diff --git a/.gitignore b/.gitignore index e75435c..5c60a7f 100644 --- a/.gitignore +++ b/.gitignore @@ -1,10 +1,20 @@ +# bookdown temp files & directories +# from https://github.com/rstudio/bookdown/blob/main/inst/examples/.gitignore +_bookdown_files +_book +docs +redcap-manual-v1.log +images/dedication.lyx +redcap-manual-v1.rds + +/.quarto/ + # History files .Rhistory .Rapp.history # Session Data files .RData -.RDataTmp # User-specific files .Ruserdata @@ -39,11 +49,7 @@ vignettes/*.pdf # R Environment Variables .Renviron -# pkgdown site -docs/ - -# translation temp files -po/*~ +# R Environment Variables +*.DS_Store -# RStudio Connect folder -rsconnect/ +/.luarc.json diff --git a/.markdownlint.json b/.markdownlint.json new file mode 100644 index 0000000..6785348 --- /dev/null +++ b/.markdownlint.json @@ -0,0 +1,22 @@ +{ + "header-style": { "style": "atx" }, + "MD007": { "indent": 2 }, + "MD013": { "line_length": 600 }, + "MD022": { + "lines_above": 1, + "lines_below": 1 + }, + "MD024": { "siblings_only": true }, + "MD033": { + "allowed_elements": [ + "a", + "br", + "details", + "div", + "img", + "span", + "sub", + "sup" + ] + } +} diff --git a/.nojekyll b/.nojekyll new file mode 100644 index 0000000..e69de29 diff --git a/.vscode/settings.json b/.vscode/settings.json new file mode 100644 index 0000000..4b18857 --- /dev/null +++ b/.vscode/settings.json @@ -0,0 +1,232 @@ +{ + "cSpell.words": [ + "adminpr", + "AHRQ", + "analyte", + "annualization", + "anonymization", + "Anschutz", + "Anzalone", + "apalike", + "biblio", + "Bioinformatics", + "Bionetworks", + "biostatisticians", + "bookdown", + "booktabs", + "bslib", + "Cahan", + "callout", + "CAMC", + "CDIS", + "Charlson", + "CITI", + "CNAME", + "codeset", + "Codesets", + "colwidths", + "comorbid", + "comorbidities", + "consortial", + "contributorship", + "COPD", + "covariate", + "covariates", + "CTSA", + "Deacy", + "deidentification", + "deidentified", + "deps", + "discoverability", + "documentclass", + "downlit", + "dplyr", + "ecmo", + "EHDEN", + "embeddable", + "epub", + "Eskenazi", + "estimand", + "ethnicities", + "eval", + "explainability", + "favicon", + "FHIR", + "flowsheet", + "fullnote", + "Gelman", + "generalizability", + "ghpagescname", + "gtsummary", + "Hadley", + "HCPCS", + "heatmaps", + "hsrp", + "hydroxychloroquine", + "ICMJE", + "inclusivity", + "informatic", + "informatician", + "informaticians", + "informaticist", + "informaticists", + "JHU's", + "kable", + "kableExtra", + "knitcitations", + "knitr", + "Kolmogorov-Smirnov", + "Kuplicki", + "Laraway", + "LHBA", + "lightbox", + "Lise", + "Ljazouli", + "LOINC", + "Loomba", + "macrovisit", + "Mariam", + "MCAR", + "McMurry", + "meds", + "methodologists", + "Microvisit", + "microvisits", + "missingness", + "mkdir", + "MNAR", + "mosio", + "natbib", + "NCATS", + "NCBI", + "Nephrology", + "NIDDK", + "NIGMS", + "ocri", + "OHDSI", + "Olex", + "OMOP", + "oneils", + "operationalizing", + "orcid", + "OU's", + "pagedown", + "pandoc", + "pango", + "PCOR", + "pdftools", + "pfaff", + "PHASTR", + "phenotyping", + "PPRL", + "prepended", + "preprocess", + "printr", + "Raton", + "reactable", + "referenceable", + "reidentification", + "remdesivir", + "reseachers", + "retinopathy", + "rmarkdown", + "Rscript", + "Saad", + "SDOH", + "setext", + "sidky", + "SNOMED", + "stoudt", + "Suver", + "svglite", + "Synpuf", + "Synthea", + "telehealth", + "templatization", + "templatized", + "tibble", + "tidyverse", + "tikz", + "tinytex", + "trackdown", + "unbillable", + "Universidad", + "Unmutes", + "unvalidated", + "usethis", + "vapply", + "Vehtari", + "Walonski", + "webshot", + "Wickham", + "workflowr", + "Workstream", + "workstreams", + "xelatex", + "Yihui", + "Yihui's", + "Zenodo", + "Zhou" + ], + "grammarly.selectors": [ + { + "language": "markdown", + "scheme": "file", + "pattern": "chapters/story.md" + }, + { + "language": "markdown", + "scheme": "file", + "pattern": "chapters/access.md" + }, + { + "language": "markdown", + "scheme": "file", + "pattern": "chapters/advanced.md" + }, + { + "language": "markdown", + "scheme": "file", + "pattern": "chapters/cycle.md" + }, + { + "language": "markdown", + "scheme": "file", + "pattern": "chapters/governance.md" + }, + { + "language": "markdown", + "scheme": "file", + "pattern": "chapters/intro.md" + }, + { + "language": "markdown", + "scheme": "file", + "pattern": "chapters/onboarding.md" + }, + { + "language": "markdown", + "scheme": "file", + "pattern": "chapters/publishing.md" + }, + { + "language": "markdown", + "scheme": "file", + "pattern": "chapters/support.md" + }, + { + "language": "markdown", + "scheme": "file", + "pattern": "chapters/tools.md" + }, + { + "language": "markdown", + "scheme": "file", + "pattern": "chapters/understanding.md" + }, + { + "language": "markdown", + "scheme": "file" + } + ] +} \ No newline at end of file diff --git a/raise-manual-v1.Rproj b/raise-manual-v1.Rproj new file mode 100644 index 0000000..4fc6567 --- /dev/null +++ b/raise-manual-v1.Rproj @@ -0,0 +1,20 @@ +Version: 1.0 + +RestoreWorkspace: No +SaveWorkspace: No +AlwaysSaveHistory: No + +EnableCodeIndexing: Yes +UseSpacesForTab: Yes +NumSpacesForTab: 2 +Encoding: UTF-8 + +RnwWeave: knitr +LaTeX: pdfLaTeX + +AutoAppendNewline: Yes +StripTrailingWhitespace: Yes + +UseNativePipeOperator: Yes + +MarkdownCanonical: No diff --git a/references.bib b/references.bib new file mode 100644 index 0000000..8de1641 --- /dev/null +++ b/references.bib @@ -0,0 +1,961 @@ +@book{hastie_2009, + title={The elements of statistical learning: data mining, inference, and prediction}, + author={Hastie, Trevor and Tibshirani, Robert and Friedman, Jerome H and Friedman, Jerome H}, + volume={2}, + year={2009}, + publisher={Springer} +} + +@book{geron_2022, + title={Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow}, + author={G{\'e}ron, Aur{\'e}lien}, + year={2022}, + publisher={" O'Reilly Media, Inc."