Towards a pervasive data mining engine: architecture overview

Current data mining engines are difficult to use, requiring optimizations by data mining experts in order to provide optimal results. To solve this problem a new concept was devised, by maintaining the functionality of current data mining tools and adding pervasive characteristics such as invisibility and ubiquity which focus on their users, providing better ease of use and usefulness, by providing autonomous and intelligent data mining processes. This article introduces an architecture to implement a data mining engine, composed by four major components: database; Middleware (control); Middleware (processing); and interface. These components are interlinked but provide independent scaling, allowing for a system that adapts to the user’s needs. A prototype has been developed in order to test the architecture. The results are very promising and showed their functionality and the need for further improvements.

Predicting triage waiting time in maternity emergency care by means of data mining

Healthcare organizations often benefit from information technologies as well as embedded decision support systems, which improve the quality of services and help preventing complications and adverse events. In Centro Materno Infantil do Norte (CMIN), the maternal and perinatal care unit of Centro Hospitalar of Oporto (CHP), an intelligent pre-triage system is implemented, aiming to prioritize patients in need of gynaecology and obstetrics care in two classes: urgent and consultation. The system is designed to evade emergency problems such as incorrect triage outcomes and extensive triage waiting times. The current study intends to improve the triage system, and therefore, optimize the patient workflow through the emergency room, by predicting the triage waiting time comprised between the patient triage and their medical admission. For this purpose, data mining (DM) techniques are induced in selected information provided by the information technologies implemented in CMIN. The DM models achieved accuracy values of approximately 94% with a five range target distribution, which not only allow obtaining confident prediction models, but also identify the variables that stand as direct inducers to the triage waiting times.

Predicting pre-triage waiting time in a maternity emergency room through data mining

An unsuitable patient flow as well as prolonged waiting lists in the emergency room of a maternity unit, regarding gynecology and obstetrics care, can affect the mother and child’s health, leading to adverse events and consequences regarding their safety and satisfaction. Predicting the patients’ waiting time in the emergency room is a means to avoid this problem. This study aims to predict the pre-triage waiting time in the emergency care of gynecology and obstetrics of Centro Materno Infantil do Norte (CMIN), the maternal and perinatal care unit of Centro Hospitalar of Oporto, situated in the north of Portugal. Data mining techniques were induced using information collected from the information systems and technologies available in CMIN. The models developed presented good results reaching accuracy and specificity values of approximately 74% and 94%, respectively. Additionally, the number of patients and triage professionals working in the emergency room, as well as some temporal variables were identified as direct enhancers to the pre-triage waiting time. The imp lementation of the attained knowledge in the decision support system and business intelligence platform, deployed in CMIN, leads to the optimization of the patient flow through the emergency room and improving the quality of services.

Real-Time decision support using data mining to predict blood pressure critical events in intensive medicine patients

Patient blood pressure is an important vital signal to the physicians take a decision and to better understand the patient condition. In Intensive Care Units is possible monitoring the blood pressure due the fact of the patient being in continuous monitoring through bedside monitors and the use of sensors. The intensivist only have access to vital signs values when they look to the monitor or consult the values hourly collected. Most important is the sequence of the values collected, i.e., a set of highest or lowest values can signify a critical event and bring future complications to a patient as is Hypotension or Hypertension. This complications can leverage a set of dangerous diseases and side-effects. The main goal of this work is to predict the probability of a patient has a blood pressure critical event in the next hours by combining a set of patient data collected in real-time and using Data Mining classification techniques. As output the models indicate the probability (%) of a patient has a Blood Pressure Critical Event in the next hour. The achieved results showed to be very promising, presenting sensitivity around of 95%.

Development of a semi-automatic self learning pattern recognition system for the control of electronic boards

This project was funded under the Applied Research Grants Scheme administered by Enterprise Ireland. The project was a partnership between Galway - Mayo Institute of Technology and an industrial company, Tyco/Mallinckrodt Galway. The project aimed to develop a semi - automatic, self - learning pattern recognition system capable of detecting defects on the printed circuits boards such as component vacancy, component misalignment, component orientation, component error, and component weld. The research was conducted in three directions: image acquisition, image filtering/recognition and software development. Image acquisition studied the process of forming and digitizing images and some fundamental aspects regarding the human visual perception. The importance of choosing the right camera and illumination system for a certain type of problem has been highlighted. Probably the most important step towards image recognition is image filtering, The filters are used to correct and enhance images in order to prepare them for recognition. Convolution, histogram equalisation, filters based on Boolean mathematics, noise reduction, edge detection, geometrical filters, cross-correlation filters and image compression are some examples of the filters that have been studied and successfully implemented in the software application. The software application developed during the research is customized in order to meet the requirements of the industrial partner. The application is able to analyze pictures, perform the filtering, build libraries, process images and generate log files. It incorporates most of the filters studied and together with the illumination system and the camera it provides a fully integrated framework able to analyze defects on printed circuit boards.

