Using kernel density estimation to model surgical procedure duration

Taaffe, Kevin; Pearce, Bryan; Ritchie, Gilbert

doi:10.1111/itor.12561

Cited by 17 publications

(6 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When training model, the features are too many to select what are contribute more for this model. So we dropped the connections that the contribution of this model is so tiny, even if drop its have no impact on the model [34]. It can reduce time consuming and study more useful features.…”

Section: Methodsmentioning

confidence: 99%

A deep learning model for fish classification base on DNA barcode

J²,

Yuan

et al. 2021

Preprint

View full text Add to dashboard Cite

Fish is one of the most extensive distributed organisms in the world, fish taxonomy is an important part of biodiversity and is also the basis of fishery resources management. However, the morphological characters are so subtle to identify and intact specimens are not available sometimes, making the research and application of morphological method laborious and time-consuming. DNA barcoding based on a fragment of the cytochrome c oxidase subunit I (COI) gene is a valuable molecular tool for species identification and biodiversity studies. In this paper, a novel deep learning classification approach that fuses Elastic Net-Stacked Autoencoder (EN-SAE) with Kernel Density Estimation (KDE), named ESK-model, is proposed bases on DNA barcode. In stage one, ESK-model preprocesses the original data from COI fragments. In stage two, EN-SAE is used to learn the deep features and obtain the outgroup score of each fish. In stage three, KDE is used to select the threshold base on the outgroup scores and classify fish from different families. The effectiveness and superiority of ESK-model have been validated by experiment on three dominant fish families and comparisons with state-of-the-art methods. Those findings confirm that the ESK-model can accurately classify fish from different family base on DNA barcode.

show abstract

Section: Methodsmentioning

confidence: 99%

A deep learning model for fish classification base on DNA barcode

J²,

Yuan

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…These estimated durations were treated as following a two-parameter log-normal distribution. Validity of this model for collection of cases at surgical suites was shown in References [ [23] , [24] , [25] , [26] ].…”

Section: Methodsmentioning

confidence: 99%

Caseload is increased by resequencing cases before and on the day of surgery at ambulatory surgery centers where initial patient recovery is in operating rooms and cleanup times are longer than typical

Wang¹,

Dexter

Zenios³

2020

Journal of Clinical Anesthesia

View full text Add to dashboard Cite

Study objective The coronavirus disease 2019 (COVID-19) pandemic impacts operating room (OR) management in regions with high prevalence (e.g., >1.0% of asymptomatic patients testing positive). Cases with aerosol producing procedures are isolated to a few ORs, initial phase I recovery of those patients is in the ORs, and multimodal environmental decontamination applied. We quantified the potential increase in productivity from also resequencing these cases among those 2 or 3 ORs. Design Computer simulation provided sample sizes requiring >100 years experimentally. Resequencing was limited to changes in the start times of surgeons' lists of cases. Setting Ambulatory surgery center or hospital outpatient department. Main results With case resequencing applied before and on the day of surgery, there were 5.6% and 5.5% more cases per OR per day for the 2 ORs and 3 ORs, respectively, both standard errors (SE) < 0.1%. Resequencing cases among ORs to start cases earlier permitted increases in the hours into which cases could be scheduled from 10.5 to 11.0 h, while assuring >90% probability of each OR finishing within the prespecified 12-h shift. Thus, the additional cases were all scheduled before the day of surgery. The greater allocated time also resulted in less overutilized time, a mean of 4.2 min per OR per day for 2 ORs (SE 0.5) and 6.3 min per OR per day for 3 ORs (SE 0.4). The benefit could be achieved while limiting application of resequencing to days when the OR with the fewest estimated hours of cases has ≤8 h. Conclusions Some ambulatory surgery ORs have unusually long OR times and/or room cleanup times (e.g., infection control efforts because of the pandemic). Resequencing cases before and on the day of surgery should be considered, because moving 1 or 2 cases occasionally has little to no cost with substantive benefit.

show abstract

“…e KDE method is one of the most popular nonparametric density estimation techniques [45]. Let X be a random variable with an absolutely continuous distribution function F. Further, let f be the corresponding density function and X 1 , .…”

Section: Kdementioning

confidence: 99%

Interval Prediction Method for Solar Radiation Based on Kernel Density Estimation and Machine Learning

Zhao

Zhang

et al. 2022

Complexity

View full text Add to dashboard Cite

Precise global solar radiation (GSR) data are indispensable to the design, planning, operation, and management of solar radiation utilization equipment. Some examples prove that the uncertainty of the prediction of solar radiation provides more value than deterministic ones in the management of power systems. This study appraises the potential of random forest (RF), V-support vector regression (V-SVR), and a resilient backpropagation artiﬁcial neural network (Rprop-ANN) for daily global solar radiation (DGSR) point prediction from average relative humidity (RHU), daily average temperature (AT), and daily sunshine duration (SD). To acquire more accurate predictions of DGSR and examine the inﬂuence of historical DGSR on the performance of point prediction models, two diﬀerent model inputs are considered: (1) three meteorological variables and (2) the lags of DGSR and three meteorological variables. Then, two interval prediction methods are developed by introducing the KDE to out-of-bag (OOB), introducing kernel density estimation (KDE) to split conformal (SC) based on the three machine learning models. The two methods for interval prediction are denoted as OOB-KDE and SC-KDE. The mean absolute error (MAE), mean relative error (MRE), and Kendall rank correlation (Kendall) are used to assess the point prediction models. The performance of interval prediction methods is evaluated by the prediction interval coverage probability (PICP), prediction interval normalized average width (PINAW), and coverage width criteria (CWC). The following conclusions are drawn from this study. First, the V-SVR model performs best with the lowest mean absolute error (MAE) of 0.016 and mean relative error (MRE) of 0.001. Second, the lags of DGSR improve the prediction accuracy by about 30%. Third, the OOB-KDE and SC-KDE methods improved the quality of the prediction interval (PI). OOB-KDE improved CWC by 81%, and SC-KDE improved CWC by 99.99%. Fourth, the best interval prediction result is obtained using the SC-KDE method using the V-SVR model. The average diﬀerence between its PICP and prediction interval nominal coverage (PINC) is only 3% of the PINC, and its PINAW is less than 0.007.

show abstract

Using kernel density estimation to model surgical procedure duration

Cited by 17 publications

References 28 publications

A deep learning model for fish classification base on DNA barcode

A deep learning model for fish classification base on DNA barcode

Caseload is increased by resequencing cases before and on the day of surgery at ambulatory surgery centers where initial patient recovery is in operating rooms and cleanup times are longer than typical

Interval Prediction Method for Solar Radiation Based on Kernel Density Estimation and Machine Learning

Contact Info

Product

Resources

About