Hb Deferral Research Articles

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

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. 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. 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. 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.

The influence of demographic and lifestyle factors on blood donation delay among student population: a retrospective study.

This study analysed blood donation deferral trends, reasons and demographic/lifestyle characteristics among students in Huzhou City. The aim was to understand the health status of students and reduce the deferral rate. Data on blood donation deferral among students in Huzhou City from 2018 to 2022 were collected and analysed. Deferral trends and main reasons were investigated. Using demographic and lifestyle data from 2,619 cases in 2022, a risk prediction model for deferral was constructed. The deferral rate among students in Huzhou City from 2018 to 2022 was 12.60% (p = 0.000, 95%CI: 12.14-13.06%), showing a significant increasing trend. Temporary deferral was the main reason, with alanine aminotransferase (ALT), blood pressure (BP) and haemoglobin (Hb) as the main deferral factors. ALT had a deferral rate of 5.23% (4.92-5.53%), BP 3.30% (3.06-3.55%), and Hb 2.92% (2.68-3.15%). Demographic and lifestyle characteristics in 2022 showed no significant differences between education level, household registration and deferral rate (p > 0.05). However, age, sex, blood donation history, sleep quality, diet and mental state had variable effects on ALT, BP, and Hb deferrals (p < 0.05). Logistic regression showed that sex, blood donation history, sleep quality, diet and mental status were independent risk factors for ALT deferral (p < 0.05), with odds ratios (ORs) of 5.057, 2.735, 1.594, 3.679, and 1.957, respectively. Age, blood donation history, sleep quality and mental state were independent risk factors for BP deferral (p < 0.05), with ORs of 0.256, 3.658, 6.042, and 1.812, respectively. Gender, blood donation history and diet were independent risk factors for Hb deferral (p < 0.05), with ORs of 0.244, 0.542, and 3.103, respectively. Students' health problems require attention. Effective health education should improve self-health management and pre-donation health behaviour to encourage regular blood donation.

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

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. 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. 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. 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 ObjectivesDeferral 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 MethodsUsing 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.ResultsWe 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.ConclusionWe 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.

Changes in minimum hemoglobin and interdonation interval: impact on donor hemoglobin and donation frequency.

To reduce donor iron deficiency in whole blood donors, we changed our hemoglobin (Hb) cutoff in males and interdonation interval in females. A change in messaging to females in fall 2016 was followed by changing the interdonation interval from 56 to 84 days in the appointment booking system (December 2016) and actual donation criterion (March 2017). The minimum Hb for males increased from 125 g/L to 130 g/L (March 2017). We evaluated Hb levels and deferral rates, donor presentations with a Hb level below 120 g/L, donation frequency, and donor base size before and after these changes. The Hb deferral rate decreased in females from 13.0% to 9.5%, increased in males from 1.2% to 2.1%, and decreased overall from 6.8% to 5.4% (all p < 0.001). Mean Hb increased from 135.0 g/L to 136.2 g/L in females and from 149.9 g/L to 150.6 g/L in males (both p < 0.0001). The percentage of presentations with Hb below 120 g/L decreased by 27% in males and females (p < 0.001). Annual donation frequency decreased by 12% in females and 4% in males; the donor base was expanded by 5.8%. Many positive impacts were seen for female donors, including a shift in the Hb distribution curve to the right, and a large reduction in Hb deferrals. For males, there was an increase in Hb deferrals and a small increase in mean Hb. Changes were related to both reduced donation frequency and a shift in composition of the donor base.

Minimum donation intervals should be reconsidered to decrease low hemoglobin deferral in whole blood donors: an observational study.

Most donor deferrals are due to low hemoglobin (Hb) levels. Previously measured Hb levels and donation intervals are known to be associated with Hb deferral. However, this relationship has never been quantified. In this study, we related the prevalence of Hb deferral to previously measured Hb levels and donation intervals. A total of 220,946 whole blood donors were categorized into groups based on their Hb level at the previous donation and on the time interval since the previous donation. For each group, the prevalence of Hb deferral was assessed. Hb deferral rates were higher when Hb levels at the previous donation were lower and donation intervals were shorter. With a donation interval shorter than 3 months, the prevalence of Hb deferral was below the 10% threshold only when the previous Hb level was at least 0.3 mmol/L above the cutoff level for donation. To maintain appropriate Hb levels, the minimum donation interval of 56 days is only sufficient for donors with Hb levels far above the cutoff level for donation. Protocols for minimum donation intervals should be reconsidered and may be based on previously measured Hb levels. This may result in a decrease of low Hb deferral.

