A separate track from our civic-data work. Different data, different venues, different review. Data research led by Kurt E. Sather, API Automations; clinical outputs led by each project's clinical lead. Resources committed by API Automations for research purposes.
What this track does
Federal health agencies publish a great deal of data that is rarely analyzed at the moment it would matter: adverse-event reports, device clearances and recalls, registered trials and their results, utilization and payment records, and the public comments that shape the guidance those agencies issue. This track takes a question a clinician actually has, builds a reproducible, dated extract of the public data that bears on it, and puts the answer where it can change something: a regulatory docket first, then the peer-reviewed literature.
Every project runs the same way. A governing technical workbook is written and versioned before any data are pulled. Inputs are named with their source, endpoint and access date. The analysis window is the newest period every input shares. A missing input withholds a figure rather than defaulting. Every table is recomputed from a dated snapshot, never appended to. Code, the coding schema, the audit sample and the derived tables are released with the work.
What we publish here, and when
This site is not a journal and does not try to be one. For each project it carries the design and the methods as soon as they exist, the regulatory comment once it is a public record, the preprint as a link to its DOI, and the dataset and code with the preprint. Results beyond what the public comment states appear here only after the journal article is published, and then as a link to the version of record. Every submission discloses the comment, the preprint and this page.
Provenance and ethics
Every input is public federal data. No individual-level record is used or produced; cohort tables carry report keys and coded fields only. An ethics determination for each project is obtained from a body qualified to make it rather than assumed. The commercial structure behind the work and any industry payments to the authors are disclosed in every output.
Two leads on every project
A clinician is clinical lead and lead author of a project's clinical outputs: the regulatory comment, clinical letters and opinion pieces, and the society abstracts they present. API Automations' data lead is lead author of the data outputs: the analysis, the preprint, the dataset and the code. Each lead is co-author on the other side's outputs and both meet ICMJE criteria on every output. The clinical lead's adjudication of coding disagreements is recorded as part of the methods, and each author's industry relationships are disclosed before submission.
Clinicians, departments and societies who want to co-author, co-sign or serve as review board of record can reach the team at medical-research@apiautomations.com.