Real-time burn depth assessment using artificial networks: a large-scale, multicentre study.

INTRODUCTION: Early judgment of the depth of burns is very important for the accurate formulation of treatment plans. In medical imaging the application of Artificial Intelligence has the potential for serving as a very experienced assistant to improve early clinical diagnosis. Due to lack of large volume of a particular feature, there has been almost no progress in burn field. METHODS: 484 early wound images are collected on patients who discharged home after a burn injury in 48 h, from five different levels of hospitals in Hunan Province China. According to actual healing time, all images are manually annotated by five professional burn surgeons and divided into three sets which are shallow(0-10 days), moderate(11-20 days) and deep(more than 21 days or skin graft healing). These ROIs were further divided into 5637 patches sizes 224 × 224 pixels, of which 1733 shallow, 1804 moderate, and 2100 deep. We used transfer learning suing a Pre-trained ResNet50 model and the ratio of all images is 7:1.5:1.5 for training:validation:test. RESULTS: A novel artificial burn depth recognition model based on convolutional neural network was established and the diagnostic accuracy of the three types of burns is about 80%. DISCUSSION: The actual healing time can be used to deduce the depth of burn involvement. The artificial burn depth recognition model can accurately infer healing time and burn depth of the patient, which is expected to be used for auxiliary diagnosis improvement.

Symposium review: Real-time continuous decision making using big data on dairy farms.

We are developing a real-time, data-integrated, data-driven, continuous decision-making engine, The Dairy Brain, by applying precision farming, big data analytics, and the Internet of Things. This is a transdisciplinary research and extension project that engages multidisciplinary scientists, dairy farmers, and industry professionals. Dairy farms have embraced large and diverse technological innovations such as sensors and robotic systems, and procured vast amounts of constant data streams, but they have not been able to integrate all this information effectively to improve whole-farm decision making. Consequently, the effects of all this new smart dairy farming are not being fully realized. It is imperative to develop a system that can collect, integrate, manage, and analyze on- and off-farm data in real time for practical and relevant actions. We are using the state-of-the-art database management system from the University of Wisconsin-Madison Center for High Throughput Computing to develop our Agricultural Data Hub that connects and analyzes cow and herd data on a permanent basis. This involves cleaning and normalizing the data as well as allowing data retrieval on demand. We illustrate our Dairy Brain concept with 3 practical applications: (1) nutritional grouping that provides a more accurate diet to lactating cows by automatically allocating cows to pens according to their nutritional requirements aggregating and analyzing data streams from management, feed, Dairy Herd Improvement (DHI), and milking parlor records; (2) early risk detection of clinical mastitis (CM) that identifies first-lactation cows under risk of developing CM by analyzing integrated data from genetic, management, and DHI records; and (3) predicting CM onset that recognizes cows at higher risk of contracting CM, by continuously integrating and analyzing data from management and the milking parlor. We demonstrate with these applications that it is possible to develop integrated continuous decision-support tools that could potentially reduce diet costs by $99/cow per yr and that it is possible to provide a new dimension for monitoring health events by identifying cows at higher risk of CM and by detecting 90% of CM cases a few milkings before disease onset. We are securely advancing toward our overarching goal of developing our Dairy Brain. This is an ongoing innovative project that is anticipated to transform how dairy farms operate.

Cost-effective stochastic MAC circuits for deep neural networks.

Stochastic computing (SC) is a promising computing paradigm that can help address both the uncertainties of future process technology and the challenges of efficient hardware realization for deep neural networks (DNNs). However the impreciseness and long latency of SC have rendered previous SC-based DNN architectures less competitive against optimized fixed-point digital implementations, unless inference accuracy is significantly sacrificed. In this paper we propose a new SC-MAC (multiply-and-accumulate) algorithm, which is a key building block for SC-based DNNs, that is orders of magnitude more efficient and accurate than previous SC-MACs. We also show how our new SC-MAC can be extended to a vector version and used to accelerate both convolution and fully-connected layers of convolutional neural networks (CNNs) using the same hardware. Our experimental results using CNNs designed for MNIST and CIFAR-10 datasets demonstrate that not only is our SC-based CNNs more accurate and 40∼490× more energy-efficient for convolution layers than conventional SC-based ones, but ours can also achieve lower area-delay product and lower energy compared with precision-optimized fixed-point implementations without sacrificing accuracy. We also demonstrate the feasibility of our SC-based CNNs through FPGA prototypes.

Implementation of Real-Time Assessment of Patient-Reported Outcomes in a Heart Failure Clinic: A Feasibility Study.

