Clinician's guide to trustworthy and responsible artificial intelligence in cardiovascular imaging.

A growing number of artificial intelligence (AI)-based systems are being proposed and developed in cardiology, driven by the increasing need to deal with the vast amount of clinical and imaging data with the ultimate aim of advancing patient care, diagnosis and prognostication. However, there is a critical gap between the development and clinical deployment of AI tools. A key consideration for implementing AI tools into real-life clinical practice is their "trustworthiness" by end-users. Namely, we must ensure that AI systems can be trusted and adopted by all parties involved, including clinicians and patients. Here we provide a summary of the concepts involved in developing a "trustworthy AI system." We describe the main risks of AI applications and potential mitigation techniques for the wider application of these promising techniques in the context of cardiovascular imaging. Finally, we show why trustworthy AI concepts are important governing forces of AI development.

Impact of respiration gating on image integration guided atrial fibrillation ablation.

BACKGROUND: Radiofrequency (RF) catheter ablation guided by electroanatomic mapping systems is an effective therapy for atrial fibrillation. However, it may be affected by respiration movements. The aim of this study was to determine the impact of respiratory gating on procedural parameters in patients undergoing catheter ablation of atrial fibrillation (AF). METHODS AND RESULTS: One-hundred forty consecutive patients undergoing pulmonary vein isolation were admitted to study. Respiratory gating module (AccuResp algorithm, Carto3, Biosense Webster) was enabled in 70 patients and disabled in 70 patients during procedures. Successful pulmonary vein isolation and sinus rhythm were obtained in all patients. A significant reduction in total procedure times [median 77, interquartile range (IQR 66-95) min vs median 82 (IQR 72-104) min, p < 0.05] and fluoroscopy times [median 14 (IQR 9-17) min vs median 16 (IQR 12-22) min, p < 0.05] were observed in the respiratory gated group. Although ablation times (duration between the first and last ablation) were significantly shorter in respiratory gated group [median 37 (IQR 32-53) min vs median 48 (IQR 39-65) min, p < 0.05], total RF application durations were not different between two groups [median 1,554 (IQR 1,213-2,196) s vs median 1,802 (IQR 1,344-2,448) s, p = 0.11]. Difference in electroanatomical map reconstruction times was not significant [median 14 (IQR 12-16) min in gated group vs median 13 (IQR 10-18) min in nongated group, p = 0.19]. CONCLUSION: Respiratory gating significantly improves fluoroscopy and ablation times during electroanatomic mapping guided AF ablation. Respiratory gated maps may provide uninterrupted continuous ablation applications. Furthermore, using automatic respiratory gating module does not prolong mapping times.

[Health care costs of acute myocardial infarction in Hungary, 2003-2005]. / Az akut myocardialis infarctus betegségterhe Magyarországon, 2003-2005.

BACKGROUND: The morbidity of acute myocardial infarction (AMI) is remarkable in Hungary, therefore understanding the disease burden more accurately is inevitable. AIM: We assessed the hospitalized AMI patient's burden on the financer both in active and chronic hospital care as well as outpatient visits and we estimated the size of indirect social costs. METHODS: We assessed the active and chronic hospital care costs of 'new' AMI patients having the event in May 2003. The costs were assessed in the subsequent 12 and 24 months to the event in the population over 25 with the morbidity from the database of the National Health Insurance Fund Administration (NHIFA). Data were collected by gender and age (age groups 25-44, 45-64, 65 and over). Costs of GPs, specialist visits, transportation and productivity losses were taken into account as other costs. RESULTS: Average health insurance costs of AMI's active hospital care in the first 12 months are generally higher in females as in males; 476.3 thousand HUF vs 391.1 thousand HUF (65 and over), 429.1 thousand HUF vs 389.4 thousand HUF (45-64) and 229.5 thousand HUF vs 240.6 thousand HUF (25-44). The burden in the chronic care is 15-40 thousand HUF per patient in the first year, which is similar to the active care costs in the 13-24th months after the AMI (22-54 thousand HUF). CONCLUSION: NHIFA was estimated to spend 4.4 billion HUF on direct health care on behalf of the nearly 12 thousand annual AMI patients in the first 12 months, 3.6 billion HUF on the active and 370 million on the chronic hospital care. Avoiding one AMI could save 345-565 thousand HUF (depending on gender and age) direct health care cost in the first 12 months. In our estimation the annual indirect costs of AMI exceed 840 million HUF (177 829 HUF/patient) in the working age group.

Supramolecular polymers based on the quadruplex formation of ditopic guanosine macromonomers in nonaqueous media.

The formation of supramolecular polymeric aggregates with a molecular mass of 100 kDa in a nonaqueous solution from a telechelic dimer of isopropylidene guanosine in the presence of K(+) ions is reported. The possible structure of macromonomers resulting from the development of G4 quartets was deduced from DOSY NMR, circular dichroism spectra, and dynamic light scattering measurements.