Prediction of viral symptoms using wearable technology and artificial intelligence: A pilot study in healthcare workers.

Conventional testing and diagnostic methods for infections like SARS-CoV-2 have limitations for population health management and public policy. We hypothesize that daily changes in autonomic activity, measured through off-the-shelf technologies together with app-based cognitive assessments, may be used to forecast the onset of symptoms consistent with a viral illness. We describe our strategy using an AI model that can predict, with 82% accuracy (negative predictive value 97%, specificity 83%, sensitivity 79%, precision 34%), the likelihood of developing symptoms consistent with a viral infection three days before symptom onset. The model correctly predicts, almost all of the time (97%), individuals who will not develop viral-like illness symptoms in the next three days. Conversely, the model correctly predicts as positive 34% of the time, individuals who will develop viral-like illness symptoms in the next three days. This model uses a conservative framework, warning potentially pre-symptomatic individuals to socially isolate while minimizing warnings to individuals with a low likelihood of developing viral-like symptoms in the next three days. To our knowledge, this is the first study using wearables and apps with machine learning to predict the occurrence of viral illness-like symptoms. The demonstrated approach to forecasting the onset of viral illness-like symptoms offers a novel, digital decision-making tool for public health safety by potentially limiting viral transmission.

ABO-incompatible kidney transplantation-proposal of an intensified apheresis strategy for patients with high initial isoagglutinine titers.

Since Tydén's description of ABO-incompatible (ABOi) kidney transplantations based on antigen-specific immunoadsorption (IA) and rituximab (Tydén et al., Am J Transplant 2005;5:145-148), this technique has been successfully adopted by many transplant centers worldwide. The majority of centers strictly adhere to the Swedish protocol and perform IAs with a target volume of 1.5-2 plasma volumes on preoperative days -6, -5, -2, and -1, and postoperative days +3, +6, and +9, respectively. Patients who initially present with an IgG anti-A/B titer higher than 1:128 are not considered suitable candidates for ABOi transplantation by the Swedish protocol. Our center has gone beyond these suggestions and follows a slightly different strategy: We do not exclude patients with initial IgG anti-A/B titers higher than 1:128 and we perform as many preoperative antigen-specific extracorporeal treatments as needed to reach a threshold isoagglutinine titer of 1:4 or less. To intensify isoagglutinine clearance preoperatively, the total target volume per treatment was increased to 2.5-3 plasma volumes. Preconditioning IAs are performed every other day, instead of daily. Postoperatively we perform IAs only, if titers mandate us to do so (Wilpert et al., Nephrol Dial Transplant 2007;22:3048-3051). We report on 11 "high-titer patients" who entered our ABOi kidney transplant program with initial titers of 1:256 or above. Seven of 11 patients (64%) could successfully be transplanted with our modified ABO-apheresis protocol. Four of 11 high-titer patients did not reach target isoagglutinine titers of 1:4 or less and therefore did not undergo transplantation. We conclude that intensified preoperative IA renders a majority of high-titer patients suitable candidates for ABOi kidney transplantation.