Forearm surface EMG signals recognition and muscoloskeletal system dynamics identification using intelligent computational methods

Biosignals processing, Biological Nonlinear and time-varying systems identification, Electomyograph signals recognition, Pattern classification, Fuzzy logic and neural networks methods

A Data mining approach to indirect inference

Consider a model with parameter phi, and an auxiliary model with parameter theta. Let phi be a randomly sampled from a given density over the known parameter space. Monte Carlo methods can be used to draw simulated data and compute the corresponding estimate of theta, say theta_tilde. A large set of tuples (phi, theta_tilde) can be generated in this manner. Nonparametric methods may be use to fit the function E(phi|theta_tilde=a), using these tuples. It is proposed to estimate phi using the fitted E(phi|theta_tilde=theta_hat), where theta_hat is the auxiliary estimate, using the real sample data. This is a consistent and asymptotically normally distributed estimator, under certain assumptions. Monte Carlo results for dynamic panel data and vector autoregressions show that this estimator can have very attractive small sample properties. Confidence intervals can be constructed using the quantiles of the phi for which theta_tilde is close to theta_hat. Such confidence intervals are found to have very accurate coverage.

Intracellular pattern-recognition receptors

The last ten years of research in the field of innate immunity have been incredibly fertile: the transmembrane Toll-like receptors (TLRs) were discovered as guardians protecting the host against microbial attacks and the emerging pathways characterized in detail. More recently, cytoplasmic sensors were identified, which are capable of detecting not only microbial, but also self molecules. Importantly, while such receptors trigger crucial host responses to microbial insult, over-activity of some of them has been linked to autoinflammatory disorders, hence demonstrating the importance of tightly regulating their actions over time and space. Here, we provide an overview of recent findings covering this area of innate and inflammatory responses that originate from the cytoplasm

Histology-driven data mining of lipid signatures from multiple imaging mass spectrometry analyses: application to human colorectal cancer liver metastasis biopsies.

Imaging mass spectrometry (IMS) represents an innovative tool in the cancer research pipeline, which is increasingly being used in clinical and pharmaceutical applications. The unique properties of the technique, especially the amount of data generated, make the handling of data from multiple IMS acquisitions challenging. This work presents a histology-driven IMS approach aiming to identify discriminant lipid signatures from the simultaneous mining of IMS data sets from multiple samples. The feasibility of the developed workflow is evaluated on a set of three human colorectal cancer liver metastasis (CRCLM) tissue sections. Lipid IMS on tissue sections was performed using MALDI-TOF/TOF MS in both negative and positive ionization modes after 1,5-diaminonaphthalene matrix deposition by sublimation. The combination of both positive and negative acquisition results was performed during data mining to simplify the process and interrogate a larger lipidome into a single analysis. To reduce the complexity of the IMS data sets, a sub data set was generated by randomly selecting a fixed number of spectra from a histologically defined region of interest, resulting in a 10-fold data reduction. Principal component analysis confirmed that the molecular selectivity of the regions of interest is maintained after data reduction. Partial least-squares and heat map analyses demonstrated a selective signature of the CRCLM, revealing lipids that are significantly up- and down-regulated in the tumor region. This comprehensive approach is thus of interest for defining disease signatures directly from IMS data sets by the use of combinatory data mining, opening novel routes of investigation for addressing the demands of the clinical setting.

Pattern recognition of sleep in rodents using piezoelectric signals generated by gross body movements.

Current research on sleep using experimental animals is limited by the expense and time-consuming nature of traditional EEG/EMG recordings. We present here an alternative, noninvasive approach utilizing piezoelectric films configured as highly sensitive motion detectors. These film strips attached to the floor of the rodent cage produce an electrical output in direct proportion to the distortion of the material. During sleep, movement associated with breathing is the predominant gross body movement and, thus, output from the piezoelectric transducer provided an accurate respiratory trace during sleep. During wake, respiratory movements are masked by other motor activities. An automatic pattern recognition system was developed to identify periods of sleep and wake using the piezoelectric generated signal. Due to the complex and highly variable waveforms that result from subtle postural adjustments in the animals, traditional signal analysis techniques were not sufficient for accurate classification of sleep versus wake. Therefore, a novel pattern recognition algorithm was developed that successfully distinguished sleep from wake in approximately 95% of all epochs. This algorithm may have general utility for a variety of signals in biomedical and engineering applications. This automated system for monitoring sleep is noninvasive, inexpensive, and may be useful for large-scale sleep studies including genetic approaches towards understanding sleep and sleep disorders, and the rapid screening of the efficacy of sleep or wake promoting drugs.

