Dataset Overview
Drug clinical trial data setsis provided byChangsha Langhui Information Technology Co., Ltd.The compilation of structured clinical trial data from the National Drug Review Authority (DNE) drug clinical trial registration and information dissemination platform, as well as from the Real World Study (RWE), adaptive disorders, application, core dimensions of entry, main endpoint, test state, etc., are being cleaned and standardized, supporting competitive drug research and development intelligence, intelligent analysis of clinical trials and line assessment.
| Dataset Name | Drug clinical trial data sets |
| Data Type | CDE Register Clinical Trial + BE Experiment + Real World Research RWE Data + Structured JSON |
| Core Content | Test registration number, trial phase (I/II/III/IV/BE), adaptation (ICD code), applicant/contract research organization (CRO), pilot programme number, main/minor endpoints, number of entry cases, test status (in progress/complete/termination), first entry/test completion date |
| Source Data | CED-Dictal Clinical Trial Registration and Information Dissemination Platform, China Clinical Trial Registration Centre (CHCTR), Clinical Trials.gov, book publication RWE research |
| Use Cases | Drug development competition intelligence, pipeline analysis and target tracking, intelligent search for clinical trials, synthesis of RWE evidence, assessment of drug registration strategies |
| Format Output | Structured JSON + CSV Export + API Access |
| Status | Coming Soon |
Core Data Dimensions
The data set is organized according to the ICH clinical trial guide and the CDE registration specifications, covering the entire chain from the pilot design to the results.
| Dimension Category | Field Count | Typical Fields | Value Tier |
|---|---|---|---|
| Test marking | 8 | CED registration number (CTR), ChicTR registration number, Clinical Trials.gov NCT number, test program number, common/scientific name of the test, date of registration, date of first release of data, date of latest update | Basic Identifier |
| Pilot design | 14 | Test phases (I/II/III/IV/BE/Other), test design types (parallel/cross/one arm/dialysis), randomization (Yes/No), blindness (open/single/blind), control types (placebot/positive drugs/empties), scope of testing (national/international multicentres), experimental purpose (treatment/preventive/diagnosis) | Core Dimensions |
| Medicine information | 12 | Test drug generic/code, drug type (chemical/biological products/Chinese/vaccinum), target/role mechanism, ATC code, drug registration classification (Impressed/Impressed/Impressed/Class/Classes/Venc), route of delivery, formulation, laboratory drug production unit | Core Dimensions |
| 适应症 | 8 | Adaptive Chinese/English description, According ICD-11 code, treatment area (oncology/cardiovascular/infection/ metabolism/neurological/self-immunisation, etc.), target population (adult/child/old age), disease stratification, biomarker layer (e.g. PD-L1/HER2/EGFR/ALK/BRAF, etc.), rare disease mark, paediatric drug mark | Core Dimensions |
| Applicant | 8 | Name of applicant (enterprise/scientific institution), type of applicant (domestic/transnational/CRO/academic institution), Organisation for Contract Research (CRO), partner, province/country of applicant, main researcher (PI), pilot person, ethics committee | Advanced Analysis |
| Group and End | 10 | Planned cluster numbers (domestic/international), actual entry cluster numbers, entry criteria/standard exclusion criteria key conditions, main endpoint indicators, secondary endpoint indicators, time of major endpoint evaluation, data monitoring committee (DMC) markers, intermediate analysis markers, adaptive design markers | Advanced Analysis |
| Test Status | 8 | Test status (ongoing - recruitment not yet ongoing/completed/completed/active suspension/termination), first entry date (FPI), final entry date (LPI), completion date of test, date of change of status, termination/suspension reason, results mark, NDA/BLA submission mark | Advanced Analysis |
| RWEdata | 10 | Type of study (forward looking/retroactive/registration study), data sources (electronic patient records/health-care database/patient registration/documentation), sample volume, exposure definition, endpoint indicator, Methodologies for control of mixed factors (PSM/IPTUW/multifactor regression), EFF (HR/OR/RD) and 95% CI, bias risk assessment | RWE feature |
| Metadata | 6 | Date of data entry, source system, data quality rating, completeness rating, standardized version, update of batch log | Quality Management |
AI Application Scenarios
Competition intelligence on drug research and development
Based on progress in CDE registration data and testing, training in competition intelligence AI models, implementation of tube panorama analysis, target heat tracking and dynamic monitoring of competitor development.
Clinical trial intelligent retrieval
Multi-dimensional search matching syntax, such as ADD+D+STP+According criteria, supports researchers in fast-tracking related tests and assessing the feasibility of entry.
RWE Evidence Synthesis and Evaluation
The Real World Research Training Evidence Integrated AI Model supports systematic evaluation, analytical and pharmaceutical clinical integrated evaluation, supporting registration decision-making and health-care negotiations.
Test success projection
Historical test data + drug properties + adaptation + business information training predictor models to assist in assessing the probability of success of clinical trials and optimizing R & D decisions.
Common problems
Need a customized data solution？
Changsha Langhui Information Technology Co., Ltd. The DataAssetsAPI platform is dedicated to providing AI enterprises and scientific institutions with high-quality, compliant data assets.
Data sample preview · Customized data solution · ProSupport