{ "openapi": "3.0.1", "info": { "title": "Pharma Research & Clinical Trial Monitor", "description": "Pull PubMed papers and ClinicalTrials.gov studies at scale. PMIDs, DOIs, abstracts, MeSH terms, NCT IDs, phases, sponsors, enrollment, primary outcomes, results. One row per record. Pay per row.", "version": "0.1", "x-build-id": "kROvPzyZXgbUtpve5" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapemint~pubmed-clinical-trials-intelligence/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapemint-pubmed-clinical-trials-intelligence", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapemint~pubmed-clinical-trials-intelligence/runs": { "post": { "operationId": "runs-sync-scrapemint-pubmed-clinical-trials-intelligence", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapemint~pubmed-clinical-trials-intelligence/run-sync": { "post": { "operationId": "run-sync-scrapemint-pubmed-clinical-trials-intelligence", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "pubmedQueries": { "title": "PubMed search queries", "type": "array", "description": "Free text or PubMed Entrez queries. Supports MeSH and field tags: \"breast cancer\"[MeSH], pembrolizumab[Title], 2024[PDAT]. Example: [\"GLP-1 receptor agonist obesity\", \"CRISPR sickle cell\"].", "default": [], "items": { "type": "string" } }, "clinicalTrialsQueries": { "title": "ClinicalTrials.gov search queries", "type": "array", "description": "Free text queries against ClinicalTrials.gov. Matches title, conditions, interventions, and sponsor fields. Example: [\"alzheimer monoclonal antibody\", \"pediatric ADHD\"].", "default": [], "items": { "type": "string" } }, "pmids": { "title": "Direct PubMed IDs", "type": "array", "description": "PMIDs to fetch directly. Skips search, enriches each one with full abstract, authors, MeSH terms, and references. Example: [\"38523054\", \"39122189\"].", "default": [], "items": { "type": "string" } }, "nctIds": { "title": "Direct NCT IDs", "type": "array", "description": "ClinicalTrials.gov NCT numbers to fetch directly. Example: [\"NCT05123456\", \"NCT04999111\"].", "default": [], "items": { "type": "string" } }, "dateFrom": { "title": "Published or updated from", "type": "string", "description": "ISO date (YYYY-MM-DD). For PubMed: publication date lower bound. For ClinicalTrials.gov: lastUpdatePostDate lower bound. Empty means no bound.", "default": "" }, "dateTo": { "title": "Published or updated until", "type": "string", "description": "ISO date (YYYY-MM-DD). Upper bound. Empty means no bound.", "default": "" }, "publicationTypes": { "title": "PubMed publication types", "type": "array", "description": "Restrict PubMed to specific publication types. Common: Clinical Trial, Randomized Controlled Trial, Meta-Analysis, Systematic Review, Review.", "default": [], "items": { "type": "string" } }, "studyStatus": { "title": "ClinicalTrials.gov status filter", "type": "array", "description": "Restrict trials to specific recruitment statuses. Empty means all statuses.", "items": { "type": "string", "enum": [ "RECRUITING", "NOT_YET_RECRUITING", "ACTIVE_NOT_RECRUITING", "COMPLETED", "TERMINATED", "WITHDRAWN", "SUSPENDED", "ENROLLING_BY_INVITATION" ], "enumTitles": [ "Recruiting", "Not yet recruiting", "Active, not recruiting", "Completed", "Terminated", "Withdrawn", "Suspended", "Enrolling by invitation" ] }, "default": [] }, "phases": { "title": "Trial phases", "type": "array", "description": "Restrict trials to specific phases. Empty means all phases.", "items": { "type": "string", "enum": [ "EARLY_PHASE1", "PHASE1", "PHASE2", "PHASE3", "PHASE4", "NA" ], "enumTitles": [ "Early Phase 1", "Phase 1", "Phase 2", "Phase 3", "Phase 4", "Not applicable" ] }, "default": [] }, "studyTypes": { "title": "Trial study types", "type": "array", "description": "Restrict trials to specific study types. Empty means all study types.", "items": { "type": "string", "enum": [ "INTERVENTIONAL", "OBSERVATIONAL", "EXPANDED_ACCESS" ], "enumTitles": [ "Interventional", "Observational", "Expanded access" ] }, "default": [] }, "fetchAbstracts": { "title": "Include full abstracts", "type": "boolean", "description": "Include the full abstract text in each PubMed row. Adds one extra efetch call per query batch. On by default since abstracts are the most valuable field.", "default": true }, "fetchMeshTerms": { "title": "Include MeSH terms", "type": "boolean", "description": "Parse Medical Subject Heading terms from the PubMed XML record. Useful for topic clustering and indexing.", "default": true }, "fetchReferences": { "title": "Include references and cited by", "type": "boolean", "description": "For each PubMed paper, pull the reference list and citing PMIDs from NCBI ELink. Adds two extra requests per paper. Best with maxRecords <= 500.", "default": false }, "fetchTrialResults": { "title": "Include trial results when available", "type": "boolean", "description": "Include posted results (primary outcomes, adverse events) for completed trials. Only ~30% of trials post results. Adds the resultsSection field per row.", "default": true }, "maxRecords": { "title": "Max records per run", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Hard cap on total rows pushed (PubMed papers + clinical trials combined). 0 means unlimited.", "default": 200 }, "maxPerQuery": { "title": "Max records per query", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Cap per individual query before moving to the next. Stops one broad query from eating the entire budget.", "default": 100 }, "ncbiApiKey": { "title": "NCBI API key (optional)", "type": "string", "description": "Free NCBI API key from https://www.ncbi.nlm.nih.gov/account. Without a key: 3 PubMed requests per second. With a key: 10 per second. Recommended for runs over 500 records." }, "email": { "title": "Contact email (optional)", "type": "string", "description": "NCBI requests an identifying email for E-utilities calls. Used in the User-Agent. No marketing.", "default": "" }, "dedupe": { "title": "Deduplicate across runs", "type": "boolean", "description": "Skip PMIDs and NCT IDs already pushed in previous runs. Use for daily incremental scrapes. Turn off to refresh stale rows.", "default": true }, "navigationDelayMs": { "title": "Delay between requests (ms)", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Pause between API calls. NCBI rate limits at 3 per second without a key. Default of 350 ms keeps you well under the limit.", "default": 350 } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } }