scholarly journals Automatic Classification of Screen Gaze and Dialogue in Doctor-Patient-Computer Interactions: Computational Ethnography Algorithm Development and Validation

10.2196/25218 ◽  
2021 ◽  
Vol 23 (5) ◽  
pp. e25218
Author(s):  
Samar Helou ◽  
Victoria Abou-Khalil ◽  
Riccardo Iacobucci ◽  
Elie El Helou ◽  
Ken Kiyono
Keyword(s):  
Research Area ◽  
Human Interaction ◽  
Care Providers ◽  
Computer Screen ◽  
Key Points ◽  
Set Up ◽  
Human Coder ◽  
Patient Relationships ◽  
Development And Validation ◽  
Computer Interactions

Background The study of doctor-patient-computer interactions is a key research area for examining doctor-patient relationships; however, studying these interactions is costly and obtrusive as researchers usually set up complex mechanisms or intrude on consultations to collect, then manually analyze the data. Objective We aimed to facilitate human-computer and human-human interaction research in clinics by providing a computational ethnography tool: an unobtrusive automatic classifier of screen gaze and dialogue combinations in doctor-patient-computer interactions. Methods The classifier’s input is video taken by doctors using their computers' internal camera and microphone. By estimating the key points of the doctor's face and the presence of voice activity, we estimate the type of interaction that is taking place. The classification output of each video segment is 1 of 4 interaction classes: (1) screen gaze and dialogue, wherein the doctor is gazing at the computer screen while conversing with the patient; (2) dialogue, wherein the doctor is gazing away from the computer screen while conversing with the patient; (3) screen gaze, wherein the doctor is gazing at the computer screen without conversing with the patient; and (4) other, wherein no screen gaze or dialogue are detected. We evaluated the classifier using 30 minutes of video provided by 5 doctors simulating consultations in their clinics both in semi- and fully inclusive layouts. Results The classifier achieved an overall accuracy of 0.83, a performance similar to that of a human coder. Similar to the human coder, the classifier was more accurate in fully inclusive layouts than in semi-inclusive layouts. Conclusions The proposed classifier can be used by researchers, care providers, designers, medical educators, and others who are interested in exploring and answering questions related to screen gaze and dialogue in doctor-patient-computer interactions.

scholarly journals Automatic Classification of Screen Gaze and Dialogue in Doctor-Patient-Computer Interactions: Computational Ethnography Algorithm Development and Validation (Preprint)

2020 ◽  
Author(s):  
Samar Helou ◽  
Victoria Abou-Khalil ◽  
Riccardo Iacobucci ◽  
Elie El Helou ◽  
Ken Kiyono
Keyword(s):  
Research Area ◽  
Human Interaction ◽  
Care Providers ◽  
Computer Screen ◽  
Key Points ◽  
Set Up ◽  
Human Coder ◽  
Patient Relationships ◽  
Development And Validation ◽  
Computer Interactions

BACKGROUND The study of doctor-patient-computer interactions is a key research area for examining doctor-patient relationships; however, studying these interactions is costly and obtrusive as researchers usually set up complex mechanisms or intrude on consultations to collect, then manually analyze the data. OBJECTIVE We aimed to facilitate human-computer and human-human interaction research in clinics by providing a computational ethnography tool: an unobtrusive automatic classifier of screen gaze and dialogue combinations in doctor-patient-computer interactions. METHODS The classifier’s input is video taken by doctors using their computers' internal camera and microphone. By estimating the key points of the doctor's face and the presence of voice activity, we estimate the type of interaction that is taking place. The classification output of each video segment is 1 of 4 interaction classes: (1) screen gaze and dialogue, wherein the doctor is gazing at the computer screen while conversing with the patient; (2) dialogue, wherein the doctor is gazing away from the computer screen while conversing with the patient; (3) screen gaze, wherein the doctor is gazing at the computer screen without conversing with the patient; and (4) other, wherein no screen gaze or dialogue are detected. We evaluated the classifier using 30 minutes of video provided by 5 doctors simulating consultations in their clinics both in semi- and fully inclusive layouts. RESULTS The classifier achieved an overall accuracy of 0.83, a performance similar to that of a human coder. Similar to the human coder, the classifier was more accurate in fully inclusive layouts than in semi-inclusive layouts. CONCLUSIONS The proposed classifier can be used by researchers, care providers, designers, medical educators, and others who are interested in exploring and answering questions related to screen gaze and dialogue in doctor-patient-computer interactions.