BACKGROUND: Patient-reported outcomes (PROs) quantify, from patients' perspectives, their symptoms, function, and quality of life. Our aim was to determine the feasibility of integrating PRO capture into routine clinical practice at a large heart failure (HF) clinic. METHODS: We examined the practicality of PRO completion at the time of clinic visit, the time required to complete the selected instruments, the completion rate, and the feasibility of immediate PRO scoring and integration of the results into the electronic health record (EHR). We deployed a computer program to capture PROs (Kansas City Cardiomyopathy Questionnaire, Patient-Reported Outcomes Measurement Information System) on a portable computer platform at the time of a clinic visit. An automated algorithm identified patients scheduled for appointments at the HF clinic at registration, provided a portable tablet computer with which to complete the appropriate PRO instruments and then scored and immediately integrated the results in the patient's EHR. RESULTS: In a 12-month period, 862 unique patients completed 1,320 PRO assessments. The mean age of this cohort was 60.1 ± 16.3 years and 66% were male. The average time for PRO assessment was 6.7 minutes and the completion rate among eligible patients was 58%, with 91% of started assessments completed in full. CONCLUSIONS: These preliminary data support the feasibility of serial PRO assessment with real-time integration into the EHR in a large outpatient population of patients with HF. We identified critical steps that should enhance adoption of this approach by clinicians and render PRO results meaningful and actionable in routine clinical care.

Real-time point of care microcirculatory assessment of shock: design, rationale and application of the point of care microcirculation (POEM) tool.

BACKGROUND: Despite over a decade of research and technological advances, sublingual microcirculatory monitoring has not yet reached clinical utility. Offline analysis is time consuming and occurs away from the patient. A system to assess the microcirculation at the point of care is desirable. We present a novel 5-point grading system (the point of care microcirculation (POEM) scoring system) that can be used at the point of care during non-invasive sublingual microcirculatory monitoring. METHODS: The POEM score is an ordinal scale from 1 (worst) to 5 (best), based on a composite assessment of flow and heterogeneity of four individual sublingual video-microscopy clips. Thirty-two healthcare professionals were trained in how to assign POEM scores. Following training they assigned scores to five test sequences (each consisting of four video clips). They were blinded to clinical status. Inter-user consistency and agreement were assessed using intra-class correlation coefficient (ICC) analysis. In addition, blinded expert scores for 68 video clips were compared to offline computer analysis using traditional microcirculatory parameters including total vessel density (TVD), perfused vessel density (PVD), proportion of perfused vessels (PPV), microcirculatory flow index (MFI) and microcirculatory heterogeneity index (MHI). The time taken to assign each was recorded. RESULTS: Participants showed good inter-rater consistency (ICC 0.83, 95 % CI 0.626, 0.976) and agreement (ICC 0.815, 95 % CI 0.602, 0.974) for assigned POEM scores. Expert scoring of videos correlated with offline values for PVD (R 2 = 0.39; p < 0.05), PPV (R 2 = 0.71; p < 0.001), MFI (R 2 = 0.75; p < 0.001), and MHI (R 2 = 0.68; p < 0.001). POEM scores took less time to assign than conventional offline computer analysis (2 minutes versus 44 minutes). CONCLUSION: We present for the first time a novel 5-point ordinal scale of microcirculatory flow and heterogeneity that can be used at the point of care. It has minimal inter-user variability amongst healthcare professionals after just 1 hour of training. POEM scores take a short time to assign, and correspond well to traditional offline computer-analyzed parameters.

Real-Time MFER Monitoring Using Interval-Saving of Health Signals.

This study proposes MFER design, an international standard for saving measured vital signs while simultaneously monitoring, for health care. The proposed method does not record vital signs as a single file, but rather, after setting header information on vital signs, it reads the measured signs in regular intervals, which are shown in a screen and saved along with header information. Shorter the interval of saving, more similar it becomes to real time monitoring. After measurement is complete, the file fragments are aggregated into a single file, including the header information. MFER constructed in this study in real time monitoring design shows that it can be efficiently used in monitoring and saving of vital signs for health care.

The experience of educational quality in undergraduate nursing students: a phenomenological study.

