references.bib

@article{hripcsak2015ObservationalHealthData,
  title = {Observational {{Health Data Sciences}} and {{Informatics}} ({{OHDSI}}): {{Opportunities}} for {{Observational Researchers}}},
  shorttitle = {Observational {{Health Data Sciences}} and {{Informatics}} ({{OHDSI}})},
  author = {Hripcsak, George and Duke, Jon D. and Shah, Nigam H. and Reich, Christian G. and Huser, Vojtech and Schuemie, Martijn J. and Suchard, Marc A. and Park, Rae Woong and Wong, Ian Chi Kei and Rijnbeek, Peter R. and {van der Lei}, Johan and Pratt, Nicole and Nor{\'e}n, G. Niklas and Li, Yu-Chuan and Stang, Paul E. and Madigan, David and Ryan, Patrick B.},
  year = {2015},
  journal = {Studies in Health Technology and Informatics},
  volume = {216},
  pages = {574--578},
  issn = {1879-8365},
  abstract = {The vision of creating accessible, reliable clinical evidence by accessing the clincial experience of hundreds of millions of patients across the globe is a reality. Observational Health Data Sciences and Informatics (OHDSI) has built on learnings from the Observational Medical Outcomes Partnership to turn methods research and insights into a suite of applications and exploration tools that move the field closer to the ultimate goal of generating evidence about all aspects of healthcare to serve the needs of patients, clinicians and all other decision-makers around the world.},
  langid = {english},
  pmcid = {PMC4815923},
  pmid = {26262116},
  keywords = {{Databases, Factual},Health Services Research,Internationality,Medical Informatics,{Models, Organizational},Observational Studies as Topic}
}

@article{hripcsak2016PreservingTemporalRelations,
  title = {Preserving Temporal Relations in Clinical Data While Maintaining Privacy},
  author = {Hripcsak, George and Mirhaji, Parsa and Low, Alexander Fh and Malin, Bradley A},
  year = {2016},
  month = nov,
  journal = {Journal of the American Medical Informatics Association},
  volume = {23},
  number = {6},
  pages = {1040--1045},
  issn = {1527-974X, 1067-5027},
  doi = {10.1093/jamia/ocw001},
  urldate = {2023-11-21},
  abstract = {Abstract             Objective Maintaining patient privacy is a challenge in large-scale observational research. To assist in reducing the risk of identifying study subjects through publicly available data, we introduce a method for obscuring date information for clinical events and patient characteristics.             Methods The method, which we call Shift and Truncate (SANT), obscures date information to any desired granularity. Shift and Truncate first assigns each patient a random shift value, such that all dates in that patient's record are shifted by that amount. Data are then truncated from the beginning and end of the data set.             Results The data set can be proven to not disclose temporal information finer than the chosen granularity. Unlike previous strategies such as a simple shift, it remains robust to frequent \textendash{} even daily \textendash{} updates and robust to inferring dates at the beginning and end of date-shifted data sets. Time-of-day may be retained or obscured, depending on the goal and anticipated knowledge of the data recipient.             Conclusions The method can be useful as a scientific approach for reducing re-identification risk under the Privacy Rule of the Health Insurance Portability and Accountability Act and may contribute to qualification for the Safe Harbor implementation.},
  langid = {english},
  file = {/Users/Adulyanukosol/Zotero/storage/C9Q9MK8P/Hripcsak et al. - 2016 - Preserving temporal relations in clinical data whi.pdf}
}