scholarly journals In-Hospital Telehealth Supports Care for Neonatal Patients in Strict Isolation

2020 ◽  
Vol 37 (08) ◽  
pp. 857-860 ◽  
Author(s):  
Rachel A. Umoren ◽  
Megan M. Gray ◽  
Sarah Handley ◽  
Nathaniel Johnson ◽  
Christina Kunimura ◽  
...  
Keyword(s):  
Health Care ◽  
Health Care Providers ◽  
Inpatient Care ◽  
Health Care Team ◽  
Hospital Inpatient ◽  
Care Providers ◽  
Supportive Services ◽  
Key Points ◽  
Viral Illness ◽  
Set Up

The aim of this study is to determine the feasibility of “in-hospital” inpatient telemedicine within a children's referral hospital to facilitate inpatient care activities such as interprofessional rounding and the provision of supportive services such as lactation consultations to pediatric patients in strict isolation. To test the feasibility of in-hospital video telemedicine, a dedicated telemedicine device was set up in the patient's room. This device and the accompanying Bluetooth stethoscope were used by the health care team located just outside the room for inpatient rounding and consultations from supportive services. Video telemedicine facilitated inpatient care and interactions with support services, reducing the number of health care providers with potential exposure to infection and decreasing personal protective equipment use. In the setting of strict isolation for highly infectious viral illness, telemedicine can be used for inpatient care activities such as interprofessional rounding and provision of supportive services. Key Points

ORAL HISTORY SOURCES AS LEARNING MATERIALS: A CASE STUDY OF THE NATIONAL UNIVERSITY OF SCIENCE AND TECHNOLOGY

2016 ◽  
Vol 3 (2) ◽  
pp. 82-93
Author(s):  
Gugulethu Shamaine Nkala ◽  
Rodreck David
Keyword(s):  
Oral History ◽  
Learning Experience ◽  
Science And Technology ◽  
Group Discussion ◽  
Human Interaction ◽  
Learning Material ◽  
Wide Range ◽  
National Archives ◽  
National University ◽  
Set Up

Knowledge presented by Oral History (OH) is unique in that it shares the tacit perspective, thoughts, opinions and understanding of the interviewee in its primary form. While teachers, lecturers and other education specialists have at their disposal a wide range of primary, secondary and tertiary sources upon which to relate and share or impart knowledge, OH presents a rich source of information that can improve the learning and knowledge impartation experience. The uniqueness of OH is presented in the following advantages of its use: it allows one to learn about the perspectives of individuals who might not otherwise appear in the historical record; it allows one to compensate for the digital age; one can learn different kinds of information; it provides historical actors with an opportunity to tell their own stories in their own words; and it offers a rich opportunity for human interaction. This article discusses the placement of oral history in the classroom set-up by investigating its use as a source of learning material presented by the National Archives of Zimbabwe to students in the Department of Records and Archives Management at the National University of Science and Technology (NUST). Interviews and a group discussion were used to gather data from an archivist at the National Archives of Zimbabwe, lecturers and students in the Department of Records and Archives Management at NUST, respectively. These groups were approached on the usability, uniqueness and other characteristics that support this type of knowledge about OH in a tertiary learning experience. The findings indicate several qualities that reflect the richness of OH as a teaching source material in a classroom set-up. It further points to weak areas that may be addressed where the source is considered a viable strategy for knowledge sharing and learning. The researchers present a possible model that can be used to champion the use of this rich knowledge source in classroom education at this university and in similar set-ups. 

