FraudAuditor: A Visual Analytics Approach for Collusive Fraud in Health Insurance.

Collusive fraud, in which multiple fraudsters collude to defraud health insurance funds, threatens the operation of the healthcare system. However, existing statistical and machine learning-based methods have limited ability to detect fraud in the scenario of health insurance due to the high similarity of fraudulent behaviors to normal medical visits and the lack of labeled data. To ensure the accuracy of the detection results, expert knowledge needs to be integrated with the fraud detection process. By working closely with health insurance audit experts, we propose FraudAuditor, a three-stage visual analytics approach to collusive fraud detection in health insurance. Specifically, we first allow users to interactively construct a co-visit network to holistically model the visit relationships of different patients. Second, an improved community detection algorithm that considers the strength of fraud likelihood is designed to detect suspicious fraudulent groups. Finally, through our visual interface, users can compare, investigate, and verify suspicious patient behavior with tailored visualizations that support different time scales. We conducted case studies in a real-world healthcare scenario, i.e., to help locate the actual fraud group and exclude the false positive group. The results and expert feedback proved the effectiveness and usability of the approach.

Cell-based phenotypic screening of mast cell degranulation unveils kinetic perturbations of agents targeting phosphorylation.

Mast cells play an essential role in initiating allergic diseases. The activation of mast cells are controlled by a complicated signal network of reversible phosphorylation, and finding the key regulators involved in this network has been the focus of the pharmaceutical industry. In this work, we used a method named Time-dependent cell responding profile (TCRP) to track the process of mast cell degranulation under various perturbations caused by agents targeting phosphorylation. To test the feasibility of this high-throughput cell-based phenotypic screening method, a variety of biological techniques were used. We further screened 145 inhibitors and clustered them based on the similarities of their TCRPs. Stat3 phosphorylation has been widely reported as a key step in mast cell degranulation. Interestingly, our TCRP results showed that a Stat3 inhibitor JSI124 did not inhibit degranulation like other Stat3 inhibitors, such as Stattic, clearly inhibited degranulation. Regular endpoint assays demonstrated that the distinctive TCRP of JSI124 potentially correlated with the ability to induce apoptosis. Consequently, different agents possibly have disparate functions, which can be conveniently detected by TCRP. From this perspective, our TCRP screening method is reliable and sensitive when it comes to discovering and selecting novel compounds for new drug developments.