Continuous renal replacement therapy (CRRT) is one of the major treatments for critically ill patients. With the development of information technology, the informatization and artificial intelligent of CRRT has received wide attention, which has promoted the optimization of CRRT in terms of workflow, teaching method as well as scientific research. Benefiting from the big data generated, artificial intelligence is expected to be applied in the precision treatment, quality control, timing of intervention, as well as prognosis assessment in severe AKI, so as to ultimately improve the therapeutic effect of CRRT among critically ill patients. This paper summarizes the information construction of CRRT and the research progress of artificial intelligence, which can be used as a reference for practitioners in kidney disease, critical medicine, emergency medicine and other related fields.
Objective To explore the risk factors affecting the prognosis of patients with acute kidney injury (AKI) after extracorporeal circulation surgery who receive continuous renal replacement therapy (CRRT). Methods Patients who developed AKI and underwent CRRT treatment after extracorporeal circulation surgery at the First Affiliated Hospital of Chongqing Medical University between May 2019 and May 2024 were retrospectively selected. According to the prognosis, patients were divided into the good prognosis group and the poor prognosis group. Basic information, duration of extracorporeal circulation during surgery, aortic occlusion time, timing and duration of CRRT initiation therapy, relevant laboratory indicators before surgery, during CRRT intervention, and upon discharge or death were collected. The risk factors affecting the prognosis of such patients were analyzed. Results A total of 45 patients were included. Among them, there were 20 cases in the good prognosis group and 25 cases in the poor prognosis group. There was no statistically significant difference in the basic information between the two groups (P>0.05). Compared with the poor prognosis group, the good prognosis group had decreased preoperative urea nitrogen and increased hemoglobin levels, reduced levels of alanine aminotransferase and aspartate aminotransferase during the initiation of CRRT treatment, and reduced levels of white blood cell count, neutrophil percentage, alanine aminotransferase and aspartate aminotransferase and elevated platelet count before discharge or death (P<0.05). The results of multivariate logistic regression analysis showed that the total duration of CRRT treatment [odds ratio (OR)=1.007, 95% confidence interval (CI) (1.000, 1.015), P=0.046], white blood cell count before discharge or death [OR=1.541, 95%CI (1.011, 2.349), P=0.044], and platelet count before discharge or death [OR=0.964, 95%CI (0.937, 0.991), P=0.010] could affect patient prognosis. Conclusions In patients with AKI after extracorporeal circulation surgery, if combined with renal dysfuction and anemia before surgery, liver function damage and secondary infection during CRRT initiation therapy may be related to poor patient prognosis. The longer the duration of CRRT treatment, the higher the white blood cells before discharge or death, and the lower the platelet count are independent risk factors for poor prognosis in patients.
Objective To summarize the research progress of acute kidney injury after liver transplantation. Method The literatures on acute kidney injury after liver transplantation was collected and reviewed. Results Acute kidney injury after liver transplantation was associated with multiple risk factors. Early prevention and treatment of risk factors in perioperative period was the main measure to reduce acute kidney injury after liver transplantation. Early postoperative diagnosis and timely intervention could reduce the incidence of chronic kidney disease and improve the long-term prognosis of liver transplantation recipients. Conclusion Acute kidney injury is a common complication after liver transplantation which affects prognosis and long-term survival of patients.
