Elsevier

Decision Support Systems

Volume 50, Issue 1, December 2010, Pages 222-233
Decision Support Systems

Framework, strategy and evaluation of health care processes with RFID

https://doi.org/10.1016/j.dss.2010.08.003Get rights and content

Abstract

The working environment in health care organizations is characterized by its demand for highly dynamic process and labor management in which (a) medical personnel are generally associated with several disparate types of tasks, (b) service location and service personnel change frequently, (c) highly uncertain environment where emergency issues could arise at any time, and (d) the stakes are high since invaluable human lives are involved. There is an urgent need from both researchers and health care organizations to develop reasonable management strategies for maintaining a good balance between efficient management and superior medical service quality. We discuss the potential for real-time health care coordination and effective medical process and labor management enabled by RFID item-level tracking/tracing identification technology. We explore the uniqueness of instance-level process mining and its application in health care environment. We then propose an adaptive learning framework that supports real-time health care coordination and analyze its benefits compared to traditional routine process and labor management. We find that while RFID-enabled real-time medical process and labor management provides marginal improvement for premium medical service providers, it generates appreciable improvement both in terms of efficiency and service quality for public health care institutions where availability of necessary resources such as medical staff and equipment are highly constrained.

Introduction

The number of preventable patient safety incidents and/or medical errors such as wrong drug item and/or quantity, transfusion using the wrong blood bag, mislabeled blood sample, among others, is on the rise as budget cuts in health care institutions and pharmaceutical industry translate to related adverse effects. RFID tags are touted to be primary contenders among the technologies used to address this issue. IDTech (2008) predicts the market for RFID tags and associated systems and services in health care to rise from $120.9 million in 2008 to $2.03 billion in 2018.

RFID tag use in health care and pharmaceutical industries has seen phenomenal growth in recent years spurred primarily through developments in tagging of drugs, real-time location and instance-level information (for items such as medical equipment, patients and medical staff), and automated error prevention. Developments in tagging of drugs are driven by the need for improved anti-counterfeiting measures, theft deterrence, and improved stock control and recalls. Real-time instance-level information, generated through RFID-tagged entities, enables the effective use of constrained resources while reducing errors due to inadvertent mismatches (e.g., mother–baby and patient–blood bag mismatch). RFID tag use in automating processes (e.g., appropriate medical record delivery) can reduce possible errors due to human input. Unlike their use in some applications (e.g., toll-payment systems), RFID use in health care and pharmaceutical industries carries with it unquantifiable benefits such as safety and security and higher tolerance for longer payback periods.

While patient privacy is a concern when using RFID tags that broadcast information without knowledge of the tagged entity, means to address such issues through cryptography has been under way for the past several years (e.g., [10], [11] and the references therein). The existence of multiple privacy frameworks including the Health Insurance Portability and Accountability Act (HIPAA), the Electronic Privacy Information Center (EPIC)'s RFID guidelines, the principles of Fair Information Practices (FIP), and the general concerns associated with the generation and use of any personally identifiable information guide the extent to which personally identifiable information can be gathered, stored, and used.

Togt, et al. [15] demonstrated that, under certain worst-case conditions when maximum power settings were used, electromagnetic interference (EMI) from RFID readers can interfere with medical devices used in critical care. Seidman et al. [13], [14] considered the Electromagnetic Compatibility (EMC) between RFID readers and several pacemakers and Implantable Cardiac Defibrillators (ICD) and report that reactions ranged from “non-clinically significant events to the potentially harmful inappropriate tachyarrhythmia detection and delivery of therapy or complete inhibition of cardiac pacing.” Standards for RF emissions such as those from the Federal Communications Commission (FCC) and European telecommunications Standards Institute (ETSI) alert medical device manufacturers of possible interference from RFID and other RF sources. The issues related to RF interference can be alleviated through appropriate technological or spatial means. Nevertheless, the beneficial aspects of RFID-generated item-level information demands serious consideration for RFID tagging entities in health care environments.

Over the years, RFID tags have been successfully incorporated at various levels in a health care setting. The recently introduced Daily RFID Silica Gel wristband tag stores medical record information in a chip rather than paper. This reusable (after high-temperature sterilization), waterproof, and heat-resistant wristband helps identify and match the correct patient and medical staff as well as provides privacy to patients through electronic records. Other examples include Siemens' use of RFID tags for marking sponges used during operations and in identification tags for the operating team itself to eliminate missing sponges that are unintentionally left inside the operated person by tracing them from storage to disposal or reduce errors due to unintended mismatches in personnel.

The health care environment is highly dynamic in its demand for real-time process and labor management where (a) medical personnel are generally associated with several disparate types of tasks, (b) service location and service personnel change frequently, (c) the environment is replete with a high level of uncertainty where emergency issues could arise at any time, and (d) the stakes are extremely high since invaluable human lives are involved. There is an urgent need from both researchers and health care organizations to develop mechanisms for maintaining a good balance between efficient management and superior medical service quality within such a high stress work environment.

