The cryptocurrency economy provides a comprehensive digital trace of human economic behavior: almost all cryptocurrency users’ activities are faithfully recorded in transactions on public blockchains. However, the user identifiers in the transaction records, i.e., blockchain addresses, are anonymous. That is, they cannot be associated with any real “off-chain” identify of actual users. Nonetheless, identifying the economic roles of the addresses from their past behaviors is still feasible. This paper analyzes Ethereum token transactions, characterizes key economic agents’ behavior from their transaction patterns, and explores their identifiability through interpretable machine learning models. Specifically, six types of most active economic agents are considered, including centralized cryptocurrency exchanges, decentralized exchanges, cryptocurrency wallets, token issuers, airdrop services, and gaming services. Transaction patterns such as trading volume, transaction tempo, and structural properties of transaction networks are defined for individual blockchain addresses. The results showed that cryptocurrency exchanges and online wallets have signature behavior patterns and hence can be accurately distinguished from other agents. Token issuers, airdrop services, and gaming services can sometimes be confused. Moreover, transaction networks’ features provide the richest information in the economic agent’s identification.

Hemorrhagic complication (HC) is the most severe complication of intravenous thrombolysis (IVT) in patients with acute ischemic stroke (AIS). This study aimed to build a machine learning (ML) prediction model and an application system for a personalized analysis of the risk of HC in patients undergoing IVT therapy. We included patients from Chongqing, Hainan and other centers, including Computed Tomography (CT) images, demographics, and other data, before the occurrence of HC. After feature engineering, a better feature subset was obtained, which was used to build a machine learning (ML) prediction model (Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), eXtreme Gradient Boosting (XGB)), and then evaluated with relevant indicators. Finally, a prediction model with better performance was obtained. Based on this, an application system was built using the Flask framework. A total of 517 patients were included, of which 332 were in the training cohort, 83 were in the internal validation cohort, and 102 were in the external validation cohort. After evaluation, the performance of the XGB model is better, with an AUC of 0.9454 and ACC of 0.8554 on the internal validation cohort, and 0.9142 and ACC of 0.8431 on the external validation cohort. A total of 18 features were used to construct the model, including hemoglobin and fasting blood sugar. Furthermore, the validity of the model is demonstrated through decision curves. Subsequently, a system prototype is developed to verify the test prediction effect. The clinical decision support system (CDSS) embedded with the XGB model based on clinical data and image features can better carry out personalized analysis of the risk of HC in intravenous injection patients.

ObjectivesWe used two automated software commonly employed in clinical practice—Olea Sphere (Olea) and Shukun-PerfusionGo (PerfusionGo)—to compare the diagnostic utility and volumetric agreement of computed tomography perfusion (CTP)-predicted final infarct volume (FIV) with true FIV in patients with anterior-circulation acute ischemic stroke (AIS).MethodsIn all, 122 patients with anterior-circulation AIS who met the inclusion and exclusion criteria were retrospectively enrolled and divided into two groups: intervention group (n = 52) and conservative group (n = 70), according to recanalization of blood vessels and clinical outcome (NIHSS) after different treatments. Patients in both groups underwent one-stop 4D-CT angiography (CTA)/CTP, and the raw CTP data were processed on a workstation using Olea and PerfusionGo post-processing software, to calculate and obtain the ischemic core (IC) and hypoperfusion (IC plus penumbra) volumes, hypoperfusion in the conservative group and IC in the intervention group were used to define the predicted FIV. The ITK-SNAP software was used to manually outline and measure true FIV on the follow-up non-enhanced CT or MRI-DWI images. Intraclass correlation coefficients (ICC), Bland–Altman, and Kappa analysis were used to compare the differences in IC and penumbra volumes calculated by the Olea and PerfusionGo software to investigate the relationship between their predicted FIV and true FIV.ResultsThe IC and penumbra difference between Olea and PerfusionGo within the same group (p < 0.001) was statistically significant. Olea obtained larger IC and smaller penumbra than PerfusionGo. Both software partially overestimated the infarct volume, but Olea significantly overestimated it by a larger percentage. ICC analysis showed that Olea performed better than PerfusionGo (intervention-Olea: ICC 0.633, 95%CI 0.439–0.771; intervention-PerfusionGo: ICC 0.526, 95%CI 0.299–0.696; conservative-Olea: ICC 0.623, 95%CI 0.457–0.747; conservative-PerfusionGo: ICC 0.507, 95%CI 0.312–0.662). Olea and PerfusionGo had the same capacity in accurately diagnosing and classifying patients with infarct volume <70 ml.ConclusionBoth software had differences in the evaluation of the IC and penumbra. Olea’s predicted FIV was more closely correlated with the true FIV than PerfusionGo’s prediction. Accurate assessment of infarction on CTP post-processing software remains challenging. Our results may have important practice implications for the clinical use of perfusion post-processing software.