Covid-19 and its financial effects on the dental fraternity and health-care workers: A literature review

2020 ◽  
Vol 11 (SPL1) ◽  
pp. 628-631
Author(s):  
Devangi Agrawal ◽  
Namisha Khara ◽  
Bhushan Mundada ◽  
Nitin Bhola ◽  
Rajiv Borle
Keyword(s):  
Health Care ◽  
Health Care Providers ◽  
Health Care Workers ◽  
Care Providers ◽  
Dental Procedures ◽  
Care Workers ◽  
Dental Practices ◽  
Precautionary Measures ◽  
The Government ◽  
Set Up

In the wake of the current outbreak of novel Covid-19, which is now declared as a 'pandemic' by the WHO, people around the globe have been dealing with a lot of difficulties. This virus had come into light in December 2019 and since then has only grown exponentially. Amongst the most affected are the ones who have been working extremely hard to eradicate it, which includes the hospitals, dental fraternity and the health-care workers. These people are financially burdened due to limited practise. In the case of dentistry, to avoid the spread of the virus, only emergency treatments are being approved, and the rest of the standard procedures have been put on hold. In some cases, as the number of covid cases is rising, many countries are even trying to eliminate the emergency dental procedures to divert the finances towards the treatment of covid suffering patients. What we need to realise is that this is probably not the last time that we are facing such a situation. Instead of going down, we should set up guidelines with appropriate precautionary measures together with the use of standardised PPEs. The government should also establish specific policies to support dental practices and other health-care providers. Together, we can fight this pandemic and come out stronger.

scholarly journals Development and validation of a rapid, aldehyde dehydrogenase bright–based cord blood potency assay

Blood ◽  
2016 ◽  
Vol 127 (19) ◽  
pp. 2346-2354 ◽  
Author(s):  
Kevin Shoulars ◽  
Pamela Noldner ◽  
Jesse D. Troy ◽  
Lynn Cheatham ◽  
Amanda Parrish ◽  
...  
Keyword(s):  
Cord Blood ◽  
Aldehyde Dehydrogenase ◽  
Blood Bank ◽  
Potency Assay ◽  
Blood Content ◽  
Cord Blood Bank ◽  
Key Points ◽  
Development And Validation

Key Points Cord blood content of ALDHbr cells correlates well with CFUs and may act as a surrogate potency assay for cord blood units. ALDHbr cells in segments are assayed rapidly, allowing potency results to be used for release of the unit from a public cord blood bank.

scholarly journals Hybrid-specific nutrient and water use of maize on chernozem soil

2013 ◽  
pp. 51-54
Author(s):  
Lajos Karancsi
Keyword(s):  
Maximum Yield ◽  
Field Research ◽  
Research Area ◽  
Control Treatment ◽  
Chernozem Soil ◽  
Set Up ◽  
The University ◽  
Optimum Nutrition ◽  
Corn Hybrid ◽  
Yield Decrease

The field research was set up on chernozem soil at the Látókép AGTC KIT research area of the University of Debrecen. The study focused on yield, water utilization, nutrient reaction and the amount of yield per kg fertilizer of corn hybrid NX 47279 in 2011 and 2012. Based on the yield results it can be concluded that the largest yield in 2011 was 15 963 kg ha-1 at level N120+PK, while in 2012, the maximum yield amounted to 14 972 kg ha-1 at level N90+PK. Surplus yield per kg fertilizer proved that in 2011 level N30+PK resulted in the highest surplus yield (42.3 kg kg-1) compared to the control treatment. In 2012, yield growth was 18.0 kg kg-1 compared to the control treatment. We measured at level N60+PK 17,5 kg kg-1 compared to at level N30+PK, at the N90+PK 17,7 kg kg-1 compared to at level N60+PK. level N30+PK kg kg-1, 17.5 kg kg-1 at level N60+PK and 17.7 kg kg-1 at level N90+PK compared to the control treatment. Results of the regression analysis showed that the amount of nitrogen fertilizer was 117 kg ha-1 in 2011 and 111 kg ha-1 in 2012 in order to reach maximum yield. Doses of fertilizers above the amounts previously mentioned resulted in yield decrease. Our results indicated that in the drought year of 2012 the hybrid used available water more efficiently than in 2011. The hybrid produced 59 kg ha-1 yield in 2012 and 51.9 kg ha-1 in 2011 at an optimum nutrition level.

