The virtual physical examination (VPE) platform is a web–based, multimedia system for medical examination education, distributed and supported by Cerner. The system was built using MySQL, Flash and PHP and developed for creating and conducting physical examinations on virtual patient cases in a simulated environment. VPE allows users to perform physical examinations virtually on patients. A user can create 3D avatars of patients, build medical cases, perform diagnosis and attach associated files including audio, video, image, text and interactive assets. VPE allows for controlled sharing of assets as well as full cases, either within the same organisation or publicly. A video demonstrating VPE can be found at http://digbio.missouri.edu/Cerner/Cerner_VPE_Demo.mp4. VPE has broad educational applications ranging from the basic introduction of medicine to high school students to advanced education for nursing and medical students. The solution is used to both teach and reinforce physical exam concepts. VPE is available at https://vpe.cernerlearningmanager.com.
The use of mobile healthcare systems is an option to provide health–monitoring services without restrictions of time and location. Rather than just storing and transmitting health signals, the current stage of the mobile technology enables the development of intelligent modules, so that mobile devices can carry out an initial analysis of the collected data, taking important decisions and acting as a personal health assistant. This work summarises the current state of the art in healthcare monitoring and proposes an extension of this technology via the use of a rule–based module for deduction. The principal advantage of this approach is the easy way to codify the knowledge of domain experts via logic sentences. As example, we discuss a cardiovascular monitoring system that was developed to run in mobile phones.
Reactive motifs are short conserved sub–sequences discovered from functional sites of enzyme sequences, and can be used as an effective representation of enzyme sequences. However, the lack of site information leads to low–coverage reactive motifs. With the use of background knowledge, a motif generalisation method is required to increase reactive motifs' coverage. We show that a fuzzy concept lattice (FCL) provides an efficient representation of both single–value and multi–value biological background knowledge and an efficient computational support for generalising reactive motifs. Compared to statistical and expert–based motifs, we show that the generalised reactive motifs using FCL with SVM classifier produce satisfactory accuracy in classifying new enzymes. Further, they improve interpretability of the classification results and provide more biological evidences to biologists. All of the generalised reactive motifs are relevant to the functional sites, and the way they are combined to perform protein function is useful for numerous applications in bioinformatics.
Studying haplotypes is an important approach for investigation of genetic variations in the human genome because they contain a lot of information related to these types of variations. The haplotype assembly problem is to reconstruct two haplotypes for an individual using a set of aligned single nucleotide polymorphism (SNP) fragments from the two haplotypes (related to a particular chromosome). This problem is recognised as an NP–hard problem due to possible sequencing errors. Therefore, in practice, heuristic algorithms are used for finding satisfactory solutions to this problem. In this paper, an optimised reimplementation of HapSAT algorithm has been used to find haplotypes for HuRef dataset. Finding more accurate haplotypes based on this dataset is of considerable importance, because HuRef haplotypes are widely used in some researches (in biology, medicine, and pharmacy). Since the HapSAT algorithm provides significantly superior results compared to previously proposed algorithms, assembled haplotypes using HapSAT algorithm will be very useful for future researches.
In the development of new drugs and improved treatment of diseases, it is essential to understand molecular networks in living organism. Especially, it is important to identify interacting domains among proteins to elucidate hidden functions for protein–protein interactions (PPIs). To date, a number of computational methods have been developed for predicting domain–domain interactions (DDIs) from known PPIs. However, they often contain a large number of false positives while the number of known structures of protein complexes is limited. In this study, we aim to develop a new method of predicting DDIs by a link prediction approach. By using a learning model including low rank matrices as latent features in combination with biological features and topological features of the domain network, the experimental results showed that our method achieved a good performance and the predicted DDIs have high fraction sharing rate with the ones known as true in gold–standard databases.
Recent developments in whole–genome sequencing technology have introduced to us, completely determined genome sequences of many individuals, called 'personal genomes'. As personal genome sequencing is being commoditised, the necessity to discover sequence dissimilarities is increasing, to facilitate clinical diagnostic studies. For this we need to have the knowledge of regions containing duplications, rearrangements and large scale gain and loss of sequences. Apart from that storage and retrieval of such a varied dataset and the basic analysis of genomic sequence is very important, to interpret the complex personal genomes. Thus, acquaintance with computational techniques that aid in easy and fast analysis of whole genome sequences is quite essential. Hereby we are discussing some of the tools that are being successfully used for gene prediction, sequencing, gene annotation, genome comparisons along with some ELSIs associated with such studies. Such modernised tools and methods can deduce the molecular make–up of each individual for the conception of personalised medicine.