@article{kahn2016HarmonizedDataQuality,
  title = {A {{Harmonized Data Quality Assessment Terminology}} and {{Framework}} for the {{Secondary Use}} of {{Electronic Health Record Data}}},
  author = {Kahn, Michael G. and Callahan, Tiffany J. and Barnard, Juliana and Bauck, Alan E. and Brown, Jeff and Davidson, Bruce N. and Estiri, Hossein and Goerg, Carsten and Holve, Erin and Johnson, Steven G. and Liaw, Siaw-Teng and {Hamilton-Lopez}, Marianne and Meeker, Daniella and Ong, Toan C. and Ryan, Patrick and Shang, Ning and Weiskopf, Nicole G. and Weng, Chunhua and Zozus, Meredith N. and Schilling, Lisa},
  year = {2016},
  month = sep,
  journal = {eGEMs (Generating Evidence \& Methods to improve patient outcomes)},
  volume = {4},
  number = {1},
  pages = {18},
  issn = {2327-9214},
  doi = {10.13063/2327-9214.1244},
  urldate = {2023-11-22},
  abstract = {Objective:~Harmonized data quality (DQ) assessment terms, methods, and reporting             practices can establish a common understanding of the strengths and limitations of             electronic health record (EHR) data for operational analytics, quality improvement, and             research. Existing published DQ terms were harmonized to a comprehensive unified             terminology with definitions and examples and organized into a conceptual framework to             support a common approach to defining whether EHR data is `fit' for specific             uses.Materials and Methods:~DQ publications, informatics and analytics experts, managers             of established DQ programs, and operational manuals from several mature EHR-based             research networks were reviewed to identify potential DQ terms and categories. Two             face-to-face stakeholder meetings were used to vet an initial set of DQ terms and             definitions that were grouped into an overall conceptual framework. Feedback received             from data producers and users was used to construct a draft set of harmonized DQ terms             and categories. Multiple rounds of iterative refinement resulted in a set of terms and             organizing framework consisting of DQ categories, subcategories, terms, definitions, and             examples. The harmonized terminology and logical framework's inclusiveness was evaluated             against ten published DQ terminologies.Results:~Existing DQ terms were harmonized and             organized into a framework by defining three DQ categories: (1) Conformance (2)             Completeness and (3) Plausibility and two DQ assessment contexts: (1) Verification and             (2) Validation. Conformance and Plausibility categories were further divided into             subcategories. Each category and subcategory was defined with respect to whether the             data may be verified with organizational data, or validated against an accepted gold             standard, depending on proposed context and uses. The coverage of the harmonized DQ             terminology was validated by successfully aligning to multiple published DQ             terminologies.Discussion:~Existing DQ concepts, community input, and expert review             informed the development of a distinct set of terms, organized into categories and             subcategories. The resulting DQ terms successfully encompassed a wide range of disparate             DQ terminologies. Operational definitions were developed to provide guidance for             implementing DQ assessment procedures. The resulting structure is an inclusive DQ             framework for standardizing DQ assessment and reporting. While our analysis focused on             the DQ issues often found in EHR data, the new terminology may be applicable to a wide             range of electronic health data such as administrative, research, and patient-reported             data.Conclusion:~A consistent, common DQ terminology, organized into a logical             framework, is an initial step in enabling data owners and users, patients, and policy             makers to evaluate and communicate data quality findings in a well-defined manner with a             shared vocabulary. Future work will leverage the framework and terminology to develop             reusable data quality assessment and reporting methods.},
  file = {/Users/Adulyanukosol/Zotero/storage/ILB8X3Y6/Kahn et al. - 2016 - A Harmonized Data Quality Assessment Terminology a.pdf}
}

@article{kunnapuu2022TrajectoriesFrameworkDetecting,
  title = {Trajectories: A Framework for Detecting Temporal Clinical Event Sequences from Health Data Standardized to the {{Observational Medical Outcomes Partnership}} ({{OMOP}}) {{Common Data Model}}},
  shorttitle = {Trajectories},
  author = {K{\"u}nnapuu, Kadri and Ioannou, Solomon and Ligi, Kadri and Kolde, Raivo and Laur, Sven and Vilo, Jaak and Rijnbeek, Peter R and Reisberg, Sulev},
  year = {2022},
  month = jan,
  journal = {JAMIA Open},
  volume = {5},
  number = {1},
  pages = {ooac021},
  issn = {2574-2531},
  doi = {10.1093/jamiaopen/ooac021},
  urldate = {2023-11-22},
  abstract = {Abstract                            Objective               To develop a framework for identifying temporal clinical event trajectories from Observational Medical Outcomes Partnership-formatted observational healthcare data.                                         Materials and Methods               A 4-step framework based on significant temporal event pair detection is described and implemented as an open-source R package. It is used on a population-based Estonian dataset to first replicate a large Danish population-based study and second, to conduct a disease trajectory detection study for type 2 diabetes patients in the Estonian and Dutch databases as an example.                                         Results               As a proof of concept, we apply the methods in the Estonian database and provide a detailed breakdown of our findings. All Estonian population-based event pairs are shown. We compare the event pairs identified from Estonia to Danish and Dutch data and discuss the causes of the differences. The overlap in the results was only 2.4\%, which highlights the need for running similar studies in different populations.                                         Conclusions               For the first time, there is a complete software package for detecting disease trajectories in health data.},
  langid = {english},
  file = {/Users/Adulyanukosol/Zotero/storage/6AJGHH2R/Künnapuu et al. - 2022 - Trajectories a framework for detecting temporal c.pdf}
}