Practical Guide How to Implement Clinical Decision Support in European Union (EU)

Get an overview of clinical decision support systems (CDSSs): benefits, clinical content, risks, and medical device regulation (MDR) related compliance. Case study

What is clinical decision support (CDS)?

Clinical decision support (CDS) is a health information technology application to improve clinical decision-making and patient outcomes.

Clinical decision support systems (CDSSs) provide clinicians, patients, or other stakeholders with knowledge and person-specific information, smartly filtered, or presented at appropriate times, to enhance health and health care.

Clinical decision support systems improve decision-making in the clinical workflow providing:

  • Computerized alerts and reminders for providers and patients
  • Clinical guidelines
  • Condition-specific order sets
  • Focused patient data reports and summaries
  • Documentation templates
  • Diagnostic support
  • Contextually relevant reference information

These functionalities can be used either as integrated service to electronic health records (EHR), pharmacy point-of-sale (POS) systems, national health information systems (HIS), patient-oriented personal health records (PHR), or as point of care (POC) reference databases on a variety of platforms (e.g., mobile, cloud-based).

The CDS Five Rights concept states that to provide benefits, CDS tools must provide:

  • the correct information (evidence-based guidance, response to clinical need)
  • to the right people (entire care team – including the patient)
  • through the proper channels (e.g., electronic health record, mobile device, portal, patient portal)
  • in the right intervention formats (e.g., order sets, flowsheets, dashboards, patient lists)
  • at the right points in the workflow (for decision making or action)

Effective clinical decision support systems must be relevant to those who can act on the information in a way that supports the completion of the right action.

Clinical decision support (CDS) requires medical knowledge, person-specific information, and a reasoning or inferencing mechanism that combines expertise and data to generate and present helpful information to clinicians as care is being delivered. By reasoning mechanism, clinical decision support systems are divided into two categories:

  • Knowledge-based CDSS. The knowledge base contains the rules and associations of compiled health data, which often take if-then rules.
  • Non-knowledge-based CDSSs use a form of artificial intelligence (AI) called machine learning, which allows computers to learn from past experiences and/or find patterns in clinical data, eliminating the need for writing rules and expert inputs.

Picture 1. npj Digital Medicine (npj Digit. Med.) ISSN 2398-6352 (online)

Benefits of clinical decision support systems (CDSS)

The clinical decision support system is much more than just automatic alerts and reminders. When a clinical decision support system is applied effectively, it increases the quality of care, enhances health outcomes, helps to avoid errors and adverse events, improves efficiency, reduces costs, and enhances provider and patient satisfaction.

Patient safety 

The use of clinical decision support reduces medication errors and possible adverse events. For example, errors involving drug-drug interactions (DDI) are cited as common and preventable, with up to 65% of inpatients being exposed to one or more potentially harmful combinations. Clinical decision support can also improve patient safety through reminder systems for other clinical events, not just medication-related ones.

Clinical management 

Studies have shown that clinical decision support can increase adherence to clinical guidelines. CDS can also alert clinicians to reach out to patients who have not followed management plans or are due for a follow-up and help identify patients eligible for research based on specific criteria.

Healthcare costs 

Clinical decision support can be cost-effective for health systems through clinical interventions, decreasing inpatient length of stay, suggesting more optimal medications, or reducing test duplication. Clinical decision support can notify users of cheaper alternatives to drugs or conditions that states or insurance companies will cover.

Quality of documentation 

Clinical decision support strengthens clinical and diagnostic coding, prescription of procedures and tests, and patient triage. CDSS can directly improve the quality of clinical documentation (e.g., using correct codes for drugs, diagnosis, procedures).

Diagnostics 

Clinical decision support can help with differential diagnosis, providing data or user selections and then outputting a list of possible or probable diagnoses.

Connecting focused patient data reports to clinical guidelines

The exponential growth of medical knowledge has created a market for dynamic and syntheses products for healthcare professionals.

  • It is estimated that the doubling time of medical knowledge in 2020 is projected to be just 73 days. Students who graduate in 2020 will experience four doublings in expertise. What was learned in the first three years of medical school will be just 6% of what is known at the end of the decade from 2010 to 2020 (Densen et al., 2011).

