In this article, a new algorithm to select the relevant features is proposed for handling microarray data with the specific aim of increasing classification accuracy. In particular, the optimal... Show More

In this article, a new algorithm to select the relevant features is proposed for handling microarray data with the specific aim of increasing classification accuracy. In particular, the optimal genes are extracted using filter and wrapper feature selection algorithms. Here, the use of non-parametric regression algorithm called Multivariate Adaptive Regression Spline (MARS) followed by proposed Random Forest Statistical Test (RFST) algorithm are being studied. The study evaluates the comparative performance of the results of RFST and MARS with existing algorithms on ten standard microarray datasets. For performance analysis, three parameters are taken into consideration, namely, the number of selected features, runtime, and classification accuracy. Experimental results indicate that different feature selection algorithms yield different candidate gene subset; therefore, a Hybrid approach is applied to determine the best candidate genes to provide maximum information about the disease. The findings foretell that the RFST is performing better on six out of ten datasets whereas MARS is performing better on other datasets.

This study was conducted among Vietnamese marriage-migrant women to investigate the effect of both cardiopulmonary resuscitation (CPR) and first aid healthcare trainings on their knowledge and... Show More

This study was conducted among Vietnamese marriage-migrant women to investigate the effect of both cardiopulmonary resuscitation (CPR) and first aid healthcare trainings on their knowledge and attitude towards CPR, self-efficacy, and first-aid. The experimental and control groups revealed statistically significant differences across all dependent variables: knowledge of CPR (t = 3.26, p = 0.002); attitude towards CPR (t = 4.46, p = 0.019); self-efficacy during CPR (t = 2.77, p = 0.010); and finally, knowledge on coping with emergency situations (t = 2.77, p = 0.008). A significant difference was indicated in their knowledge and attitude towards CPR, self-efficacy, and first aid depending on whether they attended the healthcare training program, which suggested its educative effect. CPR training and relevant information should be continually provided to Vietnamese marriage-migrant women to maintain this effect, and help provide them with guidelines to deal with an emergency situation faced by their family or neighbors.

The aim of this article is to show that the absolute measurement difference between the Kinect-based system and the marker-based system for the sit-to-stand exercise is less important provided that... Show More

The aim of this article is to show that the absolute measurement difference between the Kinect-based system and the marker-based system for the sit-to-stand exercise is less important provided that the difference is caused by systematic errors in the Kinect measurement. Three healthy individuals participated in this study. Marker trajectories and Kinect skeletal joint data were collected while each subject performed the sit-to-stand exercise. Three key parameters, the initial, minimum, and maximum hip angles obtained from the two systems are compared. This preliminary study shows that the Kinect-based system has good agreement with the marker-based system, and it has comparable between-trial reliability and variability to those of the marker-based system. This study shows that Kinect can be used to reliably assess the quality of the sit-to-stand exercise provided that the systematic measurement errors are compensated. This study establishes the foundation to implement a Kinect-based system to automatically monitor, assess, and provide realtime feedback to a patient who carries out the sit-to-stand exercise with or without the supervision of a clinician.

As wide-scale adoption by the market and consumers of ubiquitous devices or mobile apps that track fitness, sleep, nutrition, and basic metabolic parameters increases, it is vital to understand the... Show More

As wide-scale adoption by the market and consumers of ubiquitous devices or mobile apps that track fitness, sleep, nutrition, and basic metabolic parameters increases, it is vital to understand the attitudes of healthcare providers toward these devices. No researcher has previously examined how constructs related to technology acceptance have impacted healthcare providers' behavioral intention for self-monitoring devices (SMD). This was a quantitative, non-experimental study to examine SMD acceptance, intent to use, and other factors important to physicians regarding SMD. Statistical analysis of the data gathered showed that the second version of the Unified Theory of Acceptance and Usage of Technology (UTAUT2) constructs of performance expectancy, hedonic motivation, and price value were positively associated with the behavioral intention of SMD by physicians while effort expectancy and social influence were not. Furthermore, social influence was associated with use, while performance expectancy, effort expectancy, and hedonistic motivation were not. Major positive implications of these findings include: contribution to the body of literature in the health information technology (HIT) arena regarding factors that influence technology acceptance and potential increase in the adoption of SMD among healthcare providers.

