Prompt Configuration

Edit the system prompt and shaky-field re-query prompts. Changes take effect on the next classification run.

shaky_cancer_status Updated: 2026-04-21 14:38

shaky_feasibility Updated: 2026-04-21 12:45

shaky_intervention_acp Updated: 2026-04-21 12:45

shaky_intervention_chemo_immuno_radio Updated: 2026-04-21 14:38

shaky_intervention_complementary Updated: 2026-04-21 14:38

shaky_intervention_complex Updated: 2026-04-21 12:45

shaky_intervention_device Updated: 2026-04-21 14:38

shaky_intervention_digital Updated: 2026-04-21 14:38

shaky_intervention_education Updated: 2026-04-21 14:38

shaky_intervention_music Updated: 2026-04-21 14:38

shaky_intervention_other Updated: 2026-04-21 12:45

shaky_intervention_palliative Updated: 2026-04-21 12:45

shaky_intervention_pharmacologic Updated: 2026-04-21 14:38

shaky_intervention_psychological Updated: 2026-04-21 14:38

shaky_intervention_screening Updated: 2026-04-21 12:45

shaky_non_cancer_spec Updated: 2026-04-21 14:38

shaky_outcome_cost Updated: 2026-04-21 14:38

shaky_outcome_dignity Updated: 2026-04-21 14:38

shaky_outcome_other Updated: 2026-04-21 14:38

shaky_outcome_qol Updated: 2026-04-21 14:38

shaky_outcome_symptom Updated: 2026-04-21 14:38

shaky_pharmacologic_sub Updated: 2026-04-21 14:38

shaky_rct_type Updated: 2026-04-21 14:38

shaky_setting_patient Updated: 2026-04-21 14:38

shaky_setting_place Updated: 2026-04-21 12:45

system_prompt Updated: 2026-04-21 12:45

You are an expert in palliative care clinical research. You classify randomized controlled trials (RCTs) based on their registry data from ClinicalTrials.gov.

Given the study information, classify it into the following fields. Use ONLY the allowed values listed below — use exact lowercase spelling as shown. You MUST provide a value for every field. Do NOT leave any field blank or omit it.

CRITICAL RULES:
- For all "yes"/"no" fields (fields 7–24): You MUST answer "yes" or "no". NEVER use "N/A" for these fields. If you are uncertain, use your best judgment and choose "yes" or "no".
- "N/A" is ONLY permitted for: rct_type (field 1), non_cancer_spec (field 3), and pharmacologic_sub (field 25).
- All string values must be returned in exactly the casing shown in the allowed values below.
- Respond ONLY with the JSON object, no additional text.

Output a JSON object with exactly these 25 fields:

1. rct_type: "Cluster RCT" | "cross-over RCT" | "parallel RCT" | "N/A"
   - "parallel RCT": Each participant is randomly assigned to ONE arm. Most common design. If Allocation says "Randomized" with no crossover/cluster mention, default to "parallel RCT".
   - "cross-over RCT": Each participant receives ALL interventions in random sequence. Look for "crossover", "cross-over", "AB/BA".
   - "Cluster RCT": Randomization at group level (hospitals, wards, sites). Look for "cluster", "stepped-wedge".
   - "N/A": ONLY if the study truly has no randomization design described.

2. cancer_status: "Cancer" | "non-cancer"
   - "Cancer": Conditions/eligibility explicitly target cancer/malignancy patients. Determine from patient population described in the summary, not solely the conditions list. HSCT/transplant studies = Cancer unless explicitly excluded.
   - "non-cancer": Non-malignant conditions, general palliative care, or mixed populations without cancer as primary criterion.

3. non_cancer_spec: "neurodegenerative" | "respiratory" | "cardiac" | "renal" | "dementia" | "early palliative care" | "cognitive impaired" | "N/A"
   - "neurodegenerative": ALS, Parkinson's, MS, motor neuron disease.
   - "respiratory": COPD, pulmonary fibrosis, chronic respiratory failure.
   - "cardiac": Heart failure, advanced cardiac disease.
   - "renal": End-stage renal disease, CKD.
   - "dementia": Alzheimer's, vascular dementia, mixed dementia as primary condition.
   - "early palliative care": Studies on integrating palliative care early, not limited to one organ system.
   - "cognitive impaired": Cognitively impaired patients WITHOUT a specific dementia diagnosis.
   - "N/A": When cancer_status is "Cancer", or non-cancer population is too general/mixed.

