Analyzing the Correlation Between Surgeon Experience and Patient Length of Hospital Stay

Rajpal, Sharad; Shah, Mancy; Vivek, Niketna; Burneikienė, Sigita

doi:10.7759/cureus.10099

Cited by 5 publications

(5 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, because patients going to rehabilitation care could not be discharged from the hospital if a bed for rehabilitation care was not available, thus inducing delays, 44 using rehabilitation care data could improve the prediction’s accuracy. Moreover, adding data about the professionals carrying out the medical procedures could potentially improve the quality of LOS predictions 45 …”

Section: Discussionmentioning

confidence: 99%

“…Moreover, adding data about the professionals carrying out the medical procedures could potentially improve the quality of LOS predictions. 45 The number of past days used for computing aggregated temporal statistics (ie, 30 d) could be made dynamic, based on the patient's and hospital's characteristics, and optimized through gradient descent. This would allow for a better representation of seasonality in the model.…”

Section: Directions For Future Researchmentioning

confidence: 99%

See 1 more Smart Citation

Length of Stay Prediction With Standardized Hospital Data From Acute and Emergency Care Using a Deep Neural Network

Lequertier,

Wang,

Fondrevelle

et al. 2024

Medical Care

View full text Add to dashboard Cite

Objective: Length of stay (LOS) is an important metric for the organization and scheduling of care activities. This study sought to propose a LOS prediction method based on deep learning using widely available administrative data from acute and emergency care and compare it with other methods. Patients and Methods: All admissions between January 1, 2011 and December 31, 2019, at 6 university hospitals of the Hospices Civils de Lyon metropolis were included, leading to a cohort of 1,140,100 stays of 515,199 patients. Data included demographics, primary and associated diagnoses, medical procedures, the medical unit, the admission type, socio-economic factors, and temporal information. A model based on embeddings and a Feed-Forward Neural Network (FFNN) was developed to provide fine-grained LOS predictions per hospitalization step. Performances were compared with random forest and logistic regression, with the accuracy, Cohen kappa, and a Bland-Altman plot, through a 5-fold cross-validation. Results: The FFNN achieved an accuracy of 0.944 (CI: 0.937, 0.950) and a kappa of 0.943 (CI: 0.935, 0.950). For the same metrics, random forest yielded 0.574 (CI: 0.573, 0.575) and 0.602 (CI: 0.601, 0.603), respectively, and 0.352 (CI: 0.346, 0.358) and 0.414 (CI: 0.408, 0.422) for the logistic regression. The FFNN had a limit of agreement ranging from −2.73 to 2.67, which was better than random forest (−6.72 to 6.83) or logistic regression (−7.60 to 9.20). Conclusion: The FFNN was better at predicting LOS than random forest or logistic regression. Implementing the FFNN model for routine acute care could be useful for improving the quality of patients’ care.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Directions For Future Researchmentioning

confidence: 99%

Length of Stay Prediction With Standardized Hospital Data From Acute and Emergency Care Using a Deep Neural Network

Lequertier,

Wang,

Fondrevelle

et al. 2024

Medical Care

View full text Add to dashboard Cite

show abstract

“…These findings suggest that preoperative immersive viewing and freedom to cut through and manipulate the temporal bone VR models at many desired angles may have improved the mental representation of temporal bone anatomy in inexperienced trainees, which in turn was reflected in the dissection task performance and especially in the time needed to conduct the surgical tasks. Additionally, surgical time has been utilized previously as an adequate indicator of surgical skills and performance (D'Angelo et al, 2015;Mohamadipanah et al, 2021;Rajpal et al, 2020). Therefore, considering the limited time for the VR session during the course, the positive effect of VR training on the surgical time was rather encouraging.…”

Section: Discussionmentioning

confidence: 99%

The feasibility of virtual reality for anatomic training during temporal bone dissection course

Timonen

Iso-Mustajärvi

Linder

et al. 2022

Front. Virtual Real.

View full text Add to dashboard Cite

Results: No differences were noted in the overall performance between the groups. However, participants with prior VR training had a lower mean time for surgical exposure of anatomical landmarks (antrum 22.09 vs. 27.64 min, p = 0.33; incus 60.00 vs. 76.00, p = 0.03; PSCC 71.83 vs. 88.50, p = 0.17) during dissection training. The participants considered VR beneficial for anatomy teaching, surgery planning, and training. Conclusion:This study demonstrated the feasibility of implementing VR training in a temporal bone dissection course. The VR training demonstrated that even short expert-guided VR sessions are beneficial, and VR training prior to the dissections has a positive effect on the time needed to perform surgical tasks while maintaining comparable performance scores.

show abstract

“…Regardless, a surgeon's younger age is not always a determinant of worse outcomes neither is older age a predictor of better care standards, and as one study reported, LOS may not correlate with surgeon experience 21 . On the other hand, while a large population‐based cohort study concluded that increasing surgeon age correlates with low rates of postoperative death, readmission, and complications, the authors conversely found that patients of younger obstetricians‐gynecologists and urologists have improved outcomes compared with those of older surgeons, lending support to our results 22 …”

Section: Discussionmentioning

confidence: 99%

Predictors of same‐day discharge after minimally invasive hysterectomy for benign indications

AlAshqar

Wildey

Yazdy

et al. 2021

Intl J Gynecology & Obste

View full text Add to dashboard Cite

Objective: To identify predictors of same-day discharge after benign minimally invasive hysterectomy. Methods:In this retrospective cohort study, we identified women (n = 1084) undergoing benign minimally invasive hysterectomy from 2009 to 2016. Multivariate logistic regression was used to examine demographic, operative, and surgeon factors associated with discharge on postoperative day 0.Results: In our study population, 238 women (22%) were discharged on the same day.Robotic hysterectomy (risk ratio [RR] 2.24; 95% confidence interval [CI] 1.13-4.44), shorter operative time (lowest quartile; RR 5.28; 95% CI 2.66-10.46), and minimal blood loss (lowest quartile; RR 3.01; 95% CI 1.68-6.23) were associated with higher same-day discharge likelihood whereas later procedure start time (2-5 pm; RR 0.38; 95% CI 0.17-0.85) and postoperative complications (RR 0.19; 95% CI 0.06-0.55) significantly decreased its likelihood. The strongest predictor was surgeon's number of years in practice, with recently graduated surgeons more likely to discharge their patients on the same day (RR 3.15; 95% CI 2.09-4.77). Conclusion:Same-day discharge after minimally invasive hysterectomy is determined by several patient, operative, and surgeon factors that can be incorporated into an implementation plan to promote earlier discharge. Most especially, scheduling patients based on perceived case complexity and targeted surgeon education can qualify a larger cohort for same-day discharge.

show abstract

Analyzing the Correlation Between Surgeon Experience and Patient Length of Hospital Stay

Abstract: Open Access Original Article

Cited by 5 publications

References 28 publications

Length of Stay Prediction With Standardized Hospital Data From Acute and Emergency Care Using a Deep Neural Network

Length of Stay Prediction With Standardized Hospital Data From Acute and Emergency Care Using a Deep Neural Network

The feasibility of virtual reality for anatomic training during temporal bone dissection course

Predictors of same‐day discharge after minimally invasive hysterectomy for benign indications

Contact Info

Product

Resources

About