ObjectiveTo systematically evaluate the risk factors of acute kidney injury after surgery for acute type A aortic dissection.MethodsWe searched the CNKI, Wanfang Database, VIP, PubMed, Web of science, Cochrane Library (from inception to January 2019) to identify studies about the risk factors of acute kidney injury after surgery for acute type A aortic dissection. Quality of the included studies was evaluated by Kars-Ottawa scale. The meta-analysis was performed by RevMan 5.3 software.ResultsA total of 16 case-control studies were included involving 1 728 patients. The results of meta-analysis showed that gender (OR=1.58, 95% CI 1.31 to 1.89, P<0.001), body mass index (OR=1.05, 95% CI 0.66 to 1.45, P<0.001), hypertension (OR=1.58, 95% CI 1.10 to 2.26, P=0.010), smoking history (OR=1.71, 95% CI 1.12 to 2.61, P=0.010), preoperative serum creatinine level (OR=30.26, 95% CI 20.17 to 40.35, P<0.000 01), preoperative white blood cell (OR=1.73, 95% CI 0.26 to 3.20, P=0.020), extracorporeal circulation time (OR=25.60, 95% CI 21.13 to 30.08, P<0.000 01), aortic occlusion time (OR=13.24, 95% CI 10.27 to 16.22, P<0.001), deep hypothermic circulatory arrest (DHCA) time (OR=2.58, 95% CI 0.86 to 4.29, P=0.003), arch replacement (OR=2.31, 95% CI 1.31 to 4.07, P=0.004), intraoperative blood transfusion (OR=1.27, 95% CI 0.29 to 2.24, P=0.010), postoperative mean arterial pressure (OR=–2.41, 95% CI –4.59 to –0.24, P=0.030), reoperation due to postoperative hemorrhage (OR=4.19, 95% CI 2.04 to 8.63, P<0.001), postoperative acute respiratory insufficiency (OR=6.61, 95% CI 3.21 to 13.60, P<0.001), postoperative mechanical ventilation time (OR=48.51, 95% CI 21.94 to 75.09, P<0.001) were associated with acute kidney injury after surgery for acute type A aortic dissection.ConclusionCurrent evidence shows that gender, body mass index, hypertension, smoking history, preoperative serum creatinine level, preoperative white blood cell, extracorporeal circulation time, aortic occlusion time, deep hypothermic circulatory arrest (DHCA) time, arch replacement, intraoperative blood transfusion, postoperative mean arterial pressure, postoperative hemorrhage reoperation, postoperative acute respiratory insufficiency and postoperative mechanical ventilation time were risk factors for acute kidney injury after surgery for type A aortic dissection. Medical staff can strengthen perioperative management of patients with acute type A aortic dissection combined with the above factors, so as to reduce the incidence of acute kidney injury after operation and improve the clinical prognosis of patients.
ObjectiveTo compare the impact of cardiopulmonary coronary artery bypass grafting (CCABG) and off-pump coronary artery bypass grafting (OPCAB) on the incidence of postoperative acute kidney injury (AKI) in the elderly patients (age≥70 years). MethodsThe clinical data of the isolated coronary artery bypass grafting (CABG) patients (age≥70 years) in our center from January 1, 2009 to December 31, 2017 were collected and retrospectively analyzed. The patients with long-term dialysis, missing serum creatinine data, emergent surgery or CABG combined with other cardiac procedures were excluded. Totally there were 3 346 patients undergoing isolated CABG, and finally 1 405 patients (age≥70 years) entered the study. The elderly patients were divided into a CCABG group (956 patients) and an OPCAB group (449 patients) according to whether they used extracorporeal circulation. The incidence and severity of postoperative AKI in the two groups were compared. Results AKI occurred in 306 (32.0%) patients in the CCABG group and in 138 (30.7%) patients in the OPCAB group with no significant difference (P=0.677). According to the acute kidney injury network (AKIN) criteria, the severity of AKI in the CCABG vs. OPCAB was as followings, AKIN stage Ⅰ: 211 (22.1%) vs. 93 (20.7%); AKIN stage Ⅱ: 51 (5.3%) vs. 23 (5.1%); and AKIN stage Ⅲ: 44 (4.6%) vs. 22 (4.9%) with no significant difference (P=0.579, 1.000 and 0.788). There was no significant difference in the new onset of dialysis between the CCABG group (31 patients, 3.2%) and the OPCAB group (10 patients, 2.2%, P=0.376). Conclusion AKI is a common complication in the elderly CABG patients, with AKIN stage Ⅰ accounting for the most proportion, but rate of postoperative renal replacement therapy is low. Compared with CCABG, OPCAB is not associated with a significantly low rate or reduced severity of AKI in elderly patients.
Acute kidney injury (AKI) is a common critical illness in clinical practice, with complex etiologies, acute onset, and rapid progression. It not only significantly increases the mortality rate of patients, but also may progress to chronic kidney disease. Currently, its incidence remains high, and improving early diagnosis rate and treatment efficacy is a major clinical challenge. Artificial intelligence (AI), with its powerful data processing and analysis capabilities, is developing rapidly in medical field, providing new ideas for disease diagnosis and treatment, and showing great potential in revolutionizing the early diagnosis, condition assessment, and treatment decision-making models in the AKI field. This article will review the application progress of AI in AKI prediction, condition assessment, and treatment decision-making, so as to provide references for clinicians and promote the further application and development of AI in the AKI field.