} +} + +@book{chollet_2021, + title={Deep learning with Python}, + author={Chollet, Francois}, + year={2021}, + publisher={Simon and Schuster} +} + +@incollection{shapley_1953, + doi = {10.1515/9781400881970-018}, + url = {https://doi.org/10.1515/9781400881970-018}, + year = {1953}, + month = dec, + publisher = {Princeton University Press}, + pages = {307--318}, + author = {L. S. Shapley}, + title = {17. A Value for n-Person Games}, + booktitle = {Contributions to the Theory of Games ({AM}-28), Volume {II}} +} + +@misc{lundburg_2018, + doi = {10.48550/ARXIV.1802.03888}, + url = {https://arxiv.org/abs/1802.03888}, + author = {Lundberg, Scott M. and Erion, Gabriel G. and Lee, Su-In}, + keywords = {Machine Learning (cs.LG), Machine Learning (stat.ML), FOS: Computer and information sciences, FOS: Computer and information sciences}, + title = {Consistent Individualized Feature Attribution for Tree Ensembles}, + publisher = {arXiv}, + year = {2018}, + copyright = {arXiv.org perpetual, non-exclusive license} +} + +@incollection{sahner_2020, + doi = {10.1016/b978-0-12-815585-1.00028-0}, + url = {https://doi.org/10.1016/b978-0-12-815585-1.00028-0}, + year = {2020}, + publisher = {Elsevier}, + pages = {399--417}, + author = {David Sahner and David C. Spellmeyer}, + title = {Artificial Intelligence: Emerging Applications in Biotechnology and Pharma}, + booktitle = {Biotechnology Entrepreneurship} +} + +@article{muhammad_2014, + doi = {10.13140/RG.2.2.28948.04489}, + url = {http://rgdoi.net/10.13140/RG.2.2.28948.04489}, + author = {{Peshawa J Muhammad Ali} and {Rezhna Hassan Faraj}}, + language = {en}, + title = {Data Normalization and Standardization: A Technical Report}, + publisher = {Unpublished}, + year = {2014} +} + +@article{casiraghi_2023, + doi = {10.1016/j.jbi.2023.104295}, + url = {https://doi.org/10.1016/j.jbi.2023.104295}, + year = {2023}, + month = mar, + publisher = {Elsevier {BV}}, + volume = {139}, + pages = {104295}, + author = {Elena Casiraghi and Rachel Wong and Margaret Hall and Ben Coleman and Marco Notaro and Michael D. Evans and Jena S. Tronieri and Hannah Blau and Bryan Laraway and Tiffany J. Callahan and Lauren E. Chan and Carolyn T. Bramante and John B. Buse and Richard A. Moffitt and Til St\"{u}rmer and Steven G. Johnson and Yu Raymond Shao and Justin Reese and Peter N. Robinson and Alberto Paccanaro and Giorgio Valentini and Jared D. Huling and Kenneth J. Wilkins}, + title = {A method for comparing multiple imputation techniques: A case study on the U.S. national {COVID} cohort collaborative}, + journal = {Journal of Biomedical Informatics} +} + +@article{mitra_2023, + doi = {10.1038/s42256-022-00596-z}, + url = {https://doi.org/10.1038/s42256-022-00596-z}, + year = {2023}, + month = jan, + publisher = {Springer Science and Business Media {LLC}}, + volume = {5}, + number = {1}, + pages = {13--23}, + author = {Robin Mitra and Sarah F. McGough and Tapabrata Chakraborti and Chris Holmes and Ryan Copping and Niels Hagenbuch and Stefanie Biedermann and Jack Noonan and Brieuc Lehmann and Aditi Shenvi and Xuan Vinh Doan and David Leslie and Ginestra Bianconi and Ruben Sanchez-Garcia and Alisha Davies and Maxine Mackintosh and Eleni-Rosalina Andrinopoulou and Anahid Basiri and Chris Harbron and Ben D. MacArthur}, + title = {Learning from data with structured missingness}, + journal = {Nature Machine Intelligence} +} + +@article{fu_2020, + doi = {10.1186/s12911-020-1072-9}, + url = {https://doi.org/10.1186/s12911-020-1072-9}, + year = {2020}, + month = mar, + publisher = {Springer Science and Business Media {LLC}}, + volume = {20}, + number = {1}, + author = {Sunyang Fu and Lester Y. Leung and Anne-Olivia Raulli and David F. Kallmes and Kristin A. Kinsman and Kristoff B. Nelson and Michael S. Clark and Patrick H. Luetmer and Paul R. Kingsbury and David M. Kent and Hongfang Liu}, + title = {Assessment of the impact of {EHR} heterogeneity for clinical research through a case study of silent brain infarction}, + journal = {{BMC} Medical Informatics and Decision Making} +} + +@article{ledford_2019, + doi = {10.1038/d41586-019-03228-6}, + url = {https://doi.org/10.1038/d41586-019-03228-6}, + year = {2019}, + month = oct, + publisher = {Springer Science and Business Media {LLC}}, + volume = {574}, + number = {7780}, + pages = {608--609}, + author = {Heidi Ledford}, + title = {Millions of black people affected by racial bias in health-care algorithms}, + journal = {Nature} +} + +@article{roberts_2021, + doi = {10.1038/s42256-021-00307-0}, + url = {https://doi.org/10.1038/s42256-021-00307-0}, + year = {2021}, + month = mar, + publisher = {Springer Science and Business Media {LLC}}, + volume = {3}, + number = {3}, + pages = {199--217}, + author = {Michael Roberts and Derek Driggs and Matthew Thorpe and Julian Gilbey and Michael Yeung and Stephan Ursprung and Angelica I. Aviles-Rivero and Christian Etmann and Cathal McCague and Lucian Beer and Jonathan R. Weir-McCall and Zhongzhao Teng and Effrossyni Gkrania-Klotsas and Alessandro Ruggiero and Anna Korhonen and Emily Jefferson and Emmanuel Ako and Georg Langs and Ghassem Gozaliasl and Guang Yang and Helmut Prosch and Jacobus Preller and Jan Stanczuk and Jing Tang and Johannes Hofmanninger and Judith Babar and Lorena Escudero S{\'{a}}nchez and Muhunthan Thillai and Paula Martin Gonzalez and Philip Teare and Xiaoxiang Zhu and Mishal Patel and Conor Cafolla and Hojjat Azadbakht and Joseph Jacob and Josh Lowe and Kang Zhang and Kyle Bradley and Marcel Wassin and Markus Holzer and Kangyu Ji and Maria Delgado Ortet and Tao Ai and Nicholas Walton and Pietro Lio and Samuel Stranks and Tolou Shadbahr and Weizhe Lin and Yunfei Zha and Zhangming Niu and James H. F. Rudd and Evis Sala and Carola-Bibiane Sch\"{o}nlieb and}, + title = {Common pitfalls and recommendations for using machine learning to detect and prognosticate for {COVID}-19 using chest radiographs and {CT} scans}, + journal = {Nature Machine Intelligence} +} + +@article{reese_2023, + doi = {10.1016/j.ebiom.2022.104413}, + url = {https://doi.org/10.1016/j.ebiom.2022.104413}, + year = {2023}, + month = jan, + publisher = {Elsevier {BV}}, + volume = {87}, + pages = {104413}, + author = {Justin T. Reese and Hannah Blau and Elena Casiraghi and Timothy Bergquist and Johanna J. Loomba and Tiffany J. Callahan and Bryan Laraway and Corneliu Antonescu and Ben Coleman and Michael Gargano and Kenneth J. Wilkins and Luca Cappelletti and Tommaso Fontana and Nariman Ammar and Blessy Antony and T.M. Murali and J. Harry Caufield and Guy Karlebach and Julie A. McMurry and Andrew Williams and Richard Moffitt and Jineta Banerjee and Anthony E. Solomonides and Hannah Davis and Kristin Kostka and Giorgio Valentini and David Sahner and Christopher G. Chute and Charisse Madlock-Brown and Melissa A. Haendel and Peter N. Robinson and Heidi Spratt and Shyam Visweswaran and Joseph Eugene Flack and Yun Jae Yoo and Davera Gabriel and G. Caleb Alexander and Hemalkumar B. Mehta and Feifan Liu and Robert T. Miller and Rachel Wong and Elaine L. Hill and Lorna E. Thorpe and Jasmin Divers}, + title = {Generalisable long {COVID} subtypes: findings from the {NIH} N3C and {RECOVER} programmes}, + journal = {{eBioMedicine}} +} + +@article{casiraghi_2020, + doi = {10.1109/access.2020.3034032}, + url = {https://doi.org/10.1109/access.2020.3034032}, + year = {2020}, + publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, + volume = {8}, + pages = {196299--196325}, + author = {Elena Casiraghi and Dario Malchiodi and Gabriella Trucco and Marco Frasca and Luca Cappelletti and Tommaso Fontana and Alessandro Andrea Esposito and Emanuele Avola and Alessandro Jachetti and Justin Reese and Alessandro Rizzi and Peter N. Robinson and Giorgio Valentini}, + title = {Explainable Machine Learning for Early Assessment of {COVID}-19 Risk Prediction in Emergency Departments}, + journal = {{IEEE} Access} +} + +@article{alper_2023, + author = {Alper, B. S.