research-design

To design a research plan from a data dictionary and data profile report, the workflow translates data features into actionable questions and analysis strategies. It generates candidate directions, feasibility assessments, and a full research plan with narrative threads.

PICOS-style framing in biomedical study planning defines research directions using Population, Intervention, Comparison, Outcomes, and Study design. It evaluates novelty, clinical relevance, and data fit to structure candidate research questions from data profiles.

Assessing statistical feasibility for clinical research using a data dictionary evaluates sample size, variable availability, and method compatibility. It identifies potential design adjustments needed to ensure the data supports the proposed analysis strategies.

Generating narrative threads for a paper from data profiling reports is possible by seeding storytelling from data features and analysis strategies. The workflow outputs a narrative_thread.md alongside the research plan to guide the paper's structure.

Planning robust biomedical research from data features requires inputs like requirement_v1.md, data_dictionary.md, data_profile_report.md, and forensics_report.md. These files provide the foundational data context for generating actionable research plans.

Limitations of automated research design for clinical workflows include reliance on the completeness of data dictionaries and profiling reports. Incomplete variable availability or incompatible sample sizes may require manual design adjustments to achieve statistical feasibility.