How AI and Robotics Will Advance Interventional Radiology: Narrative Review and Future Perspectives

The rapid advancement of artificial intelligence (AI) and robotics has led to significant progress in various medical fields including interventional radiology (IR). This review focuses on the research progress and applications of AI and robotics in IR, including deep learning (DL), machine learning (ML), and convolutional neural networks (CNNs) across specialties such as oncology, neurology, and cardiology, aiming to explore potential directions in future interventional treatments. To ensure the breadth and depth of this review, we implemented a systematic literature search strategy, selecting research published within the last five years. We conducted searches in databases such as PubMed and Google Scholar to find relevant literature. Special emphasis was placed on selecting large-scale studies to ensure the comprehensiveness and reliability of the results. This review summarizes the latest research directions and developments, ultimately analyzing their corresponding potential and limitations. It furnishes essential information and insights for researchers, clinicians, and policymakers, potentially propelling advancements and innovations within the domains of AI and IR. Finally, our findings indicate that although AI and robotics technologies are not yet widely applied in clinical settings, they are evolving across multiple aspects and are expected to significantly improve the processes and efficacy of interventional treatments.

A prediction model based on platelet parameters, lipid levels, and angiographic characteristics to predict in-stent restenosis in coronary artery disease patients implanted with drug-eluting stents

BACKGROUND

The present study was aimed to establish a prediction model for in-stent restenosis (ISR) in subjects who had undergone percutaneous coronary intervention (PCI) with drug-eluting stents (DESs).

MATERIALS AND METHODS

A retrospective cohort study was conducted. From September 2010 to September 2013, we included 968 subjects who had received coronary follow-up angiography after primary PCI. The logistic regression analysis, receiver operator characteristic (ROC) analysis, nomogram analysis, Hosmer-Lemeshow χ2 statistic, and calibration curve were applied to build and evaluate the prediction model.

RESULTS

Fifty-six patients (5.79%) occurred ISR. The platelet distribution width (PDW), total cholesterol (TC), systolic blood pressure (SBP), low-density lipoprotein cholesterol (LDL-C), and lesion vessels had significant differences between ISR and non-ISR groups (all P < 0.05). And these variables were independently associated with ISR (all P < 0.05). Furthermore, they were identified as predictors (all AUC > 0.5 and P < 0.05) to establish a prediction model. The prediction model showed a good value of area under curve (AUC) (95%CI): 0.72 (0.64-0.80), and its optimized cut-off was 6.39 with 71% sensitivity and 65% specificity to predict ISR.

CONCLUSION

The incidence of ISR is 5.79% in CAD patients with DES implantation in the Xinjiang population, China. The prediction model based on PDW, SBP, TC, LDL-C, and lesion vessels was an effective model to predict ISR in CAD patients with DESs implantation.

Impact of intravascular ultrasound on Outcomes following PErcutaneous coronary interventioN for In-stent Restenosis (iOPEN-ISR study)

BACKGROUND

Percutaneous coronary intervention (PCI) for in-stent restenosis (ISR) remains common. Intravascular imaging allows for the determination of the mechanism of ISR, potentially guiding appropriate therapy. Intravascular ultrasound (IVUS)-guided stent implantation is associated with a reduction in adverse events after PCI, but its impact on treatment of ISR is not clear.

METHODS

All patients with 1-year follow-up after ISR treatment from 2003 through 2016 were included and stratified by IVUS use. The primary endpoint was the rate of major adverse cardiac events (MACE) at 1 year, defined as the composite of all-cause mortality, Q-wave myocardial infarction, and target vessel revascularization (TVR).

RESULTS

The final analysis included 1522 ISR patients, 65.9% of whom were treated with IVUS guidance. The primary endpoint occurred in 18.0% of patients treated with IVUS guidance vs. 24.5% of patients treated with angiography guidance (p = 0.0014). Post-dilatation was used more often with IVUS (18.6% vs. 14.1%, p < 0.001), with a larger diameter of new stents (3.04 ± 0.35 mm vs. 2.94 ± 0.47 mm, p = 0.001). At 1 year, TVR occurred in 14.5% with IVUS guidance and 19.2% with angiography guidance (p = 0.021).