}, + title = {Reflections on defining a standard for computable expression of scientific knowledge: What teach us Yoda can}, + journal = {Learn Health Syst}, + volume = {7}, + number = {1}, + pages = {e10312}, + issn = {2379-6146 (Electronic) 2379-6146 (Linking)}, + doi = {10.1002/lrh2.10312}, + url = {https://www.ncbi.nlm.nih.gov/pubmed/36654808}, + year = {2023}, + type = {Journal Article} +} + +@article{ankan_2021, + author = {Ankan, A. and Wortel, I. M. N. and Textor, J.}, + title = {Testing Graphical Causal Models Using the R Package "dagitty"}, + journal = {Curr Protoc}, + volume = {1}, + number = {2}, + pages = {e45}, + url = {https://www.ncbi.nlm.nih.gov/pubmed/33592130}, + year = {2021}, + doi = {10.1002/cpz1.45}, + type = {Journal Article} +} + +@article{anderson_2022, + author = {Andersen, K. M. and Bates, B. A. and Rashidi, E. S. and Olex, A. L. and Mannon, R. B. and Patel, R. C. and Singh, J. and Sun, J. and Auwaerter, P. G. and Ng, D. K. and Segal, J. B. and Garibaldi, B. T. and Mehta, H. B. and Alexander, G. C. and National, Covid Cohort Collaborative Consortium}, + title = {Long-term use of immunosuppressive medicines and in-hospital COVID-19 outcomes: a retrospective cohort study using data from the National COVID Cohort Collaborative}, + journal = {Lancet Rheumatol}, + volume = {4}, + number = {1}, + pages = {e33-e41}, + issn = {2665-9913 (Electronic) 2665-9913 (Linking)}, + doi = {10.1016/S2665-9913(21)00325-8}, + url = {https://www.ncbi.nlm.nih.gov/pubmed/34806036}, + year = {2022}, + type = {Journal Article} +} + +@article{anzalone_2023, + title = {Higher hospitalization and mortality rates among SARS-CoV-2-infected persons in rural America}, + author = {Anzalone, Alfred Jerrod and Horswell, Ronald and Hendricks, Brian M and Chu, San and Hillegass, William B and Beasley, William H and Harper, Jeremy R and Kimble, Wesley and Rosen, Clifford J and Miele, Lucio and others}, + journal = {The Journal of Rural Health}, + volume = {39}, + number = {1}, + pages = {39--54}, + year = {2023}, + doi = {10.1111/jrh.12689}, + publisher = {Wiley Online Library} +} + +@article{benchimol_2015, + author = {Benchimol, E. I. and Smeeth, L. and Guttmann, A. and Harron, K. and Moher, D. and Petersen, I. and Sorensen, H. T. and von Elm, E. and Langan, S. M. and Committee, Record Working}, + title = {The REporting of studies Conducted using Observational Routinely-collected health Data (RECORD) statement}, + journal = {PLoS Med}, + volume = {12}, + number = {10}, + pages = {e1001885}, + issn = {1549-1676 (Electronic) 1549-1277 (Print) 1549-1277 (Linking)}, + doi = {10.1371/journal.pmed.1001885}, + url = {https://www.ncbi.nlm.nih.gov/pubmed/26440803}, + year = {2015}, + type = {Journal Article} +} + +@article{bradwell_2022, + title = {Harmonizing units and values of quantitative data elements in a very large nationally pooled electronic health record (EHR) dataset}, + author = {Bradwell, Katie R and Wooldridge, Jacob T and Amor, Benjamin and Bennett, Tellen D and Anand, Adit and Bremer, Carolyn and Yoo, Yun Jae and Qian, Zhenglong and Johnson, Steven G and Pfaff, Emily R and others}, + journal = {Journal of the American Medical Informatics Association}, + volume = {29}, + number = {7}, + pages = {1172--1182}, + year = {2022}, + doi = {10.1093/jamia/ocac054}, + publisher = {Oxford University Press} +} + +@article{caton_2020, + author = {Caton, S and Haas, S }, + title = {Fairness in machine learning: A survey.}, + journal = {arXiv}, + url = {https://arxiv.org/abs/2010.04053}, + year = {2020}, + doi = {10.48550/arXiv.2010.0405}, + type = {Journal Article} +} + +@article{charlson_1987, + title = {A new method of classifying prognostic comorbidity in longitudinal studies: Development and validation}, + author = {Mary E. Charlson and Peter Pompei and Kathy L. Ales and C.Ronald MacKenzie}, + journal = {Journal of Chronic Diseases}, + volume = {40}, + number = {5}, + pages = {373-383}, + year = {1987}, + issn = {0021-9681}, + doi = {10.1016/0021-9681(87)90171-8}, + url = {https://www.sciencedirect.com/science/article/pii/0021968187901718} +} + +@misc{cd2h1, + title = {Informatics Playbook}, + author = {Chunlei Wu and C2DH}, + howpublished = "\url{https://playbook.cd2h.org/}", + year = {2022}, + note = "[Online; accessed 2022-11-07]" +} + +@article{cutter_2014, + author = {Cutter, SL and Ash, KD and Emrich, CT. }, + title = {The geographies of community disaster resilience}, + journal = {Global environmental change}, + volume = {29}, + number = {Nov 1}, + pages = {65-77}, + url = {https://doi.org/10.1016/j.gloenvcha.2014.08.005}, + year = {2014}, + type = {Journal Article} +} + +@article{dong_2020, + title = {COVID-19 TestNorm: A tool to normalize COVID-19 testing names to LOINC codes}, + author = {Dong, Xiao and Li, Jianfu and Soysal, Ekin and Bian, Jiang and DuVall, Scott L and Hanchrow, Elizabeth and Liu, Hongfang and Lynch, Kristine E and Matheny, Michael and Natarajan, Karthik and others}, + journal = {Journal of the American Medical Informatics Association}, + volume = {27}, + number = {9}, + pages = {1437--1442}, + year = {2020}, + doi = {10.1093/jamia/ocaa145}, + publisher = {Oxford University Press} +} + +@article{franklin_2021, + author = {Franklin, J. M. and Lin, K. J. and Gatto, N. M. and Rassen, J. A. and Glynn, R. J. and Schneeweiss, S.}, + title = {Real-World Evidence for Assessing Pharmaceutical Treatments in the Context of COVID-19}, + journal = {Clin Pharmacol Ther}, + volume = {109}, + number = {4}, + pages = {816-828}, + doi = {10.1002/cpt.2185}, + url = {https://www.ncbi.nlm.nih.gov/pubmed/33529354}, + year = {2021}, + type = {Journal Article} +} + +@article{franklin_2022, + author = {Franklin, J. M. and Platt, R. and Dreyer, N. A. and London, A. J. and Simon, G. E. and Watanabe, J. H. and Horberg, M. and Hernandez, A. and Califf, R. M.}, + title = {When Can Nonrandomized Studies Support Valid Inference Regarding Effectiveness or Safety of New Medical Treatments?