Predicting haemoglobin deferral using machine learning models: Can we use the same prediction model across countries?

BACKGROUND AND OBJECTIVES

Personalized donation strategies based on haemoglobin (Hb) prediction models may reduce Hb deferrals and hence costs of donation, meanwhile improving commitment of donors. We previously found that prediction models perform better in validation data with a high Hb deferral rate. We therefore investigate how Hb deferral prediction models perform when exchanged with other blood establishments.

MATERIALS AND METHODS

Donation data from the past 5 years from random samples of 10,000 donors from Australia, Belgium, Finland, the Netherlands and South Africa were used to fit random forest models for Hb deferral prediction. Trained models were exchanged between blood establishments. Model performance was evaluated using the area under the precision-recall curve (AUPR). Variable importance was assessed using SHapley Additive exPlanations (SHAP) values.

RESULTS

Across the validation datasets and exchanged models, the AUPR ranged from 0.05 to 0.43. Exchanged models performed similarly within validation datasets, irrespective of the origin of the training data. Apart from subtle differences, the importance of most predictor variables was similar in all trained models.

CONCLUSION

Our results suggest that Hb deferral prediction models trained in different blood establishments perform similarly within different validation datasets, regardless of the deferral rate of their training data. Models learn similar associations in different blood establishments.

An international comparison of haemoglobin deferral prediction models for blood banking

BACKGROUND AND OBJECTIVES

Blood banks use a haemoglobin (Hb) threshold before blood donation to minimize donors' risk of anaemia. Hb prediction models may guide decisions on which donors to invite, and should ideally also be generally applicable, thus in different countries and settings. In this paper, we compare the outcome of various prediction models in different settings and highlight differences and similarities.

MATERIALS AND METHODS

Donation data of repeat donors from the past 5 years of Australia, Belgium, Finland, the Netherlands and South Africa were used to fit five identical prediction models: logistic regression, random forest, support vector machine, linear mixed model and dynamic linear mixed model. Only donors with five or more donation attempts were included to ensure having informative data from all donors. Analyses were performed for men and women separately and outcomes compared.

RESULTS

Within countries and overall, different models perform similarly well. However, there are substantial differences in model performance between countries, and there is a positive association between the deferral rate in a country and the ability to predict donor deferral. Nonetheless, the importance of predictor variables across countries is similar and is highest for the previous Hb level.

CONCLUSION

The limited impact of model architecture and country indicates that all models show similar relationships between the predictor variables and donor deferral. Donor deferral is found to be better predictable in countries with high deferral rates. Therefore, such countries may benefit more from deferral prediction models than those with low deferral rates.

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

BACKGROUND AND OBJECTIVES

Accurate predictions of haemoglobin (Hb) deferral for whole-blood donors could aid blood banks in reducing deferral rates and increasing efficiency and donor motivation. Complex models are needed to make accurate predictions, but predictions must also be explainable. Before the implementation of a prediction model, its impact on the blood supply should be estimated to avoid shortages.

MATERIALS AND METHODS

Donation visits between October 2017 and December 2021 were selected from Sanquin's database system. The following variables were available for each visit: donor sex, age, donation start time, month, number of donations in the last 24 months, most recent ferritin level, days since last ferritin measurement, Hb at nth previous visit (n between 1 and 5), days since the nth previous visit. Outcome Hb deferral has two classes: deferred and not deferred. Support vector machines were used as prediction models, and SHapley Additive exPlanations values were used to quantify the contribution of each variable to the model predictions. Performance was assessed using precision and recall. The potential impact on blood supply was estimated by predicting deferral at earlier or later donation dates.

RESULTS

We present a model that predicts Hb deferral in an explainable way. If used in practice, 64% of non-deferred donors would be invited on or before their original donation date, while 80% of deferred donors would be invited later.

CONCLUSION

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).

Prediction and impact of personalized donation intervals

BACKGROUND AND OBJECTIVES

Deferral of blood donors due to low haemoglobin (Hb) is demotivating to donors, can be a sign for developing anaemia and incurs costs for blood establishments. The prediction of Hb deferral has been shown to be feasible in a number of studies based on demographic, Hb measurement and donation history data. The aim of this paper is to evaluate how state-of-the-art computational prediction tools can facilitate nationwide personalized donation intervals.

