A Two-Stage Model to Predict Surgical Patients’ Lengths of Stay From an Electronic Patient Database

Kumar, Ashwani; Anjomshoa, Hamideh

doi:10.1109/jbhi.2018.2819646

Cited by 15 publications

(6 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If there is low likelihood, we predict LOS, if there is high likelihood we acknowledge we cannot do any better given the information we have. Kumar et al 27 developed a two-stage model that first predicted LOS before admission and then utilized predictors 5 days after admission. The predictors after admission improved the predictive accuracy of prolonged LOS.…”

Section: Discussionmentioning

confidence: 99%

Predicting in-hospital length of stay: a two-stage modeling approach to account for highly skewed data

Zhao

Scales

et al. 2022

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Background In the early stages of the COVID-19 pandemic our institution was interested in forecasting how long surgical patients receiving elective procedures would spend in the hospital. Initial examination of our models indicated that, due to the skewed nature of the length of stay, accurate prediction was challenging and we instead opted for a simpler classification model. In this work we perform a deeper examination of predicting in-hospital length of stay. Methods We used electronic health record data on length of stay from 42,209 elective surgeries. We compare different loss-functions (mean squared error, mean absolute error, mean relative error), algorithms (LASSO, Random Forests, multilayer perceptron) and data transformations (log and truncation). We also assess the performance of two stage hybrid classification-regression approach. Results Our results show that while it is possible to accurately predict short length of stays, predicting longer length of stay is extremely challenging. As such, we opt for a two-stage model that first classifies patients into long versus short length of stays and then a second stage that fits a regresssor among those predicted to have a short length of stay. Discussion The results indicate both the challenges and considerations necessary to applying machine-learning methods to skewed outcomes. Conclusions Two-stage models allow those developing clinical decision support tools to explicitly acknowledge where they can and cannot make accurate predictions.

show abstract

Section: Discussionmentioning

confidence: 99%

Predicting in-hospital length of stay: a two-stage modeling approach to account for highly skewed data

Zhao

Scales

et al. 2022

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

show abstract

“…Steele and Thompson [63] developed a KNN-based pLOS prediction model for general patients and achieved an AUROC of 0.847. KNN was included as the base model in our study because it has shown superior performance in pLOS prediction in existing studies [63,64]. Given that its learning mechanism is different from the learning mechanisms of the 2 other base models (SVM and RF), KNN was expected to improve the prediction performance of the stacking model in dealing with data sets with various characteristics [37,59].…”

Section: Principal Findingsmentioning

confidence: 99%

Predicting Prolonged Length of Hospital Stay for Peritoneal Dialysis–Treated Patients Using Stacked Generalization: Model Development and Validation Study

Kong¹,

Wu²,

Chu³

et al. 2021

JMIR Med Inform

View full text Add to dashboard Cite

Background The increasing number of patients treated with peritoneal dialysis (PD) and their consistently high rate of hospital admissions have placed a large burden on the health care system. Early clinical interventions and optimal management of patients at a high risk of prolonged length of stay (pLOS) may help improve the medical efficiency and prognosis of PD-treated patients. If timely clinical interventions are not provided, patients at a high risk of pLOS may face a poor prognosis and high medical expenses, which will also be a burden on hospitals. Therefore, physicians need an effective pLOS prediction model for PD-treated patients. Objective This study aimed to develop an optimal data-driven model for predicting the pLOS risk of PD-treated patients using basic admission data. Methods Patient data collected using the Hospital Quality Monitoring System (HQMS) in China were used to develop pLOS prediction models. A stacking model was constructed with support vector machine, random forest (RF), and K-nearest neighbor algorithms as its base models and traditional logistic regression (LR) as its meta-model. The meta-model used the outputs of all 3 base models as input and generated the output of the stacking model. Another LR-based pLOS prediction model was built as the benchmark model. The prediction performance of the stacking model was compared with that of its base models and the benchmark model. Five-fold cross-validation was employed to develop and validate the models. Performance measures included the Brier score, area under the receiver operating characteristic curve (AUROC), estimated calibration index (ECI), accuracy, sensitivity, specificity, and geometric mean (Gm). In addition, a calibration plot was employed to visually demonstrate the calibration power of each model. Results The final cohort extracted from the HQMS database consisted of 23,992 eligible PD-treated patients, among whom 30.3% had a pLOS (ie, longer than the average LOS, which was 16 days in our study). Among the models, the stacking model achieved the best calibration (ECI 8.691), balanced accuracy (Gm 0.690), accuracy (0.695), and specificity (0.701). Meanwhile, the stacking and RF models had the best overall performance (Brier score 0.174 for both) and discrimination (AUROC 0.757 for the stacking model and 0.756 for the RF model). Compared with the benchmark LR model, the stacking model was superior in all performance measures except sensitivity, but there was no significant difference in sensitivity between the 2 models. The 2-sided t tests revealed significant performance differences between the stacking and LR models in overall performance, discrimination, calibration, balanced accuracy, and accuracy. Conclusions This study is the first to develop data-driven pLOS prediction models for PD-treated patients using basic admission data from a national database. The results indicate the feasibility of utilizing a stacking-based pLOS prediction model for PD-treated patients. The pLOS prediction tools developed in this study have the potential to assist clinicians in identifying patients at a high risk of pLOS and to allocate resources optimally for PD-treated patients.

show abstract

“…We develop a strategy to keep a comparable level of uncertainty in the MIP model. Kumar and Anjomshoa [10] found that classification and regression tree (CART) analysis is useful for classifying patients into lower variability LoS groups. We applied CART analysis on the ICU LoS data from the partner hospital, and we classified patients into short-stay (SS), medium-stay (MS), and long-stay (LS) groups.…”

Section: Fundamental Concepts and Our Approachmentioning

confidence: 99%

A sequential stochastic mixed integer programming model for tactical master surgery scheduling

Kumar

Costa

Fackrell

et al. 2018

European Journal of Operational Research

Self Cite

View full text Add to dashboard Cite

In this paper, we develop a stochastic mixed integer programming model to optimise the tactical master surgery schedule (MSS) in order to achieve a better patient flow under downstream capacity constraints. We optimise the process over several scheduling periods and we use various sequences of randomly generated patients' length of stay scenario realisations to model the uncertainty in the process. This model has the particularity that the scenarios are chronologically sequential, not parallel. We use a very simple approach to enhance the non-anticipative feature of the model, and we empirically demonstrate that our approach is useful in achieving the desired objective. We use simulation to show that the most frequently optimal schedule is the best schedule for implementation. Furthermore, we analyse the effect of varying the penalty factor, an input parameter that decides the trade-off between the number of cancellations and occupancy level, on the patient flow process. Finally, we develop a robust MSS to maximise the utilisation level while keeping the number of cancellations within acceptable limits.

show abstract

A Two-Stage Model to Predict Surgical Patients’ Lengths of Stay From an Electronic Patient Database

Cited by 15 publications

References 16 publications

Predicting in-hospital length of stay: a two-stage modeling approach to account for highly skewed data

Predicting in-hospital length of stay: a two-stage modeling approach to account for highly skewed data

Predicting Prolonged Length of Hospital Stay for Peritoneal Dialysis–Treated Patients Using Stacked Generalization: Model Development and Validation Study

A sequential stochastic mixed integer programming model for tactical master surgery scheduling

Contact Info

Product

Resources

About