A systematic review of factors associated with the deferral of donors failing to meet low haemoglobin thresholds

Blood donors attending a donation session may be deemed ineligible to donate blood due to a failure to meet low haemoglobin (Hb) thresholds. Several studies have identified factors associated with a donor falling below these Hb thresholds. A review of these factors will inform future prospective studies and form the basis for predictive models of deferral due to low Hb. Studies were identified by searching MEDLINE, EMBASE, The Cochrane Library and the WHO International Clinical Trials Registry from 1980 to September 2012. Demographic data, donor history, haematological/biological factors and the primary outcome of deferral due to low Hb were extracted. Analyses were descriptive and quantitative; pooled odds ratios (ORs) were obtained by meta-analysis. Fifty-five studies met the inclusion criteria. A consistently higher rate of low Hb deferral was reported in females compared with males; meta-analysis showed a significantly greater risk of deferral due to low Hb in females compared with males in studies with universal Hb thresholds for males and females (OR 14.91, 95% confidence interval (CI) 12.82-17.34) and in studies with sex-specific Hb thresholds (OR 8.19, 95% CI 4.88-13.74). Greater rates of deferral due to low Hb were also associated with increasing age, higher ambient temperature, low body weight, shorter inter-donation interval and in donors of Hispanic or African descent. This work will help to define the criteria that should be considered in any large scale study of blood donor deferral, especially those that measure or aim to change failure to meet low Hb thresholds.

External validation and updating of a Dutch prediction model for low hemoglobin deferral in Irish whole blood donors

Recently, sex-specific prediction models for low hemoglobin (Hb) deferral have been developed in Dutch whole blood donors. In the present study, we validated and updated the models in a cohort of Irish whole blood donors. Prospectively collected data from 45,031 Irish whole blood donors were used. Hb cutoff levels for donation were approximately 0.35 mmol/L lower in Ireland than the Dutch cutoff levels (8.07 mmol/L vs. 8.40 mmol/L in men; 7.45 mmol/L vs. 7.80 mmol/L in women). The predictive performance of the models was assessed with calibration plots, calibration-in-the-large, and the concordance (c)-statistic. The models were updated by revising the strength of the individual predictors in the models. A total of 613 men (2.4%) and 1624 women (8.4%) were deferred from donation because of a low Hb level. Validation demonstrated underestimation of predicted risks and lower c-statistics for men and women compared to the Dutch cohort. The strength of most predictive factors, particularly previous Hb level, was lower in Irish donors. The updated models showed a c-statistic of 0.83 (95% confidence interval [CI], 0.81-0.84) for men and 0.76 (95% CI, 0.74-0.77) for women. The performance of Dutch prediction models for Hb deferral was limited when validated in Irish whole blood donors. Updating the models resulted in different predictor effects. This improved mainly the model calibration; the improvement in discrimination was small.

Zinc protoporphyrin levels have added value in the prediction of low hemoglobin deferral in whole blood donors

Increased zinc protoporphyrin (ZPP) levels can indicate iron deficiency and may be predictive for low hemoglobin (Hb) deferral in blood donors. Prediction models for Hb deferral in whole blood donors have already been developed. In this study, we examined if addition of ZPP to these prediction models improves risk estimation of Hb deferral. This study included 4598 Dutch whole blood donors. Information on ZPP levels measured at the previous visit was added to the existing prediction models to estimate the risk of Hb deferral. Models were compared using the following measures: concordance (c)-statistic, continuous net reclassification improvement (NRI), and clinical net benefit (NB). Seventy-six male donors (2.9%) and 69 female donors (3.5%) were deferred because of a low Hb level. Previous ZPP level was associated with risk of Hb deferral (odds ratio for interquartile range of previous ZPP level, men 2.0 [95% confidence interval {CI}, 1.7-2.3]; women 2.2 [95% CI, 1.9-2.4]) in a multivariable risk model. Addition of ZPP into the models resulted in an increase of the c-statistic from 0.93 to 0.94 for men and from 0.80 to 0.85 for women. The added value of ZPP was confirmed by measures of clinical usefulness. NRI for men was 0.42, and for women, 0.56. At relevant threshold probabilities between 10 and 15%, NB was higher for models considering ZPP. This study shows that ZPP measurements obtained at the previous visit may have added value in the risk prediction of Hb deferral in whole blood donors.

Development and validation of a prediction model for low hemoglobin deferral in a large cohort of whole blood donors

Each year, approximately 5% of the invited blood donors is eventually deferred from donation because of low hemoglobin (Hb) levels. Estimating the risk of Hb deferral in blood donors can be helpful in the management of the donation program. We developed and validated a prediction model for Hb deferral in whole blood donors, separately for men and women. Data from a Dutch prospective cohort of 220,946 whole blood donors were used to identify predictors for Hb deferral using multivariable logistic regression analyses. Validity of the prediction models was assessed with a cross-validation. A total of 12,865 donors (5.8%) were deferred because of a low Hb level. The strongest predictors of Hb deferral were Hb level measured at the previous visit, age, seasonality, difference in Hb levels between the previous two visits, time since the previous visit, deferral at the previous visit, and the total number of whole blood donations in the past 2 years for both men and women. The prediction models had an area under the receiver operating characteristic curve of 0.89 for men and 0.84 for women. Cross-validation showed similar results and good calibration. Using a limited number of easy-to-measure characteristics enables a good prediction of Hb deferral risk in whole blood donors. The prediction models may guide the decision which donors to invite for a next donation and for which donors the invitation should be postponed. Potentially, this could decrease the number of Hb deferrals in blood donors.