MATERIALS AND METHODS

Using donation history data from the last 20 years in Finland, FinDonor blood donor cohort data and blood service Biobank genotyping data, we built linear and non-linear predictors of Hb deferral. Based on financial data from the Finnish Red Cross Blood Service, we then estimated the economic impacts of deploying such predictors.

RESULTS

We discovered that while linear predictors generally predict Hb relatively well, they have difficulties in predicting low Hb values. Overall, we found that non-linear or linear predictors with or without genetic data performed only slightly better than a simple cutoff based on previous Hb. However, if any of our deferral prediction methods are used to assign temporary prolongations of donation intervals for females, then our calculations indicate cost savings while maintaining the blood supply.

CONCLUSION

We find that even though the prediction accuracy is not very high, the actual use of any of our predictors in blood collection is still likely to bring benefits to blood donors and blood establishments alike.

Venous sample is superior to repeated skin-prick testing in blood donor haemoglobin second-line screening

BACKGROUND

Blood donor haemoglobin concentration (Hb) is commonly measured from a skin-prick sample. However, the skin-prick sample is prone to preanalytical error and variation, which may lead to false deferrals due to low Hb.

STUDY DESIGN AND METHODS

We assessed the efficacy of two second-line screening models for the evaluation of blood donors failing the initial skin-prick test. In the venous model (n = 305), Hb was measured from a venous sample at the donation site. In the skin-prick model (n = 331), two additional skin-prick samples were measured. All on-site Hb measurements were performed with HemoCue Hb201+ (HemoCue AB) point-of-care (POC) device. Hb in the venous samples was later also determined with a hematology analyzer (Sysmex XN, Sysmex Co.) to obtain the donor's correct Hb. A questionnaire evaluated Blood Service nurses' preferences regarding Hb assessment.

RESULTS

Significantly less donors were deferred from donation with venous model (40%) than with skin-prick model (51%; chi-square test P = 0·004). Only two donors (0·7%) were incorrectly accepted in the venous model. Further, Blood Service nurses preferred venous model over skin-prick model. After the study, the venous model was implemented nationwide, and in the first two months after implementation, the deferral rate due to low Hb decreased from 2·7% to 1·9%.

CONCLUSION

A venous sample for blood donor Hb second-line screening significantly decreased low Hb deferrals compared to repeated skin-prick testing without compromising donor safety. Valuable donations can be recovered by implementing a practical second-line screening model based on venous sampling.

Evaluation of the diagnostic accuracy and cost of different methods for the assessment of severe anaemia in hospitalised children in Eastern Uganda

Background: Severe anaemia in children requiring hospital admission is a major public health problem in malaria-endemic Africa. Affordable methods for the assessment of haemoglobin have not been validated against gold standard measures for identifying those with severe anaemia requiring a blood transfusion, despite this resource being in short supply. Methods: We conducted a prospective descriptive study of hospitalized children aged 2 months - 12 years at Mbale and Soroti Regional Referral Hospitals, assessed to have pallor at triage by a nurse and two clinicians. Haemoglobin levels were measured using the HemoCue ® Hb 301 system (gold standard); the Haemoglobin Colour Scale; Colorimetric and Sahli's methods. We report clinical assessments of the degree of pallor, clinicians' intention to transfuse, inter-observer agreement, limits of agreement using the Bland-Altman method, and the sensitivity and specificity of each method in comparison to HemoCue ® Results: We recruited 322 children, clinically-assessed by the admitting nurse (n=314) as having severe (166; 51.6%), moderate (97; 30.1%) or mild (51; 15.8%) pallor. Agreement between the clinicians and the nurse were good: Clinician A Kappa=0.68 (0.60-0.76) and Clinician B Kappa=0.62 (0.53-0.71) respectively ( P<0.0001 for both). The nurse, clinicians A and B indicated that of 94/116 (81.0%), 83/121 (68.6%) and 93/120 (77.5%) respectively required transfusion. HemoCue ® readings indicated anaemia as mild (Hb10.0-11.9g/dl) in 8/292 (2.7%), moderate (Hb5.0-9.9g/dl) in 132/292 (45.2%) and severe (Hb<5.0g/dl) in 152/292 (52.1%). Comparing to HemoCue® the Sahli's method performed best in estimation of severe anaemia, with sensitivity 84.0% and specificity 87.9% and a Kappa score of  0.70 (0.64-0.80). Conclusions: Clinical assessment of severe pallor results has a low specificity for the diagnosis of severe anaemia. To target blood transfusion Hb measurement by either Hemocue® or Sahli's method for the cost of USD 4 or and USD 0.25 per test, respectively would be more cost-effective.