}, + journal = {Clin Pharmacol Ther}, + volume = {111}, + number = {1}, + pages = {108-115}, + issn = {1532-6535 (Electronic) 0009-9236 (Print) 0009-9236 (Linking)}, + doi = {10.1002/cpt.2255}, + url = {https://www.ncbi.nlm.nih.gov/pubmed/33826756}, + year = {2022}, + type = {Journal Article} +} + +@Book{gelman_2021, + title = {Regression and Other Stories}, + author = {Andrew Gelman, Jennifer Hill, and Aki Vehtari}, + publisher = {Cambridge University Press}, + address = {New York}, + year = {2021}, + isbn = {978-1107676510}, + url = {http://www.cambridge.org/9781107676510}, +} + +@inproceedings{gold_2018, + title = {Clinical concept value sets and interoperability in health data analytics}, + author = {Gold, Sigfried and Batch, Andrea and McClure, Robert and Jiang, Guoqian and Kharrazi, Hadi and Saripalle, Rishi and Huser, Vojtech and Weng, Chunhua and Roderer, Nancy and Szarfman, Ana and others}, + booktitle = {AMIA Annual Symposium Proceedings}, + volume = {2018}, + pages = {480}, + year = {2018}, + organization = {American Medical Informatics Association}, + url = {https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6371254} +} + +@article{gold_2021, + title = {Practices, norms, and aspirations regarding the construction, validation, and reuse of code sets in the analysis of real-world data}, + author = {Gold, Sigfried and Lehmann, Harold and Schilling, Lisa and Lutters, Wayne}, + journal = {medRxiv}, + pages = {2021--10}, + year = {2021}, + doi = {10.1101/2021.10.14.21264917}, + publisher = {Cold Spring Harbor Laboratory Press} +} + +@article{griffith_2022, + author = {Griffith, G. J. and Morris, T. T. and Tudball, M. J. and Herbert, A. and Mancano, G. and Pike, L. and Sharp, G. C. and Sterne, J. and Palmer, T. M. and Davey Smith, G. and Tilling, K. and Zuccolo, L. and Davies, N. M. and Hemani, G.}, + title = {Collider bias undermines our understanding of COVID-19 disease risk and severity}, + journal = {Nature communications}, + volume = {11}, + number = {1}, + pages = {5749}, + year = {2020}, + publisher = {Nature Publishing Group UK London}, + doi = {10.1038/s41467-020-19478-2} +} + +@article{haendel_2020, + author = {Haendel, Melissa A and Chute, Christopher G and Bennett, Tellen D and Eichmann, David A and Guinney, Justin and Kibbe, Warren A and Payne, Philip R O and Pfaff, Emily R and Robinson, Peter N and Saltz, Joel H and Spratt, Heidi and Suver, Christine and Wilbanks, John and Wilcox, Adam B and Williams, Andrew E and Wu, Chunlei and Blacketer, Clair and Bradford, Robert L and Cimino, James J and Clark, Marshall and Colmenares, Evan W and Francis, Patricia A and Gabriel, Davera and Graves, Alexis and Hemadri, Raju and Hong, Stephanie S and Hripscak, George and Jiao, Dazhi and Klann, Jeffrey G and Kostka, Kristin and Lee, Adam M and Lehmann, Harold P and Lingrey, Lora and Miller, Robert T and Morris, Michele and Murphy, Shawn N and Natarajan, Karthik and Palchuk, Matvey B and Sheikh, Usman and Solbrig, Harold and Visweswaran, Shyam and Walden, Anita and Walters, Kellie M and Weber, Griffin M and Zhang, Xiaohan Tanner and Zhu, Richard L and Amor, Benjamin and Girvin, Andrew T and Manna, Amin and Qureshi, Nabeel and Kurilla, Michael G and Michael, Sam G and Portilla, Lili M and Rutter, Joni L and Austin, Christopher P and Gersing, Ken R and the N3C Consortium }, + title = "{The National COVID Cohort Collaborative (N3C): Rationale, design, infrastructure, and deployment}", + journal = {Journal of the American Medical Informatics Association}, + volume = {28}, + number = {3}, + pages = {427-443}, + year = {2020}, + month = {08}, + abstract = "{Coronavirus disease 2019 (COVID-19) poses societal challenges that require expeditious data and knowledge sharing. Though organizational clinical data are abundant, these are largely inaccessible to outside researchers. Statistical, machine learning, and causal analyses are most successful with large-scale data beyond what is available in any given organization. Here, we introduce the National COVID Cohort Collaborative (N3C), an open science community focused on analyzing patient-level data from many centers.The Clinical and Translational Science Award Program and scientific community created N3C to overcome technical, regulatory, policy, and governance barriers to sharing and harmonizing individual-level clinical data. We developed solutions to extract, aggregate, and harmonize data across organizations and data models, and created a secure data enclave to enable efficient, transparent, and reproducible collaborative analytics.Organized in inclusive workstreams, we created legal agreements and governance for organizations and researchers; data extraction scripts to identify and ingest positive, negative, and possible COVID-19 cases; a data quality assurance and harmonization pipeline to create a single harmonized dataset; population of the secure data enclave with data, machine learning, and statistical analytics tools; dissemination mechanisms; and a synthetic data pilot to democratize data access.The N3C has demonstrated that a multisite collaborative learning health network can overcome barriers to rapidly build a scalable infrastructure incorporating multiorganizational clinical data for COVID-19 analytics. We expect this effort to save lives by enabling rapid collaboration among clinicians, researchers, and data scientists to identify treatments and specialized care and thereby reduce the immediate and long-term impacts of COVID-19.}", + issn = {1527-974X}, + doi = {10.1093/jamia/ocaa196}, + url = {https://doi.org/10.1093/jamia/ocaa196}, + eprint = {https://academic.oup.com/jamia/article-pdf/28/3/427/37306721/ocaa196.pdf}, +} + +@article{hernan_2016, + author = {Hernan, M. A. and Robins, J. M.}, + title = {Using Big Data to Emulate a Target Trial When a Randomized Trial Is Not Available}, + journal = {Am J Epidemiol}, + volume = {183}, + number = {8}, + pages = {758-64}, + issn = {1476-6256 (Electronic) 0002-9262 (Print) 0002-9262 (Linking)}, + doi = {10.1093/aje/kwv254}, + url = {https://www.ncbi.nlm.nih.gov/pubmed/26994063}, + year = {2016}, + type = {Journal Article} +} + +@article{islam_2022, + author = {Islam, J. Y. and Madhira, V. and Sun, J. and Olex, A. and Franceschini, N. and Kirk, G. and Patel, R.