In this modern society, with its multitude of stressors that people encounter on a daily basis, a characteristic of mental disorders is that there is a risk of developing them at the unconscious level, and even if the patient were to detect the condition, they are difficult to treat. Furthermore, while there are tests that evaluate the level of stress, these tests still have many elements. Therefore, it is extremely important to be able to objectively assess ones stress levels, as well as to raise awareness of and pay attention to internal signals in order to control the level of risk, to create a mechanism which provides medical help. Thus, this study aims to visualize the internal signals through the heart rate which is affected by stress, develop a system to provide assistance in returning stress to normal levels, and assisting in helping patients manage their own risk levels.
In this chapter, different methods and applications of biclustering algorithms to DNA microarray data analysis that have been developed in recent years are discussed and compared. Identification of biological significant clusters of genes from microarray experimental data is a very daunting task that emerged, especially with the development of high throughput technologies. Various computational and evaluation methods based on diverse principles were introduced to identify new similarities among genes. Mathematical aspects of the models are highlighted, and applications to solve biological problems are discussed.
Decision support systems represent an important tool offering assistance with the decision making process in a variety of applications. This paper starts with recalling the basic principles and structure of decision support systems in medicine from a general perspective. Their effect in terms of both potential and limitations for finding the diagnosis, prognosis and therapy are overviewed from the points of view of health care effectiveness and patient safety. The authors are particularly interested in the specialty field of psychiatry. They discuss its specific challenges and analyze the slower penetration of telemedicine tools to psychiatry compared to other clinical fields. Finally, they claim that the development of decision support systems play a key role in the development of the concept of information-based medicine in general as well as to the particular context of information-based psychiatry.
Telemedicine is a particularly useful means to optimize the quality of care by fast medical exchanges that benefit patients whose state of health requires an appropriate and fast response, regardless of their geographic location. In this paper, the authors propose a mobile agent based architecture (DiabMAS) for remote medical monitoring of diabetic patients on an outpatient basis using mobile devices (laptops, PDAs, etc ...) by exploring the new operating Mobile system, Android. DiabMAS is a multi-agent system having as main objective the improvement of the transmission of information between patients and their physicians, especially the management of specific and critical cases.
The current study examines algorithmic approaches for analysis of multimodal attributes in localization-related epilepsy (LRE), specifically, their impact on the selection of patients for surgical consideration. Invasive electrographic data is excluded here to concentrate upon the localized anatomical landmarks and identified/initialized brain structures in volumetric MR images as well as initial clinical presentation and the varied elements of the seizure history, ictal semiology, risk and seizure-precipitating factors and physical findings in addition to several features of the neuropsychological profile including various parameters of cognition and both speech and memory lateralization. First, the imaging modality data is excluded and just clinical, electrographic and neuropsychological data are investigated. Afterward, the imaging data are investigated and a comparison between the prediction results of the two types of data is done. In the case of using non-imaging multimodal data, 56% and using imaging features, about 71% of correct outcome prediction was obtained.
As healthcare costs rise, hospitals are seeking ways to improve operations. This paper examines the usefulness of free-form notes to solve a classification problem commonly associated with customer churn. The authors show that classifiers which incorporate free-form notes, using natural language processing techniques, are up to 9% more accurate than classifiers that are solely developed using structured data. The authors suggest that hospitals and chronic disease management clinics can use structured data and free-form notes from electronic health records to predict which patients are likely to cease receiving care from their facilities. Classification tools for predicting patient churn are of interest to hospital administrators; such information can aid in resource planning and facilitate smoother handoffs between care providers.
For the past three decades rationale drug design (RDD) has been developing as an innovative, rapid and successful way to discover new drug candidates. Many strategies have been followed and several targets with diverse structures and different biological roles have been investigated. Despite the variety of computational tools available, one can broadly divide them into two major classes that can be adopted either separately or in combination. The first class involves structure-based drug design, when the target's 3-dimensional structure is available or it can be computationally generated using homology modeling. On the other hand, when only a set of active molecules is available, and the structure of the target is unknown, ligand-based drug design tools are usually used. This review describes some recent advances in rational drug design, summarizes a number of their practical applications, and discusses both the advantages and shortcomings of the various techniques used.
