A series of hitherto unknown mixed-metal phosphates of the monophosphate tungsten bronze structure family [MPTB; (WO3)2m(PO2)4] have been obtained by solution combustion synthesis followed by annealing (ϑ = 850°C) at appropriate oxygen pressures. These new phosphates show substitution of W5+ by either M3+1/3W6+2/3 (M: V, Cr, Fe, Mo) or Ti4+1/2W6+1/2. Members of the MPTB structural series with m = 2 [e.g. CrIII4/3WVI8/3O12(PO2)4; TiIV6/3WVI6/3O12(PO2)4] and m = 4 [e.g. Cr4/3W20/3O24(PO2)4] have been obtained. In the course of our investigation the crystal structure of WOPO4 (MPTB with m = 2: W4O12(PO2)4) has been re-determined from X-ray single-crystal data, showing monoclinic instead of the orthorhombic symmetry reported in literature (P21/m, Z = 1, 80 parameters, 1832 independent reflections R1 = 0.027, wR2 = 0.063). The crystal structures of MoIII4/3WVI8/3O12(PO2)4 and CrIII4/3WVI8/3O12(PO2)4 (MPTBs with m = 2) were also refined from single-crystal data {(Mo/W (Cr/W): P21/m, Z = 1, 80(86) parameters, 1782(1769) independent reflections, R1 = 0.035(0.059), wR2 = 0.081(0.146)}. These refinements indicate statistical distribution of MIII and WVI over the metal sites. By selected area electron diffraction the unit cell dimensions of CrIII4/3WVI8/3O12(PO2)4 and CrIII4/3WVI20/3O24(PO2)4 derived from XRPD and SXRD are confirmed. HRTEM images of Cr4/3W20/3O24(PO2)4 are in agreement with its assumed close structural relation to W8O24(PO2)4 and show an highly ordered atomic arrangement.
Epilepsy is a complex brain disorder characterized by repetitive seizure events. Epilepsy patients often suffer from various and severe physical and psychological comorbidities (e.g., anxiety, migraine, and stroke). While general comorbidity prevalences and incidences can be estimated from epidemiological data, such an approach does not take into account that actual patient-specific risks can depend on various individual factors, including medication. This motivates to develop a machine learning approach for predicting risks of future comorbidities for individual epilepsy patients. In this work, we use inpatient and outpatient administrative health claims data of around 19,500 U.S. epilepsy patients. We suggest a dedicated multimodal neural network architecture (Deep personalized LOngitudinal convolutional RIsk model—DeepLORI) to predict the time-dependent risk of six common comorbidities of epilepsy patients. We demonstrate superior performance of DeepLORI in a comparison with several existing methods. Moreover, we show that DeepLORI-based predictions can be interpreted on the level of individual patients. Using a game theoretic approach, we identify relevant features in DeepLORI models and demonstrate that model predictions are explainable in light of existing knowledge about the disease. Finally, we validate the model on independent data from around 97,000 patients, showing good generalization and stable prediction performance over time.
Despite available vaccinations COVID-19 case numbers around the world are still growing, and effective medications against severe cases are lacking. In this work, we developed a machine learning model which predicts mortality for COVID-19 patients using data from the multi-center ‘Lean European Open Survey on SARS-CoV-2-infected patients’ (LEOSS) observational study (>100 active sites in Europe, primarily in Germany), resulting into an AUC of almost 80%. We showed that molecular mechanisms related to dementia, one of the relevant predictors in our model, intersect with those associated to COVID-19. Most notably, among these molecules was tyrosine kinase 2 (TYK2), a protein that has been patented as drug target in Alzheimer's Disease but also genetically associated with severe COVID-19 outcomes. We experimentally verified that anti-cancer drugs Sorafenib and Regorafenib showed a clear anti-cytopathic effect in Caco2 and VERO-E6 cells and can thus be regarded as potential treatments against COVID-19. Altogether, our work demonstrates that interpretation of machine learning based risk models can point towards drug targets and new treatment options, which are strongly needed for COVID-19.