4. setting_patient: "inpatient" | "outpatient" | "mixed"
   - "inpatient": Patients hospitalized or admitted (hospital ward, hospice unit, nursing home residents).
   - "outpatient": Patients visit clinic or receive home care but are NOT admitted.
   - "mixed": Study explicitly includes BOTH settings.

5. setting_place: "nursing home" | "hospital" | "hospice" | "home care" | "other"
   - "hospital": General hospital, academic center, hospital-based palliative care unit.
   - "hospice": Dedicated hospice facility (NOT hospital-based palliative care).
   - "nursing home": Long-term care facility, skilled nursing facility.
   - "home care": Intervention in patient's own home.
   - "other": Community settings, outpatient clinics, telehealth-only, or mixed locations.

6. feasibility: "feasibility RCT" | "fully powered RCT" | "N/A"
   - "feasibility RCT": Study explicitly says "feasibility", "pilot", "proof-of-concept", OR primary outcomes focus on recruitment/retention/acceptability. Small sample alone does NOT qualify. Enrollment n≤30 → likely pilot; n≥60 + clinical outcomes → likely fully powered.
   - "fully powered RCT": Designed to test clinical effectiveness with sample size calculation. DEFAULT when no feasibility language is present.
   - "N/A": Observational study, not an RCT, or study design does not fit RCT categories.
   When in doubt, default to "fully powered RCT".

--- INTERVENTION FIELDS (7–19): classify based on the INTERVENTION arm, not comparator. Multiple fields can be "yes". Only code "yes" if it is an ACTIVE component of the experimental intervention being tested. The clinical setting/context does NOT count — e.g. a behavioral study in a radiation oncology setting ≠ intervention_chemo_immuno_radio. ---

7. intervention_pharmacologic: "yes" | "no"
   "yes" if intervention involves a drug/medication (opioids, antiemetics, antidepressants, anxiolytics, corticosteroids, etc.).

8. intervention_chemo_immuno_radio: "yes" | "no"
   "yes" ONLY for chemotherapy, immunotherapy (checkpoint inhibitors, CAR-T), or radiation therapy. General supportive meds do NOT count.

9. intervention_complementary: "yes" | "no"
   "yes" for CAM modalities: acupuncture, aromatherapy, massage, reflexology, yoga, meditation, Reiki, herbal remedies. Music therapy has its own field (14).

10. intervention_device: "yes" | "no"
    "yes" for medical devices, wearable sensors, monitoring equipment, neurostimulators, infusion pumps. Software-only tools (apps, websites) go under intervention_digital (18), NOT here.

11. intervention_psychological: "yes" | "no"
    "yes" for structured psychological therapy: CBT, dignity therapy, meaning-centered therapy, ACT, psychotherapy, grief counseling, MBSR. General supportive conversations do NOT qualify.

12. intervention_complex: "yes" | "no"
    "yes" ONLY for multi-component interventions combining TWO OR MORE distinct components from DIFFERENT categories (e.g., psychological + educational + pharmacologic). Single-modality interventions are "no" even with multiple sessions. Combining surgical procedures ≠ complex. Multi-module website ≠ complex. Examples: integrated palliative care programs with nurse visits + symptom protocols + education = "yes". CBT alone = "no".

13. intervention_acp: "yes" | "no"
    "yes" for Advance Care Planning: structured goals-of-care conversations, advance directives, POLST, Respecting Choices, Serious Illness Conversation Guide. Incidental ACP mention does NOT qualify.

14. intervention_music: "yes" | "no"
    "yes" for music therapy or music-based interventions (live music, music listening programs, songwriting therapy).

15. intervention_screening: "yes" | "no"
    "yes" if the INTERVENTION being tested IS a screening/assessment tool to identify palliative care needs (Surprise Question, SPICT, distress thermometer). Routine outcome measurement does NOT count.

16. intervention_palliative: "yes" | "no"
    "yes" if the intervention IS palliative care consultation/referral/service delivery (early PC consultation, embedded PC team, triggered PC referral). Also "yes" for studies with palliative care team involvement, SUPPORTIVE_CARE purpose, or "palliative" in title. Do NOT mark "yes" simply because the trial is in palliative care. A drug trial in PC patients = intervention_pharmacologic, NOT intervention_palliative.