There is growing emphasis on sharing and reusing dementia care-related datasets to improve the quality of dementia care. Consequently, there is a need to develop data management solutions for... Show More

There is growing emphasis on sharing and reusing dementia care-related datasets to improve the quality of dementia care. Consequently, there is a need to develop data management solutions for collecting, integrating and storing these data in formats that enhance opportunities for reuse. Dementia Care Mapping (DCM) is an observational tool that is in widespread use internationally. It produces rich, evidence-based data on dementia care quality. Currently, that data is primarily used locally, within dementia care services, to assess and improve quality of care. Information-rich DCM data provides opportunities for secondary use including research into improving the quality of dementia care. But an effective data management solution is required to facilitate this. A rationale for the warehousing of DCM data as a technical data management solution is suggested. The authors also propose a data model for a DCM data warehouse and present user-identified challenges for reusing DCM data within a warehouse.

Over the past few years, the novel appeal and increasing popularity of social networks as a medium for users to express their opinions and views have created an accumulation of a massive amount of... Show More

Over the past few years, the novel appeal and increasing popularity of social networks as a medium for users to express their opinions and views have created an accumulation of a massive amount of data. This evolving mountain of data is commonly termed Big Data. Accordingly, one area in which the application of new techniques in data mining research has significant potential to achieve more precise classification of hidden knowledge in Big Data is sentiment analysis (aka optimal mining). A hybrid approach using Naïve Bayes and Random Forest on mining Twitter datasets is presented here as an extension of previous work. Briefly, relevant data sets are collected from Twitter using Twitter API; then, use of the hybrid methodology is illustrated and evaluated against one with only Naïve Bayes classifier. Results show better accuracy and efficiency in the sentiment classification for the hybrid approach.

EHealth information systems have brought about a lot of positives which include timeous reporting, efficient data analysis, better decision making, coordination and better work processes. Zimbabwe... Show More

EHealth information systems have brought about a lot of positives which include timeous reporting, efficient data analysis, better decision making, coordination and better work processes. Zimbabwe has also adopted the eHealth information systems and this study sought to establish the effects of eHealth information systems on the management of health information in hospitals in Bulawayo, Zimbabwe. The study applies a qualitative research methodology in which a case study research design and a purposive sampling technique were used. Document analysis and face to face interviews were held with a total of eleven research participants.

Disruptive innovation has transformed business activities as well as individuals throughout a variety of industries. In healthcare, the implementation of electronic health records (EHR) innovation... Show More

Disruptive innovation has transformed business activities as well as individuals throughout a variety of industries. In healthcare, the implementation of electronic health records (EHR) innovation has changed the way healthcare organizations handle patient records. Despite the potential benefits EHR can bring to healthcare organizations, there is evidence to show that healthcare providers are avoiding EHR innovations. Little research in information system mainstream research has addressed this phenomenon. To understand EHR avoidance, a mid-range theory is evoked from this textual analysis of responses gathered from healthcare providers at a large international hospital. The data was analyzed by applying a revealed causal mapping technique (RCM). Results of the study revealed not only the key constructs surrounding EHR avoidance, but also the underlying concepts that are shaping each of these constructs. This study demonstrated that the use of the RCM methodology yielded concepts and constructs of EHR avoidance that are not suggested by generalized theory, and revealed main interactions and linkages between these constructs.

Despite key advances in healthcare informatics and management, little progress to address supply chain process-related problems has been made to date. Specifically, key healthcare supply chain... Show More

Despite key advances in healthcare informatics and management, little progress to address supply chain process-related problems has been made to date. Specifically, key healthcare supply chain processes include product recalls, monitoring of product supply shortages, expiration, and counterfeits. Implementing and executing these processes in a trusted, secure, efficient, globally accessible and traceable manner is challenging due to the fragmented nature of the healthcare supply chain, which is prone to systemic errors and redundant efforts that may compromise patient safety and impact health outcomes adversely. Blockchain, combined with the Internet of things (IoT), is an emerging technology that can offer a practical solution to these challenges. Accordingly, IoT blockchain offers a superior way to track and trace products via a peer-to-peer distributed, secure, and shared ledger of the blockchain network. This article highlights key challenges related to healthcare supply chains, and illustrates how IoT blockchain technologies can play a role in overcoming these challenges now and in the near future.

