Search

Currently, the exponential growth of biomedical data along with the complexities of managing high dimensionality, imbalanced distribution, sparse attributes instigates a difficult challenge of effectively applying functional networks as a new large-scale predictive modeling in healthcare and biomedicine. This article proposes functional networks based on propensity score and Newton Raphson-maximum-likelihood optimizations as a new large-scale machine learning classifier to enhance its performance in addressing these challenges within big biomedical data. Different use-cases scenarios based on integrated phenotypic and genomics big biomedical data were proposed: real-life biomedical data, (i) optimal design of cancer chemotherapy; (ii) identify inpatient-admission of individuals with primary diagnosis of cancer; (iii) identify severe asthma exacerbation children using integrated phenotypic and SNP repository data; and (iv) mixture models simulation studies. Comparative studies were carried to compare the performance of the new paradigm versus the common state-of-the-art of machine learning, data mining, and statistics schemes. The results of performance of the new classifier with the most common classifiers on the four benchmark databases have been recorded in tables and graphs. The obtained results of the new classifier outperform most of existing state-of-the art statistical machine learning schemes with reliable and efficient performance. The new predictive modeling classifier is saving the computational time and having reliable performances along with future avenue for extension to deal with next generation sequencing data on high performance computing platforms.

Next Generation Sequencing (NGS) technology produces large volumes of genome data, which gets processed using various open source bioinformatics tools. The configuration and compilation of some bioinformatics tools (e.g. BWAKIT, root) is a challenging activity in its own right, not to mention the need to perform more elaborate porting activities for these applications on some architectures (e.g. IBM Power). The best practices of application porting should ensure (i) the semantics of the program or algorithm should not be changed, (ii) the output generated from the original source code and the modified source code (i.e., after porting) should be same even though the code is ported into different architectures and (iii) the output should be similar across different architectures after porting. Burrows-Wheeler Aligner (BWA) is the most popular genome mapping application used in the BWAKIT toolset. This BWAKIT provides pre-compiled binaries for x86_64 architecture and an end-to-end solution for genome mapping. In this paper, we show how to port various pre-built application binaries used in BWAKIT into OpenPOWER architecture and execute the BWAKIT pipeline successfully. Additionally, we demonstrate the validity of output results on OpenPOWER as well as present benchmarking results of BWAKIT applications that indicate the suitability of the highly multithreaded OpenPOWER architecture to execute these applications.

A critical element in designing a biomedical research platform is the design of a responsible data-sharing mechanism. Such mechanism should provide high utility data in an efficient and timely manner. Existing platforms do not deliver on both timeliness and utility. In this paper, we present a theoretical privacy protection framework. The framework proposes a smart honest broker system that provides data requests with a privacy protection that matches their posed risk. It promises to deliver on both fronts.

Next generation sequencing (NGS) data analysis is highly compute intensive. In-memory computing, vectorization, bulk data transfer, CPU frequency scaling are some of the hardware features in the modern computing architectures. To get the best execution time and utilize these hardware features, it is necessary to tune the system level parameters before running the application. We studied the GATK-HaplotypeCaller which is part of common NGS workflows, that consume more than 43% of the total execution time. Multiple GATK 3.x versions were benchmarked and the execution time of HaplotypeCaller was optimized by various system level parameters which included: (i) tuning the parallel garbage collection and kernel shared memory to simulate in-memory computing, (ii) architecture-specific tuning in the PairHMM library for vectorization, (iii) including Java 1.8 features through GATK source code compilation and building a runtime environment for parallel sorting and bulk data transfer (iv) the default ’on-demand’ mode of CPU frequency is over-clocked by using ’performance-mode’ to accelerate the Java multi-threads. As a result, the HaplotypeCaller execution time was reduced by 82.66% in GATK 3.3 and 42.61% in GATK 3.7. Overall, the execution time of NGS pipeline was reduced to 70.60% and 34.14% for GATK 3.3 and GATK 3.7 respectively.

A dire need of an affordable and accessible technology in order to maintain horses' health can be seen in the animals' care sector. Technology integration at this level will not only enable users to have access to a reliable tool to measure the heartbeat of the horses but also helps to eliminate the need of costly sensors that are expensive and seldom portable. The main objective of the proposed solution is to monitor vital signs of the horses in the form of maintaining their health by an effective instrument that would help any kind of user with a little knowledge of technology to be able to take care of their horses. The sensors of the proposed system allow transmitting horses' heartbeat to a Mobile App through Bluetooth. Then, the Mobile App generates instantly statistics and required information about the horse's heartbeat rate. In addition, the Mobile App sends the horse's heartbeat to the client's servers for more analysis to give the owner of the horses a genuine competitive advantage. The results show that any kind of training program that needs to be conducted for the horse can be customized according to the horse's heart beat and the vital signs that the heartbeat of the horse denotes.

Purpose The Arabic language uses notations called diacritical marks around characters to change which letter a symbol represents, changing the word in which that letter is contained. We explore the potential for error of these marks when faxed in a critical case such as prescriptions. A large number of patients are hurt by medical errors each year [1]. Extensive literature already documents the risks from handwritten prescriptions, while little work has been done with risks from reproduced printed prescriptions. No literature exists to examine risks of prescriptions in non-Roman character alphabets being reproduced. Reproduction via fax transmission is a common practice and often produces damaged copies which can lead to medication errors [2–4]. Languages with diacritical marks, particularly small ones, used for critical contextual meaning would more likely be at risk for misreading due to fax damage. Methods We generated text in English and Arabic reproducing common prescribing instructions, such as "every day" at various font sizes. This was placed on commonly used prescription paper, and reproduced via fax between 2 medical facility fax machines. Results We demonstrate meaningful change of prescribing instructions in the Arabic text by both the fax compression algorithm changing the appearance of diacritical marks along with a large amount of stochastic noise and dropouts being present. This change produced a potentially dangerous change in the instructions in the example we present. Conclusions Prescriptions that are faxed in languages that use diacritical marks to denote contextual meaning, are at high risk for misreading when reproduced via fax. We suggest mitigating strategies, including minimal font size and use of alliteration text in other languages.

Recently, big data is becoming the key to improve the future healthcare. The era of big biomedical data comes with significant challenges in querying, storage, visualize, and analyze the available petabytes of biomedical data, which makes healthcare industry a data-driven field. Currently, the available Concurrent Risk Model (CRM) is limited to the availability of patient episodes that are sensitivity to its cost. Herein, we propose a novel hierarchical data mining based on functional networks to develop a new CRM. This new risk score evaluates the last twelve-month period of patients’ expected risk/cost/severity/illness burden/disease intervention using both medical and drugs claim-based predictors: diagnoses, medications (yes/no), and demographics. Our novel CRM predicts $50,000 permember- per month (PMPM) tracks risk trends over time for any particular group, especially severe chronic diseases. Our CRM model has R2=0.57 in comparison with the best results of Society of Actuaries.