RESUMO
Artificial intelligence (AI) uses sophisticated algorithms to "learn" from large volumes of data. This could be used to optimise recruitment of blood donors through predictive modelling of future blood supply, based on previous donation and transfusion demand. We sought to assess utilisation of predictive modelling and AI blood establishments (BE) and conducted predictive modelling to illustrate its use. A BE survey of data modelling and AI was disseminated to the International Society of Blood transfusion members. Additional anonymzed data were obtained from Italy, Singapore and the United States (US) to build predictive models for each region, using January 2018 through August 2019 data to determine likelihood of donation within a prescribed number of months. Donations were from March 2020 to June 2021. Ninety ISBT members responded to the survey. Predictive modelling was used by 33 (36.7%) respondents and 12 (13.3%) reported AI use. Forty-four (48.9%) indicated their institutions do not utilise predictive modelling nor AI to predict transfusion demand or optimise donor recruitment. In the predictive modelling case study involving three sites, the most important variable for predicting donor return was number of previous donations for Italy and the US, and donation frequency for Singapore. Donation rates declined in each region during COVID-19. Throughout the observation period the predictive model was able to consistently identify those individuals who were most likely to return to donate blood. The majority of BE do not use predictive modelling and AI. The effectiveness of predictive model in determining likelihood of donor return was validated; implementation of this method could prove useful for BE operations.
RESUMO
BACKGROUND: The COVID-19 pandemic has imposed an enormous burden on health care systems around the world. In the past, the administration of convalescent plasma of patients having recovered from SARS and severe influenza to patients actively having the disease showed promising effects on mortality and appeared safe. Whether or not this also holds true for the novel SARS-CoV-2 virus is currently unknown. METHODS: DAWn-Plasma is a multicentre nation-wide, randomized, open-label, phase II proof-of-concept clinical trial, evaluating the clinical efficacy and safety of the addition of convalescent plasma to the standard of care in patients hospitalized with COVID-19 in Belgium. Patients hospitalized with a confirmed diagnosis of COVID-19 are eligible when they are symptomatic (i.e. clinical or radiological signs) and have been diagnosed with COVID-19 in the 72 h before study inclusion through a PCR (nasal/nasopharyngeal swab or bronchoalveolar lavage) or a chest-CT scan showing features compatible with COVID-19 in the absence of an alternative diagnosis. Patients are randomized in a 2:1 ratio to either standard of care and convalescent plasma (active treatment group) or standard of care only. The active treatment group receives 2 units of 200 to 250 mL of convalescent plasma within 12 h after randomization, with a second administration of 2 units 24 to 36 h after ending the first administration. The trial aims to include 483 patients and will recruit from 25 centres across Belgium. The primary endpoint is the proportion of patients that require mechanical ventilation or have died at day 15. The main secondary endpoints are clinical status on day 15 and day 30 after randomization, as defined by the WHO Progression 10-point ordinal scale, and safety of the administration of convalescent plasma. DISCUSSION: This trial will either provide support or discourage the use of convalescent plasma as an early intervention for the treatment of hospitalized patients with COVID-19 infection. TRIAL REGISTRATION: ClinicalTrials.gov NCT04429854 . Registered on 12 June 2020 - Retrospectively registered.