5 min readClinical Decision Support Systems

Total expenditure in the global healthcare market is expected to reach over $5 trillion in 2010. A significant amount of this expenditure will go towards technology that has been developed to provide support to healthcare delivery professionals.
The development of efficient, useful, and practical clinical decision support systems (CDSS) has become a significant focus in the vendor market. However, the creation of such systems requires immense financial and intellectual investment.

The primary source of support needed is in the clinical domain. With the development of the electronic medical record, the maintenance of patient information has been simplified. EMRs provide information support to the clinician, allowing a longitudinal source of information regarding patient history, previous encounter history, drug allergies, and other relevant information.

The development of an effective clinical information system will help place healthcare organizations in an advantageous position relative to their competitors. The artificial intelligence used in CDSS focuses on case-based reasoning techniques for the estimation of medical outcomes. These systems are designed with a view to help medical and nursing personnel to assess patient status, assist in making a diagnosis, and facilitate the selection of a course of therapy. The initial prototype provided information on the closest-matching patient cases to the newest patient admission results. However, the systems have been re-designed for ever increasing healthcare demands.
Advantages and Benefits
The benefits of a CDSS are evident in terms of the reduction of medical error, the standardization of diagnosis protocol, knowledge sharing, cost control, quality control, and decision support. The number of deaths caused by medical error has been estimated to be over 1, 000, 000 per year. Having an effective CDSS will significantly reduce this number.

The ability for medical practitioners to share, update and extract information for their specific usage needs is a key factor in the development of a decision support solution. A significant contributor to the creation of a universal information sharing is the development of SNOMED. Furthermore, privacy is maintained through the use of authorization privileges, allowing best practice methodologies for cost management and quality control across sites which are integral to the business operations.

One of the key challenges that vendors have encountered is a lack of knowledge around CDSS benefits. In order to ensure successful integration, organizations must ensure that the key players, mainly the physicians, are informed. Clinical decision support software offers the possibility to improve the quality of medical decisions at the time and place that these decisions are made.

The development of an effective clinical decision support system will have a significant impact on practice methodology. The advent of such a system will provide a guideline through which the physicians can model their decisions.  Furthermore, the clinical decision support system can lead to a reduction of the practice pattern variation that plagues the healthcare delivery process. The dynamic environment surrounding patient diagnosing complicates the process of diagnosis due to the numerous variables in play, such as individual patient circumstances, the location, time and physician’s previous experiences. A clinical decision support system aims to reduce the effects of these variables.

The Six Levels of Clinical Decision Support include:

  • Alerting
  • Interpreting
  • Critiquing
  • Assisting
  • Diagnosing  
  • Managing

It is difficult to have a CDSS with all of these levels. Diagnosis is difficult to represent in an algorithmic model, as the diagnosing process requires knowledge of diseases in general, an understanding of symptoms, drug-drug interactions and patient history. The permutation and combination of illness in individual patients can also vary, leading to potential misdiagnosis.

It is therefore imperative that the diagnosing systems provide reasoning for the medical diagnosis for query comparison. Clinical decision support systems have evolved from a foundation based upon statistical algorithms to complex artificial neural networks. The early decision support systems, also termed medical diagnostic decision systems, were based on Bayesian statistical theory, providing crude probability diagnoses based on certain critical variables. However, the complexity of the healthcare environment required significant adaptations in order to maintain legitimate diagnoses. Clinicians do not combine clinical data using probability used by the computer, but use case specific knowledge and heuristics based on their experience. Hence earlier systems that attempted to replace the clinician were largely unsuccessful.  
Previous decision support systems have utilized the Arden syntax in conjunction with HL7 standards and medical logic modules to create decision systems, ranging from single decision models to complex, sequenced decision models.  Each medical logic module contains, within itself, the ability to make one single medical decision based on data entry. However, through the sequencing of various medical logic modules, fairly complex models are now being created. The neural network is able to accept numerous input variables, including demographic information, admission information, previous diagnosis information, and patient history to rapidly create possible diagnoses.  Rather than provide a single diagnosis for a specific patient, the system returns a set of possible diagnoses from which the clinician may choose based on their own discretion. Advanced systems are able to return probability estimates of the likeliness of a particular diagnosis.

Clinical practice guidelines that define which steps are necessary in order to ensure quality care provision can be separated into decisions, actions, and processes. The decision model includes selection of which variables to consider and at what weights, selection of diagnosis, and consideration of alternative diagnoses. By utilizing such a flexible system, the patient and the physician become the chooser in the environment, being able to control what information is relevant and which result to act upon. The action model specifies which actions need to be performed and the process model organizes actions sequentially and hierarchically in order to determine which actions are crucial to the care process and in what order the care should be delivered.  

With the increasing number of vendors producing such systems, there is increasing variability in their quality. This is a cause for concern, as a simple mistake in a clinical decision support can lead to the loss of a life. Hence the need for enhanced oversight and regulation is needed. The FDA has regulated that CDSS are similar to medical devices. However the legal responsibility for the treatment and advice given to the patient will rest with the clinician regardless of whether he or she was assisted by the CDSS.

The Current Product Mix
The current solutions available in the market are mostly departmental. They have exclusive data repositories of images and data sheets. The types of vendors in the market are standalone CDS vendors and specific databases that are spin-offs from universities, which act as decision support systems. These software applications are easily available, with integration alongside advanced visualization tools like 3D and CAD. The pricing model is generally an annual licensing fee according to the number of users.

Many PACS vendors are now looking at integrating CDS capabilities in their packages. This could lead to additional cost benefits and effective clinical management. The other modes of subscribing to these CDS facilities are via URL links and plug-ins.

Frost & Sullivan believes that there is a trend towards increased dependence on clinical decision support systems by physicians. Constant contact with such systems will ensure that the most optimal level of care is provided, utilizing both physician judgment and technological innovativeness. Such a future will mean that physicians and other healthcare providers will have to change the way they collect, sort, and use healthcare data.  

There are many benefits to such systems as well as barriers to their use. It is extremely important for physicians, caregivers, staff, administrators, and technical experts to work in collaboration in the design, implementation, and improvement of decision support systems. New systems are changing the ways physicians think and behave. Failure to accept these systems among physicians occurs when implementation does not provide direct benefits to their users and the process of implementation itself changes the traditional practices of the clinical environment.

Frost & Sullivan anticipates that current trends in healthcare are not only towards increased expenditure but also an accelerated acceptance of healthcare information technology. There is a growing need for innovative and dependable clinical information systems with decision support capabilities. The acceptance of these systems currently depends on the culture at specific hospitals and the involvement of physicians. The involvement of all healthcare professionals, especially physicians, in the selection and implementation of the system from the outset is therefore essential. Not only will this ensure support, but will increase levels of communication. In turn, this frequent consultation and communication is likely to better the quality of patient care as well as the patient-physician relationship. Healthcare organizations must anticipate and be prepared to handle a diverse array of changes that will occur as technology advances in clinical decision support systems.

Healthcare IT

Leave a Reply

© Mindzilla. All rights reserved.

Support & share this article: