Real-Time Prediction of Waiting Time in the Emergency Department, Using Quantile Regression

Sun, Yan; Teow, Kiok Liang; Heng, Bee Hoon; Ooi, Chee Kheong; Tay, Seow Yian

doi:10.1016/j.annemergmed.2012.03.011

Cited by 79 publications

(67 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Forecasting any health outcome on the outer arms of a conditional distribution, however, is unusual [15], and appears not to have been done in the analysis of daily time series data related to mortality. This is unfortunate, because there are things to be learned from forecasts made at, for instance, the 90 th percentile that could not be learned from forecasting the expected number of daily deaths.…”

Section: Discussionmentioning

confidence: 99%

“…There is the simple scientific interest in our capacity to make such forecasts, and what insights it might provide into the data; but there is also potential value for forecasting likely resource needs, as well as in areas such as syndromic surveillance, where the number of events exceeding a threshold is used to trigger a health systems response. Quantile regression remains a relatively unusual modelling technique in health research, which can be used to model conditional responses at any quantile of interest; and – although it has been used (rarely) for forecasting [14,15] – to our knowledge has never been used to forecast mortality.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The Use of Quantile Regression to Forecast Higher Than Expected Respiratory Deaths in a Daily Time Series: A Study of New York City Data 1987-2000

Soyiri

Reidpath

2013

PLoS ONE

View full text Add to dashboard Cite

Forecasting higher than expected numbers of health events provides potentially valuable insights in its own right, and may contribute to health services management and syndromic surveillance. This study investigates the use of quantile regression to predict higher than expected respiratory deaths.Data taken from 70,830 deaths occurring in New York were used. Temporal, weather and air quality measures were fitted using quantile regression at the 90th-percentile with half the data (in-sample). Four QR models were fitted: an unconditional model predicting the 90th-percentile of deaths (Model 1), a seasonal / temporal (Model 2), a seasonal, temporal plus lags of weather and air quality (Model 3), and a seasonal, temporal model with 7-day moving averages of weather and air quality. Models were cross-validated with the out of sample data. Performance was measured as proportionate reduction in weighted sum of absolute deviations by a conditional, over unconditional models; i.e., the coefficient of determination (R1).The coefficient of determination showed an improvement over the unconditional model between 0.16 and 0.19. The greatest improvement in predictive and forecasting accuracy of daily mortality was associated with the inclusion of seasonal and temporal predictors (Model 2). No gains were made in the predictive models with the addition of weather and air quality predictors (Models 3 and 4). However, forecasting models that included weather and air quality predictors performed slightly better than the seasonal and temporal model alone (i.e., Model 3 > Model 4 > Model 2)This study provided a new approach to predict higher than expected numbers of respiratory related-deaths. The approach, while promising, has limitations and should be treated at this stage as a proof of concept.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

The Use of Quantile Regression to Forecast Higher Than Expected Respiratory Deaths in a Daily Time Series: A Study of New York City Data 1987-2000

Soyiri

Reidpath

2013

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…Examples include: linear regression based on the current time and mean wait time of the last three and last five patients seen immediately prior (yielding regression R 2 ¼ 0.27) [13]; predicting wait time based on patient acuity category, patient queue sizes, and flow rates (resulting in an 11.9-minute prediction error median) [14].…”

Section: Introductionmentioning

confidence: 99%

Can We Predict Patient Wait Time?

Pianykh

Rosenthal

2015

Journal of the American College of Radiology

View full text Add to dashboard Cite

“…Many studies indicate that patient satisfaction is signi cantly negatively correlated with waiting time [2−8]. A well-functioning hospital ideally should not keep patients waiting too long for appointment and consultation [9,10]. Waiting time in outpatient clinics is recognized as one of the main issues in outpatient healthcare worldwide [9].…”

Section: Introductionmentioning

confidence: 99%

Artificial Intelligence-Assisted Reduction in Patients’ Waiting Time for Outpatient Procedures: A Matched Case–Control Study

Tian

et al. 2020

Preprint

View full text Add to dashboard Cite

Background: Many studies indicate that patient satisfaction is significantly negatively correlated with waiting time. A well-designed healthcare system should not keep patients waiting too long for appointment and consultation. However, in China, patients spend considerable time waiting, and the actual time spent on diagnosis and treatment in the consulting room is comparatively less.Methods: We developed an artificial intelligence (AI)-assisted module that is embedded in hospital information systems. Through its use, outpatients were automatically recommended an imaging examination or a laboratory test based on their symptoms and chief complaint. Thus, they could get examined or tested before they went to see the doctor. People who saw a doctor in the traditional way were assigned to the conventional group, and those who used the AI-assisted system were assigned to the AI-assisted group. We conducted a 1:1 case–control study that applied propensity score matching to pair the data from patients in a pediatric tertiary hospital between August 1, 2019 and January 31, 2020. Waiting time was defined as the time from registration to preparation for a laboratory test or an imaging examination. The total cost included the registration fee, test fee, examination fee, and drug fee. The Wilcoxon rank-sum test was used to compare the differences in time and cost between the AI-assisted group and the conventional group. The statistical significance level was set at 0.05 for two sides.Results: A total of 12,342 visits were recruited for this study, consisting of 6,171 visits in the conventional group and 6,171 visits in the AI-assisted group. The median waiting time was 0.38 (inter-quartile range: 0.20, 1.33) hours for the AI-assisted group compared with 1.97 (0.76, 3.48) hours for the conventional group (p < 0.05).Conclusions: Using AI can significantly reduce the waiting time of patients for outpatient procedures, and thus, enhance the outpatient process of hospitals.

show abstract

Real-Time Prediction of Waiting Time in the Emergency Department, Using Quantile Regression

Cited by 79 publications

References 21 publications

The Use of Quantile Regression to Forecast Higher Than Expected Respiratory Deaths in a Daily Time Series: A Study of New York City Data 1987-2000

The Use of Quantile Regression to Forecast Higher Than Expected Respiratory Deaths in a Daily Time Series: A Study of New York City Data 1987-2000

Can We Predict Patient Wait Time?

Artificial Intelligence-Assisted Reduction in Patients’ Waiting Time for Outpatient Procedures: A Matched Case–Control Study

Contact Info

Product

Resources

About