Aims: Artificial intelligence (AI) and machine learning (ML) promise vast advances in medicine. The current state of AI/ML applications in cardiovascular medicine is largely unknown. This systematic review aims to close this gap and provides recommendations for future applications. Methods and results: Pubmed and EMBASE were searched for applied publications using AI/ML approaches in cardiovascular medicine without limitations regarding study design or study population. The PRISMA statement was followed in this review. A total of 215 studies were identified and included in the final analysis. The majority (87%) of methods applied belong to the context of supervised learning. Within this group, tree-based methods were most commonly used, followed by network and regression analyses as well as boosting approaches. Concerning the areas of application, the most common disease context was coronary artery disease followed by heart failure and heart rhythm disorders. Often, different input types such as electronic health records and images were combined in one AI/ML application. Only a minority of publications investigated reproducibility and generalizability or provided a clinical trial registration. Conclusions: A major finding is that methodology may overlap even with similar data. Since we observed marked variation in quality, reporting of the evaluation and transparency of data and methods urgently need to be improved.

Background—There is no systematic assessment of available evidence on effectiveness and comparative effectiveness of balloon dilatation and stenting for aortic coarctation. Methods and Results—We systematically searched 4 online databases to identify and select relevant studies of balloon dilatation and stenting for aortic coarctation based on a priori criteria (PROSPERO 2014:CRD42014014418). We quantitatively synthesized results for each intervention from single-arm studies and obtained pooled estimates for relative effectiveness from pairwise and network meta-analysis of comparative studies. Our primary analysis included 15 stenting (423 participants) and 12 balloon dilatation studies (361 participants), including patients ≥10 years of age. Post-treatment blood pressure gradient reduction to ≤20 and ≤10 mm Hg was achieved in 89.5% (95% confidence interval, 83.7–95.3) and 66.5% (44.1–88.9%) of patients undergoing balloon dilatation, and in 99.5% (97.5–100.0%) and 93.8% (88.5–99.1%) of patients undergoing stenting, respectively. Odds of achieving ≤20 mm Hg were lower with balloon dilatation as compared with stenting (odds ratio, 0.105 [0.010–0.886]). Thirty-day survival rates were comparable. Numerically more patients undergoing balloon dilatation experienced severe complications during admission (6.4% [2.6–10.2%]) compared with stenting (2.6% [0.5–4.7%]). This was supported by meta-analysis of head-to-head studies (odds ratio, 9.617 [2.654–34.845]) and network meta-analysis (odds ratio, 16.23, 95% credible interval: 4.27–62.77) in a secondary analysis in patients ≥1 month of age, including 57 stenting (3397 participants) and 62 balloon dilatation studies (4331 participants). Conclusions—Despite the limitations of the evidence base consisting predominantly of single-arm studies, our review indicates that stenting achieves superior immediate relief of a relevant pressure gradient compared with balloon dilatation.

Modeling different treatment options before a procedure is performed is a promising approach for surgical decision making and patient care in heart valve disease. This study investigated the hemodynamic impact of different prostheses through patient‐specific MRI‐based CFD simulations. Ten time‐resolved MRI data sets with and without velocity encoding were obtained to reconstruct the aorta and set hemodynamic boundary conditions for simulations. Aortic hemodynamics after virtual valve replacement with a biological and mechanical valve prosthesis were investigated. Wall shear stress (WSS), secondary flow degree (SFD), transvalvular pressure drop (TPD), turbulent kinetic energy (TKE), and normalized flow displacement (NFD) were evaluated to characterize valve‐induced hemodynamics. The biological prostheses induced significantly higher WSS (medians: 9.3 vs. 8.6 Pa, P = 0.027) and SFD (means: 0.78 vs. 0.49, P = 0.002) in the ascending aorta, TPD (medians: 11.4 vs. 2.7 mm Hg, P = 0.002), TKE (means: 400 vs. 283 cm²/s², P = 0.037), and NFD (means: 0.0994 vs. 0.0607, P = 0.020) than the mechanical prostheses. The differences between the prosthesis types showed great inter‐patient variability, however. Given this variability, a patient‐specific evaluation is warranted. In conclusion, MRI‐based CFD offers an opportunity to assess the interactions between prosthesis and patient‐specific boundary conditions, which may help in optimizing surgical decision making and providing additional guidance to clinicians.

