@article{VaidSomaniRussaketal.2020, author = {Vaid, Akhil and Somani, Sulaiman and Russak, Adam J. and De Freitas, Jessica K. and Chaudhry, Fayzan F. and Paranjpe, Ishan and Johnson, Kipp W. and Lee, Samuel J. and Miotto, Riccardo and Richter, Felix and Zhao, Shan and Beckmann, Noam D. and Naik, Nidhi and Kia, Arash and Timsina, Prem and Lala, Anuradha and Paranjpe, Manish and Golden, Eddye and Danieletto, Matteo and Singh, Manbir and Meyer, Dara and O'Reilly, Paul F. and Huckins, Laura and Kovatch, Patricia and Finkelstein, Joseph and Freeman, Robert M. and Argulian, Edgar and Kasarskis, Andrew and Percha, Bethany and Aberg, Judith A. and Bagiella, Emilia and Horowitz, Carol R. and Murphy, Barbara and Nestler, Eric J. and Schadt, Eric E. and Cho, Judy H. and Cordon-Cardo, Carlos and Fuster, Valentin and Charney, Dennis S. and Reich, David L. and B{\"o}ttinger, Erwin and Levin, Matthew A. and Narula, Jagat and Fayad, Zahi A. and Just, Allan C. and Charney, Alexander W. and Nadkarni, Girish N. and Glicksberg, Benjamin S.}, title = {Machine learning to predict mortality and critical events in a cohort of patients with COVID-19 in New York City: model development and validation}, series = {Journal of medical internet research : international scientific journal for medical research, information and communication on the internet ; JMIR}, volume = {22}, journal = {Journal of medical internet research : international scientific journal for medical research, information and communication on the internet ; JMIR}, number = {11}, publisher = {Healthcare World}, address = {Richmond, Va.}, issn = {1439-4456}, doi = {10.2196/24018}, pages = {19}, year = {2020}, abstract = {Background: COVID-19 has infected millions of people worldwide and is responsible for several hundred thousand fatalities. The COVID-19 pandemic has necessitated thoughtful resource allocation and early identification of high-risk patients. However, effective methods to meet these needs are lacking. Objective: The aims of this study were to analyze the electronic health records (EHRs) of patients who tested positive for COVID-19 and were admitted to hospitals in the Mount Sinai Health System in New York City; to develop machine learning models for making predictions about the hospital course of the patients over clinically meaningful time horizons based on patient characteristics at admission; and to assess the performance of these models at multiple hospitals and time points. Methods: We used Extreme Gradient Boosting (XGBoost) and baseline comparator models to predict in-hospital mortality and critical events at time windows of 3, 5, 7, and 10 days from admission. Our study population included harmonized EHR data from five hospitals in New York City for 4098 COVID-19-positive patients admitted from March 15 to May 22, 2020. The models were first trained on patients from a single hospital (n=1514) before or on May 1, externally validated on patients from four other hospitals (n=2201) before or on May 1, and prospectively validated on all patients after May 1 (n=383). Finally, we established model interpretability to identify and rank variables that drive model predictions. Results: Upon cross-validation, the XGBoost classifier outperformed baseline models, with an area under the receiver operating characteristic curve (AUC-ROC) for mortality of 0.89 at 3 days, 0.85 at 5 and 7 days, and 0.84 at 10 days. XGBoost also performed well for critical event prediction, with an AUC-ROC of 0.80 at 3 days, 0.79 at 5 days, 0.80 at 7 days, and 0.81 at 10 days. In external validation, XGBoost achieved an AUC-ROC of 0.88 at 3 days, 0.86 at 5 days, 0.86 at 7 days, and 0.84 at 10 days for mortality prediction. Similarly, the unimputed XGBoost model achieved an AUC-ROC of 0.78 at 3 days, 0.79 at 5 days, 0.80 at 7 days, and 0.81 at 10 days. Trends in performance on prospective validation sets were similar. At 7 days, acute kidney injury on admission, elevated LDH, tachypnea, and hyperglycemia were the strongest drivers of critical event prediction, while higher age, anion gap, and C-reactive protein were the strongest drivers of mortality prediction. Conclusions: We externally and prospectively trained and validated machine learning models for mortality and critical events for patients with COVID-19 at different time horizons. These models identified at-risk patients and uncovered underlying relationships that predicted outcomes.