Decision Support Systems. Importance of clinical decision.

Decision Support Systems
Student’s Name
Institution
Date
Introduction
Decision support is an essential element for decision makers in several industries. In the healthcare industry, clinical decision support systems play an essential role in patient care. Castaneda, et al., 2015). Several state initiatives have encouraged health care professionals to create quality health information systems that target specific health practice groups such as single physician medical practices to adopt integrated delivery networks into their systems. With such efforts, this has resulted in the development of interoperable and longitudinal health records for all patients and therefore, fostered high-quality care (Fromherz, 2013).
Intelligent decision support systems through the assessment of huge patient data with creative and knowledge-based techniques, allow healthcare professionals in acquiring information rapidly and also process it in several ways that will enhance accurate diagnosis and treatment decisions for the patients (Fromherz, 2013).
These decision support system models can, therefore, be applied in healthcare in the analysis of real-time data from numerous monitoring devices. The intelligent decision support system can also monitor and determine common elements and trends in recording medical data in databases, and also the evaluation of patient histories before and during the diagnosis (Bonney, 2011).
The paper will highlight how the hybrid model combines with concept associate to data mining and artificial neural networks, and the manner that they can be applied to patient data for intelligent decision support in healthcare. The paper will also indicate the importance of clinical decision support systems in healthcare and also some of the risks associated with using these systems. Additionally, the IDSS model will also be included.
Importance of clinical decision support systems
Clinical decision support systems are important in alleviating the time demand placed on medical professionals. When the Affordable Care Act was introduced, forty-six percent of emergency medicine health professionals have observed a huge rise in the number of emergency care patients (Chaudhry, 2008). CDSS are also important in accounting for the ever-changing pharmaceutical rules and interactions and also the increasing number of sub-specialty physicians that interact with patients.
CDSS is vital in changing the economic efficiency of the care pieces through modifying the resources necessary for patient care or by altering the number of patients care for with the same level of resources available (Fromherz, 2013). The benefits of this efficiency can accrue to the healthcare institution, and therefore the implementation of the CDSS would be observed in other departments of the enterprise.
Clinical decision support systems do not replace the knowledge, and the judgment of the medical provider, however, it complements their skills and enhances the quality of care provided (Castaneda et al., 2015). Through the use of IDDS by medical professionals, this helps in reducing the incidences of preventable medical errors and adverse patient outcomes.
CDSS improves the rate at which the patient is diagnosed. When medical professionals can evaluate and determine the proper medication for the patient, they can order practical tests and make the required referrals which save time and can also reduce any stringent costs that may be highly unnecessary for the patient (Sittig et al., 2008). Additionally CDSS when integrated into the workflow of the health professional, it can reduce delays and risky interruptions that might harm the patient.
Risks associated with using CDDS
Bonney, (2011) stated that patient information stored in the CDSS is usually misinterpreted and misrepresented. This is partially due to irregularities in the data coding and poor techniques implemented during data extraction. Even though this support system can improve the overall quality of care and delivery to the patient, it can also introduce machine-related errors (Kaushal, Shojania, & Bates, 2003). Also, the use of poor quality data can lead to inaccurate medical prescriptions by the physicians that may affect the overall state of health of the patient.
CDSS heavily relies on good quality data repositories which promote the significance of standard data representation, storage, and extraction that can be managed within a centralized knowledge-based repository (Bonney, 2011). However, the lack of proper storage can have a huge impact on the quality of recommendations that emanate from the CDSS. Data mining algorithms require high-quality data repositories for mining information that promotes proper decision-making.
Analysis of decision support systems and associated systems
The clinical decision support system (CDSS) is a computer application that enhances and assists medical professionals in proper decision-making by providing evidence-based knowledge in association with the patient data. (Basu, Mukherjee & Archer, 2012). The CDSS when used during diagnosing patients, helps is assessing and determining the preliminary medical decisions of the physician that improve the health outcome of the patient. Early CDSS systems can be utilized in data extraction to derive any associations between the patient and their previous medical histories to predict possible future events.
The intelligent decision support system (IDSS) is provided by a particular model that helps in decision-making processes. This is achieved through the indication of intelligent mannerisms which comprise of learning and reasoning. Through such functions, it can, therefore, be successful in the implementation of a rule-based expert system, a knowledge-based model and also a neural network system (Kaushal, Shojania, & Bates, 2003). An IDSS also concentrates on the accumulation and integration of healthcare-specific domain knowledge and therefore, it can perform quick actions that entail learning and reasoning while making recommendations, on the best clinical steps that justify the most accurate patient outcomes.
An artificial neural network (ANN) is a mathematical system that stimulates the functional and structural components of biological neural networks. This model focuses on mimicking the simplistic mannerisms of the human brain and how it processes information. This system contains several inter-linked processing elements and has the capability of identifying complex data sets and mining complex data patterns (Chaudhry, 2008). Experts in ANN focus in the category of information that the model provides them to analyze and subsequently, can be used in prediction and answering any queries in new situations.
Neural networks have been utilized in modeling and non-linear problems and also for modeling large data repositories of patient information. When all medical professionals are trained to utilize these systems, it can optimize their performances as they can understand how to use medical databases and take the necessary steps in determining the best course of treatment for the patient (Fromherz, 2013). The ANN maintains the accurate classification rates and also allows the reduction in complexity in understanding these systems, for medical professionals.
Comparison between IDSS and DSS
An IDSS develops a specific domain-knowledge from raw data through identification and extraction of important patterns of information from the available data sets of an individual. Therefore, it ensures that the extracted patterns can be understood and eventually, effective for decision making (Basu, Fevrier-Thomas, & Sartipi, 2011). However, decision support systems only enable the health care professional in a healthcare context, to choose from various choices which include those with the worst possible outcome.
IDSS can also handle difficult issues through the application of domain-specific expertise in the assessment of the results in the execu...