Computerized clinical decision support systems (CDSS) were firstly used in the 1980s. Since then, they evolved rapidly to coordinate electronic medical records and support clinicians in making better decisions. Now CDSS usage is a part of a paradigm shift in the U.S. healthcare industry.
Clinical Decision Support Systems
The common use of CDSS is enhanced by the increasing adoption of electronic data in healthcare. They are presently integrated into EHR, (electronic health records), or used through web-applications.
Besides data coordination, they provide some other capabilities for medical decision support. Thus, individual patient medical records are matched to the clinical database, various assessments, guidelines, and researches related to the medical conditions. CDSS capability to utilize all available data allows clinicians to notice details which otherwise may remain unnoticed or unobtained.
Though CDSS may be classified into various types, they are frequently subdivided into knowledge-based (where IF-THEN rules are set by experts) and non-knowledge-based (based on machine learning rather than rules programmed by humans). Both types require data sources for analyzing the data and producing recommendations or other outputs. Non-knowledge-based are less common yet, though they are a perfect example of the growing use of artificial intelligence in healthcare. Though AI and machine learning are quite promising, many practitioners have concerns about the logic AI uses to create recommendations.
Clinical Decision Support Tools
Contemporary CDSS provide a vast scope of functions, including alerts, documentation management (forms and templates), drug control, diagnostics (patient data reports), clinical workflows (guidelines and protocols), and much more. Depending on the desired function (or their combination), medical providers may adopt various clinical decision support tools into their practice.
Alarm systems
Probably, the most common CDSS tool. Alerts pop up to notify the clinicians, warn or remind. It is an example of how CDSS target and enhance patient safety. Alarms warn about harmful drug combinations, dosing errors, or prevent clinicians from prescribing drugs to which the patient may be allergic. They also remind about medical events (such as annual check-ups) or measurements the nurses have to take regularly. Thus, CDSS tools reminded nurses about blood glucose measurements considering patient health data and treatment protocols. It resulted in a lower number of hypoglycemia events in the ICU.
Administrative function
Adoption of new guidelines and protocols is easier when utilizing clinical decision tools. The problem here is that the implementation of a new rule requires clinical adherence, which is not always sufficient. CDSS tools may take various forms, such as order sets and standardized templates so that clinicians enter required data or prescribe evidence-based drugs. That ensures documentation accuracy, and accurate medical records result in more tailored treatment protocols. For example, in a study conducted in 2010, CDSS tools were adopted to ensure the patients with removed spleen are properly vaccinated. The authors found that splenectomy was not documented on the patient problem lists of 71 percent of patients. A new CDSS tool was developed to improve documentation accuracy.
Diagnostics
CDSS tools for diagnostics are not as widespread as other tools, often because of the negative attitude and bias which practitioners have toward them. Diagnosis accuracy is also a weak point, though it is often associated with poor data (or lack of it). IT development resulting in better machine learning algorithms is believed to open the way to a more accurate diagnosis made by CDSS.
Interactions with patients
Patients may be end-users of CDSS as well as clinicians. CDSS tools help medical providers to adopt standards of patient-focused care and make the care patient-specific rather than condition-specific. CDSS helps to eliminate the information barrier which patients often experience when treating their conditions. Through CDSS tools, patients have the opportunity to communicate with their physicians and receive evidence-based information related to their illness. Patients make better life choices, provide their health information through tailored templates, and forms (symptom tracking), which is then transmitted to their physicians.
Though CDSS benefits are obvious, there are several pitfalls, such as alert fatigue (excessive or unimportant alerts), difficulties with the integration, (high cost, programming complexity, and the possibility of clinical workflow disruptions), transportability in (dealing with various clinical data sources simultaneously). CDSS effectiveness depends on the computer literacy of the users, data sources quality, and source arrangement.
Solve.Care is at the forefront of advanced CDSS, providing solutions for most of the pitfalls clinicians may experience during CDSS integration. “The healthcare industry is divided into three separate pillars: administrative, clinical, and financial. Solve.Care aims to address all three of these pillars,” Pradeep Goel, CEO of Solve.Care, said. “We want to solve interoperability challenges by making processes more effective, especially with more administrative bureaucracies that do not communicate efficiently. We offer specific solutions for each sector and for every stakeholder in healthcare. From government agencies to insurance companies, and everyday users, our unique solution gives everyone a level playing field by decentralizing healthcare and putting patients back in the center of healthcare delivery, while also providing a common platform to administer it”.
Healthcare Decision Support
The U.S. Health and Medicare rules financially incentivize CDSS integration. Thus, in 2013, 41 percent of hospitals having an EHR had a CDSS installed. Modern CDSS can be built in various devices often simultaneously such as computers, tablets, smartphones, health trackers, etc. This allows all parties to coordinate data with each other and use the data effectively to enhance the process of decision-making. Technology development and improvement of database management will lead to more effective use of a decision support system in healthcare industry, more accurate diagnosis and patient-specific treatment.