Evidence from drug class reviews is often not accessible to practicing clinicians nor is it presented in a way that allows clinicians to use the information to guide treatment and prescribing decisions. Nevertheless, information from such reviews can be very helpful to clinicians as they evaluate the "evidence" provided to them through marketing strategies implemented, primarily, by the pharmaceutical industry and designed to influence their prescribing behavior. Unfortunately, these marketing strategies can be used to promote the off-label use of drugs that may not be efficacious. One example is the pharmaceutical marketing to promote off-label use of gabapentin (Neurontin) for the treatment of bipolar disorder, the legality of which was later addressed in a major lawsuit by the National Association of Attorneys General. We describe an effort to use counter-marketing strategies to compete with those implemented by the pharmaceutical industry and to help clinicians, principally psychiatrists, make use of available evidence to inform their prescription of antiepileptic drugs (AEDs) in the treatment of bipolar disorder. A growing body of literature describes industry marketing practices designed to influence prescriber behavior. This literature suggests that use of competing approaches involving the same underlying strategies to deliver highly credible information from trusted sources can inform prescriber knowledge and prescribing practice. We describe our use of existing evidence to develop accurate and convincing messages and materials to be disseminated nationally to counter industry misinformation and promote evidence-based prescription of AEDs.
Despite available vaccinations COVID-19 case numbers around the world are still growing, and effective medications against severe cases are lacking. In this work, we developed a machine learning model which predicts mortality for COVID-19 patients using data from the multi-center ‘Lean European Open Survey on SARS-CoV-2-infected patients’ (LEOSS) observational study (>100 active sites in Europe, primarily in Germany), resulting into an AUC of almost 80%. We showed that molecular mechanisms related to dementia, one of the relevant predictors in our model, intersect with those associated to COVID-19. Most notably, among these molecules was tyrosine kinase 2 (TYK2), a protein that has been patented as drug target in Alzheimer’s Disease but also genetically associated with severe COVID-19 outcomes. We experimentally verified that anti-cancer drugs Sorafenib and Regorafenib showed a clear anti-cytopathic effect in Caco2 and VERO-E6 cells and can thus be regarded as potential treatments against COVID-19. Altogether, our work demonstrates that interpretation of machine learning based risk models can point towards drug targets and new treatment options, which are strongly needed for COVID-19.
In situations like the COVID-19 pandemic, healthcare systems are under enormous pressure as they can rapidly collapse under the burden of the crisis. Machine learning (ML) based risk models could lift the burden by identifying patients with high risk of severe disease progression. Electronic Health Records (EHRs) provide crucial sources of information to develop these models because they rely on routinely collected healthcare data. However, EHR data is challenging for training ML models because it contains irregularly timestamped diagnosis, prescription, and procedure codes. For such data, transformer-based models are promising. We extended the previously published Med-BERT model by including age, sex, medications, quantitative clinical measures, and state information. After pre-training on approximately 988 million EHRs from 3.5 million patients, we developed models to predict Acute Respiratory Manifestations (ARM) risk using the medical history of 80,211 COVID-19 patients. Compared to XGBoost and Random Forests, our transformer-based models more accurately forecast the risk of developing ARM after COVID-19 infection. We used Integrated Gradients and Bayesian networks to understand the link between the essential features of our model. Finally, we evaluated adapting our model to Austrian in-patient data. Our study highlights the promise of predictive transformer-based models for precision medicine.
Motivation A global medical crisis like the COVID-19 pandemic requires interdisciplinary and highly collaborative research from all over the world. One of the key challenges for collaborative research is a lack of interoperability among various heterogeneous data sources. Interoperability, standardization and mapping of datasets is necessary for data analysis and applications in advanced algorithms such as developing personalized risk prediction modeling. Results To ensure the interoperability and compatibility among COVID-19 datasets, we present here a Common Data Model (CDM) which has been built from 11 different COVID-19 datasets from various geographical locations. The current version of the CDM holds 4639 data variables related to COVID-19 such as basic patient information (age, biological sex, and diagnosis) as well as disease-specific data variables, for example, Anosmia and Dispnea. Each of the data variables in the data model is associated with specific data types, variable mappings, value ranges, data units, and data encodings that could be used for standardizing any dataset. Moreover, the compatibility with established data standards like OMOP and FHIR makes the CDM a well-designed common data model for COVID-19 data interoperability. Availability The CDM is available in a public repo here: https://github.com/Fraunhofer-SCAI-Applied-Semantics/COVID-19-Global-Model Supplementary information Supplementary data are available at Bioinformatics online.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.