Application of Machine Learning Techniques in the HELIAD Study Data for the Development of Diagnostic Models in MCI and Dementia.

The increase in the population's life expectancy leads to an increase in the incidence of dementia and, therefore, in diseases such as Alzheimer's. Towards this direction, the HELIAD1 study is the first large-scale epidemiological study aimed at assessing epidemiological data on dementia, mild mental decline, and other neuropsychiatric disorders associated with old age. This is a huge study with several computational challenges, most of which can be addressed by machine learning processes. The objectives of this study were to detect patterns in the HELIAD clinical data that classify with high accuracy various levels of cognitive impairment by training ML algorithms and hence apply derived model on future clinical data to predict with the same accuracy the class variable. We propose a machine learning method based on RUSBoost classifier to identify a critical subset of biomarkers that classify accurately between neurological patients with mild cognitive impairment (MCI) or dementia of the Alzheimer's type (DAT) and the cognitively healthy control (CHC) group. In this study we used a highly skewed (imbalanced) dataset with most observations (majority class) belonging to the CHC group. The method proposed predicts accurately the clinical diagnosis label and effectively classifies the neurological patients from the CHC class. In particular, the classification accuracy (actual vs predicted) for the three classes of the clinical diagnosis was 97%, 78%, and 91% for control, MCI, and dementia class, respectively.

Hysteroscopy in women with abnormal uterine bleeding: a meta-analysis on four major endometrial pathologies.

PURPOSE: To determine the accuracy of hysteroscopy in diagnosing endometrial cancer, hyperplasia, polyps and submucous myomas. METHODS: Relevant articles were retrieved from the MEDLINE and the Cochrane Library (1986-2011). Studies were selected blindly. Results for diagnostic accuracy were extracted to form separate 2 × 2 tables (for endometrial cancer, hyperplasia, polyps and submucous myomas). A summary sensitivity and specificity point reflected the average accuracy observed. Summary ROCs (SROCs) were also calculated according to the HSROC model. RESULTS: For endometrial cancer, the estimated sensitivity was 82.6% (95% CR 66.9-91.8%) and the specificity was 99.7% (95% CR 98.1-99.9%). For endometrial hyperplasia, sensitivity was 75.2% (95% CR 55.4-88.1 %), while specificity was 91.5% (95% CR 85.7-95.0%). For endometrial polyps, sensitivity was 95.4% (95% CR 87.4-98.4%) and specificity was 96.4% (95% CR 93.7-98.0%). Finally, for submucous myomas, sensitivity was estimated to 97.0% (95% CR 89.8-99.2%) and specificity to 98.9% (95% CR 93.3-99.8%). CONCLUSIONS: Diagnostic accuracy for hysteroscopy is high for endometrial cancer, polyps and submucous myomas, but only moderate for endometrial hyperplasia.

Comparative study between aquatic therapy and land-based exercises in hemiplegic patients after stroke: a randomized controlled trial.

OBJECTIVE: This study aimed to assess the effects of aquatic therapy in individuals with hemiplegia compared to those of a conventional land-based exercise program. DESIGN: This was a blinded, randomized controlled study of chronic stroke patients with hemiplegia. The participants were randomized in to aquatic therapy (experimental) or conventional therapy (control) groups. The aquatic therapy group conducted the exercise program in a swimming pool, and the conventional therapy group performed to an exercise on the land environment three times per week for six weeks. Both interventions focused on posture, balance, and weight-bearing exercises. Outcomes included the Berg Balance Scale, Brunnstrom scale, Motricity Index, muscle strength tests, Modified Ashworth Scale, Postural Assessment Scale for Stroke, Trunk Control Test and Functional Independence Measure. Also, postural sway was evaluated by using the variables of center of pressure displacements in the mediolateral and anteroposterior directions. RESULTS: The findings of the present study show that the experimental group (26 patients) exhibited significant improvements in spasticity compared to the control group (25 patients) (p = 0.01). The conventional therapy group also achieved significant improvements (p < 0.05) in anteroposterior deviation, mediolateral velocity, and total velocity of center of pressure in a sitting position with eyes closed. CONCLUSION: Land-based exercises were more beneficial in the spasticity of chronic stroke patients.

Circulating matrix metalloproteinase 3 due to myocardial ischemia.

BACKGROUND: Experimental data suggest that matrix metalloproteinases (MMPs) such as MMP-3 have a central role in the remodeling period after a myocardial infarction (MI). The aim of this study was to use an experimental small-animal model to investigate the fluctuation in MMP-3 levels occurring in vivo after an acute MI. METHODS: We studied 13 New Zealand white rabbits weighing between 3 and 4 kg. After anesthetizing the animals, we performed a tracheotomy and induced an acute MI in 10 of the animals by occluding the left anterior descending coronary artery for 45 minutes. The remaining 3 rabbits constituted the control group. Three hours after reperfusion, blood samples were taken for biomedical analyses. RESULTS: Three hours after the artificially induced acute MI, serum MMP-3 levels were decreased by almost 50%. Cardiac troponin I (cTnI) concentrations were increased greatly (90-fold) after MI, further validating the efficiency of our experimental in vivo model of acute MI. CONCLUSION: Combining the data, we demonstrated that acute MI caused an early reduction in MMP-3 levels. The range of MMP-3 reduction is limited compared with other factors predicting MI, such as cTnI, which increases its usefulness. We demonstrated, however, that plasma fluctuation in MMP-3 levels could be used as a supplementary independent predictor of cardiovascular events in patients with stable coronary artery disease. This acute MI model used in our controlled setting proved to be a reliable and safe method for conducting in vivo studies.

Wavelet analysis for detection of phasic electromyographic activity in sleep: influence of mother wavelet and dimensionality reduction.

Phasic electromyographic (EMG) activity during sleep is characterized by brief muscle twitches (duration 100-500ms, amplitude four times background activity). High rates of such activity may have clinical relevance. This paper presents wavelet (WT) analyses to detect phasic EMG, examining both Symlet and Daubechies approaches. Feature extraction included 1s epoch processing with 24 WT-based features and dimensionality reduction involved comparing two techniques: principal component analysis and a feature/variable selection algorithm. Classification was conducted using a linear classifier. Valid automated detection was obtained in comparison to expert human judgment with high (>90%) classification performance for 11/12 datasets.

Is there any difference in carotid stenosis between male and female patients undergoing coronary artery bypass grafting?

Cardiovascular diseases are among the leading causes of death in women. Significant gender differences have been reported among patients with symptomatic carotid artery disease. The aim of this study is to examine if the female sex is a predisposing factor for carotid stenosis in coronary artery bypass grafting (CABG) patients. We studied 965 CABG patients, 796 males and 169 females. We combined the gender with risk factors predicting carotid disease as a history of cerebrovascular accident (CVA), peripheral vascular disease (PVD), left main (LM) disease and advanced age. We compared the incidence of carotid disease for each gender against known risk factors, which are history of CVA, PVD, LM and advanced age. In our study, there was not a statistically significant difference for the presence of carotid disease between males and females undergoing CABG. However, patients with a history of CVA, with PVD and older age were at greater risk for carotid stenosis. We conclude that the female sex is not a predictive factor for carotid stenosis in CABG patients.