Clinical Decision Support Systems (CDSS) and Telehealth in Health Informatics

INTRODUCTION

In the healthcare world today, the climate continues to demand that hospitals do more with less, technology has been challenged to help with filling that gap. (Bresnick, 2016)  Healthcare systems have been faced with many challenges in the forms of finance, reform, government mandates and policy, technology and customer/patient satisfaction.  Clinical Decision Support Systems (CDSS) significantly impact improvements in quality, safety, efficiency, and effectiveness of health care.  With the tools that are offered with clinical decision support, clinicians, staff, patients, or other individuals are equipped with knowledge and specialty-specific information that is intelligently filtered or presented at appropriate times. (HealthIT, 2018) 

 To improve the quality of medical care in the United States, efforts are being made to increase the practice of evidence-based medicine through the use of clinical decision support (CDS) systems. CDS provides clinicians, patients, or caregivers with clinical knowledge and patient-specific information to help them make decisions that enhance patient care.  The patient’s information is matched to a clinical knowledge base, and patient-specific assessments or recommendations are then communicated effectively at appropriate times during patient care. CDS interventions can increase adherence to evidence-based medical knowledge and can reduce unnecessary variation in clinical practice. (Kropf, 2015)

 There have been a variety of DDSS that focus on specific problem areas, some of which utilize artificial intelligence approaches and other use statistical pattern recognition models. (Berner, 2006) However, the clinical decision support tool chosen for this project is a document quality review tool that is designed to address a variety of diseases and help provide decision support for physicians in an emergency medicine setting. With Cerner’s clinical decision support tool, document quality review (DQR), providers have the capability of double checking their work essentially to ensure that they are providing patients with an accurate diagnosis. (Cerner, 2018) The incorporation of evidence-based guidelines into an EMR by using a clinical decision support tool like document quality review can help align care delivery. (Kropf, 2015)

SECTION 2: OVERVIEW / INTRODUCTION

With the shift from volume to value in the healthcare world, clinical decision support systems (CDSS) have become extremely valuable and important to improving clinical care provided to patients. With the tools that are offered with clinical decision support, clinicians, staff, patients, or other individuals are equipped with knowledge and specialty-specific information that is intelligently filtered or presented at appropriate times. (HealthIT, 2018) As CMS places more rules around reimbursement in the healthcare industry, institutions are being pushed to make a change and find creative ways to follow the rules, which in-turn will provide better care to patients. In terms of providing more ‘value’, healthcare organizations are being asked to take care of chronic disease, acute disease, and all while not causing any unnecessary harm in the process. (Miliard, 2016) One healthcare vendor who has taken on the challenge to support healthcare institutions in the initiative is Cerner. They have implemented multiple CDSS within their application to aid providers and other clinicians in delivering quality care. For example, their product suite includes dynamic documentation, document quality review, and patient education. Their most influential and impactful product would be the document quality review function. This function allows providers to have the application review the documentation for a patient’s consult or examination and determine if there is existing clinical evidence to support a more specific diagnosis. (Cerner, 2018)

 Over the last few decades healthcare has struggled to meet the task of providing timely information at the point of care. With Cerner’s clinical decision support tool, document quality review (DQR), providers have the capability of double checking their work essentially to ensure that they are providing patients with an accurate diagnosis.  This tool also offers providers the opportunity to research additional diagnoses based on what is provided by the system. With document quality review providers are able to save time if they are stumped and cannot derive a diagnosis based off the symptoms and examination results. With this tool there is also another very helpful tool associated as well, patient education.  Once the diagnosis is selected the physician can then create a discharge document and select all necessary and appropriate documentation or education based on the patient’s diagnosis so that the patient has information they can read post discharge. (Cerner, 2018) With this type of tool integration there is less chance that a patient will call back with questions or come back for readmission. With readmission rates decreasing this will increase revenue for healthcare organizations. Ultimately the tool gives providers relevant information to provide to particular patients, reminders for preventative care, and warnings for escalated situations. (Clinical, 2014)