The unity of body and mind is an important concept in Chinese philosophy. Traditionally, the concept is informal and fuzzy, with no well defined meaning in the mathematical sense. This paper proposes a formal information–theoretical model for neural signal processing, arguing that physical principles are neural phenomena. For example, using the proposed model, the paper shows that time–dilation in Einstein's theory of relativity and Heisenberg's uncertainty principle can both be observed in neural signal processing. The paper therefore proposes a new concept, the neurological principle, which subsumes different natural principles. In particular, the paper shows that Yin and Yang, the two forces that according to Chinese philosophy pervade the universe and every entity therein, can be explained with the proposed model. These results provide Chinese medicine with a stronger mathematical foundation.
IgA nephropathy (IgAN) with the sore throat is common in clinical practice. It has been confirmed that a sore throat is closely related to the process of IgAN generation and development. Both doctors and patients are bothered with this disease. The application of the modern medicine in this field is limited because of antibiosis abuse and adverse effects. Traditional Chinese medicine (TCM) provides another method to treat it. In TCM theory, according to the syndrome differentiation, the two common syndromes of IgAN with sore throat are hot junction in the throat and hyperactivity of hypopyrexia. The therapy of dispersing wind to ease heat, detoxicating heat and cooling blood to stop bleeding and nourishing renal yin to lessen fire, based on the syndrome differentiation, has attained a good clinical outcome in clinical practice.
Biopsychosocial approaches are the mainstay diagnostic methods for subhealth. This paper introduces the AdaBoost Learner to handle this issue. AdaBoost algorithm combine a series of weak classifiers, each of which performs slightly better than random guessing, to a strong one. In this paper, the AdaBoost Learners with discriminant classifiers and decision trees are built and two strong classifiers, support vector machine (SVM) and k–nearest neighbour (kNN), are adopted as control experiments. Two classification processes are constructed to distinguish health states and subhealth types respectively, where Fisher Score feature selection is for comparing performance with different feature subsets. Results indicate that the AdaBoost Learner with decision trees is the best among four classifiers in health states classification while the one with discriminant classifiers has the greatest performance in subhealth types classification. In health states classification, the highest accuracy reached 85.76% with 320 questions and 87.58% with 120 questions in subhealth types classification.
In recent years, reports on the effects of nursing intervention on the incidence of peritoneal dialysis complicated with peritonitis have been increasing. With the advancement of medical technology and the development of medical materials, complications of peritoneal dialysis show a decreasing trend. Many experts and scholars have been continually exploring the causa morbid of peritoneal dialysis and excogitating measures that should be taken. In this paper a comprehensive review is done.
During the traditional Chinese medicine (TCM) treatment procedure, the manifestations of patients could be observed but the health state and TCM diagnosis of patient are uncertain. Thus, the real–world TCM therapy planning is a typical kind of dynamic decision making under uncertainty. Partially observable Markov decision process (POMDP) constitutes a powerful mathematical model for planning and is suitable for TCM therapy planning. In this paper, we apply POMDP to solve TCM therapy planning problem with all the dynamics inferred from TCM clinical data for type 2 diabetes treatment. This POMDP model contains 55 health states, 67 observation variables and 414 actions, it could order prescriptions for patients with type 2 diabetes. The results demonstrate that the POMDP model for TCM therapy planning is reasonable and helpful in clinical practice.
This paper presents a computational system to predict protein structure using N–grams and a wrapper feature selection framework (the N–gram is a subsequence composed of N characters, extracted from a larger sequence). N–gram features are extracted from a dataset consisting of 277 domains: 70 all–α domains, 61 all–β domains, 81 α/β domains and 65 α + β domains. A wrapper feature selection system, GA–SVM, is applied to obtain an optimised feature set. Using the optimised 3070–feature subset, a classifier model is trained and tested in the Support Vector Machine (SVM) learning system. This model achieves an overall accuracy of 88.09%, evaluated by a 10–fold cross–validation test. This value is 4.7% higher than the one using the initial 6,414 features. Experimental results also illustrate that employing a feature subset selection, by using the proposed GA–SVM wrapper approach, has enhanced classification accuracy in comparison to other GA–based wrapper approaches and existing protein sequence encoding methods.
