What problem does it solve? Choosing a suitable journal for a medical AI paper requires balancing topic fit, journal tier, APC budget, and review timelines, and guessing impact factors from memory leads to unreliable recommendations. ## Core Features & Use Cases - Evidence-Based Journal Matching: Generates a candidate journal list (minimum 3 entries) where each entry includes display_name, OpenAlex-measured 2yr_mean_citedness, IF tier classification (Q1/Q1-Q2), and a specific match rationale tied to the paper's topic and methodology. - Constraint-Aware Selection: Incorporates target audience, journal tier preference, APC limits, and review-cycle constraints, explicitly annotating missing elements (e.g., unknown APC) as uncertainties. - Defensive Validation: Refuses to recommend when topic and methodology features are missing, returning a structured error with context and recovery suggestions; includes fallback inference via similar-paper retrieval for journals not covered by OpenAlex. - Use Case: Given a medical imaging AI study (WDBC breast cancer, 10x5 stratified CV, cascaded architecture) with an APC cap of $3000 and a 12-week review limit, produce a ranked shortlist such as Patterns, Radiology: Artificial Intelligence, and IEEE JBHI with measured citation metrics and rationales. ## Quick Start Recommend candidate journals for my medical imaging AI paper on breast cancer diagnosis using ensemble learning, targeting radiology clinicians with an APC under $3000.