17. intervention_education: "yes" | "no"
    "yes" for primarily educational/training programs: patient/caregiver education, HCP training, communication skills training, self-management education. Must be a PRIMARY component, not incidental.

18. intervention_digital: "yes" | "no"
    "yes" if digital technology is the PRIMARY delivery mechanism: apps, web platforms, telehealth, remote monitoring, VR, digital decision aids. Must be central to intervention, not just data collection.

19. intervention_other: "yes" | "no"
    "yes" ONLY if the intervention does NOT fit ANY category in fields 7–18. This is a residual category. If ANY of 7–18 applies, intervention_other MUST be "no". Examples: exercise/physical therapy, nutritional interventions, environmental modifications, organizational changes.

--- OUTCOME FIELDS (20–24): classify based on primary AND clearly relevant secondary outcomes. ---

20. outcome_symptom: "yes" | "no"
    "yes" for specific symptom measures: pain (NRS, VAS, BPI), nausea, dyspnea, fatigue, anxiety, depression, insomnia, delirium, symptom burden scales (ESAS, MSAS). QoL scales (EORTC, FACT) are NOT symptom measures.

21. outcome_qol: "yes" | "no"
    "yes" for quality of life instruments: EORTC QLQ-C30, FACT-G, EQ-5D, McGill QoL, SF-36, etc. Patient satisfaction alone does NOT qualify.

22. outcome_dignity: "yes" | "no"
    "yes" for dignity, meaning in life, existential distress, spiritual well-being (Patient Dignity Inventory, FACIT-Sp, Demoralization Scale).

23. outcome_cost: "yes" | "no"
    "yes" for cost-effectiveness, healthcare utilization, cost analysis, hospital readmissions, length of stay as cost proxy.

24. outcome_other: "yes" | "no"
    "yes" for outcomes NOT covered by 20–23: caregiver outcomes, communication quality, goal-concordant care, place of death, survival, AD completion, feasibility metrics. If ALL outcomes fit 20–23, then "no".

Respond ONLY with the JSON object, no additional text.

Saving...

Decision Trees

Step-by-step classification logic per field. Edit the JSON to adjust rules. Trees are embedded in the system prompt.

cancer_status v1 — 2026-04-22 13:55

{
  "allowed_values": [
    "Cancer",
    "non-cancer"
  ],
  "default": "non-cancer",
  "field": "cancer_status",
  "question": "Is this a cancer or non-cancer study?",
  "steps": [
    {
      "check_fields": [
        "conditionsModule.conditions",
        "MeSH Conditions"
      ],
      "condition": "Conditions or MeSH conditions include cancer/neoplasm/tumor/malignancy/oncology terms",
      "rationale": "Explicit cancer/neoplasm condition indicates a cancer study.",
      "result": "Cancer",
      "step": 1
    },
    {
      "check_fields": [
        "armsInterventionsModule.interventions",
        "MeSH Interventions"
      ],
      "condition": "Interventions target cancer treatment (chemo, radiation, immunotherapy for cancer)",
      "rationale": "Cancer-specific interventions indicate a cancer study even if not stated in conditions.",
      "result": "Cancer",
      "step": 2
    },
    {
      "check_fields": [
        "eligibilityModule.eligibilityCriteria"
      ],
      "condition": "Population is cancer patients (eligibility criteria mention cancer diagnosis)",
      "rationale": "Eligibility requiring cancer diagnosis confirms cancer population.",
      "result": "Cancer",
      "step": 3
    }
  ]
}

feasibility v1 — 2026-04-22 13:55

{
  "allowed_values": [
    "feasibility RCT",
    "fully powered RCT",
    "N/A"
  ],
  "default": "N/A",
  "field": "feasibility",
  "question": "Is this a feasibility/pilot RCT or fully powered RCT?",
  "steps": [
    {
      "check_fields": [
        "identificationModule.officialTitle",
        "descriptionModule"
      ],
      "condition": "Title or description contains \u0027feasibility\u0027, \u0027pilot\u0027, \u0027proof of concept\u0027",
      "rationale": "Explicitly labeled as feasibility or pilot study.",
      "result": "feasibility RCT",
      "step": 1
    },
    {
      "check_fields": [
        "designModule.enrollmentInfo.count",
        "outcomesModule.primaryOutcomes"
      ],
      "condition": "Sample size is very small (\u003c 60) and primary outcome is feasibility/acceptability",
      "rationale": "Small sample with feasibility-oriented primary outcome.",
      "result": "feasibility RCT",
      "step": 2
    },
    {
      "check_fields": [
        "designModule.enrollmentInfo.count",
        "descriptionModule"
      ],
      "condition": "Study has a proper sample size calculation, enrollment \u003e 60, powered for efficacy",
      "rationale": "Adequately powered for primary efficacy endpoint.",
      "result": "fully powered RCT",
      "step": 3
    }
  ]
}

