examine the reasonable duration of continuous electrocardiographic monitoring (CEM) to detect AF at acute ischemic stroke. MATERIALS AND METHOD: 811 consecutive patients admitted to Tsuruga Municipal Hospital by acute ischemic stroke between April 2013 and December 2021 were enrolled in this study. Excluding 78 patients, 733 patients were analyzed by cluster analysis with SurvCART algorithm, followed by Kaplan-Meier analysis. RESULTS: The analysis provided step graphs for 8 subgroups. The duration of CEM to achieve the sensitivity of 0.8, 0.9, and 0.95 in each could be calculated. The duration of CEM to achieve the sensitivity of 0.8 are 18 days in female patients with heart failure (HF) (subgroup 1), 24 days in male patients with HF (subgroup 2), 22 days in patients without HF with arterial occlusion and pulse rate (PR) more than 91 (subgroup 3), 24 days in patients without HF with occlusion with PR less than 91 (subgroup 4), 18 days in patients without HF without occlusion with lacuna (subgroup 5), 26 days in patients without HF, occlusion, and lacuna, with arterial stenosis (subgroup 6), 15 days in patients without HF, occlusion, lacuna, and stenosis with BMI more than 21%(subgroup 7), and 44 days in patients without HF, occlusion, lacuna, stenosis and with BMI less than 21% (subgroup 8). CONCLUSIONS: Duration of CEM with the sensitivity of 0.8, 0.9, and 0.95 could be determined by presence of HF, female sex, arterial occlusion, PR more than 91/minute, presence of lacuna, presence of stenosis, and BMI more than 21%. (250).

Visual Evoked Potential Can Predict Deterioration of Visual Function After Direct Clipping of Paraclinoid Aneurysm With Anterior Clinoidectomy.

BACKGROUND: The role of visual evoked potential (VEP) in direct clipping of the paraclinoid internal carotid artery (ICA) aneurysm remains uncertain. OBJECTIVE: To examine whether intraoperative neuromonitoring with VEP can predict deterioration of visual function after direct clipping of the paraclinoid ICA aneurysm with anterior clinoidectomy. METHODS: Among consecutive 274 patients with unruptured cerebral aneurysm, we enrolled 25 patients with paraclinoid ICA aneurysm treated by direct clipping after anterior clinoidectomy with intraoperative neuromonitoring with VEP in this study. We evaluated the visual acuity loss (VAL) and visual field loss (VFL) before surgery, 1 month after surgery, and at the final follow-up. RESULTS: The VAL at 1 month after surgery (VAL1M) and VAL at the final follow-up (Final VAL) were significantly related to the reduction rate of VEP amplitude at the end of surgery (RedEnd%), more than 76.5%, and the maximal reduction rate of VEP amplitude during surgery (MaxRed%), more than 66.7% to 70%. The VFL at 1 month after surgery (VFL1M) and the VFL at the final follow-up (Final VFL) were significantly related to MaxRed% more than 60.7%. CONCLUSION: VAL1M, Final VAL, VFL1M, and Final VFL could be significantly predicted by the value of RedEnd% and MaxRed% in direct clipping of Al-Rodhan group Ia, Ib, and II paraclinoid ICA aneurysms with anterior clinoidectomy.

Effectiveness of high implantation of SAPIEN 3 in preventing pacemaker implantation: A propensity score analysis.

