A suspected transfusion transmitted malaria case

Agnihotri, Naveen; Pal, Lokesh

doi:10.4103/0973-6247.126697

Cited by 2 publications

(13 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[ 15 ] as well Agnihotri et al. [ 10 ] overestimated the measured Hb content significantly, with mean absolute prediction errors of 18.997 g Hb/unit (34.71%) and 13.767 g Hb/unit (25.28%) ( Figure 5 A,B and Table 2 ).…”

Section: Resultsmentioning

confidence: 84%

“…[ 15 , 18 ] The low accuracy of the second study is specifically highlighted by the substantial (20%) difference between the standard deviation of the calculated Hb content per unit and the standard deviation of the actual Hb content. [ 10 ] To the best of our knowledge we herein present for the first time highly reliable, non‐invasive Hb content/concentration predictions of individual pRBC units. Notably, our Hb prediction ML concept was validated by comparing the individual predicted to the measured Hb content of the respective pRBC unit.…”

Section: Discussionmentioning

confidence: 99%

“…In a pilot study comprising 9 pRBC units, we used the previous approaches developed by Arslan et al [15] and Agnihotri et al [10] to estimate the Hb content. Of note, both approaches substantially overestimated the measured (real) Hb content with mean prediction errors of 19.55 g Hb/unit (30.8%) and 14.35 g Hb/unit (26.4%) (Figure 2A,B).…”

Section: Previous Hb Content Prediction Approaches Substantially Over...mentioning

confidence: 99%

“…pRBCs (n = 9) were randomly picked independent from the first as well as the second cohort. For these samples, the measured Hb content and the calculated Hb content were compared based on the equations of Arslan et al [15] and Agnihotri et al [10] After weighing and gently shaking on a rocker, samples from the pRBC units were taken in S-Monovettes with potassium EDTA, 2.7 mL (Sarstedt AG & Co. KG, Nümbrecht, Germany). Hb concentration in g dL −1 and Hct in percentage were determined by two repeated measurements with the Sysmex XN-350 System (Sysmex Deutschland GmbH, Norderstedt, Germany).…”

Section: Pilot Study For Hb Content Calculation In Prbc Unitsmentioning

confidence: 99%

“…Since we supposed that the feature blood bag system may be relevant in Table 2. Performance metrics of the models for total Hb content prediction in pRBC units proposed by Arslan et al, [15] Agnihotri et al [10] and Epah et al, assessed on the second, independent data set (n = 2637). Mean squared error 378.71 (recalibrated: [43] 17.87) 205.78 (recalibrated: [43] Adjusted coefficient of determination (R 2 ) −8.72 (recalibrated: [43] 0.6147) −4.28 (recalibrated: [43] 0.6148) 0.92 0.91 the production process, we decided to consider both MLR with three and four features for an unbiased assessment of model performance in our second, independent data set (n = 2637).…”

Section: Recursive Feature Elimination Selects Unit Volume Donor Hb O...mentioning

confidence: 99%

See 4 more Smart Citations

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

et al. 2022

View full text Add to dashboard Cite

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 R 2 > 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.

show abstract

Section: Resultsmentioning

confidence: 84%

Section: Discussionmentioning

confidence: 99%

Section: Previous Hb Content Prediction Approaches Substantially Over...mentioning

confidence: 99%

Section: Pilot Study For Hb Content Calculation In Prbc Unitsmentioning

confidence: 99%

Section: Recursive Feature Elimination Selects Unit Volume Donor Hb O...mentioning

confidence: 99%

See 3 more Smart Citations

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

et al. 2022

View full text Add to dashboard Cite

show abstract

Analysis of Rhesus (Rh) Antigen Distributions in Donors and Multi-transfused Patients for Phenotype-Matched Transfusion

Zhao

et al. 2023

Indian J Hematol Blood Transfus

View full text Add to dashboard Cite

Knowledge about the frequency of Rh blood group systems in the local population help build a donor pool for multi-transfused patients and provide antigen-negative compatible blood for patients with alloantibodies. ABO and Rh antigens were identified for blood donors and patients before transfusion. The antiglobulin test based on the micro-column gel method was used to perform unexpected antibody screening and identification for patients in pre-transfusion testing. The incidence of the adverse transfusion reactions and the accordance rate of Rh phenotype-matched transfusion were analyzed retrospectively. A total of 246,340 specimens were detected with Rh blood group antigens D, C, E, c, and e. Rh D antigen was the most common phenotype with a frequency of 99.40%, followed by e antigen, C antigen, c antigen, and E antigen. In Rh D positive specimens, DCe was the most common phenotype, while DCE was the least common. At the same time, in Rh D negative specimens, ce was the most common phenotype with CE and CcE unobserved. Rh phenotype-matched transfusion has been conducted in our department since 2012. The accordance rate of Rh phenotype-matched transfusion has been kept above 95% and the resulting incidence of adverse transfusion reactions has been decreasing year by year, from 19.95‰ in 2011 to 2.21‰ in 2021. Blood transfusion with matched Rh phenotypes was able to avoid the generation of unexpected antibodies, reduce the incidence of adverse transfusion reactions, and enhance precise diagnosis and treatment.

show abstract

A suspected transfusion transmitted malaria case

Cited by 2 publications

References 4 publications

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

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

Analysis of Rhesus (Rh) Antigen Distributions in Donors and Multi-transfused Patients for Phenotype-Matched Transfusion

Contact Info

Product

Resources

About