Checking AI-written health notes — Technical https://thesis.uya.no/proposals/show-your-sources/#technical-track BACHELOR Final result: Review prototype and documented usability problems. Task: Build a note-review screen with manually prepared links to the consultation. Data: 20 scripted consultations and controlled draft notes (planned) Write 20 fictional consultations (300–500 words), generate fixed-prompt Qwen2.5-7B-Instruct notes and clinically check/correct them. Allocate 5 notes each to clean, wrong-fact, omitted-action and both-error profiles. Preserve the original outputs and alteration key. Requires: Clinical review and professional reviewers required. Method: Use the fictional consultation–note pairs; check link accuracy and observe 4 reviewers finding and correcting errors. STEPS Build and test 1. Read the starting sources and choose one established implementation method. 2. Write the requirements, data fields, system diagram and test cases. 3. Prepare 20 scripted consultations and controlled draft notes. Make the answer key and pass criteria before testing. 4. Build a working version of review prototype and documented usability problems. 5. Run function, integration and failure-case tests. Record each result. 6. Run the practical evaluation and list the changes the system still needs. MASTER Final result: Note-review prototype, scripts and error-detection results. Research question: Test whether source links support verification or merely make AI notes look credible. Compare links on/off across clean, wrong-fact and omission profiles; distinguish false alarms, missed errors and verification effort. Research result: A tested account of when traceability improves note-review decisions. STEPS Design, build and test (DSR) 1. Read the newest papers and list the closest existing systems. 2. Write down the versions, fields, data split, case assignment, random seeds and correct answers for 20 scripted consultations and controlled draft notes. 3. Draw the user workflow, data model and system architecture. List the requirements and pass criteria. 4. Build a working version of note-review prototype, scripts and error-detection results. 5. Test every function, connection and failure case. Save the failed tests as well as the passed tests. 6. Compare the system with the named alternative. Then run the user task or decision task in the assignment. 7. Report the measured result, the failed cases and the design lessons another team can reuse. CURRENT PROJECT LITERATURE Accuracy and Safety of AI-Enabled Scribe Technology: Instrument Validation Study (2025, peer-reviewed): https://doi.org/10.2196/64993 Provides validated error categories and evidence of frequent errors in generated notes. Using ChatGPT-4 to Create Structured Medical Notes From Audio Recordings of Physician-Patient Encounters: Comparative Study (2024, peer-reviewed): https://doi.org/10.2196/54419 Reports omission, addition and incorrect-fact errors against consultation transcripts. IS THEORY STARTING POINTS Buçinca et al. (2021) — To Trust or to Think: https://doi.org/10.1145/3449287 Derive a competing explanation based on verification effort and overreliance. Vasconcelos et al. (2023) — Explanations Can Reduce Overreliance: https://doi.org/10.1145/3579605 Compare verification cost with trust as explanations of observed decisions. Search Scopus or Web of Science and ACM Digital Library using the topic query, then follow citations to the thesis start date. Record searches and compare methods, data, findings and limitations in literature-matrix.csv. Use that review to confirm or revise the gap and choose a current comparator. The linked papers are starting points. PILOT QUESTION Do transcript links help reviewers correct faulty notes without wrongly flagging correct statements? EXAMPLE TOOLS Qwen2.5-7B-Instruct, Python, Streamlit Equivalent tools are fine. FIRST THREE ACTIONS 1. Write 2 scripts and clinically review the facts and actions before generating notes. Confirm access to inference compute and record model, software and hardware versions. 2. Generate and save both original and edited drafts; label natural errors separately from planted errors. 3. Create two matched note sets and pilot the review instructions before recruiting clinicians. LITERATURE SEARCH clinical documentation AI note source attribution verification DATA 20 scripted consultations and controlled draft notes (planned) Write 20 fictional consultations (300–500 words), generate fixed-prompt Qwen2.5-7B-Instruct notes and clinically check/correct them. Allocate 5 notes each to clean, wrong-fact, omitted-action and both-error profiles. Preserve the original outputs and alteration key. Qwen2.5-7B-Instruct: https://huggingface.co/Qwen/Qwen2.5-7B-Instruct Transformers generation settings: https://huggingface.co/docs/transformers/main_classes/text_generation HOW TO TEST IT 8 health professionals review 10 non-overlapping notes each, with and without source links. Balance order and case difficulty. Keep fault counts hidden. Report missed faults, false alarms, correction accuracy and time; separate natural from planted errors. FINAL RESULT Note-review prototype, scripts and error-detection results. ACCESS OR PEOPLE Clinical review and 8 professional reviewers required. TEMPLATES https://thesis.uya.no/starters/show-your-sources/technical/data-plan.csv https://thesis.uya.no/starters/show-your-sources/technical/evaluation.csv https://thesis.uya.no/starters/show-your-sources/technical/literature-matrix.csv Use participant codes instead of names or email addresses.