RESUMEN
Machine learning methods are a novel way to predict and rank donors' willingness to donate blood and to achieve precision recruitment, which can improve the recruitment efficiency and meet the challenge of blood shortage. We collected information about experienced blood donors via short message service (SMS) recruitment and developed 7 machine learning-based recruitment models using PyCharm-Python Environment and 13 features which were described as a method for ranking and predicting donors' intentions to donate blood with a floating number between 0 and 1. Performance of the prediction models was assessed by the Area under the receiver operating characteristic curve (AUC), accuracy, precision, recall, and F1 score in the full dataset, and by the accuracy in the four sub-datasets. The developed models were applied to prospective validations of recruiting experienced blood donors during two COVID-19 pandemics, while the routine method was used as a control. Overall, a total of 95,476 recruitments via SMS and their donation results were enrolled in our modelling study. The strongest predictor features for the donation of experienced donors were blood donation interval, age, and donation frequency. Among the seven baseline models, the eXtreme Gradient Boosting (XGBoost) and Support vector machine models (SVM) achieved the best performance: mean (95%CI) with the highest AUC: 0.809 (0.806-0.811), accuracy: 0.815 (0.812-0.818), precision: 0.840 (0.835-0.845), and F1 score of XGBoost: 0.843 (0.840-0.845) and recall of SVM: 0.991 (0.988-0.994). The hit rate of the XGBoost model alone and the combined XGBoost and SVM models were 1.25 and 1.80 times higher than that of the conventional method as a control in 2 recruitments respectively, and the hit rate of the high willingness to donate group was 1.96 times higher than that of the low willingness to donate group. Our results suggested that the machine learning models could predict and determine the experienced donors with a strong willingness to donate blood by a ranking score based on personalized donation data and demographical details, significantly improve the recruitment rate of blood donors and help blood agencies to maintain the blood supply in emergencies.
Asunto(s)
Donantes de Sangre , COVID-19 , Humanos , COVID-19/epidemiología , Aprendizaje Automático , Intención , Brotes de EnfermedadesRESUMEN
BACKGROUND: Although periodic blood shortages are widespread in major Chinese cities, approximately 1 x 10(5) U of whole blood are discarded yearly because of under-collection. To reduce the wastage of acid citrate dextrose solution B (ACD-B) anticoagulated under-collected whole blood (UC-WB), this study was performed to elucidate the effect of extracellular pH and holding time on erythrocyte quality. Mannitol-adenine-phosphate (MAP) erythrocyte concentrates (UC-RBCs) were prepared with UC-WB to assess the safety and efficacy of this component. METHODS: The effect of the different extracellular pH levels and storage times on erythrocytes was assessed by fluorescent probes, SDS-PAGE electrophoresis, electron microscopy and spectroscopy. In vitro properties of 34 UC-RBCs that were prepared with UC-WB at different times after collection were analyzed and compared to normal RBCs during 35 days of storage. The results of transfusion with UC-RBCs and the incidence of adverse reactions in 49 patients were determined. RESULTS: 1) Low extracellular pH levels and long storage time induced increases in RBC fluorescence polarization and mean microviscosity, changes in membrane fluidity, band 1, 2 and 3 protein expression, and erythrocyte morphology. 2) During storage for 35 days, difference in between-subjects effects of K+, hemolysis and supernatant erythrocyte membrane protein (EMP) were statistically significant (P = 0.041, 0.007 and 0.002, respectively), while the differences between these parameters in the 4 h group and comparable controls were less significant. 3) Clinical data from 49 patients confirmed that transfusions with UC-RBCs were satisfactory with no adverse reactions. CONCLUSION: These results suggest that it is feasible to prepare RBCs with ACD-B anticoagulated UC-WB at a minimum of 66% volume of the labeled collection. It was effective and safe to transfuse the UC-RBCs prepared within 4 h after collection and stored within 7 days. The use of UC-WB would be a welcome addition to limited blood resources in China. TRIAL REGISTRATION: Chinese Clinical Trial Registry ChiCTR-TRC-13003967.
Asunto(s)
Eritrocitos/metabolismo , Eritrocitos/fisiología , Adenina/metabolismo , Adulto , Anciano , Conservación de la Sangre/métodos , Transfusión Sanguínea/métodos , Femenino , Hemólisis/fisiología , Humanos , Masculino , Manitol/metabolismo , Proteínas de la Membrana/metabolismo , Persona de Mediana Edad , Adulto JovenRESUMEN
OBJECTIVE: To evaluate the clinical effectiveness and accommodative range after implanting the 1CU. METHODS: It was a prospective case series study. From March in 2004 to December in 2007, 23 cases (28 eyes) had phacoemulsification and implantation of 1CU (HumanOptics). Naked and best corrected distant acuity, Naked acuity at 35 cm and best corrected near, the amplitude of accommodation measured with subjective and objective techniques and the change in the anterior chamber depth were measured at 3-6 months, 18-24 months and over 36 months after surgery. RESULTS: After implantation, the 1CU had good centered and stable and no IOL-specific complications. Naked distant acuity of the three groups are 0.84+/-0.23, 0.81+/-0.19 and 0.78+/-0.17, between them there are no significantly statistical differences (F=0.759, P>0.05). The best corrected distant acuity of the three groups were 0.97+/-0.13, 0.99+/-0.17 and 1.00+/-0.17, between them there are no significantly statistical differences (F=0.17, P>0.05). The near acuity at 35 cm was 0.66+/-0.24, 0.52+/-0.14 and 0.47+/-0.12, between them there are significantly statistical differences (F=9.312, P<0.01). The best corrected near acuity were 0.97+/-0.13, 0.94+/-0.22 and 0.90+/-0.21, between them there are no significantly statistical differences (F=0.915, P>0.05). The accommodative range measured with subjective were 0.89+/-0.34, 0.72+/-0.17 and 0.56+/-0.16, between them there are significantly statistical differences (F=13.43, P<0.01). The accommodative range measured with objective were 3.58+/-0.54, 3.01+/-0.89 and 2.50+/-0.54, between them there were significantly statistical differences (F=17.886, P<0.01). The anterior chamber depth measured by application of 2% pilocarpine eyedrops were 0.88+/-0.40, 0.54+/-0.23 and 0.33+/-0.20, between them there were significantly statistical differences (F=26.589, P<0.01). CONCLUSIONS: The eyes with 1CU have good visual acuity and increased accommodative range more than the single-focus IOL. With the extension of time after surgery, the ability of 1CU regulation gradually declines, and nears point swift away gradually.