Iron deficiency in blood donors: the REDS‐II Donor Iron Status Evaluation (RISE) study

Blood donors are at risk of iron deficiency. We evaluated the effects of blood donation intensity on iron and hemoglobin (Hb) in a prospective study. Four cohorts of frequent and first-time or reactivated (FT/RA) blood donors (no donation in 2 years), female and male, totaling 2425, were characterized and followed as they donated blood frequently. At enrollment and the final visit, ferritin, soluble transferrin receptor (sTfR), and Hb were determined. Models to predict iron deficiency and Hb deferral were developed. Iron depletion was defined at two levels: iron deficiency erythropoiesis (IDE) [log(sTfR/ferritin) ≥ 2.07] and absent iron stores (AIS; ferritin < 12 ng/mL). Among returning female FT and RA donors, 20 and 51% had AIS and IDE at their final visit, respectively; corresponding proportions for males were 8 and 20%. Among female frequent donors who returned, 27 and 62% had AIS and IDE, respectively, while corresponding proportions for males were 18 and 47%. Predictors of IDE and/or AIS included a higher frequency of blood donation in the past 2 years, a shorter interdonation interval, and being female and young; conversely, taking iron supplements reduced the risk of iron depletion. Predictors of Hb deferral included female sex, black race, and a shorter interdonation interval. There is a high prevalence of iron depletion in frequent blood donors. Increasing the interdonation interval would reduce the prevalence of iron depletion and Hb deferral. Alternatively, replacement with iron supplements may allow frequent donation without the adverse outcome of iron depletion.

Demographic correlates of low hemoglobin deferral among prospective whole blood donors

Approximately 10% of attempted blood donations are not allowed because of low hemoglobin (Hb) deferral. Low Hb deferrals were tracked in more 715,000 whole blood donors at six blood centers across the United States. A multivariable logistic regression model was developed to comprehensively assess demographic correlates for low Hb deferral. Demographic factors significantly associated with low Hb deferral include female sex (11 times greater odds than males), increasing age in men (men over 80 have 29 times greater odds than men under 20), African American race (2-2.5 times greater odds than Caucasians), Hispanic ethnicity in women (1.29 times greater odds than Caucasian women), and weight in men (men under 124 pounds have 2.5 times greater odds than men over 200 pounds). Interestingly, increasing donation frequency is associated with decreased odds for low Hb deferral (women with one donation in the previous 12 months have two times greater odds than those with six donations). Low Hb deferral is associated with female sex, older age, African American race/ethnicity, and lower body weight in men. An inverse association with donation frequency suggests a selection bias in favor of donors able to give more frequently. These data provide useful information that can be utilized to manage blood donors to limit low Hb deferrals and assist in policy decisions such as changing the Hb cutoff or permissible frequency of donation. They also generate hypotheses for new research of the causes of anemia in defined groups of donors.

Seasonal influences on hemoglobin levels and deferral rates in whole‐blood and plasma donors

Indications exist that deferral rates in blood donors are highest in summer. However, a detailed quantitative analysis is not available. The association between Hb values, deferral rates, and daily temperatures was investigated in a large data set of blood donors. The study population consisted of both plasma and whole-blood donors from the southeast region of the Netherlands. Individual Hb levels and other examination data between January 2002 and December 2004 were extracted from the donor file. Data on daily maximum temperatures were related to Hb levels and Hb deferrals. Results are reported separately for plasma and whole-blood donors as well as for men and women. Data were available from 106,398 whole blood donors and 6983 plasma donors, resulting in data of more than 600,000 examinations. Hb levels decreased with increasing daily temperature. Highest deferral rates were observed in summer months, which were consistent over the several groups and over the three years. The highest Hb deferral of 11.1 percent was observed for female whole-blood donors on days with a maximum temperature of 25 degrees and above. In all four donor categories a gradual increase with temperature was observed with 1.7-2.2 times higher deferral rates on hot days (> or = 25 degrees C) compared to cold days (<5 degrees C). A clear seasonal pattern in Hb levels and in the percentage of Hb deferrals was observed. The observed seasonal effect could not be explained by differences in donor characteristics. Our observations might have practical implications for donor management.