Adverse Drug Event Discovery Using Biomedical Literature: A Big Data Neural Network Adventure.

BACKGROUND: The study of adverse drug events (ADEs) is a tenured topic in medical literature. In recent years, increasing numbers of scientific articles and health-related social media posts have been generated and shared daily, albeit with very limited use for ADE study and with little known about the content with respect to ADEs. OBJECTIVE: The aim of this study was to develop a big data analytics strategy that mines the content of scientific articles and health-related Web-based social media to detect and identify ADEs. METHODS: We analyzed the following two data sources: (1) biomedical articles and (2) health-related social media blog posts. We developed an intelligent and scalable text mining solution on big data infrastructures composed of Apache Spark, natural language processing, and machine learning. This was combined with an Elasticsearch No-SQL distributed database to explore and visualize ADEs. RESULTS: The accuracy, precision, recall, and area under receiver operating characteristic of the system were 92.7%, 93.6%, 93.0%, and 0.905, respectively, and showed better results in comparison with traditional approaches in the literature. This work not only detected and classified ADE sentences from big data biomedical literature but also scientifically visualized ADE interactions. CONCLUSIONS: To the best of our knowledge, this work is the first to investigate a big data machine learning strategy for ADE discovery on massive datasets downloaded from PubMed Central and social media. This contribution illustrates possible capacities in big data biomedical text analysis using advanced computational methods with real-time update from new data published on a daily basis.

Medical care providers' perspectives on dental information needs in electronic health records.

BACKGROUND: The authors conducted this study to identify the most relevant patient dental information in a medical-dental integrated electronic health record (iEHR) necessary for medical care providers to inform holistic treatment. METHODS: The authors collected input from a diverse sample of 65 participants from a large, regional health system representing 13 medical specialties and administrative units. The authors collected feedback from participants through 11 focus group sessions. Two independent reviewers analyzed focus group transcripts to identify major and minor themes. RESULTS: The authors identified 336 of 385 annotations that most medical care providers coded as relevant. Annotations strongly supporting relevancy to clinical practice aligned with 18 major thematic categories, with the top 6 categories being communication, appointments, system design, medications, treatment plan, and dental alerts. CONCLUSIONS: Study participants identified dental data of highest relevance to medical care providers and recommended implementation of user-friendly access to dental data in iEHRs as crucial to holistic care delivery. PRACTICAL IMPLICATIONS: Identification of the patients' dental information most relevant to medical care providers will inform strategies for improving the integration of that information into the medical-dental iEHR.

Evaluating Patient Usability of an Image-Based Mobile Health Platform for Postoperative Wound Monitoring.

BACKGROUND: Surgical patients are increasingly using mobile health (mHealth) platforms to monitor recovery and communicate with their providers in the postdischarge period. Despite widespread enthusiasm for mHealth, few studies evaluate the usability or user experience of these platforms. OBJECTIVE: Our objectives were to (1) develop a novel image-based smartphone app for postdischarge surgical wound monitoring, and (2) rigorously user test it with a representative population of vascular and general surgery patients. METHODS: A total of 9 vascular and general surgery inpatients undertook usability testing of an internally developed smartphone app that allows patients to take digital images of their wound and answer a survey about their recovery. We followed the International Organization for Standardization (ISO) 9241-11 guidelines, focusing on effectiveness, efficiency, and user satisfaction. An accompanying training module was developed by applying tenets of adult learning. Sessions were audio-recorded, and the smartphone screen was mirrored onto a study computer. Digital image quality was evaluated by a physician panel to determine usefulness for clinical decision making. RESULTS: The mean length of time spent was 4.7 (2.1-12.8) minutes on the training session and 5.0 (1.4-16.6) minutes on app completion. 55.5% (5/9) of patients were able to complete the app independently with the most difficulty experienced in taking digital images of surgical wounds. Novice patients who were older, obese, or had groin wounds had the most difficulty. 81.8% of images were sufficient for diagnostic purposes. User satisfaction was high, with an average usability score of 83.3 out of 100. CONCLUSION: Surgical patients can learn to use a smartphone app for postoperative wound monitoring with high user satisfaction. We identified design features and training approaches that can facilitate ease of use. This protocol illustrates an important, often overlooked, aspect of mHealth development to improve surgical care.

Exploring Dental Providers' Workflow in an Electronic Dental Record Environment.

BACKGROUND: A workflow is defined as a predefined set of work steps and partial ordering of these steps in any environment to achieve the expected outcome. Few studies have investigated the workflow of providers in a dental office. It is important to understand the interaction of dental providers with the existing technologies at point of care to assess breakdown in the workflow which could contribute to better technology designs. OBJECTIVE: The study objective was to assess electronic dental record (EDR) workflows using time and motion methodology in order to identify breakdowns and opportunities for process improvement. METHODS: A time and motion methodology was used to study the human-computer interaction and workflow of dental providers with an EDR in four dental centers at a large healthcare organization. A data collection tool was developed to capture the workflow of dental providers and staff while they interacted with an EDR during initial, planned, and emergency patient visits, and at the front desk. Qualitative and quantitative analysis was conducted on the observational data. RESULTS: Breakdowns in workflow were identified while posting charges, viewing radiographs, e-prescribing, and interacting with patient scheduler. EDR interaction time was significantly different between dentists and dental assistants (6:20 min vs. 10:57 min, p = 0.013) and between dentists and dental hygienists (6:20 min vs. 9:36 min, p = 0.003). CONCLUSIONS: On average, a dentist spent far less time than dental assistants and dental hygienists in data recording within the EDR.