CONCLUSIONS

The use of IVUS is associated with decreased MACE at 1 year following PCI for ISR. These results support routine IVUS for the treatment of ISR lesions.

A novel algorithm for the computation of the diastolic pressure ratio in the invasive assessment of the functional significance of coronary artery disease

BACKGROUND

Invasive functional assessment is a mainstay in the management of patients with coronary artery disease (CAD), but there is uncertainty on the comparative accuracy of diagnostic indices of functional significance. We aimed to validate the diagnostic performance of a novel non-hyperemic diastolic pressure ratio (dPR).

METHODS

We performed a retrospective analysis including two separate registries (VERIFY 2, Latina, Italy) of patients in whom functional indices were measured for lesions with angiographically moderate severity. On top of fractional flow reserve, distal coronary pressure (Pd)/aortic pressure (Pa) ratio, instantaneous wave-free ratio (iFR) and diastolic pressure ratio (dPR) were computed using a novel dedicated algorithm over 4 consecutive beats. Agreement/discrepancy between indexes was appraised Bland-Altman analysis, area under the receiver operating characteristic curve (AUC), and unsupervised machine learning.

RESULTS

A total of 525 lesions from 479 patients were included. The novel dPR was highly correlated with iFR (R²=0.99, P<0.001), with a mean difference of -0.004±0.014. The diagnostic performance of dPR (best cutoff value: ≤0.89) against iFR was as follows: accuracy =96%; sensitivity =94%; specificity =97%; positive-predictive value =94%; and negative-predictive value =96%. Additionally, AUC to predict iFR≤0.89 was 0.99, which was significantly higher than that of Pd/Pa (0.97, P<0.001). In the iFR range of 0.85-0.93 ("grey zone"), the diagnostic performance was well maintained (accuracy =91%; sensitivity =87%; specificity =93%; and AUC=0.96). Results were supported also by unsupervised learning analysis.

CONCLUSIONS

This multicenter registry suggests this novel dPR algorithm provides results that are numerically equivalent to iFR. Pending further studies, physicians may consider using this novel dPR algorithm to gauge the functional significance of a coronary lesion.

Long-term outcomes of percutaneous or surgical treatment in left main disease

INTRODUCTION

Long-term efficacy and safety of either surgical or percutaneous treatment left main coronary artery disease treatment is lacking.

EVIDENCE ACQUISITION

We conducted a systematic review and meta-analysis of the most updated randomized clinical trials that compared the efficacy of coronary artery bypass surgery (CABG) or percutaneous coronary intervention (PCI) for the Left Main Coronary Artery (LMCA) disease. It was also conducted a systematic search of PubMed, Google Scholar, reference lists of relevant articles, and Medline. The search utilized the following terms: "left main PCI versus CABG," "drug-eluting stents," "bypass surgery" and "left main stenting." The search of articles compatible with our inclusion and exclusion criteria was performed from inception through April 2020 and returned a combined total of 304 articles.

EVIDENCE SYNTHESIS

We identified 6 studies, providing data on 5812 patients. The mean follow-up was 6.7 years. PCI was associated with an increased risk of major vascular events (MACE) (IRR 1.24, 95% CI [1.03-1.67], P<0.01), and coronary revascularization (IRR 1.69, 95% CI [1.42-2.03], P<0.01) compared to CABG. Furthermore, all-cause death, MI and stroke events were not statistically different between the two therapeutic revascularization methodologies (IRR 1.06, 95% CI [0.90-1.24], P=0.47, IRR 1.35, 95% CI [0.84-2.16], P=0.03 and IRR 0.66, 95% CI [0.43-1.01], P=0.05, respectively).

CONCLUSIONS

LMCA PCI has an overall same survival compared to CABG in the long term follow-up. Nevertheless, MACE and revascularization events were more frequent in PCI compared to CABG.