intervention_acp v1 — 2026-04-22 13:55

intervention_chemo_immuno_radio v1 — 2026-04-22 13:55

{
  "allowed_values": [
    "yes",
    "no"
  ],
  "default": "no",
  "field": "intervention_chemo_immuno_radio",
  "question": "Does the study involve chemotherapy, immunotherapy, or radiotherapy?",
  "steps": [
    {
      "check_fields": [
        "armsInterventionsModule.interventions",
        "MeSH Interventions"
      ],
      "condition": "Interventions mention chemotherapy agents (cisplatin, doxorubicin, etc.)",
      "rationale": "Chemotherapy agent identified.",
      "result": "yes",
      "step": 1
    },
    {
      "check_fields": [
        "armsInterventionsModule.interventions",
        "MeSH Interventions"
      ],
      "condition": "Interventions mention immunotherapy (checkpoint inhibitors, CAR-T, etc.)",
      "rationale": "Immunotherapy agent identified.",
      "result": "yes",
      "step": 2
    },
    {
      "check_fields": [
        "armsInterventionsModule.interventions[].type",
        "descriptionModule"
      ],
      "condition": "Intervention type is RADIATION or description mentions radiotherapy",
      "rationale": "Radiation therapy identified.",
      "result": "yes",
      "step": 3
    }
  ]
}

intervention_complementary v1 — 2026-04-22 13:55

intervention_complex v1 — 2026-04-22 13:55

{
  "allowed_values": [
    "yes",
    "no"
  ],
  "default": "no",
  "field": "intervention_complex",
  "question": "Is this a complex intervention (multiple interacting components)?",
  "steps": [
    {
      "check_fields": [
        "armsInterventionsModule.interventions"
      ],
      "condition": "Study combines pharmacologic + non-pharmacologic interventions",
      "rationale": "Multiple interacting intervention components (drug + behavioral/other).",
      "result": "yes",
      "step": 1
    },
    {
      "check_fields": [
        "descriptionModule"
      ],
      "condition": "Description mentions multicomponent, multidisciplinary, or complex intervention",
      "rationale": "Explicitly described as complex/multicomponent intervention.",
      "result": "yes",
      "step": 2
    },
    {
      "check_fields": [
        "armsInterventionsModule.interventions[].type"
      ],
      "condition": "Multiple different intervention types are listed (e.g., DRUG + BEHAVIORAL + DEVICE)",
      "rationale": "Multiple distinct intervention types indicate complex intervention.",
      "result": "yes",
      "step": 3
    }
  ]
}

intervention_device v1 — 2026-04-22 13:55

{
  "allowed_values": [
    "yes",
    "no"
  ],
  "default": "no",
  "field": "intervention_device",
  "question": "Does the study involve a medical device intervention?",
  "steps": [
    {
      "check_fields": [
        "armsInterventionsModule.interventions[].type"
      ],
      "condition": "Intervention type is DEVICE",
      "rationale": "DEVICE intervention type.",
      "result": "yes",
      "step": 1
    },
    {
      "check_fields": [
        "oversightModule.isFdaRegulatedDevice"
      ],
      "condition": "FDA regulated device = true",
      "rationale": "Study involves an FDA-regulated device.",
      "result": "yes",
      "step": 2
    },
    {
      "check_fields": [
        "descriptionModule",
        "armsInterventionsModule.interventions[].description"
      ],
      "condition": "Description mentions medical device, implant, wearable, or specific device names",
      "rationale": "Medical device described in study.",
      "result": "yes",
      "step": 3
    }
  ]
}

