Nov. 12, 2018
Using Deep Convolutional Neural Networks To Detect And Classify Indicators Of Leukemia In Blood Samples
The successful detection of leukemia depends on the correct interpretation of the lineage and morphology of monocytes — a type of white blood cells. The monocytes have been classified into four primary stages of differentiation. However, the stages cannot be distinguished unambiguously even by panels of trained experts. A number of attempts have been made to create tissue classifiers using deep learning that did not specifically address monocyte morphology. This research attempts to leverage whole-slide imaging and deep learning tools to create an automated high-accuracy method for cancerous monocytic cell detection.
Oct. 30, 2018
Study of A Visualization Tool Development in Health Informatics
The volume and complexity of data continue to increase in the world around us, including science, business, medicine and everyday human activity. Handling these diverse data to simple and intuitive representation, using simple design and intuitive interaction for non-informatics or non-statistics expert is a pursuance for informatics researchers. Nowadays, the data visualization technology and the internet can bring meaningful information to meet the specific user needs due to it not only presents a visual data interpretation but also improves comprehension and communication with users. As an example, autism (ASD, Autism Spectrum Disorder) is a disease considered to be a neurodevelopment disorder…
Oct. 30, 2018
Promoting Healthy Coping in seniors 72 years or older with Type 2 Diabetes: A feasibility study of a mobile diabetes self-management and support application on functionality, readability, and usability
One out of four Americans older than 65 years old has diabetes. Type 2 diabetes accounts for about 90% to 95% of all diagnosed cases of diabetes. Mobile health technology provides possible solutions for seniors with type 2 diabetes to manage their daily lives. However, our preliminary research shows that only 10% of diabetes apps provided features related to Healthy Coping, which is one principle from the American Association of Diabetes Educators Self-Care Behaviors™, enables people with diabetes to find healthy ways to cope with stress. To alleviate this problem, we have designed a prototype of Healthy Coping mobile app…
Oct. 19, 2018
Using Social Network Analysis to Describe Communication Practices in Healthcare
The Electronic Medical Record (EMR) serves different purposes including documentation of care and billing. The EMR is used to document care delivery, monitor ongoing clinical conditions, and it is also the repository of the patients’ healthcare story. Many people, including healthcare providers, nurses, social workers, therapists, office staff, and nurse care managers (known as the interdisciplinary team, or IDT) work together to deliver healthcare. Members of the IDT use the secure messaging application “Message Center” via the EMR to communicate with, and receive communication from, patients via eHealth (patient portal). An essential part of care coordination is communication, and an…
Oct. 17, 2018
Challenges for the analysis of healthcare reports using natural language processing
Healthcare professionals generate, transmit, and store healthcare records as free-text documents these are the traditional“physician’s reports” or “physician’s notes”. These reports contain complex biomedical data, demographic information, location data, etc. However, free text data are a poor starting point for complex data management, aggregation and processing tasks with computational models. For data-based applications, information from healthcare reports, biomedical tests, radiology impressions and the like should be available in discrete and machine-processable form. Natural language processing (NLP), a subfield of artificial intelligence, includes techniques for manipulating and interpreting free text data for analyses with computers. Here, we briefly discuss free-textpreprocessing, an…
Oct. 16, 2018
Applying Blockchain Technology for Health Information Exchange and Persistent Monitoring for Clinical Trials
“Blockchain” is a distributed ledger technology originally applied in the financial sector. This technology ensures the integrity of transactions without third-party validation. Its functions of decentralized transaction validation, data provenance, data sharing, and data integration are a good fit for the needs of health information exchange and clinical trials. We investigated the current workflow of Health Information Exchange and clinical trials; conducted design thinking processes with clinicians, trial managers, informaticians, and blockchain professionals; and implemented a blockchain model to tackle known issues. We used coded Smart Contract regulations to simulate several scenarios in healthcare processes. This proof-of-concept work provides a…
Oct. 2, 2018
Development and Application of a high throughput multiomics pipeline to uncover molecular signatures in drought stressed Maize Nodal Roots
One of the major focus areas in agricultural research is reducing the major limiting factor of drought for agricultural production worldwide. In the maize plant, water uptake is mainly acquired by the nodal root system after the seedling stage. These roots grow from multiple stem nodes, initially from below-ground and later from above-ground nodes. In drought conditions, nodal roots have shown to grow through dry topsoil to access water found at significant depth and transport water to other parts. This means these roots are able to grow under low water potential levels which normally inhibit leaf and stem growth. However,…
Sep. 18, 2018
Using Deep learning method (CNN/RNN) for prediction of ubiquitination protein
Ubiquitination, as a post-translational modification, is a crucial biological process presented in cell signaling, death and localization. Identification of ubiquitination protein is of fundamental importance for understanding molecular mechanisms in biological systems and diseases. Although high-throughput experimental studies using mass spectrometry have identified many ubiquitination proteins and ubiquitination sites, the vast majority of ubiquitination proteins remain undiscovered, even in well studied model organisms. To reduce experimental costs, computational (in silico) methods have been introduced to predict ubiquitination sites. If we can predict whether a query protein can be ubiquitinated or not, it is meaningful by itself and helpful for predicting…
Sep. 18, 2018
Discovering novel risk factors for age-related eye diseases using subgroup data mining
In the United States, the Medicare cost for the treatment of cataract is continually increasing due to an increased number of cataract surgery done in each year, for example, more than 3 million cataract surgeries were performed in 2017. A study by the World Health Organization reported that a delay of 10 years of the onset of cataracts would cut the number of people who need cataract surgery in half. Henceforth we ventured to investigate potential risk factors for the development of cataract to tackle this growing problem. On the other hand, comorbidities of multiple risk factors and its cumulative…