Farm Mapping to Assist, Protect, and Prepare Emergency Responders: Farm MAPPER.

Responders such as firefighters and emergency medical technicians who respond to farm emergencies often face complex and unknown environments. They may encounter hazards such as fuels, solvents, pesticides, caustics, and exploding gas storage cylinders. Responders may be unaware of dirt roads within the farm that can expedite their arrival at critical sites or snow-covered manure pits that act as hidden hazards. A response to a farm, unless guided by someone familiar with the operation, may present a risk to responders and post a challenge in locating the victim. This project explored the use of a Web-based farm-mapping application optimized for tablets and accessible via easily accessible on-site matrix barcodes, or quick response codes (QR codes), to provide emergency responders with hazard and resource information to agricultural operations. Secured portals were developed for both farmers and responders, allowing both parties to populate and customize farm maps with icons. Data were stored online and linked to QR codes attached to mailbox posts where emergency responders may read them with a mobile device. Mock responses were conducted on dairy farms to test QR code linking efficacy, Web site security, and field usability. Findings from farmer usability tests showed willingness to enter data as well as ease of Web site navigation and data entry even with farmers who had limited computer knowledge. Usability tests with emergency responders showed ease of QR code connectivity to the farm maps and ease of Web site navigation. Further research is needed to improve data security as well as assess the program's applicability to nonfarm environments and integration with existing emergency response systems. The next phases of this project will expand the program for regional and national use, develop QR code-linked, Web-based extrication guidance for farm machinery for victim entrapment rescue, and create QR code-linked online training videos and materials for limited English proficient immigrant farm workers.

A rural community's involvement in the design and usability testing of a computer-based informed consent process for the Personalized Medicine Research Project.

Many informed consent studies demonstrate that research subjects poorly retain and understand information in written consent documents. Previous research in multimedia consent is mixed in terms of success for improving participants' understanding, satisfaction, and retention. This failure may be due to a lack of a community-centered design approach to building the interventions. The goal of this study was to gather information from the community to determine the best way to undertake the consent process. Community perceptions regarding different computer-based consenting approaches were evaluated, and a computer-based consent was developed and tested. A second goal was to evaluate whether participants make truly informed decisions to participate in research. Simulations of an informed consent process were videotaped to document the process. Focus groups were conducted to determine community attitudes towards a computer-based informed consent process. Hybrid focus groups were conducted to determine the most acceptable hardware device. Usability testing was conducted on a computer-based consent prototype using a touch-screen kiosk. Based on feedback, a computer-based consent was developed. Representative study participants were able to easily complete the consent, and all were able to correctly answer the comprehension check questions. Community involvement in developing a computer-based consent proved valuable for a population-based genetic study. These findings may translate to other types of informed consents, including those for trials involving treatment of genetic disorders. A computer-based consent may serve to better communicate consistent, clear, accurate, and complete information regarding the risks and benefits of study participation. Additional analysis is necessary to measure the level of comprehension of the check-question answers by larger numbers of participants. The next step will involve contacting participants to measure whether understanding of what they consented to is retained over time.

Medical providers' dental information needs: a baseline survey.

Articulation of medical and dental practices has been strongly called for based on the many oral-systemic connections. With the rapid development and adoption of electronic health records, the feasibility of integrating medical and dental patient data should be strongly considered. The objective of this study was to develop an initial understanding of the medical providers' core dental information needs and opinion of integrated medical-dental electronic health record (iEHR) environment in their workflow. This was achieved by administering a 13 question survey to a group of 1,197 medical care providers employed by Marshfield Clinic in Wisconsin, United States. The survey received a response rate of 35%. The responses were analyzed based on provider 'Role' and 'Specialty'. The majority of the respondents felt the need for patient's dental information to coordinate or provide effective medical care. An integrated electronic health record environment could facilitate this holistic patient care approach.

The role of nonverbal and verbal communication in a multimedia informed consent process.

OBJECTIVE: Nonverbal and verbal communication elements enhance and reinforce the consent form in the informed consent process and need to be transferred appropriately to multimedia formats using interaction design when re-designing the process. METHODS: Observational, question asking behavior, and content analyses were used to analyze nonverbal and verbal elements of an informed consent process. RESULTS: A variety of gestures, interruptions, and communication styles were observed. CONCLUSION: In converting a verbal conversation about a textual document to multimedia formats, all aspects of the original process including verbal and nonverbal variation should be one part of an interaction community-centered design approach.