The challenges of implementing electronic health records (EHRs) have received some attention, but little is known about the process of transitioning from paper-based to electronic files. In this paper, a mixed approach using combined qualitative and quantitative methods is utilized. The authors enrolled nine administrative managers and 87 employees from different backgrounds, all part of a regional hospital at Flacq in Mauritius, from April to May 2011. Employees responded to a survey on various aspects pertaining to their eagerness to accept the shift to electronic health records and their views on the probability of success. Descriptive and inferential statistics were used to analyze the quantitative results and content analysis was performed on the qualitative data. Nurses performing at middle level agreed that a shift to EHR is positive but felt that it might take a long time to effect the change. With its implementation, they agreed that advantages like up to date information, diminished workload, and cost effectiveness would be easily attained. In contrast, focus groups confirmed that without the collaboration and support of management, implementation of EHR would prove arduous.
Common diseases or traits in humans are often influenced by complex interactions among multiple genes as well as environmental and lifestyle factors rather than being attributable to a genetic variation within a single gene. Identification of genes that confer disease susceptibility can be facilitated by studying DNA markers such as single nucleotide polymorphism (SNP) associated with a disease trait. Genome-wide association approaches offers a systematic analysis of the association of hundreds of thousands of SNPs with a quantitative complex trait. This method has been successfully applied to a wide variety of common human diseases and traits, and has generated valuable findings that have improved the understanding of the genetic basis of many complex traits. This chapter outlines the general mapping process and methods, highlights the success stories, and describes some limitations and challenges that lie ahead.
In neuroscience, collaboration and data sharing are undermined by concerns over the management of protected health information (PHI) and personal identifying information (PII) in neuroimage datasets. The HIPAA Privacy Rule mandates measures for the preservation of subject privacy in neuroimaging studies. Unfortunately for the researcher, the management of information privacy is a burdensome task. Wide scale data sharing of neuroimages is challenging for three primary reasons: (i) A dearth of tools to systematically expunge PHI/PII from neuroimage data sets, (ii) a facility for tracking patient identities in redacted datasets has not been produced, and (iii) a sanitization workflow remains conspicuously absent. This article describes the XNAT Redaction Toolkit-an integrated redaction workflow which extends a popular neuroimage data management toolkit to remove PHI/PII from neuroimages. Quickshear defacing is also presented as a complementary technique for deidentifying the image data itself. Together, these tools improve subject privacy through systematic removal of PII/PHI.
A central building block of data privacy is the individual right of information self-determination. Following from that when dealing with shared electronic health records (SEHR), citizens, as the identified individuals of such records, have to be enabled to decide what medical data can be used in which way by medical professionals. In this context individual preferences of privacy have to be reflected by authorization policies to control access to personal health data. There are two potential challenges when enabling patient-controlled access control policy authoring: First, an ordinary citizen neither can be considered a security expert, nor does she or he have the expertise to fully understand typical activities and workflows within the health-care domain. Thus, a citizen is not necessarily aware of implications her or his access control settings have with regards to the protection of personal health data. Both privacy of citizen’s health-data and the overall effectiveness of a health-care information system are at risk if inadequate access control settings are in place. This paper refers to scenarios of a case study previously conducted and shows how privacy and information system effectiveness can be defined and evaluated in the context of SEHR. The paper describes an access control policy analysis method which evaluates a patient-administered access control policy by considering the mentioned evaluation criteria.
Clinical communication failures are considered the leading cause of medical errors (Bates et al., 1997). The complexity of the clinical culture and the significant variance in training and education levels form a challenge to enhancing communication within the clinical team. In order to improve communication, a comprehensive understanding of the overall communication process in health care is required. In an attempt to further understand clinical communication, the authors conducted a thorough methodology literature review to identify strengths and limitations of previous approaches. Their research proposes a new data collection method to study the clinical communication activities among Intensive Care Unit (ICU) clinical teams with a primary focus on the attending physician. In this paper, the authors present the first ICU communication instrument, they introduce the use of database management system to aid in discovering patterns and associations within our ICU communications data repository, and they present the authors’ Human-Computer Interaction observational study results. The authors have identified and analyzed key Human-Interaction behaviors and tools in the ICU in addition to refining the clinical communication model they previously proposed (Khairat & Gong, 2010b). their goal is to build an exhaustive knowledge representation of the clinical communication process through utilizing an ontological approach.
