PCI Shown to Be Safe for Cardio-Oncology Patients in Large Study Using Machine-Learning Augmentation

May 18, 2022—Using machine learning augmentation, data from a study of > 100 million hospitalizations has shown that the use of percutaneous coronary intervention (PCI) is safe and its use increasing among patients with cancer.

Oncology patients are commonly an underrepresented population within cardiovascular clinical trials leading to a lack of data on safe and effective treatment options for this patient cohort, noted the Society for Cardiovascular Angiography & Interventions (SCAI) in a press release announcing the findings.

According to SCAI, to better understand treatment patterns, investigators conducted the first nationally representative multiyear cardio-oncology mortality study of thrombocytopenia and coronary intervention including PCI using machine learning augmentation and propensity score (PS).

The investigators used the 2016-2018 National Inpatient Sample (NIS) to analyze 101,521,656 hospitalized adult patients and found 6,456,777 (6.36%) patients who had active cancer. Of these cancer patients, 6.14% had thrombocytopenia.

The findings were presented at the SCAI 2022 scientific sessions held May 19-22 in Atlanta, Georgia.

The investigators reported the following:

• Among thrombocytopenia patients, patients with active cancer were significantly less likely to receive left heart catheterization (1.88% vs 5.41%) and PCI (0.48% vs 1.35%) compared to patients without active cancer
• Among cancer patients, patients experiencing thrombocytopenia were more likely to have an acute myocardial infarction (4.06% vs 2.35%) and to receive intravascular ultrasound (62.65% vs 56.75%)
• PCI approximately doubled from 2016 to 2018 among patients with thrombocytopenia (10.33% vs 6.16%)
• In multivariable regression in PCI, neither active cancer (odds ratio, 0.89; 95% CI, 0.45-1.75; P = .738) nor any of the 32 tested primary malignancies significantly increased mortality

Dominique J. Monlezun, MD, who is Adjunct Assistant Professor at The University of Texas MD Anderson Cancer Center in Houston, Texas, serves as senior data scientist on the study.

“Our study aimed to leverage the power of big data and artificial intelligence to provide robust, reliable, and relevant results to guide appropriately tailored interventions for cardio-oncology patients,” commented Dr. Monlezun in the SCAI press registry. “Our hope is to decrease undertreatment among this patient population by ensuring clinicians have reassuring evidence on the safety and efficacy of revascularization techniques for this specific patient population.”

Moving forward, the investigators hope utilizing artificial intelligence technology will allow investigators and physicians to increase the amount of complex and real-time data collections, ultimately advancing patient care techniques more rapidly than traditional methods, stated SCAI.