Inferences about the global scenario of human T-cell lymphotropic virus type 1 infection using data mining of viral sequences

Human T-cell lymphotropic virus type 1 (HTLV-1) is mainly associated with two diseases: tropical spastic paraparesis/HTLV-1-associated myelopathy (TSP/HAM) and adult T-cell leukaemia/lymphoma. This retrovirus infects five-10 million individuals throughout the world. Previously, we developed a database that annotates sequence data from GenBank and the present study aimed to describe the clinical, molecular and epidemiological scenarios of HTLV-1 infection through the stored sequences in this database. A total of 2,545 registered complete and partial sequences of HTLV-1 were collected and 1,967 (77.3%) of those sequences represented unique isolates. Among these isolates, 93% contained geographic origin information and only 39% were related to any clinical status. A total of 1,091 sequences contained information about the geographic origin and viral subtype and 93% of these sequences were identified as subtype “a”. Ethnicity data are very scarce. Regarding clinical status data, 29% of the sequences were generated from TSP/HAM and 67.8% from healthy carrier individuals. Although the data mining enabled some inferences about specific aspects of HTLV-1 infection to be made, due to the relative scarcity of data of available sequences, it was not possible to delineate a global scenario of HTLV-1 infection.

Early pattern recognition in severe perinatal asphyxia: a prospective MRI study.

On the basis of MRI examinations in 88 neonates and infants with perinatal asphyxia, we defined 6 different patterns on T2-weighted images: pattern A--scattered hyperintensity of both hemispheres of the telencephalon with blurred border zones between cortex and white matter, indicating diffuse brain injury; pattern B--parasagittal hyperintensity extending into the corona radiata, corresponding to the watershed zones; pattern C--hyper- and hypointense lesions in thalamus and basal ganglia, which relate to haemorrhagic necrosis or iron deposition in these areas; pattern D--periventricular hyperintensity, mainly along the lateral ventricles, i.e. periventricular leukomalacia (PVL), originating from the matrix zone; pattern E--small multifocal lesions varying from hyper--to hypointense, interpreted as necrosis and haemorrhage; pattern F--periventricular centrifugal hypointense stripes in the centrum semiovale and deep white matter of the frontal and occipital lobes. Contrast was effectively inverted on T1-weighted images. Patterns A, B and C were found in 17%, 25% and 37% of patients, and patterns D, E and F in 19%, 17% and 35%, respectively. In 49 patients a combination of patterns was observed, but 30% of the initial images were normal. At follow-up, persistent abnormalities were seen in all children with patterns A and D, but in only 52% of those with pattern C. Myelination was retarded most often in patients with diffuse brain injury and PVL (patterns A and D).

Nestmate recognition and the genetic relatedness of nests in the ant Formica pratensis

Genetic relatedness of the mound-building ant Formica pratensis was determined by means of microsatellite DNA polymorphism, and its impact on nestmate recognition was tested in a population in Southern Sweden (Oeland). Recognition between nests was measured by testing aggression levels between single pairs of workers. The genetic distances of nests (Nei's genetic distance) and the spatial distance of nests were correlated and both showed a strong relation to the aggression behavior. Multiple regression analysis revealed a stronger impact of genetic relatedness rather than spatial distances on aggression behavior. Neighbouring nests were more closely related than distant nests, which may reflect budding as a possible spreading mechanism. The genetic distance data showed that nestmate recognition was strongly genetically influenced in F. pratensis.

Promoter recognition and activation by the global response regulator CbrB in Pseudomonas aeruginosa.

In Pseudomonas aeruginosa, the CbrA/CbrB two-component system is instrumental in the maintenance of the carbon-nitrogen balance and for growth on carbon sources that are energetically less favorable than the preferred dicarboxylate substrates. The CbrA/CbrB system drives the expression of the small RNA CrcZ, which antagonizes the repressing effects of the catabolite repression control protein Crc, an RNA-binding protein. Dicarboxylates appear to cause carbon catabolite repression by inhibiting the activity of the CbrA/CbrB system, resulting in reduced crcZ expression. Here we have identified a conserved palindromic nucleotide sequence that is present in upstream activating sequences (UASs) of promoters under positive control by CbrB and σ(54) RNA polymerase, especially in the UAS of the crcZ promoter. Evidence for recognition of this palindromic sequence by CbrB was obtained in vivo from mutational analysis of the crcZ promoter and in vitro from electrophoretic mobility shift assays using crcZ promoter fragments and purified CbrB protein truncated at the N terminus. Integration host factor (IHF) was required for crcZ expression. CbrB also activated the lipA (lipase) promoter, albeit less effectively, apparently by interacting with a similar but less conserved palindromic sequence in the UAS of lipA. As expected, succinate caused CbrB-dependent catabolite repression of the lipA promoter. Based on these results and previously published data, a consensus CbrB recognition sequence is proposed. This sequence has similarity to the consensus NtrC recognition sequence, which is relevant for nitrogen control.