Intraoperative Hypertension Is Associated with Postoperative Acute Kidney Injury after Laparoscopic Surgery.

BACKGROUND: It is well demonstrated that intraoperative blood pressure is associated with postoperative acute kidney injury (AKI); however, the association between severity and duration of abnormal intraoperative blood pressure (BP) with AKI in patients undergoing laparoscopic surgery remains unknown. METHODS: This retrospective cohort study included 12,414 patients aged ≥ 18 years who underwent a single elective laparoscopic abdominal surgery during hospitalization between October 2011 and April 2017. Multivariate stepwise logistic regressions were applied to determine the correlation between the severity and duration of intraoperative mean arterial pressure (MAP, (systolic BP + 2 × diastolic BP)/3), acute intraoperative hypertension (IOTH) and postoperative AKI, in different periods of surgery. RESULTS: A total of 482 hospitalized patients (3.9%) developed surgery-related AKI. Compared with those without IOTH or with preoperative mean MAP (80-85 mmHg), acute elevated IOTH (odds ratio, OR, 1.4, 95% CI, 1.1 to 1.7), mean MAP 95-100 mmHg (OR, 1.8; 95% CI, 1.3 to 2.7), MAP 100-105 mmHg (OR, 2.4; 95% CI, 1.6 to 3.8), and more than 105 mmHg (OR, 1.9; 95% CI, 1.1 to 3.3) were independent of other risk factors in a diverse cohort undergoing laparoscopic surgery. In addition, the risk of postoperative AKI appeared to result from long exposure (≥20 min) to IOTH (OR, 1.9; 95% CI, 1.5 to 2.5) and MAP ≥ 115 mmHg (OR, 2.2; 95% CI, 1.6 to 3.0). Intraoperative hypotension was not found to be associated with AKI in laparoscopic surgery patients. CONCLUSIONS: Postoperative AKI correlates positively with intraoperative hypertension in patients undergoing laparoscopic surgery. These findings provide an intraoperative evaluation criterion to predict the occurrence of postoperative AKI.

Adverse Drug Reaction Discovery Using a Tumor-Biomarker Knowledge Graph.

Adverse drug reactions (ADRs) are a major public health concern, and early detection is crucial for drug development and patient safety. Together with the increasing availability of large-scale literature data, machine learning has the potential to predict unknown ADRs from current knowledge. By the machine learning methods, we constructed a Tumor-Biomarker Knowledge Graph (TBKG) which contains four types of node: Tumor, Biomarker, Drug, and ADR using biomedical literatures. Based on this knowledge graph, we not only discovered potential ADRs of antitumor drugs but also provided explanations. Experiments on real-world data show that our model can achieve 0.81 accuracy of three cross-validation and the ADRs discovery of Osimertinib was chosen for the clinical validation. Calculated ADRs of Osimertinib by our model consisted of the known ADRs which were in line with the official manual and some unreported rare ADRs in clinical cases. Results also showed that our model outperformed traditional co-occurrence methods. Moreover, each calculated ADRs were attached with the corresponding paths of "tumor-biomarker-drug" in the knowledge graph which could help to obtain in-depth insights into the underlying mechanisms. In conclusion, the tumor-biomarker knowledge-graph based approach is an explainable method for potential ADRs discovery based on biomarkers and might be valuable to the community working on the emerging field of biomedical literature mining and provide impetus for the mechanism research of ADRs.