scholarly journals Preclinical Validation of a Novel Injection-Molded Swab for the Molecular Assay Detection of SARS-CoV-2

Diagnostics ◽  
2022 ◽  
Vol 12 (1) ◽  
pp. 206
Author(s):  
Chiara E. Ghezzi ◽  
Devon R. Hartigan ◽  
Justin P. Hardick ◽  
Rebecca Gore ◽  
Miryam Adelfio ◽  
...  
Keyword(s):  
Health Care Providers ◽  
Medical Devices ◽  
Clinical Studies ◽  
Cost Effective ◽  
Care Providers ◽  
Nasal Tissue ◽  
Significant Difference ◽  
Injection Molded ◽  
Development And Validation

During the COVID-19 public health emergency, many actions have been undertaken to help ensure that patients and health care providers have timely and continued access to high-quality medical devices to respond effectively. The development and validation of new testing supplies and equipment, including collection swabs, has helped to expand the availability and capability for various diagnostic, therapeutic, and protective medical devices in high demand during the COVID-19 emergency. Here, we report the initial validation of a new injection-molded anterior nasal swab, ClearTip™, that was experimentally validated in a laboratory setting as well as in independent clinical studies in comparison to gold standard flocked swabs. We have also developed an in vitro anterior nasal tissue model which offers a novel, efficient, and clinically relevant validation tool to replicate the clinical swabbing workflow with high fidelity, while being accessible, safe, reproducible, and time- and cost-effective. ClearTip™ displayed greater inactivated virus release in the benchtop model, confirmed by its greater ability to report positive samples in a small clinical study in comparison to flocked swabs. We also quantified the detection of biological materials, as a proxy for viral material, in multi-center pre-clinical and clinical studies which showed a statistically significant difference in one study and a reduction in performance in comparison to flocked swabs. Taken together, these results emphasize the compelling benefits of non-absorbent injection-molded anterior nasal swabs for COVID-19 detection, comparable to standard flocked swabs. Injection-molded swabs, as ClearTip™, could have the potential to support future swab shortages, due to its manufacturing advantages, while offering benefits in comparison to highly absorbent swabs in terms of comfort, limited volume collection, and potential multiple usage.

scholarly journals Speech-based human emotion recognition

2021 ◽  
Author(s):  
Talieh Seyed Tabtabae
Keyword(s):  
Emotion Recognition ◽  
Emotional State ◽  
Speaker Identification ◽  
Recognition System ◽  
Research Area ◽  
Speech Signals ◽  
Spectral Features ◽  
Emotional States ◽  
Human Communication ◽  
Set Up

Automatic Emotion Recognition (AER) is an emerging research area in the Human-Computer Interaction (HCI) field. As Computers are becoming more and more popular every day, the study of interaction between humans (users) and computers is catching more attention. In order to have a more natural and friendly interface between humans and computers, it would be beneficial to give computers the ability to recognize situations the same way a human does. Equipped with an emotion recognition system, computers will be able to recognize their users' emotional state and show the appropriate reaction to that. In today's HCI systems, machines can recognize the speaker and also content of the speech, using speech recognition and speaker identification techniques. If machines are equipped with emotion recognition techniques, they can also know "how it is said" to react more appropriately, and make the interaction more natural. One of the most important human communication channels is the auditory channel which carries speech and vocal intonation. In fact people can perceive each other's emotional state by the way they talk. Therefore in this work the speech signals are analyzed in order to set up an automatic system which recognizes the human emotional state. Six discrete emotional states have been considered and categorized in this research: anger, happiness, fear, surprise, sadness, and disgust. A set of novel spectral features are proposed in this contribution. Two approaches are applied and the results are compared. In the first approach, all the acoustic features are extracted from consequent frames along the speech signals. The statistical values of features are considered to constitute the features vectors. Suport Vector Machine (SVM), which is a relatively new approach in the field of machine learning is used to classify the emotional states. In the second approach, spectral features are extracted from non-overlapping logarithmically-spaced frequency sub-bands. In order to make use of all the extracted information, sequence discriminant SVMs are adopted. The empirical results show that the employed techniques are very promising.