SECTION 3: THE MODEL

Framework & Structure

The Document Quality Review (DQR) tool that Cerner provides within their EMR (electronic health record) suite is a decision support tool that is one of the most influential and impactful products.  The Document Quality Review tool is both a knowledge-based and supervised clinical decision support tool. (Cerner, 2018) Cerner uses data and research already gathered from insurance companies and CMS regarding necessary documentation for billing for a specific diagnosis. (CMS, 2014) This information helps providers do further testing or examination of a patient to determine if the patient truly has a specific diagnosis. The tool also has if-then rules in place as well, such as “if a patient is diagnosed with cancer, then pathology reports, radiology reports, and a physical examination will be required, and a certain level detail or amount of documentation will be required to submit for payment.”  There are notifications that appear as well as a prompt to EMR users if a provider selects certain ICD codes without providing sufficient documentation, such as a full review of systems. This tool can help serve as a first line of defense for hospital billing to ensure that providers are doing their due diligence the first time.  It can also help healthcare organizations with making sure that providers are properly diagnosing patients because they are performing the proper examinations and providing sufficient documentation as well as ordering sufficient labs, imaging, and any other diagnostic testing. (Health IT, 2018)

With the Document Quality Review tool clinicians are actively interacting with the systems rather than being a passive recipient of the output.  This tool can be classified as a knowledge-based tool that uses compiled information with an if-then format and has a probabilistic association of signs and symptoms with diagnosis that is mapped by the inference engine and compared to the data in the knowledge base in order to aid clinicians in making the best decision on a diagnosis and provide sufficient documentation in order for reimbursement with insurance companies. The framework for the DQR tool is that the provider will enter in documentation from the examination of a patient and then complete a free-text description of the interaction and complete the review of systems form.  Once that is complete then the previous medical diagnoses need to be selected and the plan and assessment will also be completed to include appropriate orders for testing and or imaging. Once all reporting is complete for any diagnostic testing, then the provider can select a diagnosis for the patient, and at this time is when the system will generate a notification if the ICD code selected is not appropriate for the documentation provided.  The message may state “More documentation or clinical evidence is needed to support diagnosis, please check review of systems.”  When a deficiency is identified, an electronic notice is generated and delivered over a communication network to a clinician computing device.  The notice may provide the clinician access to a user interface that allows the clinician to enter additional information or clarify information in the patient data to address the deficiency. (G, 2016)

Clinical Workflow

CDSS Application Modality

The Document Quality Review (DQR) application uses the modalities of notification pop-ups and diagnosis aiding. This tool also offers providers the opportunity to research additional diagnoses based on what is provided by the system. With document quality review providers are able to save time if they are stumped and cannot derive a diagnosis based off the symptoms and examination results. With this tool there is also another very helpful tool associated as well, patient education.  Once the diagnosis is selected the physician can then create a discharge document and select all necessary and appropriate documentation or education based on the patient’s diagnosis so that the patient has information they can read post discharge. (Cerner, 2018)

Performance Measures & Outcomes

With this type of tool integration there is less chance that a patient will call back with questions or come back for readmission. With readmission rates decreasing this will increase revenue for healthcare organizations. Ultimately the tool gives providers relevant information to provide to particular patients, reminders for preventative care, and warnings for escalated situations. (Clinical, 2014)  From a financial perspective, this tool gives healthcare organizations the opportunity to address missing documentation that delays reimbursement upfront rather than put manpower into fixing it on the back end. (G, 2016)

SECTION 4: RISK ASSESSMENT TOOL

SECTION 5: EVALUATION

In order to properly evaluate a clinical decision support tool, one must make many attempts to answer a wide range of questions involved in making decisions about safety, practicality, and utility. (Taylor, 2005) With the document quality review tool when looking at the safety of this tool there are many risks if the knowledge database is not large enough and there are not enough creditable resources to suggest the correct diagnoses. When evaluating a system like a document quality review, a management-focused model that would generate insights into work-flow disruption, productivity impact, and process changes.  A user-oriented evaluation could also be used for this CDSS as well to detect the possible usability issues that exist with the software and assess the satisfaction of the current users.  Looking at the model below you can see the efficiency of the evaluated system. After evaluating the workflow, the workflow was changed slightly to be inclusive of diagnoses that do not require labs or imaging.

SECTION 6: DISCUSSION AND CONCLUSION

In conclusion, clinical decision support tools can be used to evaluate care from a population-based perspective and to move from the measurement of care processes to the measurement of patient outcomes. Clinical decision support systems have been promoted as one of the key features of electronic health records most likely to lead to a real transformation of the healthcare system. With the document quality review tool that Cerner offers as a part of their electronic health record package, providers have the power to make supported decisions regarding diagnoses.  This tool will also help improve billing metrics because there will be more supportive documentation to support the diagnosis given to the patient by the provider.