AIM: The evaluation of academic education has become crucial in the European Union since the Bologna Process encouraged all European universities to reach high quality standards in education. Although several studies have been conducted on the quality of undergraduate nursing education, few studies have explored this topic from the students' perspective. The purpose of this study was to describe the experience of educational quality in undergraduate nursing students. METHOD: The phenomenological method was used to study 55 students (mean age 24 years; 73% female) pursuing a baccalaureate degree in nursing in three universities in central Italy. RESULTS: The following five themes emerged from the phenomenological analysis: 1) quality of faculties: teaching skills, preparation, sensitivity to students, self-discipline; 2) theory-practice integration and communication between teaching and clinical area; 3) general management and organization of the programme; 4) quality of infrastructures: libraries, classrooms, information technology, services, administration, and communication; and 5) clinical tutorship: humanity, relationships and ability of the clinical tutor to guide and support. CONCLUSION: This study's novel finding was a deeper understanding of the educational quality's meanings among undergraduate nursing students. Students thought educational quality consisted of the faculty members' sensitivity towards their problems and the clinical tutors' humanity, interpersonal skills, guidance and support.

The development of a multimedia online language assessment tool for young children with autism.

This study aimed to provide early childhood special education professionals with a standardized and comprehensive language assessment tool for the early identification of language learning characteristics (e.g., hyperlexia) of young children with autism. In this study, we used computer technology to develop a multi-media online language assessment tool that presents auditory or visual stimuli. This online comprehensive language assessment consists of six subtests: decoding, homographs, auditory vocabulary comprehension, visual vocabulary comprehension, auditory sentence comprehension, and visual sentence comprehension. Three hundred typically developing children and 35 children with autism from Tao-Yuan County in Taiwan aged 4-6 participated in this study. The Cronbach α values of the six subtests ranged from .64 to .97. The variance explained by the six subtests ranged from 14% to 56%, the current validity of each subtest with the Peabody Picture Vocabulary Test-Revised ranged from .21 to .45, and the predictive validity of each subtest with WISC-III ranged from .47 to .75. This assessment tool was also found to be able to accurately differentiate children with autism up to 92%. These results indicate that this assessment tool has both adequate reliability and validity. Additionally, 35 children with autism have completed the entire assessment in this study without exhibiting any extremely troubling behaviors. However, future research is needed to increase the sample size of both typically developing children and young children with autism and to overcome the technical challenges associated with internet issues.

Telehealth and ergonomics: a pilot study.

OBJECTIVES: As an emerging model of health care delivery, telehealth has the potential to provide individuals living in remote regions with access to health care services that are otherwise not available. This paper provides a review of the feasibility, comparative effectiveness, cost effectiveness, client and clinician satisfaction, and the barriers to providing telehealth services. A proof-of-concept study that examined the feasibility of telehealth-based ergonomic assessment and intervention is included in this paper to demonstrate the application of telehealth in occupational therapy and ergonomics. METHODS: Ten computer users received a telehealth ergonomic assessment and intervention for their computer workstations via the Telerehabilitation Computer Ergonomics System (tele-CES) - a platform for computer users to access web-based assessments and to communicate with researchers via tele-conferencing. The tele-CES was used to assess participants' computer workstations and pain and comfort levels at baseline and at 4-month follow-up. Ergonomic recommendations were also provided via the tele-CES. RESULTS: Although there was no significant improvement in pain and comfort for participants, a high rate of compliance with ergonomic recommendations - 88% of all recommendations - was observed. CONCLUSION: Further research examining the comparative effectiveness of telehealth ergonomic assessment and intervention relative to in-person ergonomic assessment and intervention is warranted.

Decreasing mislabeled laboratory specimens using barcode technology and bedside printers.

Mislabeling of laboratory samples has been found to be a high-risk issue in acute care hospitals. The goal of this study was to decrease mislabeled blood specimens. In the first year after the implementation of a positive patient identification system using barcoding and computer technology, the number of labeling errors decreased from 103 to 8 per year. The outcome was clinically and statistically significant (P < .001).

Review of ICT-based services for identified unmet needs in people with dementia.

Some of the needs that people with dementia and their informal carers currently perceive as insufficiently met by regular care and support services might be alleviated, or even be met, using modern Information and Communication Technology (ICT). The study described in this paper was designed to provide an insight into the state of the art in ICT solutions that could contribute to meet the most frequently mentioned unmet needs by people with dementia and their informal carers. These needs can be summarized as (1) the need for general and personalized information; (2) the need for support with regard to symptoms of dementia; (3) the need for social contact and company; and (4) the need for health monitoring and perceived safety. Databases that were searched include: PubMed, Cinahl, Psychinfo, Google (Scholar), INSPEC and IEEE. In total 22 websites and 46 publications were included that satisfied the following criteria: the article reports on people with dementia and/or their informal carers and discusses an ICT-device that has been tested within the target group and has proven to be helpful. Within the first need area 18 relevant websites and three studies were included; within the second need area 4 websites and 20 publications were included. Within the third and fourth need area 11 and 12 publications were included respectively. Most articles reported on uncontrolled studies. It is concluded that the informational websites offer helpful information for carers but seem less attuned to the person with dementia and do not offer personalized information. ICT solutions aimed at compensating for disabilities, such as memory problems and daily activities demonstrate that people with mild to moderate dementia are capable of handling simple electronic equipment and can benefit from it in terms of more confidence and enhanced positive effect. Instrumental ICT-support for coping with behavioral and psychological changes in dementia is relatively disregarded as yet, while support for social contact can be effectively realized through, for example, simplified (mobile) phones or videophones or (entertainment) robots. GPS technology and monitoring systems are proven to result in enhanced feelings of safety and less fear and anxiety. Though these results are promising, more controlled studies in which the developed ICT solutions are tested in real life situations are needed before implementing them in the care for people with dementia. It is recommended that future studies also focus on the integration of the current techniques and solutions.