Cervical cancer is the second most common cancer affecting women worldwide but is curable if diagnosed early. Routinely, expert pathologists visually examine histology slides for assessing cervix... Show More

Cervical cancer is the second most common cancer affecting women worldwide but is curable if diagnosed early. Routinely, expert pathologists visually examine histology slides for assessing cervix tissue abnormalities. A localized, fusion-based, hybrid imaging and deep learning approach is explored to classify squamous epithelium into cervical intraepithelial neoplasia (CIN) grades for a dataset of 83 digitized histology images. Partitioning the epithelium region into 10 vertical segments, 27 handcrafted image features and rectangular patch, sliding window-based convolutional neural network features are computed for each segment. The imaging and deep learning patch features are combined and used as inputs to a secondary classifier for individual segment and whole epithelium classification. The hybrid method achieved a 15.51% and 11.66% improvement over the deep learning and imaging approaches alone, respectively, with a 80.72% whole epithelium CIN classification accuracy, showing the enhanced epithelium CIN classification potential of fusing image and deep learning features.

In this article, the MSP430F149 is the microcontroller (MCU), and a pressure sensor, MPX5100AP, is used to measure body measurement of maximal forced expiratory volume (FEV) and peak expiratory flow... Show More

In this article, the MSP430F149 is the microcontroller (MCU), and a pressure sensor, MPX5100AP, is used to measure body measurement of maximal forced expiratory volume (FEV) and peak expiratory flow rate (PEFR). The two analog signals are processed by the signal conditioning circuit, and then the corresponding digital signals are acquired by the MCU. With the related operations of multiple respiratory parameters, a built-up time of respiration signal mutation rate values and the determination of the mutation rate, a mathematical model is built among FEV, PEFR and the rate of variation. The mathematical model of the system is analyzed, and the relationship between the detection results and the degree of airway obstruction is established. Finally, the patient's condition analysis results are given directly on the LCD, which provided the objective indicators for the medical treatment of the disease.

This article makes progress of a commonly used Apriori algorithm, and proposes a new Apriori algorithm based on event ID. In this article, association rules are gained from massive medical data... Show More

This article makes progress of a commonly used Apriori algorithm, and proposes a new Apriori algorithm based on event ID. In this article, association rules are gained from massive medical data through the new Apriori algorithm. This article proposes and then uses the association rules in the prediction system. This article aims at making the lifestyle-related diseases prediction system provide better service for people, for families and for the whole society. The prediction system can automatically give out health-related information of the user after the person's basic information is put in, and it would also give out some pieces of valuable advice according to the resultant data, helping people realize self-determinant health engagement.

The Zika virus (ZIKV) belongs to the genus Flavivirus, together with Dengue virus, yellow fever virus, and West Nile virus. The virus, which was first found in Africa in 1947, has spread across the... Show More

The Zika virus (ZIKV) belongs to the genus Flavivirus, together with Dengue virus, yellow fever virus, and West Nile virus. The virus, which was first found in Africa in 1947, has spread across the world owing to a lack of effective drugs or vaccines. The complete genome sequence of ZIKV is now available; it includes three structural and seven non-structure genes arranged in the order of capsid, pre-membrane, envelope, NS1, NS2A, NS2B, NS3, NS4A, NS4B, and NS5. Two geographically distinct lineages are known, i.e., Asian and African, but ZIKV exhibits differences in clinical progression among regions.

Predictive analytics can be used to anticipate the risks associated with some patients, and prediction models can be employed to alert physicians and allow timely proactive interventions. Recently... Show More

Predictive analytics can be used to anticipate the risks associated with some patients, and prediction models can be employed to alert physicians and allow timely proactive interventions. Recently, health care providers have been using different types of tools with prediction capabilities. Sepsis is one of the leading causes of in-hospital death in the United States and worldwide. In this study, the authors used a large medical dataset to develop and present a model that predicts in-hospital mortality among Sepsis patients. The predictive model was developed using a dataset of more than one million records of hospitalized patients. The independent predictors of in-hospital mortality were identified using the chi-square automatic interaction detector. The authors found that adding hospital attributes to the predictive model increased the accuracy from 82.08% to 85.3% and the area under the curve from 0.69 to 0.84, which is favorable compared to using only patients' attributes. The authors discuss the practical and research contributions of using a predictive model that incorporates both patient and hospital attributes in identifying high-risk patients.

