Ignite Creation Date:
2025-12-24 @ 1:29 PM
Ignite Modification Date:
2026-01-05 @ 2:58 AM
Study NCT ID:
NCT04849195
Status:
UNKNOWN
Last Update Posted:
2021-04-19
First Post:
2021-04-13
Is NOT Gene Therapy:
True
Has Adverse Events:
False
Brief Title:
Comparison of Different Feature Engineering Methods for Automated ICD Coding
Sponsor:
Organization:
Raw JSON
{'hasResults': False, 'derivedSection': {'miscInfoModule': {'versionHolder': '2025-12-24'}, 'conditionBrowseModule': {'meshes': [{'id': 'D002318', 'term': 'Cardiovascular Diseases'}]}}, 'protocolSection': {'designModule': {'studyType': 'OBSERVATIONAL', 'designInfo': {'timePerspective': 'RETROSPECTIVE', 'observationalModel': 'OTHER'}, 'enrollmentInfo': {'type': 'ESTIMATED', 'count': 6947}, 'patientRegistry': False}, 'statusModule': {'overallStatus': 'UNKNOWN', 'lastKnownStatus': 'ACTIVE_NOT_RECRUITING', 'startDateStruct': {'date': '2021-03-01', 'type': 'ACTUAL'}, 'expandedAccessInfo': {'hasExpandedAccess': False}, 'statusVerifiedDate': '2021-04', 'completionDateStruct': {'date': '2021-04', 'type': 'ESTIMATED'}, 'lastUpdateSubmitDate': '2021-04-13', 'studyFirstSubmitDate': '2021-04-13', 'studyFirstSubmitQcDate': '2021-04-13', 'lastUpdatePostDateStruct': {'date': '2021-04-19', 'type': 'ACTUAL'}, 'studyFirstPostDateStruct': {'date': '2021-04-19', 'type': 'ACTUAL'}, 'primaryCompletionDateStruct': {'date': '2021-04', 'type': 'ESTIMATED'}}, 'outcomesModule': {'primaryOutcomes': [{'measure': 'ICD-10 codes for each admission', 'timeFrame': 'At the end of enrollment', 'description': 'Each admission will be a sample in this study. The ICD-10 codes assigned by medical coders for each admission will be collected as the primary outcome.'}]}, 'oversightModule': {'isFdaRegulatedDrug': False, 'isFdaRegulatedDevice': False}, 'conditionsModule': {'conditions': ['Cardiovascular Diseases']}, 'descriptionModule': {'briefSummary': 'Using traditional machine learning classifiers, this study targets on comparing bag-of-words, word2cec and roberta on automated ICD coding related to cardiovascular diseases in Chinese corpus.', 'detailedDescription': "ICD coding is quite important as it serves as basis for a wide range of economic and academic applications. Currently, manual coding is mainly adopted, which faces several limits like being time-consuming and prone to error, and this makes automated ICD coding via machine learning a hot research topic.\n\nAs an inevitable phase during machine learning, feature engineering plays a crucially important role in leading to promising coding performance. Although have reached enlightening conclusions, existing studies lacked comparison of different feature engineering methods. Finding out what methods under what circumstances perform better can be quite helpful in promoting practical applications of automated coding.\n\nThe investigators will implement this study based on inpatient' data collected from electronic medical records from Fuwai Hospital, the world's largest medical center for cardiovascular disease. Bag-of-words, word2cec and roberta will be respectively used to extracted features from training data. Then code-wise logistic regression classifiers and support vector machine classifiers will be trained to auto-assign codes. Afterwards, performances of the models on test data will be evaluated."}, 'eligibilityModule': {'sex': 'ALL', 'stdAges': ['CHILD', 'ADULT', 'OLDER_ADULT'], 'samplingMethod': 'NON_PROBABILITY_SAMPLE', 'studyPopulation': 'Admissions in Fuwai Hospital', 'healthyVolunteers': False, 'eligibilityCriteria': 'Inclusion Criteria:\n\n* Admissions in Fuwai Hospital, from January 1, 2019, to February 28, 2019\n\nExclusion Criteria:\n\n\\-'}, 'identificationModule': {'nctId': 'NCT04849195', 'briefTitle': 'Comparison of Different Feature Engineering Methods for Automated ICD Coding', 'organization': {'class': 'OTHER_GOV', 'fullName': 'China National Center for Cardiovascular Diseases'}, 'officialTitle': 'Comparison of Different Feature Engineering Methods for Automated ICD Coding', 'orgStudyIdInfo': {'id': '2021-1425-02'}}, 'armsInterventionsModule': {'armGroups': [{'label': 'Model training and test group', 'description': 'Data set will be split into training group and test group, where training group will be used for model building, and test group for subsequent evaluation and verification.', 'interventionNames': ['Other: No intervention']}], 'interventions': [{'name': 'No intervention', 'type': 'OTHER', 'description': 'No intervention', 'armGroupLabels': ['Model training and test group']}]}, 'contactsLocationsModule': {'locations': [{'zip': '100037', 'city': 'Beijing', 'state': 'Beijing Municipality', 'country': 'China', 'facility': 'Fuwai Hospital', 'geoPoint': {'lat': 39.9075, 'lon': 116.39723}}], 'overallOfficials': [{'name': 'Wei Zhao, PhD', 'role': 'PRINCIPAL_INVESTIGATOR', 'affiliation': 'China National Center for Cardiovascular Diseases'}]}, 'ipdSharingStatementModule': {'ipdSharing': 'NO'}, 'sponsorCollaboratorsModule': {'leadSponsor': {'name': 'China National Center for Cardiovascular Diseases', 'class': 'OTHER_GOV'}, 'responsibleParty': {'type': 'SPONSOR'}}}}