scholarly journals An expert-led and artificial intelligence system-assisted tutoring course to improve the confidence of Chinese medical interns in suturing and ligature skills: a prospective pilot study

2019 ◽  
Vol 16 ◽  
pp. 7 ◽  
Author(s):  
Ying-Ying Yang ◽  
Boaz Shulruf
Keyword(s):  
Artificial Intelligence ◽  
Pilot Study ◽  
Skill Acquisition ◽  
Clinical Training ◽  
Intervention Program ◽  
Group Performance ◽  
Internal Standard ◽  
Regular Group ◽  
Intelligence System ◽  
Medical Interns

Purpose: Lack of confidence in suturing/ligature skills due to insufficient practice and assessments is common among novice Chinese medical interns. This study aimed to improve the skill acquisition of medical interns through a new intervention program. Methods: In addition to regular clinical training, expert-led or expert-led plus artificial intelligence (AI) system tutoring courses were implemented during the first 2 weeks of the surgical block. Interns could voluntarily join the regular (no additional tutoring), expert-led tutoring, or expert-led+AI tutoring groups freely. In the regular group, interns (n=25) did not receive additional tutoring. The expert-led group received 3-hour expert-led tutoring and in-training formative assessments after 2 practice sessions. After a similar expert-led course, the expert-led+AI group (n=23) practiced and assessed their skills on an AI system. Through a comparison with the internal standard, the system automatically recorded and evaluated every intern’s suturing/ligature skills. In the expert-led+AI group, performance and confidence were compared between interns who participated in 1, 2, or 3 AI practice sessions.Results: The end-of-surgical block objective structured clinical examination (OSCE) performance and self-assessed confidence in suturing/ligature skills were highest in the expert-led+AI group. In comparison with the expert-led group, the expert-led+AI group showed similar performance in the in-training assessment and greater improvement in the end-of-surgical block OSCE. In the expert-led+AI group, the best performance and highest post-OSCE confidence were noted in those who engaged in 3 AI practice sessions.Conclusion: This pilot study demonstrated the potential value of incorporating an additional expert-led+AI system–assisted tutoring course into the regular surgical curriculum.

scholarly journals Accuracy of an Artificial Intelligence System for Cancer Clinical Trial Eligibility Screening: A Pilot Study (Preprint)

10.2196/27767 ◽  
2021 ◽  
Author(s):  
Tufia Haddad ◽  
Jane M. Helgeson ◽  
Katharine E. Pomerleau ◽  
Anita M. Preininger ◽  
M. Christopher Roebuck ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Clinical Trial ◽  
Pilot Study ◽  
Cancer Clinical Trial ◽  
Artificial Intelligence System ◽  
Intelligence System

Predictors of Success Using a mHealth Intervention in Adults with Prediabetes: Results of a Pilot Study (Preprint)

2019 ◽  
Author(s):  
Nestoras Mathioudakis ◽  
Estelle Everett ◽  
Noora Al-Hajri ◽  
Mohammed Abusamaan ◽  
Clare Lee ◽  
...  
Keyword(s):  
Pilot Study ◽  
Intervention Program ◽  
Area Deprivation ◽  
Inverse Association ◽  
Small Pilot Study ◽  
Mhealth Intervention ◽  
Increased Risk ◽  
Metabolic Equivalent Of Task ◽  
Mobile Intervention ◽  
The Difference

BACKGROUND About one-third of American adults have prediabetes and are at increased risk of type 2 diabetes. Mobile health (mHealth) technologies provide a scalable approach to diabetes prevention by encouraging physical activity (PA), weight loss, and adherence to a healthy diet in large numbers of patients. OBJECTIVE To identify factors associated with improvements in PA and glycated hemoglobin (A1c) measures among prediabetic adults who received a mobile intervention program (smartphone app in combination with a digital body weight scale) in a previously completed pilot study. METHODS We conducted a post hoc analysis of a 3-month prospective, single-arm, observational study using the Sweetch™ mHealth intervention among adults with prediabetes. Change in A1C was calculated as the difference between the 3-month and baseline A1C measurements and was categorized as decrease vs. no decrease. PA was evaluated using the total minutes and metabolic equivalent of task (MET)-hours per week. Change in MET-hours/week was categorized as increase vs. no increase. Age, sex, race, education, employment status, area deprivation, smartphone usage attitudes, and PA stage of change were compared between groups by outcomes of change in A1C and change in MET-hour/week. RESULTS A total of 37 adults received the final Sweetch mobile intervention and were included in the analysis. 62% were female and 81% were white, with average age of 57 years. The median [IQR] baseline A1C was 6.0% [5.8, 6.2]. A1C measure at 3-month was decreased in 24 (65%) participants when compared to baseline A1C. There was an inverse association between average MET-hours per week and change in A1C. Among participants whose A1C decreased vs. did not decrease, the MET-hours per week in last 2 weeks of study was 18.7 (8.4) and 15.0 (7.1), respectively (P=0.19), and the change in MET-hours per week was 2.1 (7.1) and 4.1(6.1), respectively (P=0.41). There were otherwise no statistically significant differences in participant factors by A1C and PA outcomes. CONCLUSIONS In this small pilot study, Sweetch mHealth intervention achieved comparable A1C response prediabetic adults with different individual, sociodemographic and anthropometric characteristics. CLINICALTRIAL ClincialTrials.gov NCT02896010; https://clinicaltrials.gov/ct2/show/NCT02896010 (Archived by WebCite at http://www.webcitation.org/6xJYxrgse)