scholarly journals Examination of the Nutrient and Water Utilization of Different Corn Genotypes in the Hajdúság

2014 ◽  
pp. 55-59
Author(s):  
Lajos Karancsi
Keyword(s):  
Research Area ◽  
Control Treatment ◽  
Chernozem Soil ◽  
Corn Hybrids ◽  
Water Utilization ◽  
Yield Production ◽  
Set Up ◽  
The University

The research was set up on chernozem soil at the Látókép MÉK research area of the University of Debrecen in Hungary. We examined the following factors of the hybrid P9494, P9578, PR37N01 and PR37M81 in 2013.Yield, yield production per 1 kg fertilizer, water utilization and nutrient reaction. We found that the best yield results were achieved at level N120+PK in case of hybrid P9494 (17 132 kg ha-1) P9578 (16 838 kg ha-1) and PR37N01 (17 476 kg ha-1) and at level N150+PK for hybrid PR37M81 (16 754 kg ha-1). Results of yield per 1 kg NPK studies indicate that the most intense yield growth occurred at level N30+PK compared to the control treatment. This means that yield production per 1 kg NPK was 39.2 kg kg-1 in the case of hybrid P9494, 54.2 kg kg-1 in the case of P9578, 17.6 kg kg-1 for PR37N01 and 44.2 kg kg-1 in the case of PR37M81. After comparing corn hybrids’ water utilization, our conclusion was that the control treatment achieved the worst results in the case of each hybrid (P9494: 20.8 kg mm-1, P9578: 21.0 kg mm-1, PR37N01: 26.2 kg mm-1, PR37M81: 19.5 kg mm-1). For hybrid P9494, P9578 and P37N01, the best water utilization results were measured at level N120+PK (31.5 kg mm-1, 31,0 kg mm-1 and 32.1 kg mm-1), while PR37M81 reached the highest values at level N150+PK (30.8 kg mm-1). We determined the hybrids’ nutrient reaction and its optimum fertilizer values. The best nutrient reaction results were achieved by hybrid PR37N01, while that of hybrid PR37M81 proved to be the weakest.

scholarly journals Internet-Based Administration of Shared Instruments with Facility Online Manager

2006 ◽  
Vol 14 (6) ◽  
pp. 36-39
Author(s):  
Shu-You Li ◽  
Vinayak P. Dravid
Keyword(s):  
Resource Sharing ◽  
Research Council ◽  
Scientific Research ◽  
National Research Council ◽  
Research Area ◽  
Research Groups ◽  
Principal Investigators ◽  
Materials Research ◽  
Set Up ◽  
Large Research

Resource sharing has become an absolute necessity for modern scientific research because of the increasing expense and complexity of instruments, and the ever changing funding paradigm which often requires sharing of major instrumentation resource across multiple disciplines. Many universities and even large companies have set up centralized facilities to serve researchers from different departments, divisions and units to minimize expenses and maximizing usage.Just in the materials research area alone, it is estimated that there are more than 500 mid-size facilities existing nationwide, as reported in 2005 by the Committee on Smaller Facilities of National Research Council. Resource sharing is also common in large research groups, between Principal Investigators, as well as in corporate/industrial laboratories.

Sign in / Sign up

Export Citation Format

Share Document