Comparison of Blood Concentration and Weight-Based Heparin and Protamine Dosing Strategies for Cardiopulmonary Bypass: A Systematic Review and Meta-Analysis.

BACKGROUND:  The conventional method of heparin and protamine management during cardiopulmonary bypass (CPB) is based on total body weight which fails to account for the heterogeneous response to heparin in each patient. On the other hand, the literature is inconclusive on whether individualized anticoagulation management based on real-time blood heparin concentration improves post-CBP outcomes. METHODS:  We searched databases of Medline, Excerpta Medica dataBASE (EMBASE), PubMed, Cumulative Index to Nursing and Allied Health Literature (CINHL), and Google Scholar, recruiting randomized controlled trials (RCTs) and prospective studies comparing the outcomes of dosing heparin and/or protamine based on measured heparin concentration versus patient's total body weight for CPB. Random effects meta-analyses and meta-regression were conducted to compare the outcome profiles. Primary endpoints include postoperative blood loss and the correlation with heparin and protamine doses, the reversal protamine and loading heparin dose ratio; secondary endpoints included postoperative platelet counts, antithrombin III, fibrinogen levels, activated prothrombin time (aPTT), incidences of heparin rebound, and re-exploration of chest wound for bleeding. RESULTS:  Twenty-six studies, including 22 RCTs and four prospective cohort studies involving 3,810 patients, were included. Compared to body weight-based dosing, patients of individualized, heparin concentration-based group had significantly lower postoperative blood loss (mean difference (MD)=49.51 mL, 95% confidence interval (CI): 5.33-93.71), lower protamine-to-heparin dosing ratio (MD=-0.20, 95% CI: -0.32 ~ -0.12), and higher early postoperative platelet counts (MD=8.83, 95% CI: 2.07-15.59). The total heparin doses and protamine reversal were identified as predictors of postoperative blood loss by meta-regression. CONCLUSIONS:  There was a significant correlation between the doses of heparin and protamine with postoperative blood loss; therefore, précised dosing of both could be critical for reducing bleeding and transfusion requirements. Data from the enrolled studies indicated that compared to conventional weight-based dosing, individualized, blood concentration-based heparin and protamine dosing may have outcome benefits reducing postoperative blood loss. The dosing calculation of heparin based on the assumption of a one-compartment pharmacokinetic/pharmacodynamic (PK/PD) model and linear relationship between the calculated dose and blood heparin concentration may be inaccurate. With the recent advancement of the technologies of machine learning, individualized, precision management of anticoagulation for CPB may be possible in the near future.

Model-Driven Engineering Techniques and Tools for Machine Learning-Enabled IoT Applications: A Scoping Review.

This paper reviews the literature on model-driven engineering (MDE) tools and languages for the internet of things (IoT). Due to the abundance of big data in the IoT, data analytics and machine learning (DAML) techniques play a key role in providing smart IoT applications. In particular, since a significant portion of the IoT data is sequential time series data, such as sensor data, time series analysis techniques are required. Therefore, IoT modeling languages and tools are expected to support DAML methods, including time series analysis techniques, out of the box. In this paper, we study and classify prior work in the literature through the mentioned lens and following the scoping review approach. Hence, the key underlying research questions are what MDE approaches, tools, and languages have been proposed and which ones have supported DAML techniques at the modeling level and in the scope of smart IoT services.