}, language = {en} } @article{MuellerFoerstendorfSteudtneretal.2019, author = {M{\"u}ller, Katharina and Foerstendorf, Harald and Steudtner, Robin and Tsushima, Satoru and Kumke, Michael Uwe and Lef{\`e}vre, Gr{\´e}gory and Rothe, J{\"o}rg and Mason, Harris and Szab{\´o}, Zolt{\´a}n and Yang, Ping and Adam, Christian K. R. and Andr{\´e}, R{\´e}mi and Brennenstuhl, Katlen and Chiorescu, Ion and Cho, Herman M. and Creff, Ga{\"e}lle and Coppin, Fr{\´e}d{\´e}ric and Dardenne, Kathy and Den Auwer, Christophe and Drobot, Bj{\"o}rn and Eidner, Sascha and Hess, Nancy J. and Kaden, Peter and Kremleva, Alena and Kretzschmar, Jerome and Kr{\"u}ger, Sven and Platts, James A. and Panak, Petra and Polly, Robert and Powell, Brian A. and Rabung, Thomas and Redon, Roland and Reiller, Pascal E. and R{\"o}sch, Notker and Rossberg, Andr{\´e} and Scheinost, Andreas C. and Schimmelpfennig, Bernd and Schreckenbach, Georg and Skerencak-Frech, Andrej and Sladkov, Vladimir and Solari, Pier Lorenzo and Wang, Zheming and Washton, Nancy M. and Zhang, Xiaobin}, title = {Interdisciplinary Round-Robin Test on molecular spectroscopy of the U(VI) Acetate System}, series = {ACS omega / American Chemical Society}, volume = {4}, journal = {ACS omega / American Chemical Society}, number = {5}, publisher = {American Chemical Society}, address = {Washington}, issn = {2470-1343}, doi = {10.1021/acsomega.9b00164}, pages = {8167 -- 8177}, year = {2019}, abstract = {A comprehensive molecular analysis of a simple aqueous complexing system. U(VI) acetate. selected to be independently investigated by various spectroscopic (vibrational, luminescence, X-ray absorption, and nuclear magnetic resonance spectroscopy) and quantum chemical methods was achieved by an international round-robin test (RRT). Twenty laboratories from six different countries with a focus on actinide or geochemical research participated and contributed to this scientific endeavor. The outcomes of this RRT were considered on two levels of complexity: first, within each technical discipline, conformities as well as discrepancies of the results and their sources were evaluated. The raw data from the different experimental approaches were found to be generally consistent. In particular, for complex setups such as accelerator-based X-ray absorption spectroscopy, the agreement between the raw data was high. By contrast, luminescence spectroscopic data turned out to be strongly related to the chosen acquisition parameters. Second, the potentials and limitations of coupling various spectroscopic and theoretical approaches for the comprehensive study of actinide molecular complexes were assessed. Previous spectroscopic data from the literature were revised and the benchmark data on the U(VI) acetate system provided an unambiguous molecular interpretation based on the correlation of spectroscopic and theoretical results. The multimethodologic approach and the conclusions drawn address not only important aspects of actinide spectroscopy but particularly general aspects of modern molecular analytical chemistry.}, language = {en} } @inproceedings{CassinelliIgnaceWaldronetal.2007, author = {Cassinelli, Joseph P. and Ignace, R. and Waldron, W. and Cho, J. and Murphy, N. and Lazarian, A.}, title = {X-ray line emission produced in clump bow shocks}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-18057}, year = {2007}, abstract = {We summarize Chandra observations of the emission line profiles from 17 OB stars. The lines tend to be broad and unshifted. The forbidden/intercombination line ratios arising from Helium-like ions provide radial distance information for the X-ray emission sources, while the H-like to He-like line ratios provide X-ray temperatures, and thus also source temperature versus radius distributions. OB stars usually show power law differential emission measure distributions versus temperature. In models of bow shocks, we find a power law differential emission measure, a wide range of ion stages, and the bow shock flow around the clumps provides transverse velocities comparable to HWHM values. We find that the bow shock results for the line profile properties, consistent with the observations of X-ray line emission for a broad range of OB star properties.}, language = {en} }