intervention_digital v1 — 2026-04-22 13:55

intervention_education v1 — 2026-04-22 13:55

intervention_music v1 — 2026-04-22 13:55

intervention_other v1 — 2026-04-22 13:55

intervention_palliative v1 — 2026-04-22 13:55

{
  "allowed_values": [
    "yes",
    "no"
  ],
  "default": "no",
  "field": "intervention_palliative",
  "question": "Does the study involve a palliative care intervention?",
  "steps": [
    {
      "check_fields": [
        "armsInterventionsModule.interventions",
        "descriptionModule"
      ],
      "condition": "Interventions explicitly mention palliative care, supportive care, comfort care",
      "rationale": "Palliative/supportive care intervention identified.",
      "result": "yes",
      "step": 1
    },
    {
      "check_fields": [
        "conditionsModule.conditions",
        "MeSH Conditions"
      ],
      "condition": "Study conditions include palliative care, terminal illness, end-of-life",
      "rationale": "Palliative care condition indicates palliative intervention.",
      "result": "yes",
      "step": 2
    },
    {
      "check_fields": [
        "armsInterventionsModule.interventions",
        "descriptionModule"
      ],
      "condition": "Could the intervention exist ONLY in a palliative care context?",
      "rationale": "Intervention is specific to palliative care (not transferable to curative setting).",
      "result": "yes",
      "step": 3
    }
  ]
}

intervention_pharmacologic v1 — 2026-04-22 13:55

{
  "allowed_values": [
    "yes",
    "no"
  ],
  "default": "no",
  "field": "intervention_pharmacologic",
  "question": "Does the study involve a pharmacologic intervention?",
  "steps": [
    {
      "check_fields": [
        "armsInterventionsModule.interventions[].type"
      ],
      "condition": "Intervention type is DRUG or BIOLOGICAL",
      "rationale": "DRUG or BIOLOGICAL type indicates pharmacologic intervention.",
      "result": "yes",
      "step": 1
    },
    {
      "check_fields": [
        "MeSH Interventions"
      ],
      "condition": "MeSH interventions include drug terms or pharmacologic agents",
      "rationale": "MeSH drug terms confirm pharmacologic intervention.",
      "result": "yes",
      "step": 2
    },
    {
      "check_fields": [
        "descriptionModule",
        "armsInterventionsModule.interventions[].description"
      ],
      "condition": "Description mentions specific drug names, dosing, or pharmaceutical compounds",
      "rationale": "Explicit drug/pharmaceutical mentioned in study description.",
      "result": "yes",
      "step": 3
    }
  ]
}

intervention_psychological v1 — 2026-04-22 13:55

intervention_screening v1 — 2026-04-22 13:55

non_cancer_spec v1 — 2026-04-22 13:55

{
  "allowed_values": [
    "neurodegenerative",
    "respiratory",
    "cardiac",
    "renal",
    "dementia",
    "early palliative care",
    "cognitive impaired",
    "N/A"
  ],
  "default": "N/A",
  "field": "non_cancer_spec",
  "question": "What is the non-cancer disease specification?",
  "steps": [
    {
      "check_fields": [
        "cancer_status"
      ],
      "condition": "cancer_status == \u0027Cancer\u0027",
      "rationale": "Non-cancer spec is only relevant for non-cancer studies.",
      "result": "N/A",
      "step": 1
    },
    {
      "check_fields": [
        "conditionsModule.conditions",
        "MeSH Conditions"
      ],
      "condition": "Conditions include ALS, Parkinson, MS, or other neurodegenerative diseases",
      "rationale": "Specific neurodegenerative disease mentioned in conditions.",
      "result": "neurodegenerative",
      "step": 2
    },
    {
      "check_fields": [
        "conditionsModule.conditions",
        "MeSH Conditions"
      ],
      "condition": "Conditions include COPD, lung disease, respiratory failure",
      "rationale": "Respiratory disease is the primary condition.",
      "result": "respiratory",
      "step": 3
    },
    {
      "check_fields": [
        "conditionsModule.conditions",
        "MeSH Conditions"
      ],
      "condition": "Conditions include heart failure, cardiac disease, CHF",
      "rationale": "Cardiac disease is the primary condition.",
      "result": "cardiac",
      "step": 4
    },
    {
      "check_fields": [
        "conditionsModule.conditions",
        "MeSH Conditions"
      ],
      "condition": "Conditions include kidney/renal failure, dialysis, CKD",
      "rationale": "Renal disease is the primary condition.",
      "result": "renal",
      "step": 5
    },
    {
      "check_fields": [
        "conditionsModule.conditions",
        "MeSH Conditions"
      ],
      "condition": "Conditions include dementia, Alzheimer\u0027s",
      "rationale": "Dementia/Alzheimer\u0027s is the primary condition.",
      "result": "dementia",
      "step": 6
    },
    {
      "check_fields": [
        "descriptionModule",
        "conditionsModule.conditions"
      ],
      "condition": "Study focuses on early palliative care integration (not disease-specific)",
      "rationale": "Study targets early integration of palliative care.",
      "result": "early palliative care",
      "step": 7
    },
    {
      "check_fields": [
        "conditionsModule.conditions",
        "eligibilityModule.eligibilityCriteria"
      ],
      "condition": "Conditions mention cognitive impairment without specific dementia diagnosis",
      "rationale": "Cognitive impairment without a specific neurodegenerative diagnosis.",
      "result": "cognitive impaired",
      "step": 8
    }
  ]
}

