Application of Machine Learning Algorithms for Patient Length of Stay Prediction in Emergency Department During Hajj

Hijry, Hassan; Olawoyin, Richard

doi:10.1109/icphm49022.2020.9187055

Cited by 10 publications

(6 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In fact, many papers proposed using technology to improve health care facilities. For example, Hijry and Olawoyin used machine learning algorithms to predict the length of stay of pilgrims in the emergency department during Hajj [180]. The length of stay is an important metric to measure the quality of medical care of any hospital.…”

Section: F Health Informaticsmentioning

confidence: 99%

Solving Hajj and Umrah Challenges Using Information and Communication Technology: A Survey

Showail

2022

IEEE Access

View full text Add to dashboard Cite

Hajj and Umrah are Muslims' religious pilgrimages to Makkah, Saudi Arabia. Hajj is considered the largest annual gathering in the world. In Islam, each and every able-bodied adult is obligated to go for Hajj at least once in his/her lifetime. Hajj takes place between the 8 th and the 13 th day of Dhul Hijjah, which is the last month of the Islamic year while Umrah, the minor pilgrimage, could be done any time of the year. In Hajj, pilgrims, also known as Hajjis, travel around 15 km and pilgrims have the choice to do it by foot, bus or by train. The Hajj journey starts from Mina, which is considered the largest tent city in the world because it hosts more than 10,000 fire resistant tents, and includes various religious rituals. Around 3 million Muslims from more than 183 countries make Hajj every year and the Kingdom of Saudi Arabia is working on increasing this number. Since 1989, researchers in various ICT domains have tried leveraging their expertise in solving challenges and issues related to Hajj and Umrah. Although several papers have surveyed efforts using technology in Hajj and Umrah research, none of them was comprehensive. In this paper, I classified research efforts that used information and communication technologies for solving Hajj and Umrah challenges over the past 33 years based on their applications in 10 categories. I also identified more than 30 technologies used by researchers all over the world to address Hajj and Umrah issues and group research efforts based on these technologies for ease of access. Furthermore, open challenges were discussed and new technologies that could be used to address these challenges were proposed.

show abstract

Section: F Health Informaticsmentioning

confidence: 99%

Solving Hajj and Umrah Challenges Using Information and Communication Technology: A Survey

Showail

2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The prediction value of the leave node is the average of those LOS, which is 33 and accounts for 22 deviations. Due to the hard prediction for small and large LOS, some studies have avoided the problem by regarding the regression task as a classification task such as prolonged LOS (≥ 14) or short LOS (< 14) [44,45], which has poorer practicability than the regression task. Consequently, these problems still await a direct solution and deserve further exploration.…”

Section: Error Analysismentioning

confidence: 99%

Network analytics and machine learning for predicting length of stay in elderly patients with chronic diseases at point of admission

Qiu

Wang

et al. 2022

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Background An aging population with a burden of chronic diseases puts increasing pressure on health care systems. Early prediction of the hospital length of stay (LOS) can be useful in optimizing the allocation of medical resources, and improving healthcare quality. However, the data available at the point of admission (PoA) are limited, making it difficult to forecast the LOS accurately. Methods In this study, we proposed a novel approach combining network analytics and machine learning to predict the LOS in elderly patients with chronic diseases at the PoA. Two networks, including multimorbidity network (MN) and patient similarity network (PSN), were constructed and novel network features were created. Five machine learning models (eXtreme Gradient Boosting, Gradient Boosting Decision Tree, Random Forest, Linear Support Vector Machine, and Deep Neural Network) with different input feature sets were developed to compare their performance. Results The experimental results indicated that the network features can bring significant improvements to the performances of the prediction models, suggesting that the MN and PSN are useful for LOS predictions. Conclusion Our predictive framework which integrates network science with data mining can forecast the LOS effectively at the PoA and provide decision support for hospital managers, which highlights the potential value of network-based machine learning in healthcare field.

show abstract

“…The typical methodology for LOS prediction for these patient types involved the following steps: (a) recording clinical information of patients such as medication history at the time of admission, patient age, and the number of comorbidities, (b) identifying the set of predictor variables among the data available for LOS prediction, (c) training and validating the statistical learning methods on the dataset constructed via mining the available data. Examples of such studies include (Aghajani and Kargari, 2016;Baek et al, 2018;Hijry and Olawoyin, 2020), wherein the authors concluded that factors such as severity of the disease, recency of diagnosis and type of surgery, patient age, number of comorbidities, surgery type, number of days of hospitalisation before surgery, etc., were significantly correlated with patient LOS. These studies did not determine the effect of operational variables such as the number of patients in the queue for system resources, the elapsed service time of patients currently receiving care, etc., on patient LOS.…”

Section: Length Of Stay Predictionmentioning

confidence: 99%

Outpatient Diversion using Real-Time Length-of-Stay Predictions

Fatma,

Ramamohan

2021

Preprint

View full text Add to dashboard Cite

In this work, we show how real-time length-of-stay (LOS) predictions can be used to divert outpatients from their assigned facility to other facilities with lesser congestion. We illustrate the implementation of this diversion mechanism for two primary health centers (PHCs), wherein we divert patients from their assigned PHC to the other PHC based on their predicted LOSs in both facilities. We develop a discreteevent simulation model of patient flow operations at these two PHCs in an Indian district and observe significantly longer LOSs at one of the PHCs due to disparities in the patient loads across both PHCs. In this context, we first determine the expected LOS of the patient at the points in time at which they are expected to arrive at both PHCs using system state information at the PHC recorded at the current time. The real-time LOS predictions are generated by estimating patient wait times on a real-time basis at the queueing subsystems within the PHC. We then divert the patient to the appropriate PHC on the basis of the predicted LOS estimates at both PHCs, and show through simulation that the proposed framework leads to more equitable utilization of resources involved in provision of outpatient care.

show abstract

Application of Machine Learning Algorithms for Patient Length of Stay Prediction in Emergency Department During Hajj

Cited by 10 publications

References 11 publications

Solving Hajj and Umrah Challenges Using Information and Communication Technology: A Survey

Solving Hajj and Umrah Challenges Using Information and Communication Technology: A Survey

Network analytics and machine learning for predicting length of stay in elderly patients with chronic diseases at point of admission

Outpatient Diversion using Real-Time Length-of-Stay Predictions

Contact Info

Product

Resources

About