Knowledge is expanding faster than our ability to assimilate and apply it effectively. Doctors increasingly rely on health information technology to accelerate the search process without compromising the reliability and quality of information retrieved.

Point-of-care (POC) clinical databases offer predigested syntheses of evidence-based medical research intended to be used when the patient and physician interact. Point of care (POC) clinical databases provide user-friendly interfaces that may improve the retrieval, synthesis, organization, and application of evidence-based content in clinical practice.

Contextually relevant reference information at the point of care

The content of point of care (POC) clinical databases can be implemented as clinical decision support in your electronic health record, pharmacy information system, or nationwide e-prescription system. The implementation process will combine focused patient data reports with clinical guidelines and other contextually relevant reference information.

What is an example of clinical decision support?

Get an overview of a selection of evidence-based databases in the Synbase platform:

  • Drug interactions
  • Drugs in pregnancy
  • Drug dosage in renal failure
  • Drug dosage in hepatic failure
  • Drug allergies
  • Natural medicines
  • Evidence-based guidelines
  • Clinical reference tool 
  • Dentistry database
  • Clinical decision support
  • Differential diagnosis
  • Patient solutions

Customers and use cases of CDSS

Clinical decision support system receives structured health data from patient-related health repository. It returns a structured decision-support response message to the electronic health record (EHR), hospital information system (HIS), pharmacy point-of-sale (POS), personal health record (PHR), or other similar health info system.

Get an overview of clinical decision support use cases in the Synbase platform:

  • For public sector
  • For electronic health record
  • For pharmacy
  • For dental practice
  • For individual users
  • For medical publishers

Guide for successful CDSS implementation

Here are some practical tips for successful clinical decision support system implementation.

Be user-centric

Clinical decision support aims to help clinicians in clinical decision-making. Our strong recommendation is to use a user-centered design (UCD) process for implementation. At each stage of the implementation process the user needs, clinical workflow, and service process are given extensive attention. Users should be involved already starting from pre-planning activities.

Find your clinical champions

The healthcare sector is conservative; never underestimate resistance to change. Like with every technology adoption cycle, there are visionaries, pragmatists, conservatives, and skeptics. Focus on shared values and find the clinical champions that will guide you through. Effective clinical champions are tech-savvy members of the organization whom their peers trust, understand their colleagues’ technical and workflow challenges, and have strong interpersonal skills.

Start simple

Start simple and focus on an “easy win” in clinical goals and objectives and corresponding clinical decision support interventions. Implementation is challenging both technically (health data interoperability) and from a user perspective. A good recommendation is to start with a feasibility study. Start with simpler one domain clinical decision support like drug-drug interaction checking and move to more complex services.

For starters, get an overview of drug interactions services:

  • Drug interactions
  • How to Implement Nationwide Drug Interaction Service

Right person, right time, right info

For successful clinical decision support system implementation, follow these three design principles.

  • Right person – only person-specific information should be presented to users
  • Right time– customized alerts, and reminders should be presented to users at appropriate times before making the clinical decision
  • Right data– patient-related data reports should relate to the latest clinical knowledge and intelligently filtered

Engage your users

Collecting feedback after implementation is just as crucial as getting stakeholder input before going live. Measuring the impacts on workflow, patient safety, care quality, and provider or patient satisfaction can help inform future efforts and make positive changes to the process.

Do you want to implement clinical decision support as a nationwide service?

 

Case study

Drug Interactions as Nationwide Clinical Decision Support | Synbase

Read the case study >

 

 

Case study

Clinical Decision Support as Nationwide Service | Synbase

Read the case study >

 

 

Get advice on how to implement clinical decision support in European Union, including medical device regulation (MDR) related compliance. Get in touch >

Compliance with medical device regulation (MDR)

Since clinical decision support systems fall under the classification of IIa medical devices, implementing a decision support tool in European Union must be done following the requirements set in the new Medical Device Regulation (MDR) 2017/745 that entered into force on the 26th of May 2021.

The new regulation has changed the way medical devices are classified – new rules are being applied to software-based devices, devices consisting of nanomaterials, invasive devices meant for inhalation, devices consisting of substances or mixtures of substances, and therapeutic devices.

