Impact of body weight on hemoglobin increments in adult red blood cell transfusion

From Unit to Dose: A Machine Learning Approach for Precise Prediction of Hemoglobin and Iron Content in Individual Packed Red Blood Cell Units

Transfusion of packed red blood cells (pRBCs) saves lives, but iron overload limits survival of chronically transfused patients. Quality control methods, which involve entering pRBC units and removing them from the blood supply, reveal that hemoglobin (38.5-79.9 g) and heme iron (133.42-276.89 mg) vary substantially between pRBCs. Yet, neither hemoglobin nor iron content can be quantified for individual clinically used pRBCs leading to rules of thumb for pRBC transfusions. Keeping their integrity, the authors seek to predict hemoglobin/iron content of any given pRBC unit applying eight machine learning models on 6,058 pRBCs. Based on thirteen features routinely collected during blood donation, production and quality control testing, the model with best trade-off between performance and complexity in hemoglobin/iron content prediction is identified. Validation of this model in an independent cohort of 2637 pRBCs confirms an adjusted R² > 0.9 corresponding to a mean absolute prediction error of ≤1.43 g hemoglobin/4.96 mg iron (associated standard deviation: ≤1.13 g hemoglobin/3.92 mg iron). Such unprecedented precise prediction enables reliable pRBC dosing per pharmaceutically active agent, and monitoring iron uptake in patients and individual iron loss in donors. The model is implemented in a free open source web application to facilitate clinical application.

Assessing predictors of futility in patients receiving massive transfusions

BACKGROUND

Massive transfusions are associated with a high mortality rate, but there is little evidence indicating when such efforts are futile. The purpose of this study was to identify clinical variables that could be used as futility indicators in massively transfused patients.

METHODS

We retrospectively analyzed 138 adult surgical patients at our institution receiving a massive transfusion (2016-2019). Peak lactate and nadir pH within 24 h of massive transfusion initiation, along with other clinical variables, were assessed as predictors of the primary outcome, in-hospital mortality.

RESULTS

The overall rate of in-hospital mortality among our patient population was 52.9% (n = 73). Increasing lactate and decreasing pH were associated with greater mortality among massively transfused patients. Mortality rates were ~2-fold higher for patients in the highest lactate category (≥10.0 mmol/L: 25 of 37; 67.6%) compared to the lowest category (0.0-4.9 mmol/L: 17 of 48; 35.4%) (p = .005), and ~2.5-fold higher for patients in the lowest pH category (<7.00: 8 of 9; 88.9%) compared to the highest category (≥7.40: 8 of 23; 34.7%) (p = .016). Increasing age was also associated with higher mortality (≥65 years: 24 of 33; 72.7%) when compared to younger patients (18-64 years: 49 of 105; 46.7%) (p = .010).

CONCLUSIONS

Peak lactate ≥10.0 mmol/L, nadir pH <7.00, and age ≥65 years were significantly associated with higher rates of in-hospital mortality among massively transfused patients. Incorporating these clinical parameters into a futility index for massive transfusions will be useful in situations where blood products are scarce and/or mortality may be unavoidable.