BACKGROUND: In transcatheter aortic valve implantation, high implantation on the aortic annulus may prevent conduction pathway injury, leading to a decrease in the rate of permanent pacemaker implantation. AIM: To assess the impact of high implantation of SAPIEN 3 on the prevention of permanent pacemaker implantation. METHODS: Since August 2020, we have performed high implantation by fluoroscopically positioning the lower part of the lucent line at the virtual basal ring line on a coplanar view before valve implantation. Patients treated before the adoption of this method were defined as the conventional group. We compared the high implantation group with the conventional group using propensity score analysis. RESULTS: Overall, the high implantation group (n=95) showed a significantly shorter ventricular strut length than the conventional group (n=85): median 1.3 (interquartile range 0.2-2.4) mm vs 2.8 (1.8-4.1) mm (P<0.001). The permanent pacemaker implantation rate was significantly lower in the high implantation group than in the conventional group (2.1% vs 11.8%; P=0.009). According to 100 propensity score analyses based on multiple imputation and the selection of appropriate covariates, the median P value for the comparison of permanent pacemaker implantation rates after transcatheter aortic valve implantation between the high implantation group and the conventional group ranged between 0.001 and 0.017, indicating a more significant reduction in the permanent pacemaker implantation rate in the high implantation group than in the conventional group. Neither valve dislodgement nor the need for a second valve was observed in either group. CONCLUSIONS: The high implantation of SAPIEN 3 successfully decreases ventricular strut length, reducing the permanent pacemaker implantation rate after transcatheter aortic valve implantation.

Factors affecting global neurocognitive status and frontal executive functions in the early stage after surgical clipping of unruptured anterior circulation aneurysms with respect to keyhole clipping and conventional clipping.

PURPOSE: This study investigated the most significant factor for the preservation of the global neurocognitive status and frontal executive functions in the surgical clipping of unruptured anterior circulation aneurysms, specifically in keyhole and conventional clipping procedures. METHODS: The prospective study that was performed to examine the effects of aneurysm surgery on the patient's global neurocognitive status and frontal executive functions started on April 2016. After exclusion posterior circulation aneurysms, anterior communicating aneurysms treated by interhemispheric approach, giant aneurysms, and paraclinoid aneurysms, 23 patients who were enrolled before May 2017 were treated by conventional clipping, and 18 patients who were enrolled after June 2017 were treated by keyhole clipping. Two patients were excluded from each group due to missing data. Finally, 21 and 16 patients in each group were analyzed, respectively. Three-tesla magnetic resonance imaging was performed before and after surgery to detect the presence of perioperative cerebral infarctions and brain edema. The Mini-Mental State Examination, Frontal Assessment Battery, and Self-Rating Depression Scale scores were obtained before and 1 month after surgery. RESULTS: Logistic regression analyses indicated that anterior communicating and internal carotid artery aneurysms were the most significant factors for poor outcomes and that keyhole clipping for these two types of aneurysm was the most significant factor for the preservation of patient global neurocognitive status. Keyhole clipping was also the most significant factor for the preservation of frontal executive functions in patients. CONCLUSIONS: Keyhole clipping may be more favorable than conventional clipping for the preservation of the global neurocognitive status and frontal executive functions. Moreover, it may be the most effective factor for preservation of global neurocognitive status when it is indicated for anterior communicating or internal carotid artery aneurysms.

Generalized quasi-linear mixed-effects model.

The generalized linear mixed model (GLMM) is one of the most common method in the analysis of longitudinal and clustered data in biological sciences. However, issues of model complexity and misspecification can occur when applying the GLMM. To address these issues, we extend the standard GLMM to a nonlinear mixed-effects model based on quasi-linear modeling. An estimation algorithm for the proposed model is provided by extending the penalized quasi-likelihood and the restricted maximum likelihood which are known in the GLMM inference. Also, the conditional AIC is formulated for the proposed model. The proposed model should provide a more flexible fit than the GLMM when there is a nonlinear relation between fixed and random effects. Otherwise, the proposed model is reduced to the GLMM. The performance of the proposed model under model misspecification is evaluated in several simulation studies. In the analysis of respiratory illness data from a randomized controlled trial, we observe the proposed model can capture heterogeneity; that is, it can detect a patient subgroup with specific clinical character in which the treatment is effective.

Prostate-specific antigen nomogram to predict advanced prostate cancer using area under the receiver operating characteristic curve boosting.

