Needs Assessment Survey Identifying Research Processes Which may be Improved by Automation or Artificial Intelligence: ICU Community Modeling and Artificial Intelligence to Improve Efficiency (ICU-Comma)

2021 ◽  
pp. 088506662110648
Author(s):  
Vincent I. Lau ◽  
Alexandra Binnie ◽  
John Basmaji ◽  
Nadia Baig ◽  
Dawn Opgenorth ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Case Report ◽  
Human Interaction ◽  
Cross Sectional Survey ◽  
Cross Sectional ◽  
Research Personnel ◽  
Survey Responses ◽  
Community Modeling ◽  
Needs Assessment Survey ◽  
Canadian Research

Background Critical care research in Canada is conducted primarily in academically-affiliated intensive care units with established research infrastructure, including research coordinators (RCs). Recently, efforts have been made to engage community hospital ICUs in research albeit with barriers. Automation or artificial intelligence (AI) could aid the performance of routine research tasks. It is unclear which research study processes might be improved through AI automation. Methods We conducted a cross-sectional survey of Canadian ICU research personnel. The survey contained items characterizing opinions regarding research processes that may be amenable to AI automation. We distributed the questionnaire via email distribution lists of 3 Canadian research societies. Open-ended questions were analyzed using a thematic content analysis approach. Results A total of 49 survey responses were received (response rate: 8%). Tasks that respondents felt were time-consuming/tedious/tiresome included: screening for potentially eligible patients (74%), inputting data into case report forms (65%), and preparing internal tracking logs (53%). Tasks that respondents felt could be performed by AI automation included: screening for eligible patients (59%), inputting data into case report forms (55%), preparing internal tracking logs (51%), and randomizing patients into studies (45%). Open-ended questions identified enthusiasm for AI automation to improve information accuracy and efficiency while freeing up RCs to perform tasks that require human interaction. This enthusiasm was tempered by the need for proper AI education and oversight. Conclusions There were balanced supportive (increased efficiency and re-allocation of tasks) and challenges (informational accuracy and oversight) with regards to AI automation in ICU research.

An Artificial Intelligence Tool for Image Simulation in Rhinoplasty

2021 ◽  
Author(s):  
Hernan Chinsk ◽  
Ricardo Lerch ◽  
Damián Tournour ◽  
Luis Chinski ◽  
Diego Caruso
Keyword(s):  
Artificial Intelligence ◽  
Survey Study ◽  
P Value ◽  
Cross Sectional Survey ◽  
Simulated Image ◽  
Level Of Evidence ◽  
Cross Sectional ◽  
Partial Agreement ◽  
Aesthetic Rhinoplasty ◽  
Level Of Agreement

AbstractDuring rhinoplasty consultations, surgeons typically create a computer simulation of the expected result. An artificial intelligence model (AIM) can learn a surgeon's style and criteria and generate the simulation automatically. The objective of this study is to determine if an AIM is capable of imitating a surgeon's criteria to generate simulated images of an aesthetic rhinoplasty surgery. This is a cross-sectional survey study of resident and specialist doctors in otolaryngology conducted in the month of November 2019 during a rhinoplasty conference. Sequential images of rhinoplasty simulations created by a surgeon and by an AIM were shown at random. Participants used a seven-point Likert scale to evaluate their level of agreement with the simulation images they were shown, with 1 indicating total disagreement and 7 total agreement. Ninety-seven of 122 doctors agreed to participate in the survey. The median level of agreement between the participant and the surgeon was 6 (interquartile range or IQR 5–7); between the participant and the AIM it was 5 (IQR 4–6), p-value < 0.0001. The evaluators were in total or partial agreement with the results of the AIM's simulation 68.4% of the time (95% confidence interval or CI 64.9–71.7). They were in total or partial agreement with the surgeon's simulation 77.3% of the time (95% CI 74.2–80.3). An AIM can emulate a surgeon's aesthetic criteria to generate a computer-simulated image of rhinoplasty. This can allow patients to have a realistic approximation of the possible results of a rhinoplasty ahead of an in-person consultation. The level of evidence of the study is 4.

