Clinic Decision Support Systems

Clinic Decision Support System (CDSS) is a category of health information systems designed to improve clinical decision making in healthcare. At the current point for the health system, Klink Support Systems play the role of supporting the physician.

There are different techniques and tools for Big Data analytics in healthcare field, the analytics of data support the clinical decision by providing information that healthcare personnel can use to improve treatment and deliver the best care. CDSS are providing healthcare individuals with knowledge, this knowledge needs to be perfect, for that it is very important to understand the data collected in the healthcare field, and that can only be realised by using efficient tools

A Brief History

Decision support systems entered the literature in the 1960s. Since then, they have gained an increased importance with the development of technology and internet. These systems have facilitated the decision-making processes of managers in many areas ranging from education, health, finance to defense. Today, they have become much more capable thanks to the dramatic increase in digital data and artificial learning technologies. One of the areas where human mistake is irreversible and costly is the health sector.

In Todays Healhcare Systems, many patients address laboratory services directly without a doctor's referral. This causes the problem of interpretation of laboratory test results by the patients who don’t havea proper medical background .So the patients require that the laboratory services provide not only the results of the tests but also their interpretations. anaplatform Automated decision support systems have proved their efficiency for doctors can be a good solution for this problem.The experience of development and implementation of decision support systems for doctors [7-10]showsthe efficiency of such solutions for the doctors,however, developers face problems when it comes to the decision support for patients. They require different approach in data presentation and interpretation.

Challanges

The challenge is to use a suitable Data integration service that will allow the combination of data collected from various sources and provide one unified service to the users, that is dataPlatform.

Problems Encountered in Clinical Decision Support Systems

• Software editing errors due to the complexity of clinical processes
• Problems and duplicate data due to not storing data in digital environment
• Failure to provide full integration with other systems that will provide data support to KKDS
• The system is difficult to use
• Resistance of healthcare workers to use the system
• Decreased self-confidence of the system by producing false results from time to time
• High investment, maintenance and training costs
• The system loses its importance after a while due to its inflexibility

How we can apply big data analytics in healthcare for Clinical Decision Support Systems?

The goal of this service is to provide of a decision support system for the patients of a laboratory service. To achieve this goal we have developed a decision support system that solves a classification problem and defines the following parameters based on the results of laboratory tests:

• Diagnosis (group of diagnoses)
• Recommendations to run other laboratory tests
• Recommendation to refer to a specialist doctor

Our developed decision support system has two main use cases: knowledge acquisition and decision support. Knowledge acquisition mode allows defining inference rules, which are complex objects and each of them addsits element to the resulting inference.The knowledge is defined by associatingtest resultsand its reference value to a set of diagnosis[17]. In the decision support mode,the system generates recommendations applying a set of knowledge and rules to the facts that are derived form a LIS data base.

Benefits Of Clinical Decision Support System

• Reduction in misdiagnoses: Misdiagnosis presents an enormous issue as the illness can’t be enough treated until it is precisely recognized. The utilization of clinical decision support tools can incredibly reduce these types of errors and results in better health outcomes for patients.
• Reduction in medication errors: Clinical Decision Support gives doctors quick access to dosing calculators, drug monographs, weights, diseases, etc. This makes it significantly more likely that the proper drug at the right portion will be given the first time.
• Readily available information in one place: the ability to have this information readily available to a provider and the entire care team working on a patient’s case increases the efficiency of this task. By turning to CDS, clinicians can be confident that they are always receiving consistent, reliable information that is relevant to their specific patient. The information provided helps them in making an accurate diagnosis, all without having to spend a great deal of time on research.
• Improve efficiency:
making a diagnosis, and deciding on a treatment plan can often be a complex one. This task requires a great deal of thought and, in some particularly complex cases, time. Additionally, when mistakes in diagnosis are made, valuable time and resources are wasted.
• Cost-Effective System: The CDSS can be cost-effective for health systems through clinical interventions by reducing the inpatient length of stay and reducing test duplication. CDSS can notify the user of cheaper alternatives to drugs, or conditions that insurance companies will cover.

Knowledge-based CDSS:

Consists of three basic components: A knowledge base, inferences rules and communication mechanism. It is based on IF-Then logic (IF medicine A is taken, and medicine B is taken too, THEN the user will get an alert).

Non-knowledge based CDSS:

This a system that does not have a knowledge base, instead it is based on AI, which means that the computer machine learns from prior experiences to detect patterns in clinical Data.

Medical Data Visualization

Data visualization is considered as the most efficient way to improve the process of data, it is based on the use of the skills that human possesses to aid in the deal with complex and massive data. Data visualization allows the illustration of data’s relations using images and graphs, which means a well understanding of information. Since the data is raising with accelerated pace, it is very important to use tools that facilitate the management of data to obtain the valued and needed information.

Hospitals data, patient records, insurance data, and other types of data are immersing today's healthcare organizations. There are various tools to analyse the huge amount of data and improve the healthcare field performance. Visual analytics is considered as one of the most efficient tools that ameliorate the understanding of data and help in decision making.

Examples From the World

• A hospital in Alabama/USA decreased its sepsis mortality rates by 53% after implementing a computerized surveillance algorithm. Real-time analytics alerted providers to new diagnoses of sepsis or worsening vital signs and provided reminders about best practices for treating patients with the deadly condition.
• Mayo Clinic employs a CDS tool that helps nurses deliver complete and accurate phone screenings of patients seeking advice or appointments. The computerized decision software guides triage nurses through a series of standardized questions based on current care guidelines so that they do not miss important information about the patient’s health.
• At a Department of Veterans Affairs site in Indiana/USA, clinical decision support tools geared towards reducing unnecessary lab utilization helped decrease total test volume by 11.18% per year, generating cost savings of more than $150,000 without impacting care quality.

Problems in Outpatient Services

A common problem in outpatient practices is absenteeism and late cancellations. As a result:

• Drop in productivity as the registrar now has to spend time rescheduling patients
• Decrease in practice revenue as provider loses billable time
• Other patients who had to wait longer for available appointments