Evaluation of the diagnostic accuracy and cost of different methods for the assessment of severe anaemia in hospitalised children in Eastern Uganda

Background: Severe anaemia in children requiring hospital admission is a major public health problem in malaria-endemic Africa. Affordable methods for the assessment of haemoglobin have not been validated against gold standard measures for identifying those with severe anaemia requiring a blood transfusion, despite this resource being in short supply. Methods: We conducted a prospective descriptive study of hospitalized children aged 2 months - 12 years at Mbale and Soroti Regional Referral Hospitals, assessed to have pallor at triage by a nurse and two clinicians. Haemoglobin levels were measured using the HemoCue ® Hb 301 system (gold standard); the Haemoglobin Colour Scale; calorimetric and Sahli's methods. We report clinical assessments of the degree of pallor, clinicians' intention to transfuse, inter-observer agreement, limits of agreement using the Bland-Altman method, and the sensitivity and specificity of each method in comparison to HemoCue ® Results: We recruited 322 children assessed by the admitting nurse as having severe (164; 51.0%), moderate (99; 30.7%) or mild (57; 17.7%) pallor. Agreement between the clinicians and the nurse were good: Clinician A Kappa=0.68 (0.60-0.76) and Clinician B Kappa=0.62 (0.53-0.71) respectively ( P<0.0001 for both). The nurse, clinicians A and B indicated that of 94/116 (81.0%), 83/121 (68.6%) and 93/120 (77.5%) respectively required transfusion. HemoCue ® readings indicated anaemia as mild (Hb10.0-11.9g/dl) in 8/292 (2.7%), moderate (Hb5.0-9.9g/dl) in 132/292 (45.2%) and severe (Hb<5.0g/dl) in 152/292 (52.1%). Comparing to HemoCue® the Sahli's method performed best in estimation of severe anaemia, with sensitivity 84.0% and specificity 87.9% and a Kappa score of  0.70 (0.64-0.80). Conclusions: Clinical assessment of severe pallor results has a low specificity for the diagnosis of severe anaemia. To target blood transfusion Hb measurement by either Hemocue® or Sahli's method for the cost of USD 4 or and USD 0.25 per test, respectively would be more cost-effective.

Single-dose intravenous iron infusion versus red blood cell transfusion for the treatment of severe postpartum anaemia: a randomized controlled pilot study

BACKGROUND AND OBJECTIVES

There are no randomized trials comparing intravenous iron to RBC transfusion for the treatment of severe postpartum anaemia. The objectives of this study were to evaluate the feasibility of randomizing women with severe postpartum anaemia secondary to postpartum haemorrhage to RBC transfusion or intravenous iron, and to describe patient-reported outcomes, and haematological and iron parameters.

MATERIALS AND METHODS

Women with a postpartum haemorrhage exceeding 1000 ml and an Hb between 5·6 and 8·1 g/dl were randomized to 1500 mg of intravenous iron (n = 7) isomaltoside or RBC transfusion (n = 6). Participants completed the Multidimensional Fatigue Inventory and Edinburgh Postnatal Depression Scale, and blood samples were drawn at inclusion, daily during the first week and at weeks 3, 8 and 12.

RESULTS

We screened 162 women and included 13 (8%). There was no significant difference between groups in fatigue or depression scores. RBC transfusion was associated with a higher Hb on day 1, inhibition of reticulocytosis during the first week and low iron levels. Intravenous iron was associated with increased reticulocytosis during the first week, repleted iron stores and a higher Hb in weeks 3-12.

CONCLUSION

This pilot study shows that intravenous iron could be an attractive alternative to RBC transfusion in severe postpartum anaemia, and that a larger trial is needed and feasible.