Varadraj P. Gurupur

An entropy-based evaluation method for knowledge bases of medical information systems

Development of an entropy-based evaluation method to evaluate ontology strength.Evaluation an ontological semantic ontology using the evaluation method.Evaluation of the backbone of the UMLS with this method. In this paper we introduce a method to develop knowledge bases for medical decision support systems, with a focus on evaluating such knowledge bases. Departing from earlier efforts with concept maps, we developed an ontological-semantic knowledge base and evaluated its information content using the metrics we have developed, and then compared the results to the UMLS backbone knowledge base. The evaluation method developed uses information entropy of concepts, but in contrast to previous approaches normalizes it against the number of relations to evaluate the information density of knowledge bases of varying sizes. A detailed description of the knowledge base development and evaluation is discussed using the underlying algorithms, and the results of experimentation of the methods are explained. The main evaluation results show that the normalized metric provides a balanced method for assessment and that our knowledge base is strong, despite having fewer relationships, is more information-dense, and hence more useful. The key contributions in the area of developing expert systems detailed in this paper include: (a) introduction of a normalized entropy-based evaluation technique to evaluate knowledge bases using graph theory, (b) results of the experimentation of the use of this technique on existing knowledge bases.

Early Skin Cancer Detection Using Computer Aided Diagnosis Techniques

Skin cancers are cancers that due to the development of abnormal cells that have the ability to invade or spread to other parts of the body. There are three main types: basal-cell cancer, squamous-cell cancer and melanoma. Among the three melanoma spreads through metastasis, and therefore it has been proved to be very fatal. Melanomas typically occur in the skin and identification of skin cancer can be done based on the Melanoma images. A system to prevent this type of skin cancer is being awaited and is highly in-demand. Melanomas are asymmetrical and have irregular borders, notched edges, and color variations, so analyzing the shape, color, and texture of the skin lesion is important for melanoma early detection. There are two Computer Aided Diagnosis (CAD) techniques which are used for early skin cancer detection include color constancy approach and skin lesion analysis. The key contribution of this paper is the comparative study done between color constancy and skin lesion analysis for early skin cancer detection on EDRA database and PH2 database.

Evaluating student learning using concept maps and Markov chains

We first developed a methodology using Markov chains and concept maps to evaluate a student.A tool was developed using this methodology.The experiment conducted indicates that the tool fulfills the purpose. In this paper we describe a tool that can be effectively used to evaluate student learning outcomes using concept maps and Markov chain analysis. The main purpose of this tool is to advance the use of artificial intelligence techniques by using concept maps and Markov chains in evaluating a students understanding of a particular topic of study using concept maps. The method used in the tool makes use of XML parsing to perform the required evaluation. For the purpose of experimenting this tool we have taken into consideration concept maps developed by students enrolled in two different courses in Computer Science. The result of this experimentation is also discussed.

Identifying the readiness of patients in implementing telemedicine in northern Louisiana for an oncology practice

This study identified the readiness factors that may create challenges in the use of telemedicine among patients in northern Louisiana with cancer. To identify these readiness factors, the team of investigators developed 19 survey questions that were provided to the patients or to their caregivers. The team collected responses from 147 respondents from rural and urban residential backgrounds. These responses were used to identify the individuals’ readiness for utilising telemedicine through factor analysis, Cronbach’s alpha reliability test, analysis of variance and ordinary least squares regression. The analysis results indicated that the favourable factor (positive readiness item) had a mean value of 3.47, whereas the unfavourable factor (negative readiness item) had a mean value of 2.76. Cronbach’s alpha reliability test provided an alpha value of 0.79. Overall, our study indicated a positive attitude towards the use of telemedicine in northern Louisiana.

Disparities in patient record completeness with respect to the health care utilization project

Patient data completeness is an important characteristic in maintaining accurate health records and providing the highest standard of care. Furthermore, finding discrepancies in care based on different subpopulation parameters is important to identify areas of underlying systemic issues in order to address concerns and alleviate those discrepancies. In this project, the investigators use the Data Completeness Analysis Package to find trends in patient record completeness using Healthcare Cost and Utilization Project’s State Inpatient Database for the state of Florida, specifically focusing on finding discrepancies among subpopulations along the variables of age, race, and gender. The results from testing Data Completeness Analysis Package with State Inpatient Database show a variety of patterns that provides insights to the health care delivery in Florida.