BACKGROUND: For prostate cancer, accurate prediction of the pathological stage before surgery is very important. Therefore, the aim of the present study was establishing the prostate-specific antigen (PSA) threshold nomogram to predict pathologically advanced prostate cancer using the novel method of area under the receiver operating characteristic curve boosting (AUCBoost). METHODS: The medical records of patients with clinically localized prostate cancer who underwent robot-assisted radical prostatectomy were retrospectively reviewed. Multivariate logistic regression analysis was performed to identify clinical covariates significantly associated with pathological tumor stage ≥3a. The best combination of the variables was determined by validated values of the area under the curve (AUC). The optimal individualized PSA threshold values were developed using AUCBoost. RESULTS: In the multivariate logistic regression analysis, PSA, prostate volume, clinical tumor stage, Gleason Grade Group, the number of positive cores, and the percentage of positive cores were independent predictive factors for pathological tumor stage ≥3a. A combination model comprising PSA, prostate volume, clinical tumor stage, percent positive core, and Gleason Grade Group produced the highest AUC for predicting pathological tumor stage ≥3a (AUC = 0.777). The PSA threshold values for detecting pathological tumor stage ≥3a were calculated and a table of individualized PSA threshold nomogram was developed using AUCBoost. CONCLUSIONS: We developed a nomogram of the PSA threshold values for predicting adverse pathological tumor stages of prostate cancer using a novel statistical method. Further validation is necessary; however, the individualized PSA threshold nomogram may be useful in determining treatment strategies before surgery.

A Unified Formulation of k-Means, Fuzzy c-Means and Gaussian Mixture Model by the Kolmogorov-Nagumo Average.

Clustering is a major unsupervised learning algorithm and is widely applied in data mining and statistical data analyses. Typical examples include k-means, fuzzy c-means, and Gaussian mixture models, which are categorized into hard, soft, and model-based clusterings, respectively. We propose a new clustering, called Pareto clustering, based on the Kolmogorov-Nagumo average, which is defined by a survival function of the Pareto distribution. The proposed algorithm incorporates all the aforementioned clusterings plus maximum-entropy clustering. We introduce a probabilistic framework for the proposed method, in which the underlying distribution to give consistency is discussed. We build the minorize-maximization algorithm to estimate the parameters in Pareto clustering. We compare the performance with existing methods in simulation studies and in benchmark dataset analyses to demonstrate its highly practical utilities.

The significance of micro-lymphatic invasion and pathological Gleason score in prostate cancer patients with pathologically organ-confined disease and negative surgical margins after robot-assisted radical prostatectomy.

BACKGROUND: The development process of recurrence in prostate cancer patients with pathologically organ-confined (pT2) disease and negative surgical margins is unclear. The aim of the present study was to determine factors associated with the development of biochemical recurrence following robot-assisted radical prostatectomy among those prostate cancer patients. METHODS: We retrospectively reviewed the data of patients who underwent robot-assisted radical prostatectomy without neoadjuvant endocrine therapy. We evaluated prognostic factors in 1096 prostate cancer patients with pT2 disease and negative surgical margins. Univariate and multivariate Cox proportional hazards regression analyses were used to identify independent predictors for biochemical recurrence. RESULTS: Of the 1096 patients, 55 experienced biochemical recurrence during the follow-up period. The 5-year biochemical recurrence-free survival rate for patients with pT2 and negative surgical margins was 91.8%. On univariate analysis, clinical stage, biopsy Gleason score, percent of positive core, pathological Gleason score, and the presence of micro-lymphatic invasion were significantly associated with biochemical recurrence. On a multivariate analysis, the presence of micro-lymphatic invasion and a pathological Gleason score ≥ 4 + 3 were significant prognostic factors for biochemical recurrence. Based on these factors, we developed a risk stratification model. The biochemical recurrence-free survival rate differed significantly among the risk groups. CONCLUSIONS: The prognosis of prostate cancer patients with pT2 disease and negative surgical margins is favorable. However, patients with the presence of micro-lymphatic invasion and a pathological Gleason score ≥ 4 + 3 tend to experience biochemical recurrence more often after surgery. Therefore, careful follow-up might be necessary for those patients.

