Cerebrovascular Patients Data for Prognosis — collection of anonymized data about patients in the cardiology department
The dataset includes data from 9544 patients of the cardiology department, obtained from a depersonalized fragment of the Aesculap patient visit database. Each patient's data is represented as a sparse binary 1436-dimensional vector. 1 more dimension is added to each vector - the class label. T...
Gespeichert in:
| Datum: | 2026 |
|---|---|
| 1. Verfasser: | |
| Format: | Data |
| Veröffentlicht: |
DataverseUA
2026
|
| Schlagworte: | |
| Online Zugang: | https://doi.org/10.48788/DVUA/VHVDAJ |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Назва журналу: | Open Data Repository of the National Academy of Sciences of Ukraine |
Institution
Open Data Repository of the National Academy of Sciences of Ukraine| _version_ | 1871374725976948736 |
|---|---|
| author | Denkov, Ivan |
| author2 | Denkov, Ivan |
| author_facet | Denkov, Ivan Denkov, Ivan |
| author_sort | Denkov, Ivan |
| collection | DSpace |
| description | The dataset includes data from 9544 patients of the cardiology department, obtained from a depersonalized fragment of the Aesculap patient visit database. Each patient's data is represented as a sparse binary 1436-dimensional vector. 1 more dimension is added to each vector - the class label.
The dataset is intended for testing, validation and comparative analysis of algorithms that solve the classification problem. The dataset is suitable for use in educational purposes and scientific research. |
| format | Data |
| id | doi-10-48788-DVUA-VHVDAJ |
| institution | Open Data Repository of the National Academy of Sciences of Ukraine |
| publishDate | 2026 |
| publisher | DataverseUA |
| record_format | dspace |
| spelling | doi-10-48788-DVUA-VHVDAJ2026-07-21T02:00:01ZCerebrovascular Patients Data for Prognosis — collection of anonymized data about patients in the cardiology departmenthttps://doi.org/10.48788/DVUA/VHVDAJDenkov, IvanDataverseUAThe dataset includes data from 9544 patients of the cardiology department, obtained from a depersonalized fragment of the Aesculap patient visit database. Each patient's data is represented as a sparse binary 1436-dimensional vector. 1 more dimension is added to each vector - the class label. The dataset is intended for testing, validation and comparative analysis of algorithms that solve the classification problem. The dataset is suitable for use in educational purposes and scientific research.Computer and Information Scienceclassification problemnaive Bayes classifierstructural riskoverfittingcomputational efficiencyfeature space dimensionalityparallel computing2026-07-20Denkov, IvanDataA depersonalized fragment of the "Aesculapius" database, which contains the texts of medical reports with information about the anamnesis, diagnoses, and prescribed treatment. |
| spellingShingle | Computer and Information Science classification problem naive Bayes classifier structural risk overfitting computational efficiency feature space dimensionality parallel computing Denkov, Ivan Cerebrovascular Patients Data for Prognosis — collection of anonymized data about patients in the cardiology department |
| title | Cerebrovascular Patients Data for Prognosis — collection of anonymized data about patients in the cardiology department |
| title_full | Cerebrovascular Patients Data for Prognosis — collection of anonymized data about patients in the cardiology department |
| title_fullStr | Cerebrovascular Patients Data for Prognosis — collection of anonymized data about patients in the cardiology department |
| title_full_unstemmed | Cerebrovascular Patients Data for Prognosis — collection of anonymized data about patients in the cardiology department |
| title_short | Cerebrovascular Patients Data for Prognosis — collection of anonymized data about patients in the cardiology department |
| title_sort | cerebrovascular patients data for prognosis collection of anonymized data about patients in the cardiology department |
| topic | Computer and Information Science classification problem naive Bayes classifier structural risk overfitting computational efficiency feature space dimensionality parallel computing |
| url | https://doi.org/10.48788/DVUA/VHVDAJ |
| work_keys_str_mv | AT denkovivan cerebrovascularpatientsdataforprognosiscollectionofanonymizeddataaboutpatientsinthecardiologydepartment |