}, + title = {Racial disparities in COVID-19 test positivity among people living with HIV in the United States}, + journal = {Int J STD AIDS}, + volume = {33}, + number = {5}, + pages = {462-466}, + issn = {1758-1052 (Electronic) 0956-4624 (Print) 0956-4624 (Linking)}, + doi = {10.1177/09564624221074468}, + url = {https://www.ncbi.nlm.nih.gov/pubmed/35306931}, + year = {2022}, + type = {Journal Article} +} + +@article{kharrazi_2017, + title = {Comparing population-based risk-stratification model performance using demographic, diagnosis and medication data extracted from outpatient electronic health records versus administrative claims}, + author = {Kharrazi, Hadi and Chi, Winnie and Chang, Hsien-Yen and Richards, Thomas M and Gallagher, Jason M and Knudson, Susan M and Weiner, Jonathan P}, + journal = {Medical care}, + volume = {55}, + number = {8}, + pages = {789--796}, + year = {2017}, + doi = {10.1097/MLR.0000000000000754}, + publisher = {JSTOR} +} + +@book{klein_1996, + author = {Klein, Julie Thompson}, + title = {Crossing boundaries knowledge, disciplinarities, and interdisciplinarities}, + publisher = {University Press of Virginia}, + address = {Charlottesville ; London}, + series = {Knowledge : disciplinarity and beyond}, + url = {https://www.google.com/books/edition/Crossing_Boundaries/bNJvYf3ROPAC}, + isbn = {978-0813916798}, + year = {1996}, + type = {Book} +} + +@article{kleinberg_2016, + author = {Jon M. Kleinberg and Sendhil Mullainathan and Manish Raghavan}, + title = {Inherent Trade-Offs in the Fair Determination of Risk Scores}, + journal = {CoRR}, + volume = {abs/1609.05807}, + year = {2016}, + url = {http://arxiv.org/abs/1609.05807}, + eprinttype = {arXiv}, + eprint = {1609.05807}, + timestamp = {Mon, 13 Aug 2018 16:46:05 +0200}, + doi = {10.48550/arXiv.1609.05807}, + bibsource = {dblp computer science bibliography, https://dblp.org} +} + +@article{knuth_1984, + title = {Literate Programming}, + author = {Knuth, Donald E.}, + year = {1984}, + issue_date = {May 1984}, + publisher = {Oxford University Press, Inc.}, + address = {USA}, + volume = {27}, + number = {2}, + issn = {0010-4620}, + url = {https://doi.org/10.1093/comjnl/27.2.97}, + doi = {10.1093/comjnl/27.2.97}, + journal = {Comput. J.}, + month = may, + pages = {97-111}, + numpages = {15} +} + +@article{kuehne_2019, + author = {Kuehne, F. and Jahn, B. and Conrads-Frank, A. and Bundo, M. and Arvandi, M. and Endel, F. and Popper, N. and Endel, G. and Urach, C. and Gyimesi, M. and Murray, E. J. and Danaei, G. and Gaziano, T. A. and Pandya, A. and Siebert, U.}, + title = {Guidance for a causal comparative effectiveness analysis emulating a target trial based on big real world evidence: when to start statin treatment}, + journal = {J Comp Eff Res}, + volume = {8}, + number = {12}, + pages = {1013-1025}, + issn = {2042-6313 (Electronic) 2042-6305 (Linking)}, + doi = {10.2217/cer-2018-0103}, + url = {https://www.ncbi.nlm.nih.gov/pubmed/31512926}, + year = {2019}, + type = {Journal Article} +} + +@article {li_2023, + author = {Chenyu Li and Abdulrahman M. Alsheikh and Karen A. Robinson and Harold P. Lehmann}, + title = {Use of Recommended Real-World Methods for Electronic Health Record Data Analysis Has Not Improved Over 10 Years}, + elocation-id = {2023.06.21.23291706}, + year = {2023}, + doi = {10.1101/2023.06.21.23291706}, + publisher = {Cold Spring Harbor Laboratory Press}, + URL = {https://www.medrxiv.org/content/early/2023/06/22/2023.06.21.23291706}, + eprint = {https://www.medrxiv.org/content/early/2023/06/22/2023.06.21.23291706.full.pdf}, + journal = {medRxiv} +} + +@article{madlock_brown_2022a, + author = {Madlock-Brown, C. and Wilkens, K. and Weiskopf, N. and Cesare, N. and Bhattacharyya, S. and Riches, N. O. and Espinoza, J. and Dorr, D. and Goetz, K. and Phuong, J. and Sule, A. and Kharrazi, H. and Liu, F. and Lemon, C. and Adams, W. G.}, + title = {Clinical, social, and policy factors in COVID-19 cases and deaths: methodological considerations for feature selection and modeling in county-level analyses}, + journal = {BMC Public Health}, + volume = {22}, + number = {1}, + pages = {747}, + issn = {1471-2458 (Electronic) 1471-2458 (Linking)}, + doi = {10.1186/s12889-022-13168-y}, + url = {https://www.ncbi.nlm.nih.gov/pubmed/35421958}, + year = {2022}, + type = {Journal Article} +} + +@article{madlock_brown_2022b, + author = {Madlock-Brown, C. and Wilkens, K. and Weiskopf, N. and Cesare, N. and Bhattacharyya, S. and Riches, N. O. and Espinoza, J. and Dorr, D. and Goetz, K. and Phuong, J. and Sule, A. and Kharrazi, H. and Liu, F. and Lemon, C. and Adams, W. G.}, + title = {Correction: Clinical, social, and policy factors in COVID-19 cases and deaths: methodological considerations for feature selection and modeling in county-level analyses}, + journal = {BMC Public Health}, + volume = {22}, + number = {1}, + pages = {1250}, + issn = {1471-2458 (Electronic) 1471-2458 (Linking)}, + doi = {10.1186/s12889-022-13562-6}, + url = {https://www.ncbi.nlm.nih.gov/pubmed/35751109}, + year = {2022}, + type = {Journal Article} +} + +@article{mehta_2021, + title = "Use of hydroxychloroquine, remdesivir, and dexamethasone among adults hospitalized with covid-19 in the united states: A retrospective cohort study", + author = "Mehta, {Hemalkumar B.} and Huijun An and Andersen, {Kathleen M.} and Omar Mansour and Vithal Madhira and Rashidi, {Emaan S.} and Benjamin Bates and Soko Setoguchi and Corey Joseph and Kocis, {Paul T.} and Richard Moffitt and Bennett, {Tellen D.} and Chute, {Christopher G.} and Garibaldi, {Brian T.} and {Caleb Alexander}, G.", + year = "2021", + month = oct, + day = "1", + doi = "10.7326/M21-0857", + language = "English (US)", + volume = "174", + pages = "1395--1403", + journal = "Annals of Internal Medicine", + issn = "0003-4819", + publisher = "American College of Physicians", + number = "10", +} + +@article{mitra_2023, + title = {Learning from data with structured missingness}, + author = {Mitra, Robin and McGough, Sarah F and Chakraborti, Tapabrata and Holmes, Chris and Copping, Ryan and Hagenbuch, Niels and Biedermann, Stefanie and Noonan, Jack and Lehmann, Brieuc and Shenvi, Aditi and others}, + journal = {Nature Machine Intelligence}, + volume = {5}, + number = {1}, + pages = {13--23}, + year = {2023}, + doi = {10.1038/s42256-022-00596-z}, + publisher = {Nature Publishing Group UK London} +} + +@article{morgan_2018, + author = {Morgan, R. L. and Whaley, P. and Thayer, K. A. and Schunemann, H. J.}, + title = {Identifying the PECO: A framework for formulating good questions to explore the association of environmental and other exposures with health outcomes}, + journal = {Environ Int}, + volume = {121}, + number = {Pt 1}, + pages = {1027-1031}, + ISSN = {1873-6750 (Electronic) 0160-4120 (Print) 0160-4120 (Linking)}, + DOI = {10.1016/j.envint.2018.07.015}, + url = {https://www.ncbi.nlm.nih.gov/pubmed/30166065}, + year = {2018}, + type = {Journal Article} +} + +@article{narrett_2023, + author = {Narrett, J. A. and Mallawaarachchi, I. and Aldridge, C. M. and Assefa, E. D. and Patel, A. and Loomba, J. J. and Ratcliffe, S. and Sadan, O. and Monteith, T. and Worrall, B. B. and Brown, D. E. and Johnston, K. C. and Southerland, A. M. and consortium, N. C.