Robust kernel canonical correlation analysis to detect gene-gene co-associations: A case study in genetics.

The kernel canonical correlation analysis based U-statistic (KCCU) is being used to detect nonlinear gene-gene co-associations. Estimating the variance of the KCCU is however computationally intensive. In addition, the kernel canonical correlation analysis (kernel CCA) is not robust to contaminated data. Using a robust kernel mean element and a robust kernel (cross)-covariance operator potentially enables the use of a robust kernel CCA, which is studied in this paper. We first propose an influence function-based estimator for the variance of the KCCU. We then present a non-parametric robust KCCU, which is designed for dealing with contaminated data. The robust KCCU is less sensitive to noise than KCCU. We investigate the proposed method using both synthesized and real data from the Mind Clinical Imaging Consortium (MCIC). We show through simulation studies that the power of the proposed methods is a monotonically increasing function of sample size, and the robust test statistics bring incremental gains in power. To demonstrate the advantage of the robust kernel CCA, we study MCIC data among 22,442 candidate Schizophrenia genes for gene-gene co-associations. We select 768 genes with strong evidence for shedding light on gene-gene interaction networks for Schizophrenia. By performing gene ontology enrichment analysis, pathway analysis, gene-gene network and other studies, the proposed robust methods can find undiscovered genes in addition to significant gene pairs, and demonstrate superior performance over several of current approaches.

Development of novel diagnostic system for pancreatic cancer, including early stages, measuring mRNA of whole blood cells.

Pancreatic ductal adenocarcinoma (PDAC) is the most life-threating disease among all digestive system malignancies. We developed a blood mRNA PDAC screening system using real-time detection PCR to detect the expression of 56 genes, to discriminate PDAC from noncancer subjects. We undertook a clinical study to assess the performance of the developed system. We collected whole blood RNA from 53 PDAC patients, 102 noncancer subjects, 22 patients with chronic pancreatitis, and 23 patients with intraductal papillary mucinous neoplasms in a per protocol analysis. The sensitivity of the system for PDAC diagnosis was 73.6% (95% confidence interval, 59.7%-84.7%). The specificity for noncancer volunteers, chronic pancreatitis, and patients with intraductal papillary mucinous neoplasms was 64.7% (54.6%-73.9%), 63.6% (40.7%-82.8%), and 47.8% (26.8%-69.4%), respectively. Importantly, the sensitivity of this system for both stage I and stage II PDAC was 78.6% (57.1%-100%), suggesting that detection of PDAC by the system is not dependent on the stage of PDAC. These results indicated that the screening system, relying on assessment of changes in mRNA expression in blood cells, is a viable alternative screening strategy for PDAC.

Quasi-linear score for capturing heterogeneous structure in biomarkers.

BACKGROUND: Linear scores are widely used to predict dichotomous outcomes in biomedical studies because of their learnability and understandability. Such approaches, however, cannot be used to elucidate biodiversity when there is heterogeneous structure in target population. RESULTS: Our study was focused on describing intrinsic heterogeneity in predictions. Because heterogeneity can be captured by a clustering method, integrating different information from different clusters should yield better predictions. Accordingly, we developed a quasi-linear score, which effectively combines the linear scores of clustered markers. We extended the linear score to the quasi-linear score by a generalized average form, the Kolmogorov-Nagumo average. We observed that two shrinkage methods worked well: ridge shrinkage for estimating the quasi-linear score, and lasso shrinkage for selecting markers within each cluster. Simulation studies and applications to real data show that the proposed method has good predictive performance compared with existing methods. CONCLUSIONS: Heterogeneous structure is captured by a clustering method. Quasi-linear scores combine such heterogeneity and have a better predictive ability compared with linear scores.

Reproducible detection of disease-associated markers from gene expression data.

