Artificial Intelligence in Interventional Cardiology
Bina Ahmed, MD, FACC
The following are key points to remember from this state-of-the-art
review on the impact of artificial intelligence (AI) on interventional
cardiology:
1. AI encompasses a broad application of
mathematical algorithms to train machines to mimic human behavior. There
is increasing interest in developing AI technology for application in
healthcare.
2. AI operations include machine
learning (ML), deep learning (DL), natural language processing (NLP),
cognitive computing, computer vision, and robotics.
3. ML is an automated system that
learns to perform a task or make decisions from available data sources.
Once an algorithm is programmed, ML has the ability to figure large
complex and heterogeneous data sets and make predictions with fewer
assumptions compared to conventional statistical methods.
4. DL is a part of ML, which is
based in algorithms called neural networks. DL networks use digitized
inputs that work through layers of connected neurons and perform advance
pattern recognition to generate an output. DL does not require
continued human input. DL is currently best applied to image recognition
such as during angiography or echocardiography.
5. Virtual applications of AI have
the potential to enhance image reconstruction, analysis, and
interpretation. This is currently being used for coronary anatomic and
functional lesion analysis.
6. Clinical decision support systems
apply the use of ML, NLP, and pattern recognition to assist with
imitating human thought processing. IBM is currently developing Medical
Sieve, an automated cognitive assistant for cardiologists and
radiologists to aid in clinical decision making.
7. Virtual reality platforms are currently being used for periprocedural planning of structural heart interventions.
8. Robotics are in their initial
phase of application in interventional cardiology and not likely to
replace a human interventional cardiologist in the near future.
Although they can provide physical assistance, they do not perform
intelligence assistance at this time.
9. Challenges to integration of AI
in interventional cardiology practice include complexity of its
integration, inability to ‘mimic’ human touch and emotions, and how it
would impact the workforce.
10. AI is poised to transform and
enhance the practice of interventional cardiology. Whether we can use it
intelligently to enhance patient care and outcomes remains to be
determined.
http://www.cbsmd.cn Contact us by cbs@cbsmd.cn
Copyright ⓒ CBSMD Nanjing China. All rights reserved.