outcome_cost v1 — 2026-04-22 13:55

outcome_dignity v1 — 2026-04-22 13:55

outcome_other v1 — 2026-04-22 13:55

outcome_qol v1 — 2026-04-22 13:55

outcome_symptom v1 — 2026-04-22 13:55

{
  "allowed_values": [
    "yes",
    "no"
  ],
  "default": "no",
  "field": "outcome_symptom",
  "question": "Does the study measure symptom outcomes?",
  "steps": [
    {
      "check_fields": [
        "outcomesModule.primaryOutcomes",
        "outcomesModule.secondaryOutcomes"
      ],
      "condition": "Outcomes measure pain (NRS, VAS, BPI), dyspnea (mMRC, Borg), nausea, fatigue, anxiety, depression",
      "rationale": "Symptom measurement instrument identified in outcomes.",
      "result": "yes",
      "step": 1
    },
    {
      "check_fields": [
        "outcomesModule.primaryOutcomes",
        "outcomesModule.secondaryOutcomes"
      ],
      "condition": "Outcomes use symptom instruments: ESAS, MSAS, BPI, PHQ-9, GAD-7, HADS, NRS, Edmonton Symptom",
      "rationale": "Validated symptom assessment instrument used.",
      "result": "yes",
      "step": 2
    },
    {
      "check_fields": [
        "outcomesModule"
      ],
      "condition": "Outcomes mention symptom burden, symptom control, symptom management",
      "rationale": "Symptom-related outcome described.",
      "result": "yes",
      "step": 3
    }
  ]
}

pharmacologic_sub v1 — 2026-04-22 13:55

{
  "allowed_values": [
    "controlled substances",
    "off label use",
    "not yet FDA/EMA approved",
    "chemotherapy",
    "immunotherapy",
    "radiation",
    "phytotherapies",
    "acupuncture",
    "music therapy",
    "other",
    "N/A"
  ],
  "default": "other",
  "field": "pharmacologic_sub",
  "question": "What subcategory of pharmacologic intervention?",
  "steps": [
    {
      "check_fields": [
        "intervention_pharmacologic"
      ],
      "condition": "intervention_pharmacologic == \u0027no\u0027",
      "rationale": "No pharmacologic intervention, so sub-classification is not applicable.",
      "result": "N/A",
      "step": 1
    },
    {
      "check_fields": [
        "armsInterventionsModule.interventions",
        "MeSH Interventions"
      ],
      "condition": "Drug is a controlled substance (opioids, benzodiazepines, psilocybin, MDMA, ketamine, cannabis)",
      "rationale": "Drug is classified as a controlled substance.",
      "result": "controlled substances",
      "step": 2
    },
    {
      "check_fields": [
        "armsInterventionsModule.interventions[].description",
        "descriptionModule"
      ],
      "condition": "Drug is used off-label (approved for different indication)",
      "rationale": "Drug being used for an indication outside its approved label.",
      "result": "off label use",
      "step": 3
    },
    {
      "check_fields": [
        "oversightModule.isFdaRegulatedDrug",
        "designModule.phases"
      ],
      "condition": "Drug is investigational / not yet approved by FDA or EMA",
      "rationale": "Investigational drug, not yet regulatory approved.",
      "result": "not yet FDA/EMA approved",
      "step": 4
    },
    {
      "check_fields": [
        "armsInterventionsModule.interventions",
        "MeSH Interventions"
      ],
      "condition": "Drug is a chemotherapy agent",
      "rationale": "Chemotherapy agent identified.",
      "result": "chemotherapy",
      "step": 5
    },
    {
      "check_fields": [
        "armsInterventionsModule.interventions",
        "MeSH Interventions"
      ],
      "condition": "Drug is an immunotherapy agent",
      "rationale": "Immunotherapy agent identified.",
      "result": "immunotherapy",
      "step": 6
    },
    {
      "check_fields": [
        "armsInterventionsModule.interventions"
      ],
      "condition": "Intervention involves herbal medicine, plant-based therapies",
      "rationale": "Plant-based/herbal therapy identified.",
      "result": "phytotherapies",
      "step": 7
    }
  ]
}

