Family history information in biomedical research

PURPOSE: Obtainment of family history and accurate assessment is essential for the identification of families at risk for hereditary cancer. Our study compared the extent to which the family cancer history in the physician medical record reflected that entered by patients directly into a touch-screen family history computer program. PATIENTS AND METHODS: The study cohort consisted of 362 patients seen at a comprehensive cancer center ambulatory clinic over a 1-year period who voluntarily used the computer program and were a mixture of new and return patients. The computer entry was assessed by genetics staff and then compared with the medical record for corroboration of family history information and appropriate physician risk assessment. RESULTS: Family history information from the medical record was available for comparison to the computer entry in 69%. It was most often completed on new patients only and not routinely updated. Of the 362 computer entries, 101 were assigned to a high-risk category. Evidence in the records confirmed 69 high-risk individuals. Documentation of physician risk assessment (ie, notation of significant family cancer history or hereditary risk) was found in only 14 of the high-risk charts. Only seven high-risk individuals (6.9%) had evidence of referral for genetic consultation. CONCLUSION: This study demonstrates the need to collect family history information on all new and established patients in order to perform adequate cancer risk assessment. The lack of identification of patients at highest risk seems to be directly correlated with insufficient data collection, risk assessment, and documentation by medical staff.

Download Full-text

Family history information extraction via deep joint learning

BMC Medical Informatics and Decision Making ◽

10.1186/s12911-019-0995-5 ◽

2019 ◽

Vol 19 (S10) ◽

Cited By ~ 7

Author(s):

Xue Shi ◽

Dehuan Jiang ◽

Yuanhang Huang ◽

Xiaolong Wang ◽

Qingcai Chen ◽

...

Keyword(s):

Family History ◽

Language Processing ◽

Family Members ◽

Decision Making Process ◽

Family History Information ◽

Health Records ◽

Joint Learning ◽

Clinical Text ◽

History Information ◽

Entity Identification

Abstract Background Family history (FH) information, including family members, side of family of family members (i.e., maternal or paternal), living status of family members, observations (diseases) of family members, etc., is very important in the decision-making process of disorder diagnosis and treatment. However FH information cannot be used directly by computers as it is always embedded in unstructured text in electronic health records (EHRs). In order to extract FH information form clinical text, there is a need of natural language processing (NLP). In the BioCreative/OHNLP2018 challenge, there is a task regarding FH extraction (i.e., task1), including two subtasks: (1) entity identification, identifying family members and their observations (diseases) mentioned in clinical text; (2) family history extraction, extracting side of family of family members, living status of family members, and observations of family members. For this task, we propose a system based on deep joint learning methods to extract FH information. Our system achieves the highest F1- scores of 0.8901 on subtask1 and 0.6359 on subtask2, respectively.

Download Full-text