Percutaneous Coronary Intervention Compared with Coronary Artery Bypass Graft Surgery for Patients With 3-vessel Disease: A Preferred Reporting Items for Systematic Reviews and Meta-Analyses-compliant Systematic Review and Meta-analysis

OBJECTIVES

Previous investigations showed inconsistent results for comparison in clinical outcomes between patients with 3-vessel disease (3VD) treated with percutaneous coronary intervention (PCI) and coronary artery bypass graft (CABG) surgery. A systematic review and meta-analysis is essential to compare the clinical outcomes of PCI with CABG surgery for patients with 3VD.

METHODS

We systematically searched on PubMed and Web of Science for articles which compared PCI with CABG for patients with 3VD and published from January 1989 to January 2020. We computed the hazard ratios (HRs) and 95% confidence intervals (CIs) for individual clinical outcomes.

RESULTS

This study indicated that the PCI group was associated with a 1.51-fold higher risk of all-cause mortality compared with the CABG group in patients with 3VD (HR 1.51, 95% CI 1.38-1.65). In addition, the PCI group showed a 3.08-fold and 2.94-fold higher risk compared with the CABG group in risks of myocardial infarction (MI) and target-vessel revascularization (TVR), respectively (MI: HR 3.08, 95% CI 2.61-3.63; TVR: HR 2.94, 95% CI 1.94-4.46).

CONCLUSIONS

In conclusion, in patients with 3VD, PCI was consistently associated with higher rates of all-cause mortality, MI, and TVR, compared with CABG.

Impact of Intravascular Ultrasound on Outcomes Following PErcutaneous Coronary InterventioN in Complex Lesions (iOPEN Complex)

BACKGROUND

Clinical data support the use of intravascular ultrasound (IVUS)-guided percutaneous coronary intervention (PCI) as being associated with improved outcomes. Nonetheless, global utilization of IVUS remains low. We hypothesize that, in the revascularization of complex lesions, IVUS use is associated with improved outcomes.

METHODS

All patients with complex lesions treated with PCI at a single center from 2003 to 2016 were stratified by use of IVUS. Complex lesions were defined as follows: American College of Cardiology/American Heart Association type C lesions, in-stent restenosis, long lesions, bifurcations, severe calcification, left main lesions, and chronic total occlusions. The primary end point was the rate of major adverse cardiac events (MACE) at 1-year follow-up, defined as the composite of all-cause mortality, Q-wave myocardial infarction, and target vessel revascularization. Inverse probability weighting was used in the adjusted analysis.

RESULTS

A total of 6,855 patients were included in the final analysis, of whom 67.3% had IVUS and 32.7% had angiography alone. The primary end point occurred in 13.4% of patients treated with IVUS and 18.3% of patients treated with angiography alone (P < .001). Inverse probability weighting-adjusted 1-year MACE rates demonstrated significant reduction with IVUS for each complex lesion type.

CONCLUSIONS

Among patients with complex lesions, the use of IVUS was associated with lower MACE 1 year after PCI than angiography alone was. Because of the increased procedural risk in complex lesions, routine utilization of IVUS-guided PCI should be considered in this subset of patients.

The Role of Novel Oral Anticoagulants and Antiplatelet Therapy after Percutaneous Coronary Intervention: Individualizing Therapy to Optimize Outcomes

The number of patients undergoing percutaneous coronary intervention (PCI) who mandate additional oral anticoagulant therapy has been increasing. Dual antiplatelet therapy (DAPT) is associated with reduced ischemic events including stent thrombosis, myocardial infarction and stroke following PCI. However, the tradeoff is an increased risk for bleeding while on DAPT. The addition of a novel oral anticoagulant (NOAC) further increases the likelihood of bleeding while on antiplatelet therapy. Thus, the overall risks and benefits for each patient undergoing PCI on NOAC must be assessed and therapy individualized to ensure optimal therapy for each unique situation. Patients on NOAC undergoing PCI should undergo routine assessment with intravascular imaging as the role of high-risk lesion-related features have increased importance prior to determining optimal duration of treatment with DAPT. We review the best practices for the pharmacologic management of patients requiring anticoagulation with NOAC who are treated with PCI and require antiplatelet therapy.