Diagnosing Schizophrenia: A Deep Learning Approach

This paper presents a new method for diagnosing schizophrenia using deep learning. This experiment used a secondary dataset supplied by the National Institute of Health. The experiment analyzes the dataset and identifies schizophrenia using traditional machine learning methods such as logistic regression, support vector machines, and random forest. Finally, a deep neural network with three hidden layers is applied to the dataset. The results show that the neural network model yielded the highest accuracy, suggesting that deep learning may be a feasible method for diagnosing schizophrenia.

We Have Built It, But They Have Not Come: Examining the Adoption and Use of Assistive Technologies for Informal Family Caregivers

We conducted interviews with 14 informal family caregivers of elderly Alzheimer’s and dementia patients in the U.S. to understand opportunities to increase the adoption and use of assistive technologies (ATs) in the home. We identified three key themes: (1) Most of the caregivers were interested in adopting assistive technologies, but they did not know where to begin; healthcare providers gave little to no guidance. (2) Caregivers demonstrated a need for assistive technologies that enabled or enhanced remote caregiving, as many were adult children who worked full-time and had to leave their elderly parent at home, unattended during the day. (3) While caregivers rarely adopted assistive technologies designed specifically for caregiving, they often repurposed everyday technologies (e.g., home security systems, calendar applications) to aid in care. These findings provide insights for how we can better support the use of assistive technologies by informal family caregivers.

Recent advances in Big Data Analytics, Internet of Things and Machine Learning

Abstract Big data analytics, Internet of Things, and machine learning are some of the rising areas of science and technology forming the next generation of artificial intelligence-based computing systems. It is also important to note that this aforementioned emerging field is diverse and in some strange ways both transformative and transdisciplinary in nature. This transformative and transdisciplinary nature of this field enables it to grow both in terms of its theoretical foundations and applications. In this special issue we focus on some advanced research projects in these areas that are transformative and transdisciplinary in nature. The projects and experiments discussed in this special issue constitute the advancement in synthesis of decision support systems that aid further advancement of healthcare delivery, diagnosing diseases, and analysis of behavioral science.

Design of Health Information Systems

This special issue is intended to generate new knowledge as well as provocative research questions. Application is showcased in several articles. This collection of papers permits researchers throughout the world to gain insight and understanding of what others are doing in their fields and possibilities for future study. In the past, multidisciplinary research teams often came together by pure chance. A biologist, an engineer, and a medical doctor might run into one another at the local sandwich shop at a university. Over time, they came to discuss their work. After more time, they might see possibilities for combining their disciplines to solve a complex problem. Evolving rom the chance luncheon encounters came a new discovery or means of applying new knowledge. However, we can no longer depend on such opportunistic encounters. Researchers need more determined methods of coming together, such as special issue journals in order to assure occasions for multidisciplinary scholarship. The world seems to be constantly changing. We cannot follow the leader and do more of the same. We have to seek knowledge and identify scholars and pathways to discovery. In today’s world, doing more of the same is a recipe for failure. We must challenge ourselves and others to collaborate with those who think broadly and differently about the world. The research landscape for STEM fields is undergoing especially dramatic and rapid change. Universities, governments, and private sector enterprises are funding research endeavors to capitalize on existing knowledge and new developments. Furthermore, applied research is coming under the spotlight. Increasingly our technological developments are enabling research to move quickly beyond the theoretical into real-world applications. Mobile phones have enhanced our communication and most certainly our research capabilities, including opportunities to work with scholars round the world. 3-D printers offer the potential to produce cars that cost less and can be produced rapidly without the need for a factory of skilled workers (Malvey & Slovensky, 2014). 3-D printers have already grabbed news headlines for the production of bionic arms. The “Internet of Things” has been a guiding force demonstrating the many possibilities enhanced connectivity beyond our individual lives. The complexity involved in designing health information systems (Plsek & Greenhalgh, 2001) has many facets. Some of the most challenging facets include: a) designing the human-machine interface between the system and the user, b) assuring the system’s ability to capture and enhance the relevant body or bodies of knowledge, c) designing the system to adapt to new methodologies or discoveries in biomedical informatics, and d) designing for compliance with standards, trends in technology, and statutory regulations. The articles selected for this special issue explore current knowledge and research corresponding to these facets.