Background: Approximately 15% of neonates require respiratory support at birth, the demand of which increases with decreasing gestational age. Positive end-expiratory pressure (PEEP) stabilizes the airways and improves both pulmonary functional residual capacity and compliance. Self-inflating bags, which can be used with and without a PEEP-valve, are most commonly used for neonatal resuscitation, pressure limited T-piece resuscitators are becoming increasingly popular. The aim of the study was to investigate the reliability of PEEP provision of both systems. Material and methods: An intubated, leak free mannequin (equivalent to 1 kg neonate, pulmonary compliance 0.2 ml*cmH₂O⁻¹) was used for testing both devices. Eleven PEEP-valves attached to a 240 ml self-inflating bag and 5 T-piece resuscitators were investigated. Provision of a PEEP of 5 cmH₂O (gas flow of 8l/min) at manual ventilation at breaths 40/min was investigated. Data were recorded using a standard pneumotachograph. Results: Only 1/11 PEEP-valves provided a PEEP of 5 cmH₂O (mean (SD) 2.95 (1.82) cmH₂O, CV 0.62%), in 5/11 (45%) PEEP was 5 cmH₂O (mean 5.59 (0.32) cmH₂O, CV 0.06%). Significant differences in individual performance per device (p<0.05) and between systems (p=0.007) were found. Conclusion: Self-inflating bags did not reliably provide the desired PEEP of 5 cmH₂O, whereas T-piece resuscitators did reliably provide the set PEEP-level, with less variability. When using self-inflating bags with PEEP-valves, neonatologists should check the equipment regarding the reliability of PEEP provision. Hintergrund: Bis zu 15% aller Neugeborenen benötigen postnatal eine Atemunterstützung. Ein positiver endexspiratorischer Druck (PEEP) von 4–6 cm H₂O stabilisiert die Atemwege und verbessert die funktionelle Residualkapazität und die Compliance. Selbstentfaltende Beatmungsbeutel sind das am häufigsten eingesetzte Handbeatmungsgerät in der Erstversorgung Neugeborener. Diese werden in vielen Einrichtungen mit einem aufsteckbaren PEEP-Ventil verwendet. Auch T-Stück-Beatmungssysteme sind in der Lage, PEEP zu generieren. Fragestellung: Wie zuverlässig können beide Systeme im Vergleich PEEP generieren? Methodik: Zur Untersuchung beider Systeme wurde eine intubierte Modellpuppe (entsprechend einem 1-kg-Neugeborenen, Pulmonary Compliance 0,2 ml*kPa⁻¹) verwendet. Elf PEEP-Ventile wurden an einem selbstentfaltenden Beatmungsbeutel für Neugeborene (240 ml) im Vergleich zu 5 T-Stück-Beatmungssystemen untersucht. Bei einem einheitlichen Gasfluss (8 l/min) und einer manuellen Atemfrequenz von 40/min wurde die Zuverlässigkeit der Geräte beurteilt, einen PEEP von 5 cm H₂O zu generieren. Die Beatmungsdaten wurden mit einem Pneumotachografen erfasst. Ergebnis: Nur 1/11 PEEP-Ventilen erreichte einen PEEP von 5 cmH₂O (Mittelwert (Standardabweichung) 2,95 (1,82) cmH₂O, VC 0,6%). Bei 5/11 Ventilen (45%) lag der PEEP unter 3 cmH₂O, bei 2 Ventilen unter 0,3 cmH₂O. Im Vergleich dazu erreichten alle T-Stück-Systeme einen PEEP von über 5 cmH₂O (Mittelwert 5,59 (0,32) cmH₂O, VC 0,06%). Es wurden signifikante Unterschiede innerhalb der Systeme (p<0,05) und zwischen den Geräten (p=0,007) gefunden. Diskussion: Selbstentfaltende Beatmungsbeutel konnten keinen zuverlässigen PEEP von 5 cmH₂O garantieren. Im Gegensatz dazu erzeugten T-Stück-Beatmungssysteme PEEP wesentlich konsistenter und zuverlässiger. Bei der Benutzung von selbstentfaltenden Beatmungsbeuteln mit PEEP-Ventilen sollte das verwendete Equipment regelmäßig mittels Manometer geprüft werden.