Background and ObjectivesRed blood cell (RBC) transfusions pose a risk of alloantibody development in patients. For patients with increased alloimmunization risk, extended preventive matching is... Show moreBackground and ObjectivesRed blood cell (RBC) transfusions pose a risk of alloantibody development in patients. For patients with increased alloimmunization risk, extended preventive matching is advised, encompassing not only the ABO-D blood groups but also the most clinically relevant minor antigens: C, c, E, e, K, Fya, Fyb, Jka, Jkb, S and s. This study incorporates patient-specific data and the clinical consequences of mismatching into the allocation process.Materials and MethodsWe have redefined the MINimize Relative Alloimmunization Risks (MINRAR) model to include patient group preferences in selecting RBC units from a finite supply. A linear optimization approach was employed, considering both antigen immunogenicity and the clinical impact of mismatches for specific patient groups. We also explore the advantages of informing the blood bank about scheduled transfusions, allowing for a more strategic blood distribution. The model is evaluated using historical data from two Dutch hospitals, measuring shortages and minor antigen mismatches.ResultsThe updated model, emphasizing patient group-specific considerations, achieves a similar number of mismatches as the original, yet shifts mismatches among patient groups and antigens, reducing expected alloimmunization consequences. Simultaneous matching for multiple hospitals at the distribution centre level, considering scheduled demands, led to a 30% decrease in mismatches and a 92% reduction in shortages.ConclusionThe reduction of expected alloimmunization consequences by incorporating patient group preferences demonstrates our strategy's effectiveness for patient health. Substantial reductions in mismatches and shortages with multi-hospital collaboration highlights the importance of sharing information in the blood supply chain. Show less
Kroes, S.K.S.; Leeuwen, M. van; Groenwold, R.H.H.; Janssen, M.P. 2022
Objective: Privacy is a concern whenever individual patient health data is exchanged for scientific research. We propose using mixed sum-product networks (MSPNs) as private representations of data... Show moreObjective: Privacy is a concern whenever individual patient health data is exchanged for scientific research. We propose using mixed sum-product networks (MSPNs) as private representations of data and take samples from the network to generate synthetic data that can be shared for subsequent statistical analysis. This anonymization method was evaluated with respect to privacy and information loss. Materials and methods: Using a simulation study, information loss was quantified by assessing whether synthetic data could reproduce regression parameters obtained from the original data. Predictors variable types were varied between continuous, count, categorical, and mixed discrete-continuous. Additionally, we measured whether the MSPN approach successfully anonymizes the data by removing associations between background and sensitive information for these datasets. Results: The synthetic data generated with MSPNs yielded regression results highly similar to those generated with original data, differing less than 5% in most simulation scenarios. Standard errors increased compared to the original data. Particularly for smaller datasets (1000 records), this resulted in a discrepancy between the estimated and empirical standard errors. Sensitive values could no longer be inferred from background information for at least 99% of tested individuals. Discussion: The proposed anonymization approach yields very promising results. Further research is required to evaluate its performance with other types of data and analyses, and to predict how user parameter choices affect a bias-privacy trade-off. Conclusion: Generating synthetic data from MSPNs is a promising, easy-to-use approach for anonymization of sensitive individual health data that yields informative and private data. Show less
Kroes, S.K.S.; Leeuwen, M. van; Groenwold, R.H.H.; Janssen, M.P. 2022
OBJECTIVE\nMATERIALS AND METHODS\nRESULTS\nDISCUSSION\nCONCLUSION\nPrivacy is a concern whenever individual patient health data is exchanged for scientific research. We propose using mixed sum... Show moreOBJECTIVE\nMATERIALS AND METHODS\nRESULTS\nDISCUSSION\nCONCLUSION\nPrivacy is a concern whenever individual patient health data is exchanged for scientific research. We propose using mixed sum-product networks (MSPNs) as private representations of data and take samples from the network to generate synthetic data that can be shared for subsequent statistical analysis. This anonymization method was evaluated with respect to privacy and information loss.\nUsing a simulation study, information loss was quantified by assessing whether synthetic data could reproduce regression parameters obtained from the original data. Predictors variable types were varied between continuous, count, categorical, and mixed discrete-continuous. Additionally, we measured whether the MSPN approach successfully anonymizes the data by removing associations between background and sensitive information for these datasets.\nThe synthetic data generated with MSPNs yielded regression results highly similar to those generated with original data, differing less than 5% in most simulation scenarios. Standard errors increased compared to the original data. Particularly for smaller datasets (1000 records), this resulted in a discrepancy between the estimated and empirical standard errors. Sensitive values could no longer be inferred from background information for at least 99% of tested individuals.\nThe proposed anonymization approach yields very promising results. Further research is required to evaluate its performance with other types of data and analyses, and to predict how user parameter choices affect a bias-privacy trade-off.\nGenerating synthetic data from MSPNs is a promising, easy-to-use approach for anonymization of sensitive individual health data that yields informative and private data. Show less