There is growing interest in the discovery of clinically useful, robust biomarkers for Alzheimer’s disease (AD) and pre-AD; the ability to accurately diagnose AD or to predict conversion from a preclinical state to AD would aid in both prevention and early intervention. This study aimed to evaluate the usefulness of a statistical assessment of cortical activity using electroencephalograms (EEGs) with normative data and the ability of such an assessment to contribute to the diagnosis of AD. 15 patients with AD and 8 patients with mild cognitive impairment (MCI) were studied. Eyes-closed resting EEGs were digitally recorded at 200 Hz from 20 electrodes placed according to the international 10/20 system on the scalp, and 20 artifact-free EEG epochs lasting 2.56 ms were selected. Each EEG epoch was down-sampled to 100 Hz and matched to the normal data sets. The selected EEGs from each subject were analyzed by standardized Low Resolution Electromagnetic Tomography (sLORETA) and statistically compared with the age-matched normal data sets at all frequencies. This procedure resulted in cortical z values for each EEG frequency with 0.39 Hz frequency resolution for each subject. Some of the AD and MCI patients presented a peak of negative z value around 20 Hz, revealing hypoactivity of the parahippocampal gyrus and the insula in the sLORETA cortical image. In addition, severe cases of AD showed decreased parietal activation. These results were in agreement with evidence from statistical neuroimaging using MRI/SPECT. Submission of normal EEG data sets to sLORETA might be useful for the detection of diagnostic and predictive markers of AD and MCI in individual patients.
Biomedical signals which help monitor patients’ physical conditions are a crucial part of the healthcare industry. The healthcare professionals’ ability to monitor patients and detect early signs of conditions such as blocked arteries and abnormal heart rhythms can be accomplished by performing data clustering on biomedical signals. More importantly, clustering on streams of biomedical signals make it possible to look for patterns that may indicate developing conditions. While there are a number of clustering algorithms that perform data streams clustering by example, few algorithms exist that perform clustering by variable. This paper presents POD-Clus, a clustering method which uses a model-based clustering principle and, in addition to clustering by example, also cluster data streams by variable. The clustering result from POD-Clus was superior to the result from ODAC, a baseline algorithm, for both with and without cluster evolutions.
The upward trend in breast cancer globally and in India has become a matter of great concern. Breast cancer is the most common malignancy among women globally. The objective of the authors’ study was to explore the various risk factors of breast cancer in among women in an Indian context. A search was performed using the search engine Pubmed during years 2005-2011 using key words risk factor and breast cancer and India. They searched criteria found 16 final analyzable articles. Results of the review showed high mortality due to late stage breast cancer diagnosis as women usually present at an advanced stage. The results showed that the predominant reason was because of lack of awareness about the risk factors of breast cancer and non-existence of breast cancer screening programs. Financial and social reasons were other factors that resulted in delay in seeking advice for this problem resulting in its delayed diagnosis. Educational awareness might be an effective tool for modifying lifestyles and thereby reducing breast cancer risks.
There are two major parallel pathways in humans: the parvocellular (P) and magnocellular (M) pathways. The former has excellent spatial resolution with color selectivity, while the latter shows excellent temporal resolution with high contrast sensitivity. Visual stimuli should be tailored to answer specific clinical and/or research questions. This chapter examines the neural mechanisms of face perception using event-related potentials (ERPs). Face stimuli of different spatial frequencies were used to investigate how low-spatial-frequency (LSF) and high-spatial-frequency (HSF) components of the face contribute to the identification and recognition of the face and facial expressions. The P100 component in the occipital area (Oz), the N170 in the posterior temporal region (T5/T6) and late components peaking at 270-390 ms (T5/T6) were analyzed. LSF enhanced P100, while N170 was augmented by HSF irrespective of facial expressions. This suggested that LSF is important for global processing of facial expressions, whereas HSF handles featural processing. There were significant amplitude differences between positive and negative LSF facial expressions in the early time windows of 270-310 ms. Subsequently, the amplitudes among negative HSF facial expressions differed significantly in the later time windows of 330–390 ms. Discrimination between positive and negative facial expressions precedes discrimination among different negative expressions in a sequential manner based on parallel visual channels. Interestingly, patients with schizophrenia showed decreased spatial frequency sensitivities for face processing. Taken together, the spatially filtered face images are useful for exploring face perception and recognition.