In addition, MDR 2017/745 has introduced a Unique Device Identification (UDI) system and the European Database of Medical Devices (EUDAMED).

Other changes include the addition of the terms “importer” and “distributor” and changes in the obligations of importers and distributors, as well as stricter post-market surveillance requirements.

What is your role in implementing clinical decision support?

  • A manufacturer is a natural or legal person who manufactures or fully refurbishes a device or has a device designed, manufactured, or fully refurbished and markets that device under its name or trademark.
  • An authorized representative is any natural or legal person established within the European Union who has received and accepted a written mandate from a manufacturer located outside the EU to act on the manufacturer’s behalf in relation to specified tasks regarding the latter’s obligations under this regulation.
  • An importer is any natural or legal person established within the European Union that places a device from a third country on the EU market.
  • A distributor is a natural or legal person in the supply chain, other than the manufacturer or the importer, that makes the medical device available on the market up until the point of putting it into service.

How to register clinical decision support as a medical device?

The deadline for all medical device parties (manufacturers, authorized representatives, importers, system/procedure package manufacturers) for mandatory registration with EUDAMED is the 26th of May 2022, when the database is expected to become fully functional.

Table of obligations for different supply chain parties

Position

Obligations

EUDAMED

Manufacturer

Production of technical documentation

Manufacturing

Distribution

Corrective actions

UDI

Liability coverage

Complaints

Post-market surveillance

PRRC (Person Responsible for Regulatory Compliance)

Must register

Authorized Representative

Verify and keep a copy of the EU declaration of conformity and the technical documentation

Registration check

Audit support

Post-market surveillance

Compliance

Governmental regulatory tasks

PRRC (Person Responsible for Regulatory Compliance)

Must register

Importer

Keep a copy of technical documentation

Verify CE mark, EU declaration of conformity and IFU (Instructions for Use)

Verify manufacturer and authorized representative (if needed)

Verify labelling compliance with the MDR and UDI

Include importer´s data to documentation and labelling

Keep a register of complaints

PRRC (Person Responsible for Regulatory Compliance)

Does not have to register

Distributor

Verify CE marking and EU declaration of conformity

Verify UDIs, labels and IFU (in official language of the Member States in which the device is made available)

Verify importer´s contact information

Keep a register of complaints

Must register

 

Drug interactions database

The UDI number combination will be used together with the EUDAMED database for identifying and tracking any medical device on the market, thereby enhancing patient safety.

For CDS tools, the UDI must consist of 2 parts: UDI-DI (Device Identifier) and UDI-PI (Production Identifier). The manufacturer of a CDS must see that the UDI is displayed through an application programming interface in Human Readable Interpretation (HRI). Importers and distributors will need to determine whether the device carries a UDI or not.

 Distributors will not be registering with EUDAMED. Nor will custom medical devices go to the database. The deadline for applying UDIs on class IIa medical devices is the 26th of May 2023.

Compliance with GDPR

After the Data Protection Directive 95/46/EC that was enacted in 1995, the General Data Protection Regulation (GDPR) 2016/679 is the most recent legislative framework on data privacy today. Clinical decision support (CDS) systems process health data to great extents, meaning that they are subject to the highest standards of privacy and GDPR overall.

Although fundamental principles have remained the same as in the Data Protection Directive, certain confinements can be detected. For instance, Article 35 of the GDPR explains that data controllers must carry out a Data Protection Impact Assessment before any data processing actions take place. This is especially important in cases where data processing includes the use of new technologies, and because of the processing, there is a high risk to the rights and freedoms of individuals. In addition, consent of data objects plays a central role during health data handling.

According to GDPR Article 9, processing data that concerns an individual’s health is prohibited unless the data subject has given explicit consent for processing this personal data for one or more specified purposes. Consent must be a freely given, specific, informed, and unambiguous indication of the individual’s wishes by which he or she, by a statement or by clear affirmative action, signifies agreement to the processing of personal data relating to him or her. Consent can be in the form of a written statement, including by electronic means, or an oral statement.

As another key part of CDS compliance with GDPR, consent shall also be obtained for instances where decision-making is fully automated. While decision support systems enhance and simplify doctors’ and nurses’ jobs, it is essential to retain human involvement in the process of decision making.