Awareness and Perception of Dentists Regarding Role and Future of Artificial Intelligence in Dentistry

2021 ◽  
Vol 15 (12) ◽  
pp. 3555-3558
Author(s):  
Isma Sajjad ◽  
Yawar Ali Abidi ◽  
Nabeel Baig ◽  
Humera Akhlak ◽  
Maham Muneeb Lone ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Online Survey ◽  
Clinical Decision ◽  
Utilization Rate ◽  
Cross Sectional Survey ◽  
Cross Sectional ◽  
Dental Practitioner ◽  
Cad Cam ◽  
Great Passion ◽  
Graduate Trainees

Background: Every single field preferred artificial intelligence with great passion and thereby the discipline of dental science is no exemption. Aims: To evaluate the awareness and perception of dentists regarding artificial intelligence among dentists working in Karachi Methods: The current online cross-sectional survey conducted in Karachi during july 2021 . The survey included house officers, post-graduate trainees, and general dental practitioner and specialist consultant dental surgeons of either gender. A questionnaire was adopted from an existing similar study and modifications were made according to our settings. The link of survey was created using Google Docs and disseminated through various open social media groups of dental practitioner in Karachi. Results: Total 118 complete responses were received with almost equal responses from males (n=56, 47.5%) and females (n=52.5%). The mean age of study participants was 30.3±5.9 years. 83(70.3%) had awareness of the artificial intelligence driven tools in dentistry. 75.9%, 77.1%, 10.8%, 28.9%, 39.8%, 2.4% and 10.8% reported the use of digital intraoral radiographs, CAD-CAM, CBCT, digital dental records, clinical decision support system and none of the tool in their practice respectively. All of the participants had opinion that AI applications should be part of dental trainings. Conclusion: The present survey showed that the majority had awareness of AI applications in dentistry and had positive perception regarding its future role but there was lacking in the utilization rate of AI tools in their practice. Therefore, it is recommended to attend AI trainings to bring and adapt the AI related changes in local settings. Keywords: Artificial intelligence, dentistry, online survey, perception, awareness, Karachi

Dermatologists’ Perspectives on Artificial Intelligence and Augmented Intelligence — A Cross-sectional Survey

2021 ◽  
Author(s):  
Caroline A. Nelson ◽  
Swapna Pachauri ◽  
Rosie Balk ◽  
Jeffrey Miller ◽  
Rushan Theunis ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Cross Sectional Survey ◽  
Cross Sectional

Brief Report

2021 ◽  
pp. 181-196
Author(s):  
Sean G Massey ◽  
Richard E. Mattson ◽  
Mei-Hsiu Chen ◽  
Melissa Hardesty ◽  
Ann Merriwether ◽  
...  
Keyword(s):  
United States ◽  
Sexual Orientation ◽  
Emerging Adults ◽  
Emerging Adult ◽  
The United States ◽  
Cross Sectional Survey ◽  
Cross Sectional ◽  
Trend Study ◽  
Attraction Behavior ◽  
Survey Responses

This trend study analyzed 9 years (2011–2019) of cross-sectional survey responses to Klein’s Sexual Orientation Grid to explore changes in sexual orientation among emerging adult college students. Categorical regression models based on ordinal responses revealed that participants were moving away from exclusive heterosexuality on attraction, behavior, and identity subscales at a rate of approximately 6% per year. This trend augments for women after 2014, coinciding with increased advocacy efforts related to U.S. marriage equality, but attenuates for men. Participants’ race also related to variations in sexual orientation: Black participants were less likely than White participants to identify as exclusively heterosexual, whereas the pattern reversed for Asian participants relative to White participants. These findings suggest that changes in sexual orientation are occurring among emerging adults in the United States, potentially in response to changing social and political contexts, but these changes are more pronounced in women and Black emerging adults.