Endoscopic prediction of submucosal invasion in Barrett’s cancer with the use of Artificial Intelligence: A pilot Study

Endoscopy ◽  
2020 ◽  
Author(s):  
Alanna Ebigbo ◽  
Robert Mendel ◽  
Tobias Rückert ◽  
Laurin Schuster ◽  
Andreas Probst ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Pilot Study ◽  
White Light ◽  
Submucosal Invasion ◽  
Learning System ◽  
Endoscopic Images ◽  
Barrett’S Cancer ◽  
Significant Difference ◽  
Sensitivity Specificity

Background and aims: The accurate differentiation between T1a and T1b Barrett’s cancer has both therapeutic and prognostic implications but is challenging even for experienced physicians. We trained an Artificial Intelligence (AI) system on the basis of deep artificial neural networks (deep learning) to differentiate between T1a and T1b Barrett’s cancer white-light images. Methods: Endoscopic images from three tertiary care centres in Germany were collected retrospectively. A deep learning system was trained and tested using the principles of cross-validation. A total of 230 white-light endoscopic images (108 T1a and 122 T1b) was evaluated with the AI-system. For comparison, the images were also classified by experts specialized in endoscopic diagnosis and treatment of Barrett’s cancer. Results: The sensitivity, specificity, F1 and accuracy of the AI-system in the differentiation between T1a and T1b cancer lesions was 0.77, 0.64, 0.73 and 0.71, respectively. There was no statistically significant difference between the performance of the AI-system and that of human experts with sensitivity, specificity, F1 and accuracy of 0.63, 0.78, 0.67 and 0.70 respectively. Conclusion: This pilot study demonstrates the first multicenter application of an AI-based system in the prediction of submucosal invasion in endoscopic images of Barrett’s cancer. AI scored equal to international experts in the field, but more work is necessary to improve the system and apply it to video sequences and in a real-life setting. Nevertheless, the correct prediction of submucosal invasion in Barret´s cancer remains challenging for both experts and AI.

scholarly journals 411 - Implementing the STrAtegies for RelaTives (START) intervention in Portugal – preliminary findings

2020 ◽  
Vol 32 (S1) ◽  
pp. 127-127
Author(s):  
Fatima Urzal ◽  
Ana Quintão ◽  
Catarina Santos ◽  
Nuno Moura ◽  
Ana Banazol ◽  
...  
Keyword(s):  
Pilot Study ◽  
Coping Strategies ◽  
Family Caregivers ◽  
Clinical Training ◽  
Unmet Needs ◽  
Depression Scale ◽  
Subjective Impression ◽  
Implementation Challenges ◽  
People With Dementia ◽  
The Uk

IntroductionAs in other countries, Portuguese family caregivers have unmet needs regarding information and distress. START (STrAtegies for RelaTives) is a manual-based coping intervention for families of people with dementia, including coping strategies and stress-management components, by Livingston and colleagues (https://www.ucl.ac.uk/psychiatry/research/mental-health-older-people/projects/start). In the UK, START has been clinically effective, immediately and continuing even after 6-years, without increasing costs. Clinical training and supervision ensures treatment fidelity. In Portugal, these kind of interventions are less available and, when provided, are mostly supportive and fail to address coping strategies. Paradoxically, recruitment may also prove challenging.ObjectivesWe describe the development of the Portuguese translation of START, incorporating guidance from the UK team, and a pilot study of delivery to family caregivers of people with dementia. We will also discuss the challenges of recruiting participants and delivering the intervention.MethodWe translated the START intervention and recruited family caregivers from neurology and psychiatry outpatients, in a central hospital in Lisbon. Our baseline assessment included the Hospital Anxiety and Depression Scale and the Zarit Burden Interview. The pilot is still ongoing at time of submitting, so we focus on recruitment, baseline assessments and process issues.ResultsDuring a three-month period, we recruited six caregivers. Five were primary caregivers (spouses or adult children) who had been caring for their relatives for 2 up to 10 years. Two caregivers met the international cutoff for clinically relevant affective disorder . The most frequent motivators for taking part were learning to communicate with their relatives and increasing knowledge to build community resources. Overall, the subjective impression of the therapist in charge is that the intervention seems acceptable and promising.Discussion/ConclusionsThis pilot study will eventually lead to an improved version of the Portuguese version of the START manual. So far, the intervention seems appropriate for selected caregivers in Portugal. However, response to striking unmet needs, particularly basic home support, may need to precede interventions like START. We look forward to concluding the intervention study and analyzing the implementation challenges, as a basis to inform a wider-scale trial.

330 DEVELOPMENT AND VALIDATION OF AN ARTIFICIAL INTELLIGENCE SYSTEM TO OPTIMIZE CLINICIAN REVIEW OF PATIENT RECORDS

2021 ◽  
Vol 160 (6) ◽  
pp. S-64-S-65
Author(s):  
Ethan A. Chi ◽  
Gordon Chi ◽  
Cheuk To Tsui ◽  
Yan Jiang ◽  
Karolin Jarr ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Patient Records ◽  
Artificial Intelligence System ◽  
Intelligence System ◽  
Development And Validation
Sign in / Sign up

Export Citation Format

Share Document