Search

Abstract Background Waste and fraud are important problems for health insurers to deal with. With the advent of big data, these insurers are looking more and more towards data mining and machine learning methods to help in detecting waste and fraud. However, labeled data is costly and difficult to acquire as it requires expert investigators and known care providers with atypical behavior. Methods In this work we show how recent advances in machine learning can be used to set up a workflow that can aid investigators in discovering practitioners or groups of practitioners with unusual resource use in order to more efficiently combat waste and fraud. We combine three different techniques, which have not been used in the context of healthcare insurance anomaly detection: categorical embeddings to deal with high-cardinality categorical variables, state-of-the-art unsupervised anomaly detection techniques to detect anomalies and Shapley additive explanations (SHAP) to explain the model output. Results The method has been evaluated on providers with a known anomalous profile and with the help of experts of the largest health insurance fund in Belgium. The quantitative experiments show that categorical embeddings offer a significant improvement compared to standard methods and that the state-of-the-art unsupervised anomaly detection techniques generally show an improvement over traditional methods. In a practical setting, the proposed workflow with SHAP was able to detect a previously unknown, anomalous trend among general practitioners. Conclusions The proposed workflow is able to detect known care providers with atypical behaviour and helps expert investigators in making informed decisions concerning possible fraud or overconsumption in the health insurance field.

The Rift Valley fever virus (RVFV) causes haemorrhagic fever, encephalitis, and permanent blindness and has been listed by the WHO as a priority pathogen. To study RVFV pathogenesis and identify small-molecule antivirals, we established a novel In Vivo model using zebrafish larvae. Pericardial injection of RVFV resulted in ~4 log10 viral RNA copies/larva, which was inhibited by the antiviral 2′-fluoro-2′-deoxycytidine. The optical transparency of the larvae allowed detection of RVFVeGFP in the liver and sensory nervous system, including the optic tectum and retina, but not the brain or spinal cord. Thus, RVFV-induced blindness likely occurs due to direct damage to the eye and peripheral neurons, rather than the brain. Treatment with the JAK-inhibitor ruxolitinib, as well as knockout of stat1a but not stat1b, enhanced RVFV replication to ~6 log10 viral RNA copies/larva and ultra-bright livers, although without dissemination to sensory neurons or the eye, thereby confirming the critical role of stat1 in RVFV pathogenesis.

Background: Waste and fraud are important problems for health insurers to deal with. With the advent of big data, these insurers are looking more and more towards data mining and machine learning methods to help in detecting waste and fraud. However, labeled data is costly and difficult to acquire as it requires expert investigators and known care providers with atypical behavior. Methods: In this work we show how recent advances in machine learning can be used to set up a workflow that can aid investigators in discovering practitioners or groups of practitioners with unusual resource use in order to more efficiently combat waste and fraud. We combine three different techniques, which have not been used in the context of healthcare insurance anomaly detection: categorical embeddings to deal with high-cardinality categorical variables, state-of-the-art unsupervised anomaly detection techniques to detect anomalies and Shapley additive explanations (SHAP) to explain the model output. Results: The method has been evaluated on providers with a known anomalous profile and with the help of experts of the largest health insurance fund in Belgium. The quantitative experiments show that categorical embeddings offer a significant improvement compared to standard methods and that the state-of-the-art unsupervised anomaly detection techniques generally show an improvement over traditional methods. In a practical setting, the proposed workflow with SHAP was able to detect a previously unknown, anomalous trend among general practitioners. Conclusions: The proposed workflow is able to detect known care providers with atypical behaviour and helps expert investigators in making informed decisions concerning possible fraud or overconsumption in the health insurance field. [ABSTRACT FROM AUTHOR]

The Rift Valley fever virus (RVFV) causes haemorrhagic fever, encephalitis, and permanent blindness and has been listed by the WHO as a priority pathogen. To study RVFV pathogenesis and identify small-molecule antivirals, we established a novel In Vivo model using zebrafish larvae. Pericardial injection of RVFV resulted in ~4 log10 viral RNA copies/larva, which was inhibited by the antiviral 2′-fluoro-2′-deoxycytidine. The optical transparency of the larvae allowed detection of RVFVeGFP in the liver and sensory nervous system, including the optic tectum and retina, but not the brain or spinal cord. Thus, RVFV-induced blindness likely occurs due to direct damage to the eye and peripheral neurons, rather than the brain. Treatment with the JAK-inhibitor ruxolitinib, as well as knockout of stat1a but not stat1b, enhanced RVFV replication to ~6 log10 viral RNA copies/larva and ultra-bright livers, although without dissemination to sensory neurons or the eye, thereby confirming the critical role of stat1 in RVFV pathogenesis. [ABSTRACT FROM AUTHOR]