An international comparison of haemoglobin deferral prediction models for blood banking

Article Hematology

Individualized risk trajectories for iron-related adverse outcomes in repeat blood donors

W. Alton Russell et al.

Summary: This study developed multiclass prediction models to estimate the risk of iron deficiency in repeat blood donors, comparing the use of extra biomarkers like ferritin and soluble transferrin receptor. Results showed that ferritin was the most important variable in predicting adverse outcomes, and identified three risk archetypes based on individual risk trajectories.

TRANSFUSION (2022)

添加到收藏夹

Article Hematology

Prediction and impact of personalized donation intervals

Jarkko Toivonen et al.

Summary: The study evaluated the possibility of predicting blood donor deferral due to low hemoglobin levels using computational prediction tools. While linear predictors were found to generally predict hemoglobin levels well, difficulties were encountered in predicting low hemoglobin values. The use of any of the predictors in blood collection could potentially lead to cost savings and benefits for blood donors and establishments.

VOX SANGUINIS (2022)

添加到收藏夹

Article Hematology

A computational model for prediction of ferritin and haemoglobin levels in blood donors

Yared Paalvast et al.

Summary: This study used a computational model and baseline values to predict the levels of hemoglobin and ferritin in blood donors, and calculated the optimal donation frequencies. The results showed that baseline ferritin levels were the most important factor in predicting future levels, which can help donors determine the most suitable donation frequency.

BRITISH JOURNAL OF HAEMATOLOGY (2022)

添加到收藏夹

Article Hematology

Why the majority of on-site repeat donor deferrals are completely unwarranted horizontal ellipsis

Mart P. Janssen

Summary: This study aims to address the issue of donor deferral due to the variability in hemoglobin measurement outcomes. A new algorithm for donor deferral, incorporating the information of measurement variability, was tested on a cohort of new Dutch donors. The results revealed that a majority of deferrals were unnecessary, while some donors who did not meet the eligibility criteria were still able to donate.

TRANSFUSION (2022)

添加到收藏夹

Article Hematology

Explainable haemoglobin deferral predictions using machine learning models: Interpretation and consequences for the blood supply

Marieke Vinkenoog et al.

Summary: This study presents a model that predicts Hb deferral in an explainable way. If implemented, 64% of non-deferred donors would be invited before or on their original donation date, while 80% of deferred donors would be invited later. By using this model to invite donors, the number of blood bank visits would increase by 15%, while deferral rates would decrease by 60% (currently 3% for women and 1% for men).

VOX SANGUINIS (2022)

添加到收藏夹

Article Hematology