A Novel Clinical Decision Support System for Concordance with Expert Decision


One of the issues health care providers and institutions face is how to deliver evidence-based medical care at lower cost to an ever growing portion of society in need. Translation of clinical studies to everyday practice and adoption of national and international guidelines have not met expectations. This disappointing problem comes primarily from a lack of communication between ever growing and changing medical literature and individual patient profile. At the same time, threats of penalties for underperformance and poor reimbursement related to improper documentation are increasing. Therefore, transition to comprehensive clinical decision support systems (CDSS) will not just be inevitable but also rewarding.


In a new published article Dr. Demir Baykal, Gorica Malisanovic and Dr. Nirav Raval examine the level of correlation between the novel CDSS and health care providers’ clinical decisions.


Heart Failure Treatment


CDSS for diagnosis and treatment of heart failure (Cardiologist Evaluator) was developed using a USPO patented methodology with artificial intelligence to function as an assistant to the health care provider. It serves as a search engine to select evidence-based diagnostic and therapeutic options for a patient. A total of 389 patients with suspected heart failure were available between 2017 and 2018 at a suburban tertiary care hospital. Both Cardiologist Evaluator and health care providers gave recommendations regarding diagnosis and treatment for each patient independently. With that, the doctors went on to look into and evaluate the concordance rate between Cardiologist Evaluator recommendations and actual health care providers’ decisions. Alongside that, ICD-10 coding provided by Cardiologist Evaluator was compared to ICD-10 coding of health care provider in order to evaluate immediate cost effectiveness. Recommendations given by Cardiologist Evaluator (the heart failure treatment app) were later presented to board certified heart failure cardiologists who were then asked if they found them acceptable or unacceptable for care of each individual patient. With that, this new concordance rate between Cardiologist Evaluator and heart failure specialists was evaluated.


Results of the Cardiologist Evaluator


After the research process, the overall concordance rate between Cardiologist Evaluator recommendations and actual healthcare providers’ decisions was of 69.7%. Most discrepancies were related to adoption of new therapies, dose advancements, workup for new onset heart failure, and/or referral for LVAD. Heart failure specialists found recommendations given by Cardiologist Evaluator acceptable 99.3% of the time. Overall concordance rate between Cardiologist Evaluator and HF specialists was 98.9%. Cardiologist Evaluator provided superior, automated ICD-10 coding in order of relevance.


In the end, Cardiologist Evaluator shows high accuracy in evidence-based diagnosis and treatment of heart failure. It may be useful for consistent implementation of clinical guidelines and more reliable coding, especially in centers without heart failure specialists.


If you want to learn more, you can read the full study by clicking here.