Article 22 of the GDPR states that individuals have the right not to be subject to a decision based solely on automated processing which significantly affects him or them. Although the same regulation provides a place for fully automated decision-making and profiling under specific conditions and consents lawfully, the main aim of CDS tools is to aid clinicians with decision-making in the clinical workflow and enhance patient safety.

Liability

Clinical decision support systems (CDSS) use smartly filtered and person-specific data to increase the quality of care, improve health outcomes and help avoid medical errors.

If medical devices are defective and not functioning properly, natural or legal persons may claim compensation for damage caused by a defective device in accordance with applicable Union and national law according to the Medical Device Regulation, article 10 (16). In this case, manufacturers shall have measures in place to provide sufficient financial coverage in respect of their potential liability. To avoid such errors and adverse events and establish the safety of the device, clinical evaluations are conducted before the device enters the market.

If medical errors or adverse events occur not due to the functioning of the CDSS but because of misuse of CDSS, misinterpretation of results, or other unrelated negligence, liability rests with the health care professional calling the final decisions. Decision support systems provide knowledge for enhancing decision-making, not replacing it.

Challenges for implementing CDSS

Enhancing the usefulness of clinical decision support systems requires thoughtful design, application implementation, and review. Here are some most common challenges for implementing CDSS.

Fragmented workflows 

Clinical decision support (CDS) can disrupt clinician workflow with computerized alerts and reminders and lead to the increased cognitive effort, more time required to complete tasks, and less time face-to-face with patients.

Alert fatigue 

If physicians are presented with excessive or unimportant alerts, they can suffer from alert fatigue. User-centric service design is very important in developing CDSS services.

Poor data quality

Clinical decision support (CDS) often relies on data from external systems, and this can create deficiencies. For example, the quality of active medication lists is often problematic or electronic documentation of chronic and temporary diagnosis codes. The quality of data can affect the quality of decision support.

Health data interoperability

Despite the standardization of healthcare, clinical decision support (CDS) can suffer from numerous interoperability issues. Interoperability standards are continuously being developed and improved, such as Health Level 7 (HL7) and Fast Healthcare Interoperability Resources (FHIR).

Clinical decision support systems for patients

The rise of personal health records (PHR) has been seen as the biggest digital health trend in Europe (HIMSS 2019).

In the EU, the patient is the owner and manager of personal health data, but current technical solutions offer very limited access to health data, and the potential of PHR-supported patient safety activities are not widely used.

Clinical decision-supported PHRs are the ideal tool to implement shared decision-making between patient and provider, specifically because CDSS can remove information asymmetry as a barrier to a patient’s participation in their own care.

Get an overview of patient solutions in Synbase platform:

Clinical Decision Support for Patients

The future of health information technology

Clinical decision support represents one of the most important applications of healthcare informatics and continues to advance, as does the widespread deployment of electronic health records (EHR) and the professionalization of clinical informatics.

The trend for the future – clinical decision support systems are primed to become the user interface of choice for clinical interactions with health IT, ultimately supplanting the electronic health records as the primary health IT point of interface for clinicians (Frost & Sullivan 2019).

Clinical decision support systems platforms 

The growth of the clinical decision support systems market brings the rise of clinical decision support platforms like Synbase that combine different services into one, taking care of integration to electronic health records, localization, interoperability, authentication, and compliance.

Population health analytics 

To optimize clinical effectiveness, healthcare organizations can leverage more advanced clinical decision support systems for population health that focus on helping patients with the highest risk/highest benefit conditions and get an overview of the status of clinical quality measures. CDSS based population health services cover the whole population with the goal to improve patient outcomes.

AI and machine learning 

In 2021, the American Medical Informatics Association (AMIA) issued new recommendations regarding how clinical decision support tools that adapt their algorithms as they’re trained with new data should be overseen to ensure safety and efficacy. The fast rise of artificial intelligence (AI) and machine learning (ML) in clinical decision support tools has generated excitement over the potential for providers to revolutionize diagnostics, including in the areas of pathology, radiology, and imaging.

Let us know what you're looking for, and a Synbase expert will help you find the best solution

Get in touch
By clicking Submit button you agree with Synbase Terms of Use