RFID tag applications, despite their potential in health care industry and their unique applications, have not been extensively studied in this area. Their benefits including both tangible and intangible pay-offs and possible application mechanisms are generally not widely known in many business sectors (e.g., [16], [19]). We consider the uniqueness of RFID, such as their ability to provide instantaneous item-level information [18] in health care environments and propose an adaptive learning framework to utilize this technology to facilitate human resource management decisions.

While existing research addresses some of the issues discussed above, there is a paucity of published research on improving processes in health care environments using information generated through RFID tags. Although various applications of process mining have been studied in the field of health care, we find that a majority of existing research in this field are focused at the process optimization stage. We extend this to investigate health care optimization problem from a process and labor management perspective to dynamically determine and update medical personnel assignments based on an RFID instance-level tracing/tracking system. Our proposed mechanism provides a fresh look at medical process and labor management utilizing advanced instance-level identification data to improve health care provider/patient efficiency/satisfaction.

Section snippets

Literature review

Hersh et al. [8] assess the value of electronic health care information exchange and inter-operability between providers (hospitals and medical group practices) and independent laboratories, radiology centers, pharmacies, payers, public health departments, and other providers. Their analysis indicates that savings from fully standardized inter-operability and information sharing between health care providers and other types of organizations could save billions of dollars each year.

Clinical and

Motivating examples

Consider a small clinic in which the medical staff includes two doctors, three nurses and two supporting staff. Our objective is to consider health care resource management such that certain efficiency and service quality are maintained. Assume that necessary jobs in this clinic include 10 repetitive tasks and an uncertain number of non-repetitive tasks. Each repetitive task follows a pre-determined routine with an initial learning cost and only a marginal service cost thereafter.

Health care process optimization with RFID

Process optimization has been studied extensively through various disciplines. The unique problem of process and labor management in health care domain, however, has not received necessary attention from researchers in the area. The problem of resource allocation including medical personnel is very different from process and labor management in other domains. In health care environment, employees are more likely to be simultaneously involved with multiple tasks, to handle emergency issues, and

Health care management strategies

Public health care institutions are generally characterized by their medical staff taking on multiple tasks. For example, nurses are required to simultaneously take care of several patients and get involved in different kinds of tasks such as cleaning and preparing medical equipment. In a health care institution where appointment is required, uncertainty arising from dynamic medical service requirement is reduced to minimum. In an emergency clinic, on the other hand, the variance from

Discussion

Health care process and labor management problems have unique characteristics given that they occur under highly dynamic medical environments. The primary characteristic that differentiates this scenario is the fact that human lives are at stake with every patient who walks in and every decision that is made in these work environments. Although traditional static routine-based management has its advantages and is merits, we develop an innovative mechanism based on instantaneous item-level

Wei Zhou received his Ph.D. in Information Systems from the University of Florida in 2008. He is Assistant Professor of Information Systems and Technologies and a member of the RFID European Lab at ESCP Europe. His research interests include RFID-enabled item-level information visibility, Internet advertising, and knowledge-based learning systems. His work has appeared in European Journal of Operational Research, IEEE Transactions on Geosciences and Remote Sensing, International Journal of

References (19)

There are more references available in the full text version of this article.

Cited by (48)

  • Stable heuristic miner: Applying statistical stability to discover the common patient pathways from location event logs

    2022, Intelligent Systems with Applications
    Citation Excerpt :

    Moreover, if the model was unstable, the algorithm revealed which activities were causing such instabilities. Wearable devices have shown many advantages in the healthcare sector (Corchado, Bajo, de Paz, & Tapia, 2008; Thibaud, Chi, Zhou, & Piramuthu, 2018; Zhou & Piramuthu, 2010). However, similar to most process mining applications, the proposed method here is also highly dependent on the quality, accuracy and reliability of the data.

  • Coping with stress in emergency department physicians through improved patient-flow management

    2020, Socio-Economic Planning Sciences
    Citation Excerpt :

    As the patient proceeds through the different care stages, more information about their illness is revealed and the level of uncertainty subsides. RFID item-level tracking/tracing identification technology is a very useful source of instantaneous information about all patients in the hospital [28,29], which works by recording each stage in the treatment of every patient. Several methods have been developed for assessing stress exposures and outcomes.

View all citing articles on Scopus

Wei Zhou received his Ph.D. in Information Systems from the University of Florida in 2008. He is Assistant Professor of Information Systems and Technologies and a member of the RFID European Lab at ESCP Europe. His research interests include RFID-enabled item-level information visibility, Internet advertising, and knowledge-based learning systems. His work has appeared in European Journal of Operational Research, IEEE Transactions on Geosciences and Remote Sensing, International Journal of Electronic Commerce, and Optical Engineering.

Selwyn Piramuthu is Professor of Information Systems at the University of Florida. He is a member of the RFID European Lab at ESCP Europe. His research interests include RFID systems, pattern recognition and its application in supply chain management, computer-aided manufacturing, and financial credit-risk analysis.

View full text