In the development of drugs intended for oral use, good drug absorption and appropriate drug delivery are very important. Now the predictions for drug absorption and oral bioavailability follow similar approach: calculate molecular descriptors for molecules and build the prediction models. This approach works well for the prediction of compounds which cross a cell membrane from a region of high concentration to one of low concentration, but it does not work very well for the prediction of oral bioavailability, which represents the percentage of an oral dose which is able to produce a pharmacological activity. The models for bioavailability had limited predictability because there are a variety of pharmacokinetic factors influencing human oral bioavailability. Recent study has shown that good quantitative relationship could be obtained for subsets of drugs, such as those that have similar structure or the same pharmacological activity, or those that exhibit similar absorption and metabolism mechanisms. In this work, using MLR (Multiple Linear Regression) and SVM (Support Vector Machine), quantitative bioavailability prediction models were built for four kinds of drugs, which are Angiotensin Converting Enzyme Inhibitors or Angiotensin II Receptor Antagonists, Calcium Channel Blockers, Sodium and Potassium Channels Blockers and Quinolone Antimicrobial Agents. Explorations into subsets of compounds were performed and reliable prediction models were built for these four kinds of drugs. This work represents an exploration in predicting human oral bioavailability and could be used in other dataset of compounds with the same pharmacological activity.
Incremental document clustering is important in many applications, but particularly so in healthcare contexts where text data is found in abundance, ranging from published research in journals to day-to-day healthcare data such as discharge summaries and nursing notes. In such dynamic environments new documents are constantly added to the set of documents that have been used in the initial cluster formation. Hence it is important to be able to incrementally update the clusters at a low computational cost as new documents are added. In this paper the authors describe a novel, low cost approach for incremental document clustering. Their method is based on conducting singular value decomposition (SVD) incrementally. They dynamically fold in new documents into the existing term-document space and dynamically assign these new documents into pre-defined clusters based on intra-cluster similarity. This saves the cost of re-computing SVD on the entire document set every time updates occur. The authors also provide a way to retrieve documents based on different window sizes with high scalability and good clustering accuracy. They have tested their proposed method experimentally with 960 medical abstracts retrieved from the PubMed medical library. The authors’ incremental method is compared with the default situation where complete re-computation of SVD is done when new documents are added to the initial set of documents. The results show minor decreases in the quality of the cluster formation but much larger gains in computational throughput.
Amplitude equation may be used to study pattern formatio. In this chapter, we establish a new mechanical algorithm AE_Hopf for calculating the amplitude equation near Hopf bifurcation based on the method of normal form approach in Maple. The normal form approach needs a large number of variables and intricate calculations. As a result, deriving the amplitude equation from diffusion-reaction is a difficult task. Making use of our mechanical algorithm, we derived the amplitude equations from several biology and physics models. The results indicate that the algorithm is easy to apply and effective. This algorithm may be useful for learning the dynamics of pattern formation of reaction-diffusion systems in future studies.
In the development of the nervous system, the migration of neurons driven by chemotactic cues has been known since a long time to play a key role. In this mechanism, the axonal projections of neurons detect very small differences in extracellular ligand concentration across the tiny section of their distal part, the growth cone. The internal transduction of the signal performed by the growth cone leads to cytoskeleton rearrangement and biased cell motility. A mathematical model of neuron migration provides hints of the nature of this process, which is only partially known to biologists and is characterized by a complex coupling of microscopic and macroscopic phenomena. This chapter focuses on the tight connection between growth cone directional sensing as the result of the information collected by several transmembrane receptors, a microscopic phenomenon, and its motility, a macroscopic outcome. The biophysical hypothesis investigated is the role played by the biased re-localization of ligand-bound receptors on the membrane, actively convected by growing microtubules. The results of the numerical simulations quantify the positive feedback exerted by the receptor redistribution, assessing its importance in the neural guidance mechanism.