In this article, the authors explore the potential of a big data analytics approach to unstructured text analytics of cancer blogs. The application is developed using Cloudera platform's Hadoop... Show More

In this article, the authors explore the potential of a big data analytics approach to unstructured text analytics of cancer blogs. The application is developed using Cloudera platform's Hadoop MapReduce framework. It uses several text analytics algorithms, including word count, word association, clustering, and classification, to identify and analyze the patterns and keywords in cancer blog postings. This article establishes an exploratory approach to involving big data analytics methods in developing text analytics applications for the analysis of cancer blogs. Additional insights are extracted through various means, including the development of categories or keywords contained in the blogs, the development of a taxonomy, and the examination of relationships among the categories. The application has the potential for generalizability and implementation with health content in other blogs and social media. It can provide insight and decision support for cancer management and facilitate efficient and relevant searches for information related to cancer.

Intraductal papillary mucinous neoplasms (IPMN) are a type of mucinous pancreatic cyst. IPMN have been shown to be pre-malignant precursors to pancreatic cancer, which has an extremely high... Show More

Intraductal papillary mucinous neoplasms (IPMN) are a type of mucinous pancreatic cyst. IPMN have been shown to be pre-malignant precursors to pancreatic cancer, which has an extremely high mortality rate with average survival less than 1 year. The purpose of this analysis is to utilize methodological triangulation using artificial neural networks and regression to examine the impact and effectiveness of a collection of variables believed to be predictive of malignant IPMN pathology. Results indicate that the triangulation is effective in both finding a new predictive variable and possibly reducing the number of variables needed for predicting if an IPMN is malignant or benign.

Nowadays, information technology tools are widely used in the healthcare industry to record and integrate medical data so as to provide complete access to patients' information for coordinated... Show More

Nowadays, information technology tools are widely used in the healthcare industry to record and integrate medical data so as to provide complete access to patients' information for coordinated healthcare delivery. Yet, the efficacy of these technologies depends on their successful implementation for, adoption by and/or adaptation to support health professional workers such as physicians and nurses. This study addresses the impact of specific factors including result observability, autonomy, perceived barriers, task structure, privacy and security anxiety on the nurses' perception of their performance using health information technologies. Additionally, the effects of nurses' personality factors are examined as moderating factors on the relationships between the organizational factors and nurses' perception of performance. Multiple linear regression was applied to validate the proposed research model and professional autonomy, result observability, privacy and security anxiety were found to be key factors predicting the nurses' perception of performance.

Healthcare insurance applications are increasingly vital to and have gained popularity with consumers. Previous information systems research featured perceived ease of use and perceived usefulness... Show More

Healthcare insurance applications are increasingly vital to and have gained popularity with consumers. Previous information systems research featured perceived ease of use and perceived usefulness as key independent variables to explain behavioural intention impacting the use of information systems. In today's environment, however, many consumers already rely on websites and mobile applications as a key means of communication with healthcare insurance providers. Examining the data from 333 survey respondents, this study reports that perceived ease of use and perceived usefulness are strongly influenced by three communication content variables (information quality, interaction ease, and provider competence). Importantly, consumers may judge applications' ease of use based on the quality of communication contents. Once applications reach some maturity, the prominence of communication quality may drive their use more significantly than before.

Social network communities can serve as a health resource for cancer patients to share and disseminate information. Even so, theory-based research into evaluating cancer patients' performance... Show More

Social network communities can serve as a health resource for cancer patients to share and disseminate information. Even so, theory-based research into evaluating cancer patients' performance empirically using social network sites (SNSs) is limited, representing an identifiable knowledge gap. This study proposes a research model that integrates social cognitive theory and task technology fit theory to contribute to the understanding of key factors impacting the performance of breast cancer patients using SNSs. Data were collected via a structured paper-based questionnaire. A total of one hundred seventy-eight (178) participants from six cancer support groups and hospitals in Peninsular Malaysia responded to the administered survey. Survey data were analyzed using the partial least squares (PLS) method while Smart PLS was used to test the hypotheses and to validate the proposed model. Results indicate that outcome expectation, self-efficacy, negative affect, positive affect, social support and task technology fit are significant factors affecting the performance of breast cancer patients vis-à-vis Malaysian social network support groups.