Representatives from a consortium of academic institutions, healthcare organisations, and commercial entities have collaborated to implement and evaluate a multi–layered representation framework targeted to promote the sharing and distribution of clinical practice guideline knowledge artefacts. Definition of a metadata model for knowledge artefacts submitted to a shared repository based on this framework proceeded through an iterative process that sought to strike a balance between the need to provide enough specification to allow for efficient indexing and retrieval and recognition of the potential burden imposed by excessive requirements.
Temporal clustering of time series data is a powerful tool to delaminate the dynamics of transcription and interactions among genes on a large scale. Different algorithms have been proposed to organize experimental data with meaningful biological clusters; however, these approaches often fail to generate well-defined temporal clusters, especially when genes exert their functions or response to stimulation coordinately only in a short time span. In this study, we propose an algorithm using sliding windows to identify different temporal patterns based on fold changes of gene expression. The algorithm was applied to simulated data and real experimental data. Furthermore, a comparison study has been carried out with the clusters obtained from commercial software packages. The identified clusters using our algorithm demonstrated better temporal matching and consistency.
In biological sequence analysis, long and frequently occurring patterns tend to be interesting. Data miners designed pattern growth algorithms to obtain frequent patterns with periodical wildcard gaps, where the pattern frequency is defined as the number of pattern occurrences divided by the number of offset sequences. However, the existing definition set does not facilitate further research works. First, some extremely frequent patterns are obviously uninteresting. Second, the Apriori property does not hold; consequently, state-of-the art algorithms are all Apriori-like and rather complex. In this paper, we propose an alternative definition of the number of offset sequences by adding a number of dummy characters at the tail of sequence. With the new definition, these uninteresting patterns are no longer frequent, and the Apriori property holds, hence our Apriori algorithm can mine all frequent patterns with minimal endeavor. Moreover, the computation of the number of offset sequences becomes straightforward. Experiments with a DNA sequence indicate 1) the pattern frequencies under two definition sets have little difference, therefore it is reasonable to replace the existing one with the new one in practice, and 2) our algorithm runs less rounds than the best case of MMP which is based on the existing definition set.
Reviewing video of capsule endoscopy is a tedious work that takes hours. Hence, efficient and scalable approaches are needed to automate the process of large dataset and be able to refine the model given new examples. This paper presents an incremental SVM to learn from large dataset with dynamic patterns. Our method extends the reduced convex hull concept and defines the approximate skin segments of convex hulls. Experiments were conducted using synthetic data set, real–world data sets, and CE videos. Our results demonstrated highly competitive performance that requires much less resource, which cast new light on learning with limited resource.
Traditional Chinese Medicine (TCM) has a long history and has been recognized as a popular alternative medicine in western countries. Tongue diagnosis is a significant procedure in computer-aided TCM, where tongue image analysis plays a dominant role. In this paper, we proposed a fully automatic tongue detection and tongue segmentation framework, which is an essential step in computer-aided tongue image analysis. Comparing with other existing methods, our method is fully automatic without any need of adjusting parameters for different images and do not need any initialization.
In many areas of practice and research, clinical observations are recorded on data collection forms by asking and answering questions, yet without being represented in accepted terminology standards these results cannot be easily shared among clinical care and research systems. LOINC contains a well-developed model for representing variables, answer lists, and the collections that contain them. We have successfully added many assessments and other collections of variables to LOINC in this model. By creating a uniform representation and distributing it worldwide at no cost, LOINC aims to lower the barriers to interoperability among systems and make this valuable data available across settings when and where it is needed.
The United States Health Information Knowledgebase (USHIK) is an online, publicly accessible registry/repository of healthcare metadata originally developed by Center for Medicare and Medicaid Services (CMS) and the Department of Defense (DoD) and currently maintained by the Agency for Healthcare Research and Quality (AHRQ). It contains metadata for various healthcare standards, measures, forms and other data sets. Its users include researchers, Standards Development Organisations (SDOs), clinicians, Electronic Health Record (EHR) developers and users, and various Federal- and state-level government entities. USHIK provides the capability to visually organise summary metadata, analyse metadata sets and interactively compare metadata sets. This functionality can be used for analysing and harmonising standards, measures and other healthcare data sets.