The final reason paediatric Cardiac ICU patients require care prior to discharge to the floor: a single-centre survey

2020 ◽  
Vol 30 (8) ◽  
pp. 1109-1117
Author(s):  
Melissa M. Winder ◽  
Zhining Ou ◽  
Angela P. Presson ◽  
Madolin K. Witte ◽  
Adam L. Ware ◽  
...  
Keyword(s):  
Length Of Stay ◽  
Vascular Ring ◽  
Single Centre ◽  
Cross Sectional Survey ◽  
Cross Sectional ◽  
Lengths Of Stay ◽  
Icu Length Of Stay ◽  
Icu Discharge ◽  
Survey Responses ◽  
Research Initiatives

AbstractObjective:To determine the Final ICU Need in the 24 hours prior to ICU discharge for children with cardiac disease by utilising a single-centre survey.Methods:A cross-sectional survey was utilised to determine Final ICU Need, which was categorised as “Cardiovascular”, “Respiratory”, “Feeding”, “Sedation”, “Systems Issue”, or “Other” for each encounter. Survey responses were obtained from attending physicians who discharged children (≤18 years of age with ICU length of stay >24 hours) from the Cardiac ICU between April 2016 and July 2018.Measurements and results:Survey response rate was 99% (n = 1073), with 667 encounters eligible for analysis. “Cardiovascular” (61%) and “Respiratory” (26%) were the most frequently chosen Final ICU Needs. From a multivariable mixed effects logistic regression model fitted to “Cardiovascular” and “Respiratory”, operations with significantly reduced odds of having “Cardiovascular” Final ICU Need included Glenn palliation (p = 0.003), total anomalous pulmonary venous connection repair (p = 0.024), truncus arteriosus repair (p = 0.044), and vascular ring repair (p < 0.001). Short lengths of stay (<7.9 days) had significantly higher odds of “Cardiovascular” Final ICU Need (p < 0.001). “Cardiovascular” and “Respiratory” Final ICU Needs were also associated with provider and ICU discharge season.Conclusions:Final ICU Need is a novel metric to identify variations in Cardiac ICU utilisation and clinical trajectories. Final ICU Need was significantly influenced by benchmark operation, length of stay, provider, and season. Future applications of Final ICU Need include targeting quality and research initiatives, calibrating provider and family expectations, and identifying provider-level variability in care processes and mental models.

Emergency medicine registrar training in Africa: overview of programmes, faculty and sustainability

2020 ◽  
pp. emermed-2019-208668
Author(s):  
Abena Obenewaa Akomeah ◽  
Hendry Robert Sawe ◽  
Juma A Mfinanga ◽  
Michael S Runyon ◽  
Erin Elizabeth Noste
Keyword(s):  
Emergency Medicine ◽  
Training Programme ◽  
Descriptive Statistics ◽  
African Countries ◽  
Cross Sectional Survey ◽  
Cross Sectional ◽  
Career Options ◽  
Survey Responses ◽  
Collaborative Efforts ◽  
Registrar Training

