An RFID and Algorithmic Based Approach for Patient Experience Management System (PEMS)

Abstract

Patient experience is a multi-dimensional construct encompassing a number of elements

of care. The most common areas covering the patient experience are appointment schedul- ing, waiting times, long queues, attitude and courtesy of staff, provision of lab reports,

cleanliness of environment, information assistance by nurses and treatment by doctors. The feedback given by patients identifies the weaknesses and strengths of what happened

in these areas. The quality of hospital services is frequently measured using patient feed- back ratings. Patient responses are mostly captured by manual paper-based surveys with

questionnaires and face-to-face interviews. The conclusion-drawing process takes a long

time with these methods. There are no automated ways for monitoring patient satisfac- tion in broad-spectrum. There are a slew of other concerns with performing these man- ual surveys, like entering massive volumes of data, no real-time patient tracking, late

survey responses, and delays in improvements, to name a few. Furthermore, the assess- ment process can only begin once all of the data has been obtained, delaying reaction to

concerns that require immediate attention.

This work introduces a novel framework that combines the outputs from Radio Fre- quency Identification (RFID) technology, the automated outpatient feedback survey form,

Hospital Management Information System (HMIS) to develop an automated patient ex- perience management system (PEMS) using Genetic algorithm (GA). The data is collected

by deploying RFID machines at three stations (registration, vitals, doctor). The patient scan their RFID tag at each stations machine which saves their time and location. After the patient is seen by the doctor an electronic form on tablet is given to the patient. The output from the automated survey are the ratings about each service of various stations and an overall satisfaction index (OSI), which is the overall experience (in the form of a number) a patient has during their stay in the hospital. HMIS has details regarding

the structure of the hospital; this includes details about doctors, nurses, rooms and lo- cation of various departments. The collected data (timing information, survey data) is

given as input to GA that generates the optimized weights which are then applied to the final PEMS to automatically produce/generates the patient experience index for all the patients visiting the hospital without getting manual feedback in the future. The experiments are performed using the developed tool, in a local hospital and the results

demonstrate the accuracy of 80%. This accuracy gives a good indication to hospital man- agement to take measures against areas in real time, where the patient experience is

going relatively low. Another important concern which increases the frustration level of patients is the wait time associated with different stations. The system also reduces the wait time of doctors and patients by introducing a data-driven scheduling algorithm. The data is modelled

using different probability distributions, then K-means clustering is applied which cate- gories the patients into different categorise. The treatment time is given to the patient as

per their specified category. Then doctors scheduling algorithm is applied to reduce the waiting time by using different set-up times. The system provides solution to the hospital management as a trade-off graph between doctor and patient waiting times. The results help the management to select the waiting times of doctors and patients, that how much

i

time they want a doctor or patient to wait depending on the overcrowding situation. The average patient waiting time at the doctor’s station calculated through proposed DDSA

is less than ten minutes. The proposed framework has reduced the time taken by man- ual statistics, by automating the complete interaction of patient and hospital staff at all

stations. The system is helpful for the hospital management in case of congestion, as the patient does not need to interact with the staff every time. Patients scan their RFID card at each station which saves their time and location. The proposed system is helpful for hospital management especially in the case of congestion and limited staff, patient flow can be monitored. The system is also very helpful in maintaining social distancing in case of viral diseases like (SARS, COVID) as each patient has their own card. They do not need

to stand in queues and interact with other patients while waiting. The developed frame- work can help hospitals to quantitatively measure patient experience so that hospitals

can deliver better healthcare services that increases the profitability.