rct_type v1 — 2026-04-22 13:55

{
  "allowed_values": [
    "parallel RCT",
    "cross-over RCT",
    "Cluster RCT",
    "N/A"
  ],
  "default": "N/A",
  "field": "rct_type",
  "question": "What type of RCT is this?",
  "steps": [
    {
      "check_fields": [
        "designInfo.interventionModel"
      ],
      "condition": "interventionModel == \u0027PARALLEL\u0027",
      "rationale": "Parallel assignment means participants are randomized to one of multiple arms simultaneously.",
      "result": "parallel RCT",
      "step": 1
    },
    {
      "check_fields": [
        "designInfo.interventionModel"
      ],
      "condition": "interventionModel == \u0027CROSSOVER\u0027",
      "rationale": "Crossover design means participants receive all treatments in sequence.",
      "result": "cross-over RCT",
      "step": 2
    },
    {
      "check_fields": [
        "descriptionModule",
        "designInfo.allocation"
      ],
      "condition": "\u0027cluster\u0027 in description or allocation mentions cluster",
      "rationale": "Cluster randomization randomizes groups/sites rather than individuals.",
      "result": "Cluster RCT",
      "step": 3
    }
  ]
}

setting_patient v1 — 2026-04-22 13:55

{
  "allowed_values": [
    "inpatient",
    "outpatient",
    "mixed"
  ],
  "default": "outpatient",
  "field": "setting_patient",
  "question": "What is the patient setting?",
  "steps": [
    {
      "check_fields": [
        "eligibilityModule.eligibilityCriteria",
        "descriptionModule"
      ],
      "condition": "Eligibility or description explicitly states inpatient/hospitalized patients",
      "rationale": "Explicit inpatient/hospitalized requirement.",
      "result": "inpatient",
      "step": 1
    },
    {
      "check_fields": [
        "eligibilityModule.eligibilityCriteria",
        "descriptionModule"
      ],
      "condition": "Eligibility or description explicitly states outpatient/ambulatory",
      "rationale": "Explicit outpatient/ambulatory requirement.",
      "result": "outpatient",
      "step": 2
    },
    {
      "check_fields": [
        "eligibilityModule.eligibilityCriteria",
        "descriptionModule"
      ],
      "condition": "Study includes both inpatient and outpatient phases or both are mentioned",
      "rationale": "Study serves both inpatient and outpatient populations.",
      "result": "mixed",
      "step": 3
    }
  ]
}

setting_place v1 — 2026-04-22 13:55

{
  "allowed_values": [
    "nursing home",
    "hospital",
    "hospice",
    "home care",
    "other"
  ],
  "default": "other",
  "field": "setting_place",
  "question": "Where does the study take place?",
  "steps": [
    {
      "check_fields": [
        "contactsLocationsModule.locations",
        "descriptionModule"
      ],
      "condition": "Location/description mentions nursing home, long-term care facility, skilled nursing",
      "rationale": "Study takes place in nursing home or long-term care setting.",
      "result": "nursing home",
      "step": 1
    },
    {
      "check_fields": [
        "contactsLocationsModule.locations",
        "descriptionModule"
      ],
      "condition": "Location/description mentions hospice, hospice unit, end-of-life facility",
      "rationale": "Study takes place in hospice setting.",
      "result": "hospice",
      "step": 2
    },
    {
      "check_fields": [
        "descriptionModule",
        "eligibilityModule.eligibilityCriteria"
      ],
      "condition": "Description mentions home-based care, home visits, telehealth from home",
      "rationale": "Intervention delivered at patient\u0027s home.",
      "result": "home care",
      "step": 3
    },
    {
      "check_fields": [
        "contactsLocationsModule.locations",
        "descriptionModule"
      ],
      "condition": "Location is a hospital, medical center, or university clinic",
      "rationale": "Study takes place in hospital or medical center.",
      "result": "hospital",
      "step": 4
    }
  ]
}

Contradiction Analysis

Analyze provider disagreements to identify systematic contradiction patterns and generate improvement suggestions.