BackgroundThe specialty of emergency medicine (EM) is new in most African countries, where emergency medicine registrar (residency) programmes (EMRPs) are at different stages of evolution and little is known about the programmes. Identifying and describing these EMRPs will facilitate planning for sustainability, collaborative efforts and curriculum development for existing and future programmes. Our objective was to identify and provide an overview of existing EMRPs in Africa and their applicant requirements, faculty characteristics and plans for sustainability.MethodsWe conducted a descriptive cross-sectional survey of Africa’s EMRPs between January and December 2017, identifying programmes through an online search supplemented by discussions with African EM leaders. Leaders of all identified African EMRPs were invited to participate. Data were collected prospectively using a structured survey and are summarised with descriptive statistics.ResultsWe identified 15 programmes in 12 countries and received survey responses from 11 programmes in 10 countries. Eight of the responding EMRPs began in 2010 or later. Only 36% of the EMRPs offer a 3-year programme. Women make up an average of 33% of faculty. Only 40% of EMRPs require faculty to be EM specialists. In smaller samples that reported the relevant data, 67% (4/6) of EMRPs have EM specialists who trained in that EMRP programme making up more than half of their faculty; 57% of Africa’s 288 EMRP graduates to date are men; and an average of 39% of EMRP graduates stay on as faculty for 78% (7/9) of EMRPs.ConclusionEMRPs currently produce most of their own EM faculty. Almost equal proportions of men and women have graduated from a predominantly >3-year training programme. Graduates have a variety of opportunities in academia and private practice. Future assessments may wish to focus on the evolution of these programme’ curricula, faculty composition and graduates’ career options.

scholarly journals Medical Students’ Attitudes Towards Cardiothoracic Surgery in the United Kingdom: A Cross-Sectional Survey of 1675 Students

2022 ◽  
Vol 9 ◽  
pp. 238212052110727
Author(s):  
Samiullah Dost ◽  
Lana Al-Nusair ◽  
Mai Shehab ◽  
Arwa Hagana ◽  
Aleena Hossain ◽  
...  
Keyword(s):  
Medical Students ◽  
Extracurricular Activities ◽  
Online Survey ◽  
Negative Relationship ◽  
Medical Schools ◽  
Cardiothoracic Surgery ◽  
Cross Sectional Survey ◽  
Cross Sectional ◽  
Students Attitudes ◽  
Survey Responses

Objectives The objectives of this study were the following: (i) assess interest levels in cardiothoracic surgery (CTS) among UK-based medical students, (ii) identify potential motivators and barriers to pursuing CTS training, (iii) explore the influence of gender on interest in CTS in greater depth. Methods Medical students from all year groups across UK medical schools were invited to participate in a cross-sectional, national online survey. Responses were collected from 02/12/2019 to 08/12/2019. Results 1675 medical students from 31 UK medical schools responded, with an estimated 5.3% response rate. Of the respondents, 33.7% respondents reported having exposure to CTS, primarily through their medical school or through extracurricular activities (48.4% and 38.8%, respectively). When assessing interest in CTS, 31.4% were interested in undertaking a career in CTS, with a larger proportion of students expressing interest with no exposure to CTS than those with exposure. However, interest in pursuing CTS decreased with exposure as medical students transitioned from pre-clinical to clinical stages. Additionally, male participants were more interested in seeking a CTS post than their female counterparts (38% vs. 27.6%). The length of training ( p = 0.0009) and competitive nature ( p < 0.0001) of gaining a CTS post were the primary deterring factor for female participants, compared to their male counterparts. Conclusions This study shows the importance of quality of exposure and its impact on students’ interests in pursuing a career in CTS. The negative relationship between exposure and interest in CTS can be associated with the realisation of the challenges that come with pursuing CTS.

scholarly journals The Impact of Explanations on Layperson Trust in Artificial Intelligence–Driven Symptom Checker Apps: Experimental Study (Preprint)

2021 ◽  
Author(s):  
Claire Woodcock ◽  
Brent Mittelstadt ◽  
Dan Busbridge ◽  
Grant Blank
Keyword(s):  
Artificial Intelligence ◽  
Temporal Arteritis ◽  
Statistical Significance ◽  
Group Differences ◽  
P System ◽  
Cross Sectional Survey ◽  
Cross Sectional ◽  
Information Gap ◽  
Social Theories ◽  
The Impact