Proposal for fulfilling strategic objectives of the U.S. Roadmap for national action on clinical decision support through a service-oriented architecture leveraging HL7 services.

Despite their demonstrated effectiveness, clinical decision support (CDS) systems are not widely used within the U.S. The Roadmap for National Action on Clinical Decision Support, published in June 2006 by the American Medical Informatics Association, identifies six strategic objectives for achieving widespread adoption of effective CDS capabilities. In this manuscript, we propose a Service-Oriented Architecture (SOA) for CDS that facilitates achievement of these six objectives. Within the proposed framework, CDS capabilities are implemented through the orchestration of independent software services whose interfaces are being standardized by Health Level 7 and the Object Management Group through their joint Healthcare Services Specification Project (HSSP). Core services within this framework include the HSSP Decision Support Service, the HSSP Common Terminology Service, and the HSSP Retrieve, Locate, and Update Service. Our experiences, and those of others, indicate that the proposed SOA approach to CDS could enable the widespread adoption of effective CDS within the U.S. health care system.

Quality of service provision assessment in the healthcare information and telecommunications infrastructures.

The continuous increase in the complexity and the heterogeneity of corporate and healthcare telecommunications infrastructures will require new assessment methods of quality of service (QoS) provision that are capable of addressing all engineering and social issues with much faster speeds. Speed and accessibility to any information at any time from anywhere will create global communications infrastructures with great performance bottlenecks that may put in danger human lives, power supplies, national economy and security. Regardless of the technology supporting the information flows, the final verdict on the QoS is made by the end user. The users' perception of telecommunications' network infrastructure QoS provision is critical to the successful business management operation of any organization. As a result, it is essential to assess the QoS Provision in the light of user's perception. This article presents a cost effective methodology to assess the user's perception of quality of service provision utilizing the existing Staffordshire University Network (SUN) by adding a component of measurement to the existing model presented by Walker. This paper presents the real examples of CISCO Networking Solutions for Health Care givers and offers a cost effective approach to assess the QoS provision within the campus network, which could be easily adapted to any health care organization or campus network in the world.

Use of operating windows in the assessment of integrated robotic systems for the measurement of bioprocess kinetics.

This study examines the utility of an automated liquid handling robot integrated with a microwell plate reader to enable the rapid acquisition of bioprocess kinetic data. The relationship between the key parameters for liquid handling accuracy and precision and the sample detection period has been characterized for typical low-viscosity (<2.0 mPa x s) aqueous and organic phases and for a high-viscosity aqueous phase (60 mPa x s), all exhibiting Newtonian rheology. The use of a simple graphical method enables the suitability of a given automation platform to be assessed once the user has determined the minimum sample detection period and the minimum accurate and precise dispense volume. This provides for a reduction in the duration of any experiment by maximizing well usage within each microwell plate. The suitability of employing an integrated automation platform to gather kinetic data for systems typical of those encountered in bioprocessing is analyzed via a series of case studies. Application to alkaline cell lysis, where disruption is complete within 120 s, showed that the range of available dispense volumes and the number of wells that can be utilized is limited. In contrast, analysis of a system exhibiting slow process kinetics, the fermentation of Escherichia coli TOP10 pQR239 in microwell plates, demonstrated that, for a typical sample detection period of 30 min, the only restrictions on the degree of well utilization are the liquid handling accuracy and precision and the volume capacity of the liquid handling robot. Finally, liquid-liquid extraction, an example of a kinetically independent operation, was also examined. In this case, only a single equilibrium measurement is required, which means that the only restrictions to the utilization of the integrated devices are the liquid handling accuracy and precision. Integrated automation platforms represent a powerful process development tool over traditional experimental methods used for bioprocess development. Smaller volumes of reagent and sample can be used to achieve greater throughput, while high levels of reproducibility and sensitivity are maintained.