Dataset Overview
Definition：All during hospitalizationis provided byChangsha Langhui Information Technology Co., Ltd.Medical data set provided. Covers 20 million full-cycle hospital and PDF texts, from admission records to discharge, containing data on patient history control and payment by the DRG/DIP, and provides complete language for full-process training in the AIT.
| Dataset Name | All clerical data sets during hospitalization |
| Total Data Volume | 20 million hospitalization papers |
| Data Type | Text / PDF |
| Coverage | Full-cycle inpatient documentation (remote) |
| Feature Value | Medical records control, DRG/DIP analysis |
| License Type | Sublicensing |
Core Data Fields
Each piece of data contains complete structured fields that cover everything from raw data to specialized diagnostics.
| Field Category | Field Count | Typical Fields |
|---|---|---|
| Admission documents | 6 | Hospital admissions, first medical history, care assessment forms, informed consent |
| Hospital records. | 10 | Daily medical records, house searches, medical consultations, surgical records, anesthesia records, nursing records |
| 5 | Inspection reports, test reports, pathological reports, video reports, electrocardiogram reports | |
| discharge documents | 6 | Discharge, certificate of diagnosis, cost list, medical advice, transfer records |
| Quality control/payment | 4 | Diagram, DRG Group, DIP score, main diagnostic selection basis |
Data Sample Showcase
The following is a de-identified structured JSON sample illustrating the typical data format.
Other Organiser
"Record id": "INP-2023-0012345",
"admission": "date": "2023-06-15", "dept": "cardiology", "chief complaint": "heart pains": "acute coronary syndrome"
"progress notes": [("date": "2023-06-16", " type": "Major inspection room", "content": "the patient's chest pain is eased..."],
"discharge": "Date": "2023-06-22", "final dx": "Acute non-ST lift myocardial infarction", "drg": "FM31Z", "dip score": 1895}
♪ I'm sorry ♪AI Application Scenarios
I'm in full AIS.
Full cycle of clerical training in hospitalization process AI to achieve smart pathology records and automatic discharge summaries.
Automatically generated medical records
Big clerical training end to end file automatically generates AI.
Medical Records Control AI
Training model for the assessment of the quality of medical records, using qualitative and control marker data.
DRG/DIP Smart Group
DRG/DIP flags the model for training health insurance payments group forecasting.
Clinical Decision Support
Full-cycle data training for clinically assisted decision-making during hospitalization.
Auto-code the home page of the case
Diagnostic-coding associated data training on the ICD Auto-Coding Model.
Frequently asked questions
Need for customised medical data programs?
Changsha Langhui Information Technology Co., Ltd. The DataAssetsAPI platform is dedicated to providing high-quality, compliant medical data assets for AI companies and scientific research institutions. Cooperate with 50 + hospitals, including Fudan 100 type hospitals.
Data Sample Preview · Customized Data Solutions · Professional Technical Support