Health care organisations must now understand the problems of assessing health care quality and establishing programmes to improve it. The literature covers quality and performance measures in primary, quaternary, public health, and voluntary healthcare. Due to healthcare expansion, reaction time, security, and data volume, latency has become an issue. This systematic study examines fog-based healthcare system approaches. IoT, cloud, and fog computing have created many medical care platforms. Thus, an internet of things and fog computing-based diabetes monitoring system was created to aid diagnosis and prediction. The fog computing-based diabetes monitoring and prediction system includes logistic regression and a decision tree. ML methods can identify if the patient has diabetes. Diabetic patients apply the Donabedian method to improve healthcare quality. This chapter explores, classifies, discusses, and proposes a way to improve Donabedian model, analyses and critique current healthcare metrics, indicators, quality and safety measures, and challenges in measuring health care systems.
Top1. Introduction
Healthcare is one of the prominent application areas which require real-time and understandable results and the adoption of fog computing to this sector has resulted to a good influence. IoT is rapidly evolving into the healthcare area and it strives to bring simplicity for patients. In the context of rising healthcare expenditures, quality and performance measurement are increasingly integral to accountability which included business planning, annual reporting and contracting. But, recently the accountability has emphasized the achievement of Quality and Performance Measures in Health Care Systems effectively and efficiently. Although the evaluating the health-care sector is difficult and time-consuming, still, it is more common and important to measure the performance of healthcare institutions and society at large. It is difficult for most organizations to assess the quality of anything. Long waiting times (WTs), inefficiency, dissatisfied patients, and burnout among health care workers (HCWs) can all contribute to poor performance. Furthermore, data and accurate information are essential for achieving measurable health improvements. All of these challenges have been met by the healthcare industry by determining quality by measuring specific outcomes of care. To achieve healthcare improvement goals, quality measures must align stakeholder priorities. They must also be evidence-based and unlikely to have negative consequences. The core measure sets should be patient-cantered and aware of socioeconomic determinants of health as a whole. Metrics should be varied, but outcomes and measures that span several aspects of quality performance should be prioritised. Health plans should think outside the box when it comes to gathering performance data (Smith, 2008).
Healthcare performance metrics are data on a specific healthcare-related activity that has been gathered, quantified, and evaluated. Their mission is to find ways to save money and expenses, improve care quality, and increase efficiency in the delivery of care. Substantial resources have been invested on quality and performance measurement system development from the policy level through front-line care delivery. However, because scientific and experiential information about quality and performance measurement spans multiple sources and disciplines, there is no easy way to identify and summarize relevant evidence. Quality Indicators are standardised, evidence-based metrics of health-care quality that may be used to monitor and track clinical performance and outcomes using easily available hospital inpatient administrative data. The measures should not place an undue burden on stakeholders or healthcare professionals. All stakeholders should benefit from the information they supply.
1.1 Background
As needed by the Health Information Technology for Economic and Clinical Health, numerous hospitals have already upgraded their software to comply with the standard. Client-server architecture, a time-honoured technology, is used in the construction of electronic health records. However, information technology has led to the development of procedures that are both more successful and more focused on the needs of patients, and cloud computing has made the process both easier and more cost-effective. Between the cloud and the physical location of the user's devices is where computing occurs in the fog. Trends in cloud computing throughout all industries, including smart homes, factories, and hospitals, for example. The application of fog computing in the creation of intelligent hospitals. A multitude of authors have designed various architectures and suggestions. Numerous researchers have gone through the studies and created a variety of designs to demonstrate the fundamental idea of fog computing in the medical field. The architecture presented fog data, which, in addition to reducing the amount of data, might also make the data more adaptable while simultaneously increasing their level of safety. Between the years 2015 and 2021, sensors based on the body, glucose, skin, and others were utilised in the healthcare industry to detect problems and warn clinicians as soon as possible. Some of these sensors have been used to transport data from healthcare devices to cloud layers for the purpose of processing the patient's health data and identifying early signs of sickness after being used in conjunction with fog computing and Internet of Things technology. Several well-known Internet of Things (IoT)-based healthcare apps are currently operating well.