BACKGROUND Artificial intelligence (AI)–driven symptom checkers are available to millions of users globally and are advocated as a tool to deliver health care more efficiently. To achieve the promoted benefits of a symptom checker, laypeople must trust and subsequently follow its instructions. In AI, explanations are seen as a tool to communicate the rationale behind black-box decisions to encourage trust and adoption. However, the effectiveness of the types of explanations used in AI-driven symptom checkers has not yet been studied. Explanations can follow many forms, including <i>why</i>-explanations and <i>how</i>-explanations. Social theories suggest that <i>why</i>-explanations are better at communicating knowledge and cultivating trust among laypeople. OBJECTIVE The aim of this study is to ascertain whether explanations provided by a symptom checker affect explanatory trust among laypeople and whether this trust is impacted by their existing knowledge of disease. METHODS A cross-sectional survey of 750 healthy participants was conducted. The participants were shown a video of a chatbot simulation that resulted in the diagnosis of either a migraine or temporal arteritis, chosen for their differing levels of epidemiological prevalence. These diagnoses were accompanied by one of four types of explanations. Each explanation type was selected either because of its current use in symptom checkers or because it was informed by theories of contrastive explanation. Exploratory factor analysis of participants’ responses followed by comparison-of-means tests were used to evaluate group differences in trust. RESULTS Depending on the treatment group, two or three variables were generated, reflecting the prior knowledge and subsequent mental model that the participants held. When varying explanation type by disease, migraine was found to be nonsignificant (<i>P</i>=.65) and temporal arteritis, marginally significant (<i>P</i>=.09). Varying disease by explanation type resulted in statistical significance for input influence (<i>P</i>=.001), social proof (<i>P</i>=.049), and no explanation (<i>P</i>=.006), with counterfactual explanation (<i>P</i>=.053). The results suggest that trust in explanations is significantly affected by the disease being explained. When laypeople have existing knowledge of a disease, explanations have little impact on trust. Where the need for information is greater, different explanation types engender significantly different levels of trust. These results indicate that to be successful, symptom checkers need to tailor explanations to each user’s specific question and discount the diseases that they may also be aware of. CONCLUSIONS System builders developing explanations for symptom-checking apps should consider the recipient’s knowledge of a disease and tailor explanations to each user’s specific need. Effort should be placed on generating explanations that are personalized to each user of a symptom checker to fully discount the diseases that they may be aware of and to close their information gap.

Concerns and coping strategies of older adult Veterans in Canada at the outset of the COVID-19 pandemic

2021 ◽  
pp. e20210712
Author(s):  
Alyson Mahar ◽  
Christina Reppas-Rindlisbacher ◽  
Megan Edgelow ◽  
Shailee Siddhpuria ◽  
Julie Hallet ◽  
...  
Keyword(s):  
Coping Strategies ◽  
Family Member ◽  
Well Being ◽  
Cross Sectional Survey ◽  
College Hospital ◽  
Cross Sectional ◽  
Travel Restrictions ◽  
Survey Responses ◽  
Retail Services ◽  
And Coping

Introduction The COVID-19 pandemic, including associated public health measures such as travel restrictions, cancellation of elective surgeries, and the closure of public spaces and retail services (full list available at: https://github.com/jajsmith/COVID-19NonPharmaceuticalInterventions ), has resulted in risks to the health and well-being of Veterans, including disruptions to healthcare, loss of income, social isolation, and viral infection and mortality. Although a few studies are ongoing to better understand who may be at greatest risk, little is known about how Veterans experienced the pandemic and what coping strategies they employed at the outset. This infographic summarizes national cross-sectional survey responses collected from 210 Veterans aged 55 years and older who participated in the Canadian COVID-19 Coping Study between May-June 2020 (Women’s College Hospital Research Ethics Board REB # 2020-0045-E). The average age of Veterans who participated was 72 years; 29% were female, 93% completed the survey in English and 84% were retired. This population is older and more likely to be female than the gen-eral Veteran population.4 None of the Veterans included in this study had been diagnosed with COVID-19 at the time of study. A total of 11% had a family member or friend with a diagnosis or symptoms, and less than 5% had a family member or friend hospitalized, or who died as a result of COVID-19.

Sign in / Sign up

Export Citation Format

Share Document