With every clinical decision support system there are strengths and there are weaknesses.  The strengths of the document quality review are that patients will be more accurately diagnosed by providers at the point of care. It will also help relieve providers from the added stress of remembering so much information, because it will provide decision support from a reliable knowledge database.  Some weakness that could occur with this clinical decision support tool would be that providers could begin to solely rely on the decisions of the document quality review tool and not derive the answers themselves and use the tool as a quality review. This type of weakness could cause inaccurate diagnoses to be given to patients and therefore cause inappropriate patient care. In most clinical care environments decision support features are often not used and clinicians frequently ignore, override, or fail to seek out suggestions that could improve care. In this case however, the fear would be that the tool would be over utilized or underutilized, which are the two extremes. (Berner, 2006)

Recommendations for this clinical decision tool to be more effective and accurate would be to increase the knowledge base and this could improve the lack of reference annotations to provide more data to support a clinical diagnosis suggested. Future work suggestions for Cerner to improve this clinical data support tool would be to employ and consult with more academic healthcare institutions to acquire more data and knowledge to ultimately expand the database and begin building out the specialty branches, which could equip residents and fellows in an academic setting with a better way to quality check their work. Future work could also include doing further research and evaluation into whether the document quality review tool has a significant impact on billing because diagnosis codes are aligned with supportive data such as imaging reports and lab results.

REFERENCES

• Berner, E. S. (2006). Diagnostic Decision Support Systems: Why Aren’t They Used More And What Can We Do About It? Retrieved October 1, 2018, from https://www.ncbi.nlm.nih.gov/pmc/articles/PMC1839633/
• Bresnick, J. (2016, July 08). Top 4 Emerging Tech Trends in Healthcare Big Data Analytics. Retrieved February 18, 2018, from https://healthitanalytics.com/news/top-4-emerging-tech-trends-in-healthcare-big-data-analytics
• Clinical Decision Support. (2014, April 02). Retrieved September 10, 2018, from https://www.ahrq.gov/professionals/prevention-chronic-care/decision/clinical/index.html
• Clinical Solutions | Cerner. (2018). Retrieved September 10, 2018, from https://www.cerner.com/solutions/clinical-solutions
• CMS. (2014). Clinical Decision Support: More Than Just ‘Alerts’ Tipsheet. Retrieved August 28, 2018, from https://www.cms.gov/regulations-and-guidance/legislation/EHRincentiveprograms/downloads/clinicaldecisionsupport_tipsheet-.pdf
• Eichner, J., & Das, M. (2010). Challenges and Barriers to Clinical Decision Support (CDS) Design and Implementation Experienced in the Agency for Healthcare Research and Quality CDS Demonstrations. AHRQ National Resource Center for Health Information Technology, 10(0065), ef. Retrieved October 1, 2018, from https://healthit.ahrq.gov/sites/default/files/docs/page/CDS_challenges_and_barriers.pdf.
• G., Lorenzo, A., M., Elaine, B., D., & Scott, J. (2016, April 28). CLINICAL DOCUMENT QUALITY REVIEW – CERNER INNOVATION, INC. Retrieved September 17, 2018, from http://www.freepatentsonline.com/y2016/0117455.html
• HealthIT. Systems Approach. (2018). Retrieved August 28, 2018, from https://www.healthit.gov/topic/safety/clinical-decision-support
• Marr, Bernard. (2017) Machine Learning – What’s The Difference? Retrieved September 3, 2018, from https://www.forbes.com/sites/bernardmarr/2017/03/16/supervised-v-unsupervised-machine-learning-whats-the-difference/#65de5068485d
• Miliard, M. (2016, March 11). Clinical decision support: No longer just a nice-to-have. Retrieved September 10, 2018, from https://www.healthcareitnews.com/news/clinical-decision-support-no-longer-just-nice-have
• Taylor, P. (2005). Evaluating telemedicine systems and services. Journal of Telemedicine and Telecare, 11(4). Retrieved October 1, 2018, from file:///C:/Users/blink/AppData/Local/Packages/Microsoft.MicrosoftEdge_8wekyb3d8bb we/TempState/Downloads/evaluation of telemedicine (2).pdf.