ObjectiveTo determine value of texture analysis based on bi-phasic enhanced CT images in diagnosis of acute pancreatitis (AP) with acute renal injury (AKI).MethodsA total of 62 patients with clinically proven AP including 39 patients with AKI and 23 patients without AKI were analyzed retrospectively. The region of interest (ROI) was chosen at the axial CT-enhanced images of bilateral kidneys using the ITK-Snap software and the texture analysis was performed by the Analysis-Kinetics (A.K.) analysis software. Using the Analysis of Variance, Mann-Whitney U test, Spearman correlation analysis and LASSO regression to reduce the features dimension, and screening out the textures by the logistic regression. The receiver operating characteristic (ROC) curve was established to determine the diagnostic performance of the features.ResultsIn the total of 396 image histological features originally extracted from the texture analysis, 6 features were finally screened out through the dimensionality reduction, involving the Haralick correlation, Inertia, Mean value, Cluster prominence, Short run high grey level emphasis, and Surface area. The area under curve (AUC), threshold, sensitivity, specificity, and accuracy in diagnosing of AP with AKI respectively was 0.926, 0.619, 89.4%, 71.4% and 82.7% by the Haralick correlation; which respectively was 0.790, 0.665, 59.6%, 82.1%, 68.0% by the Inertia; which respectively was 0.983, 0.662, 89.4%, 100%, 93.3% by the Mean value; which respectively was 0.903, 0.696, 80.9%, 85.7%, 82.7% by the Cluster prominence; which respectively was 0.980, 0.778, 76.6%, 100%, 85.3% by the Short run high grey level emphasis; which respectively was 0.819, 0.604, 78.7%, 75.0%, 77.3% by the Surface area.ConclusionTextures of contrast-enhanced CT images have better resolving ability and higher accuracy in diagnosis of AP with AKI and diagnostic efficiency of Mean value is the best.
ObjectiveTo identify the predictors of postoperative acute kidney injury in patients undergoing surgery for Stanford type A acute aortic dissection. MethodsA total of 220 patients who underwent surgery for type A acute aortic dissection in Qingdao Municipal Hospital from September 2010 to September 2017 were divided into two groups including a group A and a group B based on whether acute kidney injury occurred or not after surgery. There were 40 patients with 29 males and 11 females with the mean age of 54.6±9.2 years in the group A, 180 patients with 133 males and 47 females with the mean age of 48.5±7.9 years in the group B. Univariate and multivariate analyses (logistic regression) were used to identify the predictive risk factors.ResultsOverall in-hospital mortality was 5.5%. In univariate analysis, there were statistically significant differences with respect to the age, preoperative creatinine, preoperative white blood cell, the European system for cardiac operative risk evaluation (EuroSCORE), total cardiopulmonary bypass (CPB) time, deep hypothermic circulatory arrest (DHCA) time, arch replacement, red blood cell transfusion intraoperative and in 24 hours postoperatively, postoperative mechanical ventilation time, ICU stay duration, hospital stay duration and in hospital mortality. Multivariate logistic analysis showed that preoperative creatinine, preoperative white blood cell, CPB time, and red blood cell transfusion intraoperative and in 24 hours postoperatively were the independent predictors for postoperative acute kidney injury.ConclusionThe incidence of acute kidney injury is high after surgery for acute Stanford type A aortic dissection. It can be predicted based on above factors, for patients with these risk factors, more perioperative care strategies are needed in order to induce the incidence of acute kidney injury.
