{"id":1323,"identifier":"DVUA/VHVDAJ","persistentUrl":"https://doi.org/10.48788/DVUA/VHVDAJ","protocol":"doi","authority":"10.48788","publisher":"DataverseUA","publicationDate":"2026-07-20","storageIdentifier":"local://10.48788/DVUA/VHVDAJ","datasetVersion":{"id":116,"datasetId":1323,"datasetPersistentId":"doi:10.48788/DVUA/VHVDAJ","storageIdentifier":"local://10.48788/DVUA/VHVDAJ","versionNumber":1,"versionMinorNumber":0,"versionState":"RELEASED","lastUpdateTime":"2026-07-20T18:28:51Z","releaseTime":"2026-07-20T18:28:51Z","createTime":"2026-07-03T08:50:17Z","publicationDate":"2026-07-20","citationDate":"2026-07-20","license":{"name":"CC BY 4.0","uri":"http://creativecommons.org/licenses/by/4.0","iconUri":"https://licensebuttons.net/l/by/4.0/88x31.png"},"fileAccessRequest":true,"metadataBlocks":{"citation":{"displayName":"Citation Metadata","name":"citation","fields":[{"typeName":"title","multiple":false,"typeClass":"primitive","value":"Cerebrovascular Patients Data for Prognosis — collection of anonymized data about patients in the cardiology department"},{"typeName":"author","multiple":true,"typeClass":"compound","value":[{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Denkov, Ivan"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"V.M. Glushkov Institute of Cybernetics of the NAS of Ukraine"},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"0009-0007-7989-2169"}}]},{"typeName":"datasetContact","multiple":true,"typeClass":"compound","value":[{"datasetContactName":{"typeName":"datasetContactName","multiple":false,"typeClass":"primitive","value":"Denkov, Ivan"},"datasetContactAffiliation":{"typeName":"datasetContactAffiliation","multiple":false,"typeClass":"primitive","value":"V.M. Glushkov Institute of Cybernetics of the NAS of Ukraine"},"datasetContactEmail":{"typeName":"datasetContactEmail","multiple":false,"typeClass":"primitive","value":"havoc85@gmail.com"}}]},{"typeName":"dsDescription","multiple":true,"typeClass":"compound","value":[{"dsDescriptionValue":{"typeName":"dsDescriptionValue","multiple":false,"typeClass":"primitive","value":"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.\nThe 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."},"dsDescriptionDate":{"typeName":"dsDescriptionDate","multiple":false,"typeClass":"primitive","value":"2026-07-03"}}]},{"typeName":"subject","multiple":true,"typeClass":"controlledVocabulary","value":["Computer and Information Science"]},{"typeName":"keyword","multiple":true,"typeClass":"compound","value":[{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"classification problem"},"keywordVocabulary":{"typeName":"keywordVocabulary","multiple":false,"typeClass":"primitive","value":"ACM CCS"},"keywordVocabularyURI":{"typeName":"keywordVocabularyURI","multiple":false,"typeClass":"primitive","value":"https://dl.acm.org/ccs"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"naive Bayes classifier"},"keywordVocabulary":{"typeName":"keywordVocabulary","multiple":false,"typeClass":"primitive","value":"ACM CCS"},"keywordVocabularyURI":{"typeName":"keywordVocabularyURI","multiple":false,"typeClass":"primitive","value":"https://dl.acm.org/ccs"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"structural risk"},"keywordVocabulary":{"typeName":"keywordVocabulary","multiple":false,"typeClass":"primitive","value":"ACM CCS"},"keywordVocabularyURI":{"typeName":"keywordVocabularyURI","multiple":false,"typeClass":"primitive","value":"https://dl.acm.org/ccs"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"overfitting"},"keywordVocabulary":{"typeName":"keywordVocabulary","multiple":false,"typeClass":"primitive","value":"ACM CCS"},"keywordVocabularyURI":{"typeName":"keywordVocabularyURI","multiple":false,"typeClass":"primitive","value":"https://dl.acm.org/ccs"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"computational efficiency"},"keywordVocabulary":{"typeName":"keywordVocabulary","multiple":false,"typeClass":"primitive","value":"ACM CCS"},"keywordVocabularyURI":{"typeName":"keywordVocabularyURI","multiple":false,"typeClass":"primitive","value":"https://dl.acm.org/ccs"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"feature space dimensionality"},"keywordVocabulary":{"typeName":"keywordVocabulary","multiple":false,"typeClass":"primitive","value":"ACM CCS"},"keywordVocabularyURI":{"typeName":"keywordVocabularyURI","multiple":false,"typeClass":"primitive","value":"https://dl.acm.org/ccs"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"parallel computing"},"keywordVocabulary":{"typeName":"keywordVocabulary","multiple":false,"typeClass":"primitive","value":"UNESCO Thesaurus"},"keywordVocabularyURI":{"typeName":"keywordVocabularyURI","multiple":false,"typeClass":"primitive","value":"https://vocabularies.unesco.org/unesco/en/"}}]},{"typeName":"publication","multiple":true,"typeClass":"compound","value":[{"publicationCitation":{"typeName":"publicationCitation","multiple":false,"typeClass":"primitive","value":"Тульчинський В. Г., Денков І. Д. Ефективний баєсівський класифікатор для великої кількості атрибутів : препринт. 