BACKGROUND: Detection of disease-associated markers plays a crucial role in gene screening for biological studies. Two-sample test statistics, such as the t-statistic, are widely used to rank genes based on gene expression data. However, the resultant gene ranking is often not reproducible among different data sets. Such irreproducibility may be caused by disease heterogeneity. RESULTS: When we divided data into two subsets, we found that the signs of the two t-statistics were often reversed. Focusing on such instability, we proposed a sign-sum statistic that counts the signs of the t-statistics for all possible subsets. The proposed method excludes genes affected by heterogeneity, thereby improving the reproducibility of gene ranking. We compared the sign-sum statistic with the t-statistic by a theoretical evaluation of the upper confidence limit. Through simulations and applications to real data sets, we show that the sign-sum statistic exhibits superior performance. CONCLUSION: We derive the sign-sum statistic for getting a robust gene ranking. The sign-sum statistic gives more reproducible ranking than the t-statistic. Using simulated data sets we show that the sign-sum statistic excludes hetero-type genes well. Also for the real data sets, the sign-sum statistic performs well in a viewpoint of ranking reproducibility.

Preoperative predictive factors and further risk stratification of biochemical recurrence in clinically localized high-risk prostate cancer.

BACKGROUND: To identify preoperative predictive factors for biochemical recurrence (BCR) and to further stratify its risk in high-risk localized prostate cancer patients receiving radical prostatectomy (RP). METHODS: Subjects included 195 high-risk prostate cancer patients undergoing RP from 2000 to 2012. RP consisted of retropubic radical prostatectomy and robot-assisted radical prostatectomy, involving 84 cases and 111 cases, respectively. BCR was defined as a prostate serum antigen (PSA) level ≥0.2 ng/mL. BCR-free survival (BCRFS) was calculated using the Kaplan-Meier method. Preoperative predictors of BCR were assessed with Cox's proportional hazard regression analysis. RESULTS: Eighty-nine patients (45.6 %) experienced recurrence. BCRFS rates 3 and 5 years after RP were 58 and 50 %, respectively. Prostate volume, transition zone volume, and Gleason score were not significantly associated with BCR. Patients with higher preoperative PSA, PSA density (PSAD), PSA density of the transition zone, percentage of positive cores (PPC), and PPC from the dominant side showed significantly lower BCRFS. The PPC from the dominant side and PSAD were significant independent prognostic factors for BCR. Using these variables, the hazard ratio of BCR could be calculated and patients stratified into three risk groups. The 5-year BCRFS rates for Groups 1, 2, and 3 were 64.9 %, 48.1 %, and 21.3 %, respectively. CONCLUSIONS: Patients with high-risk localized prostate cancer as currently defined do not have uniformly poor prognosis after RP. PPC from the dominant side and PSAD are significant predictors of BCR. These factors can identify high-risk patients with very poor prognosis.

Generalized t-statistic for two-group classification.

In the classic discriminant model of two multivariate normal distributions with equal variance matrices, the linear discriminant function is optimal both in terms of the log likelihood ratio and in terms of maximizing the standardized difference (the t-statistic) between the means of the two distributions. In a typical case-control study, normality may be sensible for the control sample but heterogeneity and uncertainty in diagnosis may suggest that a more flexible model is needed for the cases. We generalize the t-statistic approach by finding the linear function which maximizes a standardized difference but with data from one of the groups (the cases) filtered by a possibly nonlinear function U. We study conditions for consistency of the method and find the function U which is optimal in the sense of asymptotic efficiency. Optimality may also extend to other measures of discriminatory efficiency such as the area under the receiver operating characteristic curve. The optimal function U depends on a scalar probability density function which can be estimated non-parametrically using a standard numerical algorithm. A lasso-like version for variable selection is implemented by adding L1-regularization to the generalized t-statistic. Two microarray data sets in the study of asthma and various cancers are used as motivating examples.

Individualized prostate-specific antigen threshold values to avoid overdiagnosis of prostate cancer and reduce unnecessary biopsy in elderly men.