Vinkenoog, M.; Leeuwen, M. van; Janssen, M.P. 2022
BACKGROUND AND OBJECTIVES\nMATERIALS AND METHODS\nRESULTS\nCONCLUSION\nAccurate predictions of haemoglobin (Hb) deferral for whole-blood donors could aid blood banks in reducing deferral rates and... Show moreBACKGROUND AND OBJECTIVES\nMATERIALS AND METHODS\nRESULTS\nCONCLUSION\nAccurate 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.\nDonation 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.\nWe 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.\nBy 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). Show less
Luken, J.S.; Ritsema, S.P.; Wal, M.M. van der; Schoot, C.E. van der; Rouwette, E.A.J.A.; Haas, M. de; Janssen, M.P. 2022
Background and objectives: Current genotyping techniques allow typing of all relevant red cell, human leukocyte and platelet antigens in a single analysis. Even genetic markers related to donor... Show moreBackground and objectives: Current genotyping techniques allow typing of all relevant red cell, human leukocyte and platelet antigens in a single analysis. Even genetic markers related to donor health can be added. Implementation of this technology will affect various stakeholders within the transfusion chain. This study aims to systematically map the anticipated advantages and disadvantages of a national rollout of blood group genotyping of donors, which will affect the availability of rare donors and the implementation of an extensively typed blood transfusion policy. Materials and methods: Two focus-group sessions were held with a wide representation of stakeholders, including representatives of donor and patient organisations. A dedicated software tool was used to collect the reflections of participants on genotyping for blood group antigens and extensive matching. Additionally, stakeholders and experts discussed various prepared propositions. All information collected was categorised. Results: From 162 statements collected, 59 statements (36%) were labelled as 'hopes' and 77 (48%) as 'fears'. Twenty-six (16%) statements remained unlabelled. The statements were divided in 18 categories under seven main themes: patient health, genotyping, privacy issues and ethical aspects, donor management, inventory management and logistics, hospital and transfusion laboratory and general aspects. The discussion on the propositions was analysed and summarised. Conclusion: Stakeholders believe that a genotyped donor pool can result in a reduction of alloimmunization and higher availability of typed blood products. There are concerns regarding logistics, costs, consent for extended typing, data sharing, privacy issues and donor management. These concerns need to be carefully addressed before further implementation. Show less
Kroes, S.K.; Janssen, M.P.; Groenwold, R.H.; Leeuwen, M. van 2021
Although data protection is compulsory when personal data is shared, there is no systematic method available to evaluate to what extent each individual is at risk of a privacy breach. We use a... Show moreAlthough data protection is compulsory when personal data is shared, there is no systematic method available to evaluate to what extent each individual is at risk of a privacy breach. We use a collection of measures that quantify how much information is needed to uncover sensitive information. Combined with visualization techniques, our approach can be used to perform a detailed privacy analysis of medical data. Because privacy is evaluated per variable, these adjustments can be made while incorporating how likely it is that these variables will be exploited to uncover sensitive information in practice, as is mandatory in the European Union. Additionally, the analysis of privacy can be used to evaluate to what extent knowledge on specific variables in the data can contribute to privacy breaches, which can subsequently guide the use of anonymization techniques, such as generalization. Show less
Luken, J.S.; Folman, C.C.; Lukens, M.V.; Meekers, J.H.; Ligthart, P.C.; Schonewille, H.; ... ; Haas, M. de 2021
Background: During pregnancy, maternal red blood cell (RBC) antibodies can lead to life-threatening fetal hemolysis and anemia. Women can become immunized by a pregnancy or an unmatched transfusion... Show moreBackground: During pregnancy, maternal red blood cell (RBC) antibodies can lead to life-threatening fetal hemolysis and anemia. Women can become immunized by a pregnancy or an unmatched transfusion. Our aim was to quantify the effect of a nationwide K-matched transfusion policy for women of childbearing age potential to prevent K-immunization in pregnancy.Study Design and Methods: In this nation-wide policy change evaluation study we determined the occurrence of RBC antibodies before and after introduction of a K-matched transfusion policy and evaluated the cause K alloimmunization 10 years after introduction of this measure. K-matched transfusion for females under 45 years of age is advised in the Dutch transfusion guideline since 2004. We used laboratory data from pregnancies with RBC antibodies identified in the period 1999-2018 obtained as part of a population-based screening program in the Netherlands.Results: Tests of 36 286 pregnancies produced a positive antibody screening result which concerned anti-K in 1550 pregnancies. The occurrence of anti-K decreased from 67.9 to 20.2 per 100 000 pregnancies. The relative risk reduction was 0.70 which largely exceeded the relative risk reduction of 0.27 for antibodies against RBC antigens for which no preventive matching is required. The number of pregnancies at risk for anti-K-mediated disease decreased from 9.7 to 4.2 per 100 000 pregnancies.Conclusions: A K-matched transfusion policy is associated with a major decrease in a number of pregnant women with anti-K and pregnancies at risk for anti-K-mediated disease. A relatively simple measure is now shown to impact prevention of hemolytic disease in the fetus and newborn. Show less
Kroes, S.K.; Janssen, M.P.; Groenwold, R.H.; Leeuwen, M. van 2021