Application of Advanced Bioinformatics to Understand and Predict Burnout Among Surgical Trainees

Kurbatov, Vadim; Shaughnessy, Matthew P.; Baratta, Vanessa; Heller, Danielle R.; Freedman-Weiss, Mollie; Resio, Benjamin J.; Fleming, M.; Yoo, Peter S.

doi:10.1016/j.jsurg.2019.11.008

Cited by 18 publications

(7 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, three clusters were identified, which the authors corresponded to the underlying risk of burnout. Their analysis showed less clear separation when using principal component analysis compared to our results, which may be explained by the greater number of input features using by Kurbatov et al 37 This group also included scales measuring professional fulfillment, grit, occupational fatigue, and demographic factors in their clustering analysis. 37 Taken together, these studies suggest that distinct profiles of burnout based on the MBI and similar scales are identifiable and interpretable.…”

Section: Discussioncontrasting

confidence: 93%

“…Their analysis showed less clear separation when using principal component analysis compared to our results, which may be explained by the greater number of input features using by Kurbatov et al 37 This group also included scales measuring professional fulfillment, grit, occupational fatigue, and demographic factors in their clustering analysis. 37 Taken together, these studies suggest that distinct profiles of burnout based on the MBI and similar scales are identifiable and interpretable. Given the previously mentioned challenges in setting cut-offs for dichotomizing burnout using the MBI, 34 further work should continue to explore novel burnout profiles using clustering methods.…”

Section: Discussioncontrasting

confidence: 93%

See 1 more Smart Citation

Profiles of Burnout and Response to the COVID-19 Pandemic Among General Surgery Residents at a Large Academic Training Program

et al. 2022

View full text Add to dashboard Cite

Background COVID-19 has placed demands on General Surgery residents, who are already at high risk of burnout. This study examined the pandemic’s impact on burnout and wellness among General Surgery residents at a large training program. Methods General Surgery residents at our institution completed a survey focused on self-reported burnout, mental health, perceptions of wellness resources, and changes in activities during the pandemic. Burnout was measured using the Maslach Burnout Inventory (MBI). Unsupervised machine learning ( k-means clustering) was used to identify profiles of burnout and comparisons between profiles were made. Results Of 82 eligible residents, 51 completed the survey (62% response rate). During COVID-19, 63% of residents had self-described burnout, 43% had depression, 18% acknowledged binge drinking/drug use, and 8% had anxiety. There were no significant differences from pre-pandemic levels ( p all >.05). Few residents perceived available wellness resources as effective (6%). Based on MBI scores, the clustering analysis identified three clusters, characterized as “overextended”, “engaged”, and “ineffective”. Engaged residents had the least concerning MBI scores and were significantly more likely to exercise, retain social contact during the pandemic, and had less self-reported anxiety or depression. Research residents were overrepresented in the ineffective cluster (46%), which had high rates of self-reported burnout (77%) and was characterized by the lowest personal accomplishment scores. Rates of self-reported burnout for overextended and engaged residents were 73% and 48%, respectively. Conclusion Surgical residents have high rates of self-reported burnout and depression during the COVID-19 pandemic. Clusters of burnout may offer targets for individualized intervention.

show abstract

Section: Discussioncontrasting

confidence: 93%

Section: Discussioncontrasting

confidence: 93%

Profiles of Burnout and Response to the COVID-19 Pandemic Among General Surgery Residents at a Large Academic Training Program

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Next, the convolutional neural network (CNN) deep learning method was applied to the predictive model to estimate 38 parameters for the burnout sample. Kurbatov et al (2020) applied k-means unsupervised clustering (k-means analysis) and supervised clustering (k-means cluster group) to identify and predict burnout in surgical trainees. As collected data shows the stress, and health of the respondents were predicted.…”

Section: Machine Learning Usage In Prediction Burnout and Stressmentioning

confidence: 99%

Prediction of Iranian EFL Teachers' Burnout Level Using Machine Learning Algorithms and Maslach Burnout Inventory