OBJECTIVE: To individualize prostate-specific antigen threshold values to avoid overdiagnosis of prostate cancer and reduce unnecessary biopsy in elderly men. METHODS: A total of 406 men aged over 70 years old with prostate-specific antigen levels between 4.0 and 20.0 ng/ml, normal digital rectal examination results and diagnosed by transrectal needle biopsy were retrospectively analyzed. The patients were divided into a no/favorable-risk cancer group or an unfavorable-risk cancer group based on their Gleason score and the number of positive cores. Prostate-specific antigen levels, percent free prostate-specific antigen level, prostate transition zone volume and the number of previous biopsies were used to discriminate between the two groups. The optimal individualized prostate-specific antigen threshold values based on the other variables that gave a sensitivity of 95% for the detection of unfavorable-risk cancer were calculated using a boosting method for maximizing the area under the receiver operating characteristic curve. RESULTS: A total of 66 men had favorable-risk cancer, and 139 had unfavorable-risk cancer. The area under the receiver operating characteristic curve of the combination model determined by the boosting method for maximizing the area under the receiver operating characteristic curve was 0.852. The sensitivity and specificity of the threshold values for the detection of unfavorable-risk cancer were 95 and 36%, respectively. By using the threshold values, 100 (25%) of the subjects with no/favorable-risk cancer could have avoided undergoing biopsies, with a <5% risk of missing the detection of unfavorable-risk cancer. CONCLUSIONS: These individualized prostate-specific antigen threshold values may be useful for determining an indication of prostate biopsy for elderly men to avoid overdiagnosis of prostate cancer and reduce unnecessary biopsy.

Spontaneous clustering via minimum γ-divergence.

We propose a new method for clustering based on local minimization of the gamma-divergence, which we call spontaneous clustering. The greatest advantage of the proposed method is that it automatically detects the number of clusters that adequately reflect the data structure. In contrast, existing methods, such as K-means, fuzzy c-means, or model-based clustering need to prescribe the number of clusters. We detect all the local minimum points of the gamma-divergence, by which we define the cluster centers. A necessary and sufficient condition for the gamma-divergence to have local minimum points is also derived in a simple setting. Applications to simulated and real data are presented to compare the proposed method with existing ones.

Multiple suboptimal solutions for prediction rules in gene expression data.

This paper discusses mathematical and statistical aspects in analysis methods applied to microarray gene expressions. We focus on pattern recognition to extract informative features embedded in the data for prediction of phenotypes. It has been pointed out that there are severely difficult problems due to the unbalance in the number of observed genes compared with the number of observed subjects. We make a reanalysis of microarray gene expression published data to detect many other gene sets with almost the same performance. We conclude in the current stage that it is not possible to extract only informative genes with high performance in the all observed genes. We investigate the reason why this difficulty still exists even though there are actively proposed analysis methods and learning algorithms in statistical machine learning approaches. We focus on the mutual coherence or the absolute value of the Pearson correlations between two genes and describe the distributions of the correlation for the selected set of genes and the total set. We show that the problem of finding informative genes in high dimensional data is ill-posed and that the difficulty is closely related with the mutual coherence.

An extension of the receiver operating characteristic curve and AUC-optimal classification.

While most proposed methods for solving classification problems focus on minimization of the classification error rate, we are interested in the receiver operating characteristic (ROC) curve, which provides more information about classification performance than the error rate does. The area under the ROC curve (AUC) is a natural measure for overall assessment of a classifier based on the ROC curve. We discuss a class of concave functions for AUC maximization in which a boosting-type algorithm including RankBoost is considered, and the Bayesian risk consistency and the lower bound of the optimum function are discussed. A procedure derived by maximizing a specific optimum function has high robustness, based on gross error sensitivity. Additionally, we focus on the partial AUC, which is the partial area under the ROC curve. For example, in medical screening, a high true-positive rate to the fixed lower false-positive rate is preferable and thus the partial AUC corresponding to lower false-positive rates is much more important than the remaining AUC. We extend the class of concave optimum functions for partial AUC optimality with the boosting algorithm. We investigated the validity of the proposed method through several experiments with data sets in the UCI repository.