ObjectiveTo determine the predictive value of the preoperative prognostic nutritional index (PNI) regarding the development of acute kidney injury (AKI) after non-coronary artery bypass grafting (CABG) cardiac surgery.MethodsThe clinical data of 584 patients who underwent elective non-CABG cardiac surgery with cardiopulmonary bypass (CPB) in our hospital from May to September 2019 were reviewed. There were 268 (45.9%) males and 316 (54.1%) females, with a mean age of 52.1±11.6 years. The mean cardiopulmonary time and aortic-clamp time was 124.8±50.1 min and 86.4±38.9 min, respectively. Totally 449 (76.9%) patients received isolate valve surgery. We developed the risk prediction model of AKI using multivariable logistic regression. The predictive values of preoperative PNI, Cleveland Clinic Score (CCS) and risk prediction model were estimated by the area under the receiver operating characteristic curve (AUC) and Hosmer-Lemeshow goodness-of-fit test. The improvement of preoperative PNI to predictive values of CCS or AKI risk prediction models were defined by the net reclassification index (NRI) and variation of AUC.ResultsThe preoperative PNI could neither effectively predict the occurrence of AKI following non-CABG cardiac surgery (AUC=0.553, 95%CI 0.489-0.617, P=0.095) nor improve the predictive effect of other AKI predictive models. The risk prediction model of AKI structured by our study had high predictive value on AKI or severe AKI (stage 2-3) (AUC=0.741, 95%CI 0.686-0.796, P<0.001) and superior to CCS (AUC=0.512, 95%CI 0.449-0.576, P=0.703).ConclusionThe preoperative PNI can neither predict the occurrence of AKI following elective non-CABG cardiac surgery nor improve the prediction values of other AKI prediction models.
Objective To investigate the early warning value of urinary selenium binding protein 1 (SBP1) in acute kidney injury (AKI) and its risk factor exposure, and compare it with urinary neutrophil gelatinase-associated lipocalin (NGAL). Methods Adult AKI inpatients and medical workers from the Department of Nephrology of the Second Affiliated Hospital of Xi’an Jiaotong University between April 2023 and April 2024 were selected. Patients who underwent percutaneous coronary intervention (PCI) in the Department of Cardiology of the Second Affiliated Hospital of Xi’an Jiaotong University were selected in June 2023. Patients who received cisplatin treatment in the Respiratory Department of the Second Affiliated Hospital of Xi’an Jiaotong University were selected in June 2023. Urinary SBP1 and NGAL levels of patients and medical workers were detected by enzyme-linked immunosorbent assay. Results A total of 14 medical workers and 36 AKI patients were included. Except for gender, alanine aminotransferase, aspartate aminotransferase, total cholesterol (P>0.05), there were statistically significant differences in other indicators between the medical workers and the AKI patients (P<0.05). The urine SBP1 [100.30 (71.50, 138.75) vs.75.60 (65.90, 80.08) pg/mL; U=2.918, P=0.004] and NGAL [423.70 (73.93, 839.80) vs. 14.80 (5.83, 29.98) ng/mL; U=4.668, P<0.001] levels in the AKI group were higher than those in the control group. But the area under the curve of receiver operative characteristic curve of urine SBP1 was smaller than that of urine NGAL (0.768 vs. 0.929). The urine SBP1 level in AKI patients was positively correlated with alanine aminotransferase, aspartate aminotransferase, serum creatinine, and serum glucose (P＜0.05), but negatively correlated with estimated glomerular filtration rate and total cholesterol (P＜0.05). A total of 14 patients who underwent PCI were included. The urinary SBP1/creatinine levels of PCI patients increased 6 hours after surgery compared to preoperative levels [(39.54 ± 8.00) vs. (19.34±2.90) pg/μmol; F=8.862, P=0.011]. The urea nitrogen level decreased 72 hours after surgery compared to preoperative levels (P=0.036), while there were no statistically significant differences in other indicators at other time points (P>0.05). There was no significant change in urinary NGAL levels before and after PCI treatment in patients. A total of 19 patients received cisplatin treatment were included. After cisplatin treatment, the level of urinary SBP1 increased compared to before treatment (P=0.024), while there was no significant change in the level of urinary NGAL after treatment compared to before treatment (P=0.350). After treatment, the levels of urea nitrogen (P=0.041) and cystatin C (P=0.002) increased compared to before surgery, while there was no statistically significant difference in blood creatinine and estimated glomerular filtration rate compared to before treatment (P>0.05). Conclusions Urinary SBP1 levels have certain diagnostic value for AKI, but the diagnostic efficacy is not as good as urinary NGAL. Urinary SBP1 is more sensitive to renal tubular injury caused by nephrotoxic drugs than urinary NGAL.