Prediction of adverse events in mid-term follow-up after transcatheter aortic valve implantation (TAVI) is challenging. We sought to develop and validate a machine learning model for prediction of 1-year all-cause mortality in patients who underwent TAVI and were discharged following the index procedure. The model was developed on data of patients who underwent TAVI at a high-volume centre between January 2013 and March 2019. Machine learning by extreme gradient boosting was trained and tested with repeated 10-fold hold-out testing using 34 pre- and 25 peri-procedural clinical variables. External validation was performed on unseen data from two other independent high-volume TAVI centres. Six hundred four patients (43% men, 81 ± 5 years old, EuroSCORE II 4.8 [3.0–6.3]%) in the derivation and 823 patients (46% men, 82 ± 5 years old, EuroSCORE II 4.7 [2.9–6.0]%) in the validation cohort underwent TAVI and were discharged home following the index procedure. Over the 12 months of follow-up, 68 (11%) and 95 (12%) subjects died in the derivation and validation cohorts, respectively. In external validation, the machine learning model had an area under the receiver-operator curve of 0.82 (0.78–0.87) for prediction of 1-year all-cause mortality following hospital discharge after TAVI, which was superior to pre- and peri-procedural clinical variables including age 0.52 (0.46–0.59) and the EuroSCORE II 0.57 (0.51–0.64), P < 0.001 for a difference. Machine learning based on readily available clinical data allows accurate prediction of 1-year all-cause mortality following a successful TAVI.

DOI: 10.33963/KP.15307, Published online: April 23, 2020, Authors: Łukasz Kalińczuk, Zbigniew Chmielak, Kamil Zieliński, Jaffar Khan, Maciej Dąbrowski, Michał Świerczewski, Ilona Michałowska, Marcin Demkow, Adam Witkowski, Gary S. Mintz

A 29-year-old patient (♀) with idiopathic pulmonary arterial hypertension (PAH, WHO functional class IV) treated with sildenafil, treprostinil, and nifedipine suddenly developed recurrent chest pain at rest, accompanied by an acute inversion of T-waves in V3–V6 and a troponin I increase of up to 1.9 ng/mL. Progressive pulmonary trunk dilatation was observed in all her previous echocardiography examinations. Multi-detector computer tomography scan (128 row dual source SOMATOM Definition, Siemens, Forchheim, Germany) revealed huge (∼70 mm) aneurysmal dilatation of the pulmonary trunk (PT, Panel A), but no sign of dissection. Coronary CT angiography revealed that the dilated PT displaced and compressed the entire course of the left main coronary artery (LMCA) against the wall of the left sinus of Valsalva, resulting in a critical lumen narrowing (Panel A, ‘1’). Angiography confirmed these findings (Panel B, ‘1’). Intravascular ultrasound (Atlantis SR Pro, Boston Scientific, USA, Panel B, 1–3) revealed more extensive left anterior descending (LAD) artery compression, which was evident in CT or invasive angiography and, in addition to that extrinsic coronary artery compression, atherosclerotic plaque accumulation in the ostium of the LAD (Panel B, 2, asterisk). Because the extrinsic coronary artery compression reduced the size of the LAD, even the modest amount of atherosclerotic plaque contributed importantly to the lumen narrowing with a minimal lumen cross-sectional area of only 2.5 mm². Therefore, we stented the LMCA from its origin into the proximal LAD (Panel B, 3) using a Liberte^TM 3.5 × 20 mm stent (Panel C, 4–6).