2026. Архів препринтів НАН України."},"publicationIDType":{"typeName":"publicationIDType","multiple":false,"typeClass":"controlledVocabulary","value":"doi"},"publicationIDNumber":{"typeName":"publicationIDNumber","multiple":false,"typeClass":"primitive","value":"10.71942/2m49-6745"},"publicationURL":{"typeName":"publicationURL","multiple":false,"typeClass":"primitive","value":"https://doi.org/10.71942/2m49-6745"}}]},{"typeName":"grantNumber","multiple":true,"typeClass":"compound","value":[{"grantNumberAgency":{"typeName":"grantNumberAgency","multiple":false,"typeClass":"primitive","value":"Дослідження отримало фінансування в рамках проєкту \"Розробити моделі та методи машинного навчання у прикладних задачах інформатизації\""},"grantNumberValue":{"typeName":"grantNumberValue","multiple":false,"typeClass":"primitive","value":"0125U001129"}}]},{"typeName":"depositor","multiple":false,"typeClass":"primitive","value":"Denkov, Ivan"},{"typeName":"dateOfDeposit","multiple":false,"typeClass":"primitive","value":"2026-07-03"},{"typeName":"timePeriodCovered","multiple":true,"typeClass":"compound","value":[{"timePeriodCoveredStart":{"typeName":"timePeriodCoveredStart","multiple":false,"typeClass":"primitive","value":"2013-01-02"},"timePeriodCoveredEnd":{"typeName":"timePeriodCoveredEnd","multiple":false,"typeClass":"primitive","value":"2023-03-31"}}]},{"typeName":"dateOfCollection","multiple":true,"typeClass":"compound","value":[{"dateOfCollectionStart":{"typeName":"dateOfCollectionStart","multiple":false,"typeClass":"primitive","value":"2026-01-04"},"dateOfCollectionEnd":{"typeName":"dateOfCollectionEnd","multiple":false,"typeClass":"primitive","value":"2026-01-04"}}]},{"typeName":"kindOfData","multiple":true,"typeClass":"primitive","value":["CSV file"]},{"typeName":"software","multiple":true,"typeClass":"compound","value":[{"softwareName":{"typeName":"softwareName","multiple":false,"typeClass":"primitive","value":"Python"},"softwareVersion":{"typeName":"softwareVersion","multiple":false,"typeClass":"primitive","value":"3.12.4"}},{"softwareName":{"typeName":"softwareName","multiple":false,"typeClass":"primitive","value":"Visual Studio Code"},"softwareVersion":{"typeName":"softwareVersion","multiple":false,"typeClass":"primitive","value":"1.19.1"}}]},{"typeName":"dataSources","multiple":true,"typeClass":"primitive","value":["A depersonalized fragment of the \"Aesculapius\" database, which contains the texts of medical reports with information about the anamnesis, diagnoses, and prescribed treatment."]}]}},"files":[{"label":"ReadMe.txt","restricted":false,"version":1,"datasetVersionId":116,"dataFile":{"id":1427,"persistentId":"","filename":"ReadMe.txt","contentType":"text/plain","friendlyType":"Plain Text","filesize":3687,"storageIdentifier":"local://19f76d09b47-7af9624cb274","rootDataFileId":-1,"md5":"c81150022f0e944c521536f8a4d98299","checksum":{"type":"MD5","value":"c81150022f0e944c521536f8a4d98299"},"tabularData":false,"creationDate":"2026-07-18","publicationDate":"2026-07-20","fileAccessRequest":true}},{"label":"sparse_vectors_patients.csv","restricted":false,"version":1,"datasetVersionId":116,"dataFile":{"id":1324,"persistentId":"","filename":"sparse_vectors_patients.csv","contentType":"text/comma-separated-values","friendlyType":"Comma Separated Values","filesize":27439000,"storageIdentifier":"local://19f272a4778-9010a20029bd","rootDataFileId":-1,"md5":"122e605b122207e39a06ec903d00a789","checksum":{"type":"MD5","value":"122e605b122207e39a06ec903d00a789"},"tabularData":false,"creationDate":"2026-07-03","publicationDate":"2026-07-20","fileAccessRequest":true}}],"citation":"Denkov, Ivan, 2026, \"Cerebrovascular Patients Data for Prognosis — collection of anonymized data about patients in the cardiology department\", https://doi.org/10.48788/DVUA/VHVDAJ, DataverseUA, V1"}}