Global demand for donated blood far exceeds supply, and unmet need is greatest in low- and middle-income countries; experts suggest that large-scale coordination is necessary to alleviate demand. Using the Facebook Blood Donation tool, we conduct the first large-scale algorithmic matching of blood donors with donation opportunities. While measuring actual donation rates remains a challenge, we measure donor action (e.g., making a donation appointment) as a proxy for actual donation. We develop automated policies for matching donors with donation opportunities, based on an online matching model. We provide theoretical guarantees for these policies, both regarding the number of expected donations and the equitable treatment of blood recipients. In simulations, a simple matching strategy increases the number of donations by 5-10%; a pilot experiment with real donors shows a 5% relative increase in donor action rate (from 3.7% to 3.9%). When scaled to the global Blood Donation tool user base, this corresponds to an increase of around one hundred thousand users taking action toward donation. Further, observing donor action on a social network can shed light onto donor behavior and response to incentives. Our initial findings align with several observations made in the medical and social science literature regarding donor behavior.

For a medical diagnosis, health professionals use different kinds of pathological ways to make a decision for medical reports in terms of patients medical condition. In the modern era, because of the advantage of computers and technologies, one can collect data and visualize many hidden outcomes from them. Statistical machine learning algorithms based on specific problems can assist one to make decisions. Machine learning data driven algorithms can be used to validate existing methods and help researchers to suggest potential new decisions. In this paper, multiple imputation by chained equations was applied to deal with missing data, and Principal Component Analysis to reduce the dimensionality. To reveal significant findings, data visualizations were implemented. We presented and compared many binary classifier machine learning algorithms (Artificial Neural Network, Random Forest, Support Vector Machine) which were used to classify blood donors and non-blood donors with hepatitis, fibrosis and cirrhosis diseases. From the data published in UCI-MLR [1], all mentioned techniques were applied to find one better method to classify blood donors and non-blood donors (hepatitis, fibrosis, and cirrhosis) that can help health professionals in a laboratory to make better decisions. Our proposed ML-method showed better accuracy score (e.g. 98.23% for SVM). Thus, it improved the quality of classification.

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) incidence peaked in Manaus, Brazil, in May 2020 with a devastating toll on the city's inhabitants, leaving its health services shattered and cemeteries overwhelmed. Buss et al. collected data from blood donors from Manaus and São Paulo, noted when transmission began to fall, and estimated the final attack rates in October 2020 (see the Perspective by Sridhar and Gurdasani). Heterogeneities in immune protection, population structure, poverty, modes of public transport, and uneven adoption of nonpharmaceutical interventions mean that despite a high attack rate, herd immunity may not have been achieved. This unfortunate city has become a sentinel for how natural population immunity could influence future transmission. Events in Manaus reveal what tragedy and harm to society can unfold if this virus is left to run its course. Science , this issue p. [288][1]; see also p. [230][2] Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) spread rapidly in Manaus, the capital of Amazonas state in northern Brazil. The attack rate there is an estimate of the final size of the largely unmitigated epidemic that occurred in Manaus. We use a convenience sample of blood donors to show that by June 2020, 1 month after the epidemic peak in Manaus, 44% of the population had detectable immunoglobulin G (IgG) antibodies. Correcting for cases without a detectable antibody response and for antibody waning, we estimate a 66% attack rate in June, rising to 76% in October. This is higher than in São Paulo, in southeastern Brazil, where the estimated attack rate in October was 29%. These results confirm that when poorly controlled, COVID-19 can infect a large proportion of the population, causing high mortality. [1]: /lookup/doi/10.1126/science.abe9728 [2]: /lookup/doi/10.1126/science.abf7921

By the end of July 2020, Kenya h ad reported only 341 deaths and ∼20,000 cases of COVID-19. This is in marked contrast to the tens of thousands of deaths reported in many higher-income countries. The true extent of COVID-19 in the community was unknown and likely to be higher than reports indicated. Uyoga et al. found an overall seroprevalence among blood donors of 4.3%, peaking in 35- to 44-year-old individuals (see the Perspective by Maeda and Nkengasong). The low mortality can be partly explained by the steep demographics in Kenya, where less than 4% of the population is 65 or older. These circumstances combine to result in Kenyan hospitals not currently being overwhelmed by patients with respiratory distress. However, the imposition of a strict lockdown in this country has shifted the disease burden to maternal and child deaths as a result of disruption to essential medical services. Science , this issue p. [79][1]; see also p. [27][2] The spread of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) in Africa is poorly described. The first case of SARS-CoV-2 in Kenya was reported on 12 March 2020, and an overwhelming number of cases and deaths were expected, but by 31 July 2020, there were only 20,636 cases and 341 deaths. However, the extent of SARS-CoV-2 exposure in the community remains unknown. We determined the prevalence of anti–SARS-CoV-2 immunoglobulin G among blood donors in Kenya in April–June 2020. Crude seroprevalence was 5.6% (174 of 3098). Population-weighted, test-performance-adjusted national seroprevalence was 4.3% (95% confidence interval, 2.9 to 5.8%) and was highest in urban counties Mombasa (8.0%), Nairobi (7.3%), and Kisumu (5.5%). SARS-CoV-2 exposure is more extensive than indicated by case-based surveillance, and these results will help guide the pandemic response in Kenya and across Africa. [1]: /lookup/doi/10.1126/science.abe1916 [2]: /lookup/doi/10.1126/science.abf8832