Abstract— Now a days, to minimize patient wait delays and patientovercrowding is one of the major challenges faced by hospitals, mostly usedEffective patient queue management. Annoying waits for long periods result insubstantial human resource and time wastage and which increase the frustrationendured by patients. The total treatment time of all the patients before him isthe time that he must wait for each patient in the queue. It would be favorableand excellent if the patients could receive the most efficient treatment planand know the adumbrated waiting time through a mobile application that updatesin real time. Hence, we propose a Patient Treatment Time Prediction (PTTP)algorithm to predict the waiting time for each treatment task for a patient. Todevelop such idea, we use realistic patient data from various hospitals toobtain a patient treatment time model for each task. The treatment time foreach patient in the current queue of each task is anticipated which us based onthis large-scale, realistic dataset, similarly based on the predicted waitingtime, a Hospital Queuing- Recommendation (HQR) system is developed. HQRappraises and calls an adequate and convenient treatment plan recommended forthe patient. Realistic dataset and the requirement for real-time response,which is result of the large-scale, the PTTP algorithm and HQR system decreecompetence and low-latency response. We use an Apache Spark-based cloudimplementation to achieve the aforementioned goals. Extensive experimentationand simulation results establish the effectiveness and appropriatenessof our proposed model to recommend an effective treatment plan for patients tocurtail their wait times in hospitals.
Keywords— Apache Spark, Patient Treatment Time Prediction, RF (Random Forest)Algorithm, CART Algorithm.