Skills › Scientific Agent Skills › clinical-decision-support › README.md

README.md

62 lines · skills/clinical-decision-support/references/README.md at 5f2bc03

1# Clinical Decision-Support References

3Version 2.0 is the breaking safety redesign dated 2026-07-23. It replaces

4the former recommendation-oriented templates, references, and scripts with

5offline research-evaluation and governance artifacts.

Clinical Decision-Support References

Version 2.0 is the breaking safety redesign dated 2026-07-23. It replaces the former recommendation-oriented templates, references, and scripts with offline research-evaluation and governance artifacts.

Raw lines 1 to 6

7## Boundary

9These references support aggregate or synthetic research evaluation, methods documentation, evidence profiles, privacy review, and governance traceability. They do not support diagnosis, treatment recommendations, dosing, triage, alarms, bedside use, autonomous decisions, or patient-specific output.

11No reference or script establishes regulatory authorization, HIPAA compliance, clinical validity, or fitness for live use. Route care decisions to licensed professionals using validated and appropriately authorized systems.

Boundary

These references support aggregate or synthetic research evaluation, methods documentation, evidence profiles, privacy review, and governance traceability. They do not support diagnosis, treatment recommendations, dosing, triage, alarms, bedside use, autonomous decisions, or patient-specific output.

No reference or script establishes regulatory authorization, HIPAA compliance, clinical validity, or fitness for live use. Route care decisions to licensed professionals using validated and appropriately authorized systems.

Raw lines 7 to 12

13## Navigation

15| File | Purpose |

16|---|---|

17| `safety_and_scope.md` | Refusal rules, escalation, and intended-use language |

18| `regulatory_and_governance.md` | FDA CDS/AI, ONC HTI-1, and ICH context |

19| `evidence_profiles.md` | Human GRADE evidence-profile workflow |

20| `study_reporting.md` | STROBE/RECORD, TRIPOD+AI, CONSORT-AI, SPIRIT-AI, DECIDE-AI, STARD-AI, REMARK, and PROBAST+AI |

21| `cohort_evaluation.md` | Aggregate cohort reporting and disclosure-aware tables |

22| `survival_analysis.md` | Estimand-led time-to-event planning |

23| `model_biomarker_evaluation.md` | Aggregate validation, calibration, uncertainty, and subgroup review |

24| `privacy_and_disclosure.md` | HHS de-identification methods and output controls |

25| `decision_logic_traceability.md` | Research/governance logic matrices |

26| `sources.md` | Authoritative source ledger checked 2026-09-30 |

27| `security_validation.md` | Baseline remediation, scan results, and accepted LOW findings |

Navigation

File	Purpose
`safety_and_scope.md`	Refusal rules, escalation, and intended-use language
`regulatory_and_governance.md`	FDA CDS/AI, ONC HTI-1, and ICH context
`evidence_profiles.md`	Human GRADE evidence-profile workflow
`study_reporting.md`	STROBE/RECORD, TRIPOD+AI, CONSORT-AI, SPIRIT-AI, DECIDE-AI, STARD-AI, REMARK, and PROBAST+AI
`cohort_evaluation.md`	Aggregate cohort reporting and disclosure-aware tables
`survival_analysis.md`	Estimand-led time-to-event planning
`model_biomarker_evaluation.md`	Aggregate validation, calibration, uncertainty, and subgroup review
`privacy_and_disclosure.md`	HHS de-identification methods and output controls
`decision_logic_traceability.md`	Research/governance logic matrices
`sources.md`	Authoritative source ledger checked 2026-09-30
`security_validation.md`	Baseline remediation, scan results, and accepted LOW findings

Raw lines 13 to 28

29## Assets

31All assets are JSON skeletons. They contain no patient rows or real identifiers:

33- `artifact_intended_use_template.json`

34- `evidence_profile_template.json`

35- `aggregate_model_evaluation_template.json`

36- `aggregate_cohort_table_template.json`

37- `survival_analysis_plan_template.json`

38- `decision_logic_traceability_template.json`

39- `deidentification_checklist_template.json`

41Every template includes intended use, prohibited uses, limitations, data level, and human-review fields.

Assets

All assets are JSON skeletons. They contain no patient rows or real identifiers:

artifact_intended_use_template.json
evidence_profile_template.json
aggregate_model_evaluation_template.json
aggregate_cohort_table_template.json
survival_analysis_plan_template.json
decision_logic_traceability_template.json
deidentification_checklist_template.json

Every template includes intended use, prohibited uses, limitations, data level, and human-review fields.

Raw lines 29 to 42

43## Scripts

45The standard-library scripts read bounded local JSON and produce bounded local JSON, Markdown, or CSV:

47- `validate_cds_artifact.py`

48- `evidence_profile_check.py`

49- `model_biomarker_evaluation.py`

50- `cohort_table_generator.py`

51- `survival_plan_validator.py`

52- `decision_logic_traceability.py`

53- `deidentification_checklist.py`

55They do not use networks, API keys, environment variables, dynamic evaluation, serialization formats that execute code, LLMs, or image services.

Scripts

The standard-library scripts read bounded local JSON and produce bounded local JSON, Markdown, or CSV:

validate_cds_artifact.py
evidence_profile_check.py
model_biomarker_evaluation.py
cohort_table_generator.py
survival_plan_validator.py
decision_logic_traceability.py
deidentification_checklist.py

They do not use networks, API keys, environment variables, dynamic evaluation, serialization formats that execute code, LLMs, or image services.

Raw lines 43 to 56

57## Method Selection

59Use the study design and evaluation stage—not the presence of “AI” in a title—to select a framework. Reporting checklists are minimum disclosure guidance. Risk-of-bias tools require informed human judgments. GRADE certainty is outcome-specific and cannot be inferred from text.

61For an actual protocol, product, regulated submission, certified health IT module, or data release, obtain review from the relevant methodologist, privacy official, legal/regulatory counsel, governance owner, and domain experts.

Method Selection

Use the study design and evaluation stage—not the presence of “AI” in a title—to select a framework. Reporting checklists are minimum disclosure guidance. Risk-of-bias tools require informed human judgments. GRADE certainty is outcome-specific and cannot be inferred from text.

For an actual protocol, product, regulated submission, certified health IT module, or data release, obtain review from the relevant methodologist, privacy official, legal/regulatory counsel, governance owner, and domain experts.

Raw lines 57 to 62