The main goals of percutaneous coronary intervention (PCI) are symptom improvement in stable patients as well as symptom relief, myocardial preservation, and occasional survival benefit in acute coronary syndrome patients compared to medical therapy alone. Usually implicit and intuitive estimates of individual patients’ acute and long‐term survival prospects, both pre‐ and post‐procedure, guide our clinical decision‐making. The PCI itself is sometimes intended to incrementally improve acute and long‐term survival. To potentially enhance our post‐PCI intuition, van Boven et al.'s risk prediction model based on nine simple factors known after diagnostic catheterization but prior to PCI permits reasonable precision in estimating individual patient mortality risk for at least 5 years .The original rationale for the model was identification of patients likely to live long enough to accrue the hoped for long‐term benefits of bioabsorbable stents. Despite withdrawal of the bioabsorbable stent, explicit long‐term mortality prediction post‐PCI might help guide or target other therapies. Models such as van Boven et al.'s are a step in this direction. Since age largely drives survival, predicted compared to age and gender adjusted expected population survival would help identify individuals and their time‐frames of inordinately increased risk. Models considering the causes of death (competing risks) could better target potentially modifiable factors. Larger studies are required to precisely predict 5‐year mortality risks of >30%. Novel methods incorporating low incidence but highly impactful comorbidities into the models should be a goal. As electronic health records (EHRs) become automatically linked to vital status and other outcome data, natural language processing and machine learning will permit efficient collection and analysis of a broader set of information to improve the models yielding patient‐specific outcome predictions.For now, automated implementation of the van Boven model as well as other well‐known and validated acute outcome prediction models (such as the National Cardiovascular Data Registry PCI mortality model with c‐index = 0.94) into the EHR would permit real‐time comparison of implicit and intuitive pre‐ and post‐procedural risk assessments with explicit model estimates . Clinicians should continue to astutely consider factors not included in the models that may account for their assessments diverging from these models. Straightforward and providing predictions of absolute risk, the van Boven et al. long‐term mortality risk prediction model after PCI is a step into this emerging real‐time data‐driven future. Ultimately, in an “efficient, learning, and precision” healthcare system, model predicted outcome risks should inform the development, targeting, and testing of new patient care strategies and interventions.REFERENCESvan Boven N, van Domburg RT, Kardys I, Umans VA, Akkerhuis KM, Lenzen MJ, Valgimigli M, Daemen J, Zijlstra F, Boersma E, van Geuns RJ. Development and validation of a risk model for long‐term mortality after percutaneous coronary intervention: The IDEA‐BIO study. Catheter Cardiovasc Interv 2018;91:686–695.Brennan JM, Curtis JP, Dai D, Fitzgerald S, Khandelwal AK, Spertus JA, Rao SV, Singh M, Shaw RE, Ho KK, Krone RJ, Weintraub WS, Weaver WD, Peterson ED. Enhanced mortality risk prediction with a focus on high‐risk percutaneous coronary intervention: Results from 1,208,137 procedures in the NCDR (National Cardiovascular Data Registry). JACC Cardiovasc Interv 2013;6:790–799.
Catheterization and Cardiovascular Interventions – Wiley
Published: Jan 1, 2018
It’s your single place to instantly
discover and read the research
that matters to you.
Enjoy affordable access to
over 18 million articles from more than
15,000 peer-reviewed journals.
All for just $49/month
Query the DeepDyve database, plus search all of PubMed and Google Scholar seamlessly
Save any article or search result from DeepDyve, PubMed, and Google Scholar... all in one place.
Get unlimited, online access to over 18 million full-text articles from more than 15,000 scientific journals.
Read from thousands of the leading scholarly journals from SpringerNature, Elsevier, Wiley-Blackwell, Oxford University Press and more.
All the latest content is available, no embargo periods.
“Hi guys, I cannot tell you how much I love this resource. Incredible. I really believe you've hit the nail on the head with this site in regards to solving the research-purchase issue.”Daniel C.
“Whoa! It’s like Spotify but for academic articles.”@Phil_Robichaud
“I must say, @deepdyve is a fabulous solution to the independent researcher's problem of #access to #information.”@deepthiw
“My last article couldn't be possible without the platform @deepdyve that makes journal papers cheaper.”@JoseServera