}, + title = {Increased stroke severity and mortality in patients with SARS-CoV-2 infection: An analysis from the N3C database}, + journal = {J Stroke Cerebrovasc Dis}, + volume = {32}, + number = {3}, + pages = {106987}, + issn = {1532-8511 (Electronic) 1052-3057 (Print) 1052-3057 (Linking)}, + doi = {10.1016/j.jstrokecerebrovasdis.2023.106987}, + url = {https://www.ncbi.nlm.nih.gov/pubmed/36641948}, + year = {2023}, + type = {Journal Article} +} + +@book{ohdsi_2019, + title = {The Book of OHDSI: Observational Health Data Sciences and Informatics}, + author = {OHDSI}, + isbn = {9781088855195}, + url = {https://ohdsi.github.io/TheBookOfOhdsi/}, + address = {United States}, + year = {2019}, + publisher = {OHDSI} +} + +@misc{palantir_2023, + title = {Documentation: Code repositories overview}, + author = {Palantir}, + howpublished = "\url{https://www.palantir.com/docs/foundry/code-repositories/overview/}", + year = {2023}, + note = "[Online; accessed 2023-03-14]" +} + +@article{pfaff_2022a, + title = {Identifying who has long COVID in the USA: a machine learning approach using N3C data.}, + author = {Pfaff, E. R. and Girvin, A. T. and Bennett, T. D. and Bhatia, A. and Brooks, I. M. and Deer, R. R. and Dekermanjian, J. P. and Jolley, S. E. and Kahn, M. G. and Kostka, K. and McMurry, J. A. and Moffitt, R. and Walden, A. and Chute, C. G. and Haendel, M. A. and Bramante, C. and Dorr, D. and Morris, M. and Parker, A. M. and Sidky, H. and Gersing, K. and Hong, S. and Niehaus, E.}, + year = {2022}, + issue_date = {May 2022}, + volume = {4}, + number = {7}, + issn = {0010-4620}, + url = {https://doi.org/10.1016/S2589-7500(22)00048-6}, + doi = {10.1016/S2589-7500(22)00048-6}, + journal = {Lancet Digit Health}, + month = may, + pages = {e532-e541}, + numpages = {10} +} + +@article{pfaff_2022b, + title = {Synergies between centralized and federated approaches to data quality: a report from the national COVID cohort collaborative}, + author = {Pfaff, Emily R and Girvin, Andrew T and Gabriel, Davera L and Kostka, Kristin and Morris, Michele and Palchuk, Matvey B and Lehmann, Harold P and Amor, Benjamin and Bissell, Mark and Bradwell, Katie R and others}, + journal = {Journal of the American Medical Informatics Association}, + volume = {29}, + number = {4}, + pages = {609--618}, + year = {2022}, + doi = {10.1093/jamia/ocab217}, + publisher = {Oxford University Press} +} + +@article{pfaff_2023a, + title = {Coding long COVID: characterizing a new disease through an ICD-10 lens}, + author = {Pfaff, Emily R and Madlock-Brown, Charisse and Baratta, John M and Bhatia, Abhishek and Davis, Hannah and Girvin, Andrew and Hill, Elaine and Kelly, Elizabeth and Kostka, Kristin and Loomba, Johanna and others}, + journal = {BMC medicine}, + volume = {21}, + number = {1}, + pages = {1--13}, + year = {2023}, + doi = {10.1186/s12916-023-02737-6}, + publisher = {BioMed Central} +} + +@article{redelmeier_2023, + author = {Redelmeier, D. A. and Wang, J. and Thiruchelvam, D.}, + title = {COVID Vaccine Hesitancy and Risk of a Traffic Crash}, + journal = {Am J Med}, + volume = {136}, + number = {2}, + pages = {153-162 e5}, + issn = {1555-7162 (Electronic) 0002-9343 (Print) 0002-9343 (Linking)}, + doi = {10.1016/j.amjmed.2022.11.002}, + url = {https://www.ncbi.nlm.nih.gov/pubmed/36470796}, + year = {2023}, + type = {Journal Article} +} + +@article{reese_2023, + title = {Generalisable long COVID subtypes: Findings from the NIH N3C and RECOVER programmes}, + author = {Reese, Justin T and Blau, Hannah and Casiraghi, Elena and Bergquist, Timothy and Loomba, Johanna J and Callahan, Tiffany J and Laraway, Bryan and Antonescu, Corneliu and Coleman, Ben and Gargano, Michael and others}, + journal = {EBioMedicine}, + volume = {87}, + year = {2023}, + doi = {10.1016/j.ebiom.2022.104413}, + publisher = {Elsevier} +} + +@article{richesson_2013, + title = {Electronic health records based phenotyping in next-generation clinical trials: a perspective from the NIH Health Care Systems Collaboratory}, + author = {Richesson, Rachel L and Hammond, W Ed and Nahm, Meredith and Wixted, Douglas and Simon, Gregory E and Robinson, Jennifer G and Bauck, Alan E and Cifelli, Denise and Smerek, Michelle M and Dickerson, John and others}, + journal = {Journal of the American Medical Informatics Association}, + volume = {20}, + number = {e2}, + pages = {e226--e231}, + year = {2013}, + doi = {10.1136/amiajnl-2013-001926}, + publisher = {BMJ Publishing Group} +} + +@article{schneeweiss_2019, + author = {Schneeweiss, S. and Rassen, J. A. and Brown, J. S. and Rothman, K. J. and Happe, L. and Arlett, P. and Dal Pan, G. and Goettsch, W. and Murk, W. and Wang, S. V.}, + title = {Graphical Depiction of Longitudinal Study Designs in Health Care Databases}, + journal = {Ann Intern Med}, + volume = {170}, + number = {6}, + pages = {398-406}, + issn = {1539-3704 (Electronic) 0003-4819 (Linking)}, + doi = {10.7326/M18-3079}, + url = {https://www.ncbi.nlm.nih.gov/pubmed/30856654}, + year = {2019}, + type = {Journal Article} +} + +@article{schuemie_2018, + author = {Schuemie, M. J. and Ryan, P. B. and Hripcsak, G. and Madigan, D. and Suchard, M. A.}, + title = {Improving reproducibility by using high-throughput observational studies with empirical calibration}, + journal = {Philos Trans A Math Phys Eng Sci}, + volume = {376}, + number = {2128}, + issn = {1471-2962 (Electronic) 1364-503X (Print) 1364-503X (Linking)}, + doi = {10.1098/rsta.2017.0356}, + url = {https://www.ncbi.nlm.nih.gov/pubmed/30082302}, + year = {2018}, + type = {Journal Article} +} + +@article{schuemie_2020, + author = {Schuemie, M. J. and Ryan, P. B. and Pratt, N. and Chen, R. and You, S. C. and Krumholz, H. M. and Madigan, D. and Hripcsak, G. and Suchard, M. A.}, + title = {Large-scale evidence generation and evaluation across a network of databases (LEGEND): assessing validity using hypertension as a case study}, + journal = {J Am Med Inform Assoc}, + volume = {27}, + number = {8}, + pages = {1268-1277}, + issn = {1527-974X (Electronic) 1067-5027 (Print) 1067-5027 (Linking)}, + doi = {10.1093/jamia/ocaa124}, + url = {https://www.ncbi.nlm.nih.gov/pubmed/32827027}, + year = {2020}, + type = {Journal Article} +} + +@article{sharafeldin_2021, + author = {Sharafeldin, Noha and Bates, Benjamin and Song, Qianqian and Madhira, Vithal and Yan, Yao and Dong, Sharlene and Lee, Eileen and Kuhrt, Nathaniel and Shao, Yu Raymond and Liu, Feifan and Bergquist, Timothy and Guinney, Justin and Su, Jing and Topaloglu, Umit}, + title = {Outcomes of COVID-19 in Patients With Cancer: Report From the National COVID Cohort Collaborative (N3C)}, + journal = {Journal of Clinical Oncology}, + volume = {39}, + number = {20}, + pages = {2232-2246}, + year = {2021}, + doi = {10.1200/JCO.21.01074}, + note ={PMID: 34085538}, +} + +@article{sidky_2023, + author = {Sidky, H. and Young, J. C. and Girvin, A. T. and Lee, E. and Shao, Y. R. and Hotaling, N. and Michael, S. and Wilkins, K. J. and Setoguchi, S. and Funk, M. J. and Consortium, N. C.