Metabolomic data are frequently acquired using chromatographically coupled mass spectrometry (MS) platforms. For such datasets, the first step in data analysis relies on feature detection, where a feature is defined by a mass and retention time. While a feature typically is derived from a single compound, a spectrum of mass signals is more a more-accurate representation of the mass spectrometric signal for a given metabolite. Here, we report a novel feature grouping method that operates in an unsupervised manner to group signals from MS data into spectra without relying on predictability of the in-source phenomenon. We additionally address a fundamental bottleneck in metabolomics, annotation of MS level signals, by incorporating indiscriminant MS/MS (idMS/MS) data implicitly: feature detection is performed on both MS and idMS/MS data, and feature-feature relationships are determined simultaneously from the MS and idMS/MS data. This approach facilitates identification of metabolites using in-source MS and/or idMS/MS spectra from a single experiment, reduces quantitative analytical variation compared to single-feature measures, and decreases false positive annotations of unpredictable phenomenon as novel compounds. This tool is released as a freely available R package, called RAMClustR, and is sufficiently versatile to group features from any chromatographic-spectrometric platform or feature-finding software.

This paper presents automatic detection and localization of myocardial infarction (MI) using K-nearest neighbor (KNN) classifier. Time domain features of each beat in the ECG signal such as T wave amplitude, Q wave and ST level deviation, which are indicative of MI, are extracted from 12 leads ECG. Detection of MI aims to classify normal subjects without myocardial infarction and subjects suffering from Myocardial Infarction. For further investigation, Localization of MI is done to specify the region of infarction of the heart. Total 20,160 ECG beats from PTB database available on Physio-bank is used to investigate the performance of extracted features with KNN classifier. In the case of MI detection, sensitivity and specificity of KNN is found to be 99.9% using half of the randomly selected beats as training set and rest of the beats for testing. Moreover, Arif-Fayyaz pruning algorithm is used to prune the data which will reduce the storage requirement and computational cost of search. After pruning, sensitivity and specificity are dropped to 97% and 99.6% respectively but training is reduced by 93%. Myocardial Infarction beats are divided into ten classes based on the location of the infarction along with one class of normal subjects. Sensitivity and Specificity of above 90% is achieved for all eleven classes with overall classification accuracy of 98.8%. Some of the ECG beats are misclassified but interestingly these are misclassified to those classes whose location of infarction is near to the true classes of the ECG beats. Pruning is done on the training set for eleven classes and training set is reduced by 70% and overall classification accuracy of 98.3% is achieved. The proposed method due to its simplicity and high accuracy over the PTB database can be very helpful in correct diagnosis of MI in a practical scenario.

In this paper, Pruned Fuzzy K-nearest neighbor (PFKNN) classifier is proposed to classify different types of Arrhythmia beats present in the MIT-BIH Arrhythmia database. We have tested our classifier on ~103100 beats for six beat types present in the database. Fuzzy KNN (FKNN) can be implemented very easily but large number of training examples used for classification which can be very time consuming and requires large storage space. Hence, we have proposed a time efficient pruning algorithm especially suitable for FKNN which can maintain good classification accuracy with appropriate retained ratio of training data. By using the pruning algorithm with Fuzzy KNN, we have achieved beat classification accuracy of 97% and geometric mean of sensitivity is 94.5% with only 19% of the total training examples. The accuracy and sensitivity is comparable to FKNN when all the training data is used.

In this paper, we describe a technique for automatic detection of ST segment deviations that can be used in the diagnosis of coronary heart disease (CHD) using ambulatory electrocardiogram (ECG) recordings. Preprocessing is carried out prior to the extraction of the ST segment which involves noise and artifact filtering using a digital bandpass filter, baseline removal and application of a discrete wavelet transform (DWT) based technique for detection and delineation of the QRS complex in ECG. Lead-dependent Karhunen-Loève transform (KLT) bases are used for dimensionality reduction of the ST segment data. ST deviation episodes are detected by a classifier ensemble comprising backpropagation neural networks. Results obtained through the use of our proposed method (sensitivity/positive predictive value = 90.75%/89.2%) compare well with those given in the existing research. Hence, the proposed method exhibits the potential to be adopted in the design of a practical ischemia detection system.