An experiment on the impact of predictive analytics on kidney offers acceptance decisions.

Because of the breadth of factors that might affect kidney transplant decisions to accept an organ or wait for another, presumably "better" offer, a high degree of heterogeneity in decision making exists among transplant surgeons and hospitals. These decisions do not typically include objective predictions regarding the future availability of equivalent or better-quality organs or the likelihood of patient death while waiting for another organ. To investigate the impact of displaying such predictions on organ donation decision making, we conducted a statistically designed experiment involving 53 kidney transplant professionals, in which kidney offers were presented via an online application and systematically altered to observe the effects on decision making. We found that providing predictive analytics for time-to-better offers and patient mortality improved decision consensus and decision-maker confidence in their decisions. Providing a visual display of the patient's mortality slope under accept/reject conditions shortened the time-to-decide but did not have an impact on the decision itself. Presenting the risk of death in a loss frame as opposed to a gain frame improved decision consensus and decision confidence. Patient-specific predictions surrounding future organ offers and mortality may improve decision quality, confidence, and expediency while improving organ utilization and patient outcomes.

Inferring True COVID19 Infection Rates From Deaths.

The novel coronavirus, SARS-CoV-2, commonly known as COVID19 has become a global pandemic in early 2020. The world has mounted a global social distancing intervention on a scale thought unimaginable prior to this outbreak; however, the economic impact and sustainability limits of this policy create significant challenges for government leaders around the world. Understanding the future spread and growth of COVID19 is further complicated by data quality issues due to high numbers of asymptomatic patients who may transmit the disease yet show no symptoms; lack of testing resources; failure of recovered patients to be counted; delays in reporting hospitalizations and deaths; and the co-morbidity of other life-threatening illnesses. We propose a Monte Carlo method for inferring true case counts from observed deaths using clinical estimates of Infection Fatality Ratios and Time to Death. Findings indicate that current COVID19 confirmed positive counts represent a small fraction of actual cases, and that even relatively effective surveillance regimes fail to identify all infectious individuals. We further demonstrate that the miscount also distorts officials' ability to discern the peak of an epidemic, confounding efforts to assess the efficacy of various interventions.