}, + title = {Data quality considerations for evaluating COVID-19 treatments using real world data: learnings from the National COVID Cohort Collaborative (N3C)}, + journal = {BMC Med Res Methodol}, + volume = {23}, + number = {1}, + pages = {46}, + issn = {1471-2288 (Electronic) 1471-2288 (Linking)}, + doi = {10.1186/s12874-023-01839-2}, + url = {https://www.ncbi.nlm.nih.gov/pubmed/36800930}, + year = {2023}, + type = {Journal Article} +} + +@article{stoudt_2021, + author = {Stoudt, S. and Vasquez, V. N. and Martinez, C. C.}, + title = {Principles for data analysis workflows}, + journal = {PLoS Comput Biol}, + volume = {17}, + number = {3}, + pages = {e1008770}, + issn = {1553-7358 (Electronic) 1553-734X (Print) 1553-734X (Linking)}, + doi = {10.1371/journal.pcbi.1008770}, + url = {https://www.ncbi.nlm.nih.gov/pubmed/33735208}, + year = {2021}, + type = {Journal Article} +} + +@article{sun_2022, + title = "Association Between Immune Dysfunction and COVID-19 Breakthrough Infection After SARS-CoV-2 Vaccination in the US", + author = "Jing Sun and Qulu Zheng and Vithal Madhira and Olex, {Amy L.} and Anzalone, {Alfred J.} and Amanda Vinson and Singh, {Jasvinder A.} and Evan French and Abraham, {Alison G.} and Jomol Mathew and Nasia Safdar and Gaurav Agarwal and Fitzgerald, {Kathryn C.} and Namrata Singh and Umit Topaloglu and Chute, {Christopher G.} and Mannon, {Roslyn B.} and Kirk, {Gregory D.} and Patel, {Rena C.}", + note = "Funding Information: tools through the N3C Data Enclave (ncats.nih.gov/ n3c/about), which is supported by grant U24 TR002306 from National Center for Advancing Translational Sciences (NCATS). National COVID Cohort Collaborative (N3C) is funded by grant U24 TR002306 from NCATS. Ms Olex and Mr French were supported by Clinical and Translational Science Awards UL1TR002649 from NCATS. Mr Anzalone was supported by grants U54GM104942-05S2 and U54GM115458 from National Institute of General Medical Sciences, which funds the West Virginia Clinical & Translational Science Institute and the Great Plains IDeA Clinical and Translational Research Network. Dr Safdar was supported by grant DP2AI144244 from National Institute of Allergy and Infectious Diseases (NIAID) and by a grant from the US Department of Veterans Affairs. Dr N. Singh was supported in part by grant DP2AI144244 from NIAID. Dr Kirk was supported in part by grant K24AI118591 from NIAID. Dr Patel was supported by grant K23AI120855 from NIAID. Funding Information: reported receiving grants from Paladin Labs Inc and personal fees from Paladin Labs Inc advisory board outside the submitted work. Dr J.A. Singh reported receiving personal fees from Crealta/Horizon, Medisys, Fidia, PK Med, Two Labs Inc, Adept Field Solutions, Clinical Care Options, ClearView Healthcare Partners, Putnam Associates, Focus Forward, Navigant, Spherix, MedIQ, Jupiter Life Science, UBM LLC, Trio Health, Medscape, WebMD, Practice Point Communications, National Institutes of Health (NIH), American College of Rheumatology, and Simply Speaking; holding stock options from TPT Global Tech, Vaxart Pharmaceuticals, Atyu Biopharma, and Charlotte's Web Holdings Inc outside the submitted work. Dr Abraham reported receiving grants from NIH and personal fees from Implementation Group Inc outside the submitted work. Dr Topaloglu reported being a stockholder of CareDirections LLC. Dr Chute reported receiving grants from NIH outside the submitted work. Dr Mannon reported serving as a steering committee member for IMAGINE trial from Vitaeris; receiving honorarium as deputy editor of American Journal of Transplantation; grants from Mallinckrodt Pharmaceuticals, and grants to institution for clinical trial from CSL Behring, Transplant Genomics, and Quark Pharmaceuticals outside the submitted work; and serving as chair of Policy and Advocacy Committee of American Society of Nephrology and co-chair of review committee of Scientific Registry of Transplant Recipients. No other disclosures were reported. Publisher Copyright: {\textcopyright} 2021 American Medical Association.", + year = "2022", + month = feb, + doi = "10.1001/jamainternmed.2021.7024", + language = "English (US)", + volume = "182", + pages = "153--162", + journal = "Archives of internal medicine (Chicago, Ill. : 1908)", + issn = "2168-6106", + publisher = "American Medical Association", + number = "2", +} + +@article{tan_2023, + author = {Tan, A. L. M. and Getzen, E. J. and Hutch, M. R. and Strasser, Z. H. and Gutierrez-Sacristan, A. and Le, T. T. and Dagliati, A. and Morris, M. and Hanauer, D. A. and Moal, B. and Bonzel, C. L. and Yuan, W. and Chiudinelli, L. and Das, P. and Zhang, H. G. and Aronow, B. J. and Avillach, P. and Brat, G. A. and Cai, T. and Hong, C. and La Cava, W. G. and Hooi Will Loh, H. and Luo, Y. and Murphy, S. N. and Yuan Hgiam, K. and Omenn, G. S. and Patel, L. P. and Jebathilagam Samayamuthu, M. and Shriver, E. R. and Shakeri Hossein Abad, Z. and Tan, B. W. L. and Visweswaran, S. and Wang, X. and Weber, G. M. and Xia, Z. and Verdy, B. and EHR, Covid- by and Long, Q. and Mowery, D. L. and Holmes, J. H.}, + title = {Informative missingness: What can we learn from patterns in missing laboratory data in the electronic health record?