Artificial intelligence belongs to the field of computer science. In the past few decades, artificial intelligence has shown broad application prospects in the medical field. With the development of computer technology in recent years, doctors and computer scientists have just begun to discover its potential for clinical application, especially in the field of congenital heart disease. Artificial intelligence now has been successfully applied to the prediction, intelligent diagnosis, medical image segmentation and recognition, clinical decision support of congenital heart disease. This article reviews the application of artificial intelligence in congenital cardiology.
Cardiovascular diseases are the leading cause of death and their diagnosis and treatment rely heavily on the variety of clinical data. With the advent of the era of medical big data, artificial intelligence (AI) has been widely applied in many aspects such as imaging, diagnosis and prognosis prediction in cardiovascular medicine, providing a new method for accurate diagnosis and treatment. This paper reviews the application of AI in cardiovascular medicine.
ObjectiveTo study the clinical characteristics of patients with partial and transitional atrioventricular septal defects (P/TAVSDs) in our hospital, and to evaluate the early follow-up outcomes from a real-world research perspective.MethodsThe clinical data of all patients diagnosed with P/TAVSDs from January 1, 2018 to July 12, 2020, in our hospital were collected, and all patients' examination results were used as the real-world follow-up data, univariable Cox risk proportional model was used to analyze the outcomes. A total of 93 patients were finally included in the analysis, 72 with partial and 21 with transitional AVSD. There were 38 males and 55 females at age of 182.0 months (20.0 d to 779.5 months).ResultsUnivariable Cox proportional risk model suggested that at least one cardiac malformation (HR=15.00, 95%CI 3.00 to 75.00, P=0.001), preoperative moderate or greater mitral regurgitation (HR=6.60, 95%CI 1.70 to 26.00, P=0.007), and preoperative moderate or greater tricuspid regurgitation (HR=13.00, 95%CI 3.10 to 51.00, P<0.0001) were risk factors for moderate or greater postoperative atrioventricular valve regurgitation.ConclusionChildren with coarctation of the aorta or partial pulmonary vein connection, moderate or greater preoperative mitral regurgitation, and moderate or greater preoperative tricuspid regurgitation need to be alerted to the risk of moderate or greater postoperative atrioventricular valve regurgitation. Real-world data, with relaxed statistical P values and combined expertise, can suggest clinical conclusions that are close to those of high-quality retrospective studies.
ObjectiveTo review the characteristics of patients who underwent atrioventricular septal defects (AVSD) repair with prosthetic valve ring implantation in our hospital, and to analyze the safety and effectiveness of this intervention.MethodsThe clinical data of all patients diagnosed with AVSD who received surgery repair and prosthetic valve ring implantation from January 1, 2018 to July 12, 2020 in Guangdong Provincial People's Hospital were collected and analyzed. There were 22 patients with 9 males and 13 females at a median age of 35.00 (14.10, 53.00) years. There were 9 (40.9%) patients with prosthetic half or full rings placed on the left atrioventricular valve and 18 (81.8%) patients with prosthetic half or full rings placed on the right atrioventricular valve. ResultsThe median postoperative hospital stay was 7.00 (6.00, 8.80) d, and the postoperative mechanically assisted ventilation time was 11.00 (6.25, 19.00) h. There were 2 (9.1%) patients of moderate or higher postoperative atrioventricular valve regurgitation, 1 on the left and 1 on the right. There was one patient (4.5%) of the postoperative residual septal defect. There was no left ventricular inflow or outflow tract obstruction and no postoperative residual atrial septal defect during the follow-up of 152.00 (124.00, 1 030.00) d.ConclusionImplantation of a prosthetic ring is safe and effective in patients with AVSD, and the structural strength of the ring may be improved after the implantation. The physiological development of the AVSD annulus after prosthetic ring implantation and the results of long-term follow-up needs further attention.
ObjectiveTo quest the risk factors of poor prognoses in children with tetralogy of Fallot (TOF) during perioperative period and evaluate its clinical application values.MethodsA retrospective analysis of the clinical data of 119 children who underwent one-stage correction of TOF in Guangdong Provincial People's Hospital from September 2016 to January 2019. The cohort includes 75 males and 44 females, with ages ranging from 3.2-137.1 (13.2±1.4) months and weights ranging from 4.6-21.0 (8.3±0.2) kg. Perioperative poor prognosis was defined as duration of mechanically assisted ventilation >48 h or secondary intubation, vasoactive-inotropic score (VIS) within 48 h >40, postoperative length of stay >14 d, and the occurrence of the major adverse events. Major adverse events were defined as early death, malignant arrhythmia, low cardiac output syndrome, non-fatal cardiac arrest, postoperative reintervention, diaphragm paralysis, and other clinical complications. Univariate and multivariate logistic analyses were used to analyze the correlation between risk factors and poor prognoses.ResultsThere was 1 perioperative death, and 9 with major adverse events. Variables selected by Least Absolute Shrinkage and Selection Operator (LASSO) included 2 preoperative variables (McGoon index, aortic root diameter index) and 4 intra-operative variables [left-right direction of bicuspid pulmonary valve, total length of right ventricular outflow tract (RVOT) incision index, pulmonary valve with commissurotomy, and minimum temperature in cardiopulmonary bypass (CPB)]. Univariate and multivariate logistic analyses were used to the above factors, respectively. The variables with statistical significance (P≤0.05) were McGoon index, aortic root diameter index, left-right direction of bicuspid pulmonary valve, and minimum temperature in CPB. A nomogram was established based on the above factors, and the results showed that the left-right direction of bicuspid pulmonary valve was more risky than the tricuspid pulmonary valve and the anterior-posterior direction of bicuspid pulmonary valve. The lower the McGoon index, the higher aortic root diameter, and the lower temperature in CPB, the higher risk of poor prognostic events in children with TOF.ConclusionThe left-right direction of the pulmonary bicuspid valve has a higher risk of poor prognosis than the tricuspid pulmonary valve and the anterior-posterior direction of bicuspid pulmonary valve. With the smaller McGoon index and the larger aortic root diameter, the risk of poor prognoses in children with TOF is higher. The temperature in CPB being lower than medium-low temperature obviously relates to the high incidence of poor prognostic events, which can be used as an auxiliary reference standard for decision-making in pediatric TOF surgery in the future.