Home-care alerts — Technical https://thesis.uya.no/proposals/signals-that-matter/#technical-track BACHELOR Final result: Working alert interface, rule tests and a prioritised usability-fix list. Task: Build a rule-based alert list with missing-data warnings and acknowledgement. Data: 30 fictional home-care alert cases (planned) Create 30 CSV cases: 15 routine and 15 urgent, with 5 incomplete cases in each group. Store case_id, signal_type, value, unit, required_fields, present_fields, time, urgency_gold, follow_up_gold and owner_gold separately from participant data. Requires: Recruit home-care staff; obtain clinical review of cases. Method: Use the reviewed fictional CSV cases; check every rule and observe 4 staff completing follow-up tasks. Use established usability criteria. 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 30 fictional home-care alert cases. Make the answer key and pass criteria before testing. 4. Build a working version of working alert interface, rule tests and a prioritised usability-fix list. 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: Alert prototype, labelled cases and comparison report. Research question: Investigate whether explanation benefits depend on missing information. Cross explanation on/off with complete/incomplete cases in the same alert interface; distinguish successful follow-up from increased willingness to trust an alert. Research result: Evidence about when explanations help, plus design rules for incomplete alerts. 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 30 fictional home-care alert cases. 3. Draw the user workflow, data model and system architecture. List the requirements and pass criteria. 4. Build a working version of alert prototype, labelled cases and comparison report. 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 Intelligent systems in healthcare: A systematic survey of explainable user interfaces (2024, peer-reviewed): https://doi.org/10.1016/j.compbiomed.2024.108908 Synthesizes current evidence on explanation interfaces and clinical decision support. The Role of Explanations in AI-Generated Alerts: Qualitative Study of Clinical Views on Explainable AI in Predictive Tools (2026, peer-reviewed): https://doi.org/10.2196/81460 Examines how clinicians interpret explanations, accuracy and workflow fit in predictive alerts. 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 explanations reduce missed follow-ups without increasing unnecessary escalation? EXAMPLE TOOLS Python, pandas, Streamlit Equivalent tools are fine. FIRST THREE ACTIONS 1. Draft routine/urgent cases with complete/incomplete information; have a clinical reviewer check acceptable follow-ups. 2. Render the same cases in a plain list and an explained list; keep alert order identical. 3. Pilot 4 tasks with one reviewer; finalise two non-overlapping case sets before recruitment. LITERATURE SEARCH home care alert explanations decision making DATA 30 fictional home-care alert cases (planned) Create 30 CSV cases: 15 routine and 15 urgent, with 5 incomplete cases in each group. Store case_id, signal_type, value, unit, required_fields, present_fields, time, urgency_gold, follow_up_gold and owner_gold separately from participant data. HOW TO TEST IT Require 100% branch and explanation-fidelity coverage before the participant study. Eight home-care staff review 12 non-overlapping cases balanced across urgency, completeness and explanation. Report per-person missed required follow-up, unnecessary escalation, information requests, owner choice, confidence calibration and time. FINAL RESULT Alert prototype, labelled cases and comparison report. ACCESS OR PEOPLE Recruit 8 home-care staff; obtain clinical review of cases. TEMPLATES https://thesis.uya.no/starters/signals-that-matter/technical/data-plan.csv https://thesis.uya.no/starters/signals-that-matter/technical/evaluation.csv https://thesis.uya.no/starters/signals-that-matter/technical/literature-matrix.csv Use participant codes instead of names or email addresses.