Dizaj

2021

Preprint

View full text Add to dashboard Cite

Burnout is that the result of extreme work-related stress and it's categorized by emotional, psychological, and physical exhaustion. we will count it as a modern epidemic within the teaching profession likewise as different professions. The measures that may have an effect on a lecturer and can cause burnout are categorized as Depersonalization, Emotional Exhaustion, Personal Accomplishment. though articles on educator burnout vary in their approach, they incline to specialize in the causes of burnout, the way to assess the signs of burnout, methods to stop burnout, and/or next steps for directors and teachers. The main issue that has been incomprehensible is the prediction of obtaining burned out. Through prediction, we will cut back the prices of the burnout impact on teachers, students, schools, and society and stop its consequences like depression, coronary failure, or perhaps suicide. Our objective is to research and predict the burnout level in English as a far-off Language (EFL) teacher. we are going to use Maslach Burnout Inventory (MBI) to gather a dataset and live the 3 subscales of teacher burnout: emotional exhaustion, depersonalization, and reduced personal accomplishment. when analyzing the collected dataset that consisted of 1433 teachers’ data, 9 machine learning classification algorithms by implementing exploitation python programing language is applied and accuracy is employed as a performance parameter.

show abstract

“…Next, the convolutional neural network (CNN) deep mastering approach turned into implemented to the predictive version to estimate 38 parameters for the burnout pattern. Kurbatov et al (2020) implemented kapproach unsupervised clustering (k-approach analysis) and supervised clustering (k-approach cluster institution) to discover and expect burnout in surgical trainees. As gathered information indicates the strain, and fitness of the respondents have been predicted.…”

Section: Machine Learning Usage In Prediction Burnout and Stressmentioning

confidence: 99%

Prediction of Iranian EFL Teachers' Burnout Level Using Machine Learning Algorithms and Maslach Burnout Inventory

Dizaj

2021

Preprint

View full text Add to dashboard Cite

Burnout is that the end result of excessive work-associated pressure and it is categorized through emotional, psychological, and bodily exhaustion. we can remember it as a cutting-edge epidemic withinside the coaching career likewise as distinct professions. The measures that could have an impact on a lecturer and may reason burnout are categorized as Depersonalization, Emotional Exhaustion, Personal Accomplishment. alevin though articles on educator burnout range of their approach, they incline to specialize withinside the reasons of burnout, the manner to evaluate the symptoms and symptoms of burnout, strategies to forestall burnout, and/or subsequent steps for administrators and teachers. The principal problem that has been incomprehensible is the prediction of acquiring burned out. Through prediction, we can reduce lower back the fees of the burnout effect on teachers, students, schools, and society and forestall its results like depression, coronary failure, or possibly suicide. Our goal is to investigate and are expecting the burnout stage in English as a faraway Language (EFL) instructor. we're going to use Maslach Burnout Inventory (MBI) to collect a dataset and stay the three subscales of instructor burnout: emotional exhaustion, depersonalization, and decreased non-public accomplishment. whilst studying the amassed dataset that consisted of 1433 teachers' data, nine system getting to know type algorithms through enforcing exploitation python programing language is implemented and accuracy is hired as an overall performance parameter.

show abstract

Application of Advanced Bioinformatics to Understand and Predict Burnout Among Surgical Trainees

Cited by 18 publications

References 18 publications

Profiles of Burnout and Response to the COVID-19 Pandemic Among General Surgery Residents at a Large Academic Training Program

Profiles of Burnout and Response to the COVID-19 Pandemic Among General Surgery Residents at a Large Academic Training Program

Prediction of Iranian EFL Teachers' Burnout Level Using Machine Learning Algorithms and Maslach Burnout Inventory

Prediction of Iranian EFL Teachers' Burnout Level Using Machine Learning Algorithms and Maslach Burnout Inventory

Contact Info

Product

Resources

About