}, + journal = {J Biomed Inform}, + volume = {139}, + pages = {104306}, + doi = {10.1016/j.jbi.2023.104306}, + url = {https://www.ncbi.nlm.nih.gov/pubmed/36738870}, + year = {2023}, + type = {Journal Article} +} + +@misc{usfda_2017, + author = {{U.S. Food and Drug Administration}}, + title = {Software as a Medical Device (SAMD): Clinical Evaluation/Guidance for Industry and Food and Drug Administration Staff}, + publisher = {FDA}, + url = {https://www.fda.gov/media/100714/download}, + year = {2017}, + type = {Web Page} +} + +@misc{usfda_2019, + author = {{U.S. Food and Drug Administration and the Duke-Margolis Center for Health Policy}}, + title = {Developing Real-World Data and Evidence to Support Regulatory Decision-Making}, + url = {https://www.youtube.com/watch?v=-G6ltatA71I}, + year = {2019}, + type = {Online Multimedia} +} + +@article{usfda_2021, + author = {{U.S. Food and Drug Administration, Health Canada, and the United Kingdom's Medicines and Healthcare products Regulatory Agency (MHRA)}}, + title = {Good Machine Learning Practice for Medical Device Development: Guiding Principles}, + publisher = {FDA}, + url = {https://www.fda.gov/medical-devices/software-medical-device-samd/good-machine-learning-practice-medical-device-development-guiding-principles}, + year = {2021}, + type = {Web Page} +} + +@techreport{usfda_2023, + author = {{U.S. Food and Drug Administration}}, + title = {Considerations for the Design and Conduct of Externally Controlled Trials for Drug and Biological Products Guidance for Industry}, + institution = {Food and Drug Administration}, + url = {https://www.fda.gov/media/164960/download}, + year = {2023}, + type = {Report} +} + +@article{vonelm_2014, + author = {von Elm, E. and Altman, D. G. and Egger, M. and Pocock, S. J. and Gotzsche, P. C. and Vandenbroucke, J. P. and Initiative, Strobe}, + title = {The Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) Statement: guidelines for reporting observational studies}, + journal = {Int J Surg}, + volume = {12}, + number = {12}, + pages = {1495-9}, + issn = {1743-9159 (Electronic) 1743-9159 (Linking)}, + doi = {10.1016/j.ijsu.2014.07.013}, + url = {https://www.ncbi.nlm.nih.gov/pubmed/25046131}, + year = {2014}, + type = {Journal Article} +} + +@article{walonoski_2020, + title = {Synthea™ Novel coronavirus (COVID-19) model and synthetic data set}, + journal = {Intelligence-Based Medicine}, + volume = {1-2}, + pages = {100007}, + year = {2020}, + issn = {2666-5212}, + doi = {doi.org/10.1016/j.ibmed.2020.100007}, + url = {https://www.sciencedirect.com/science/article/pii/S2666521220300077}, + author = {Jason Walonoski and Sybil Klaus and Eldesia Granger and Dylan Hall and Andrew Gregorowicz and George Neyarapally and Abigail Watson and Jeff Eastman}, + keywords = {Synthetic data, COVID-19, Electronic health records}, +} + +@article{wang_2021, + author = {Wang, S. V. and Pinheiro, S. and Hua, W. and Arlett, P. and Uyama, Y. and Berlin, J. A. and Bartels, D. B. and Kahler, K. H. and Bessette, L. G. and Schneeweiss, S.}, + title = {STaRT-RWE: structured template for planning and reporting on the implementation of real world evidence studies}, + journal = {BMJ}, + volume = {372}, + pages = {m4856}, + url = {https://www.ncbi.nlm.nih.gov/pubmed/33436424}, + year = {2021}, + doi = {10.1136/bmj.m4856}, + type = {Journal Article} +} + +@article{weiskopf_2023, + author = {Weiskopf, N. G. and Dorr, D. A. and Jackson, C. and Lehmann, H. P. and Thompson, C. A.}, + title = {Healthcare utilization is a collider: an introduction to collider bias in EHR data reuse}, + journal = {J Am Med Inform Assoc}, + doi = {10.1093/jamia/ocad013}, + url = {https://www.ncbi.nlm.nih.gov/pubmed/36752649}, + year = {2023}, + type = {Journal Article} +} + +@Book{wickham_2022, + title = {R for Data Science}, + author = {Hadley Wickham, Mine Çetinkaya-Rundel, and Garrett Grolemund}, + publisher = {O'Reilly Media}, + address = {United States}, + year = {2022}, + isbn = {978-1491910399}, + url = {https://r4ds.hadley.nz/}, +} + +@article{wilkinson_2016, + title = {The FAIR Guiding Principles for scientific data management and stewardship}, + author = {Wilkinson, Mark D and Dumontier, Michel and Aalbersberg, IJsbrand Jan and Appleton, Gabrielle and Axton, Myles and Baak, Arie and Blomberg, Niklas and Boiten, Jan-Willem and da Silva Santos, Luiz Bonino and Bourne, Philip E and others}, + biburl = {https://www.bibsonomy.org/bibtex/284ff5b88120fbf405870b49cf7e60767/joschirr}, + journal = {Scientific data}, + keywords = {imported}, + publisher = {Nature Publishing Group}, + volume = 3, + year = 2016, + doi = {10.1038/sdata.2016.18} +} + +@InCollection{xie_2014, + booktitle = {Implementing Reproducible Computational Research}, + author = {Yihui Xie}, + editor = {Victoria Stodden and Friedrich Leisch and Roger D. Peng}, + title = {knitr: A Comprehensive Tool for Reproducible Research in {R}}, + publisher = {Chapman and Hall/CRC}, + year = {2014}, + isbn = {978-1466561595}, + url = {http://www.crcpress.com/product/isbn/9781466561595}, +} + +@Book{xie_2015, + title = {Dynamic Documents with {R} and knitr}, + author = {Yihui Xie}, + publisher = {Chapman and Hall/CRC}, + address = {Boca Raton, Florida}, + year = {2015}, + edition = {2nd}, + isbn = {978-1498716963}, + url = {http://yihui.org/knitr/}, +} + +@Book{xie_2016, + title = {bookdown: Authoring Books and Technical Documents with {R} Markdown}, + author = {Yihui Xie}, + publisher = {Chapman and Hall/CRC}, + address = {Boca Raton, Florida}, + year = {2016}, + isbn = {978-1138700109}, + url = {https://bookdown.org/yihui/bookdown}, +} + +@Book{xie_2018, + title = {R Markdown: The Definitive Guide}, + author = {Yihui Xie and J.J. Allaire and Garrett Grolemund}, + publisher = {Chapman and Hall/CRC}, + address = {Boca Raton, Florida}, + year = {2018}, + isbn = {978-1138359338}, + url = {https://bookdown.org/yihui/rmarkdown}, +} + +@Book{xie_2020, + title = {R Markdown Cookbook}, + author = {Yihui Xie and Christophe Dervieux and Emily Riederer}, + publisher = {Chapman and Hall/CRC}, + address = {Boca Raton, Florida}, + year = {2020}, + isbn = {9780367563837}, + url = {https://bookdown.org/yihui/rmarkdown-cookbook}, +} + +@article{yang_2021, + title = {Associations between HIV infection and clinical spectrum of COVID-19: a population level analysis based on US National COVID Cohort Collaborative (N3C) data}, + author = {Yang, Xueying and Sun, Jing and Patel, Rena C and Zhang, Jiajia and Guo, Siyuan and Zheng, Qulu and Olex, Amy L and Olatosi, Bankole and Weissman, Sharon B and Islam, Jessica Y and others}, + journal = {The Lancet HIV}, + volume = {8}, + number = {11}, + pages = {690--700}, + year = {2021}, + doi = {10.1016/S2352-3018(21)00239-3}, + publisher = {Elsevier} +} + +@article{zhou_2022, + author = {Zhou, R. and Johnson, K. E. and Rousseau, J. F. and Rathouz, P. J. and Consortium, N. C.}, + title = {Comparative Effectiveness of Dexamethasone in Treatment of Hospitalized COVID-19 Patients during the First Year of the Pandemic: The N3C Data Repository}, + journal = {medRxiv}, + doi = {10.1101/2022.10.22.22281373}, + url = {https://www.ncbi.nlm.nih.gov/pubmed/36324806}, + year = {2022}, + type = {Journal Article} +} +# Book References to add +# * Python & Spark + +# Useful tools: +# The "Cite" link for entries in https://scholar.google.com/ +# https://www.bioinformatics.org/texmed/