Systematic Analysis of Free-Text Family History in Electronic Health Record

Abstract

Family history is an important component in modern clinical care especially in the era of precision medicine. Family history information in the Electronic Health Record (EHR) system is usually stored in structured format as well as in free-text format. In this study, we systematically analyzed a family history text corpus from 3 million clinical notes for the patients receiving their primary care at Mayo Clinic. Family members, medical problems, and their associations were analyzed and reported. Our findings showed a great agreement between positive/negated medical problems mentioned in the diagnosis report and the family history, as measured by observed agreement and random agreement. We also found that the family history of some medical problems existed up to 10~15 years prior to the diagnosis date of such problems. Finally two patient cases were studied to show the medical problems in the diagnosis and family history associated with the timeline.

Figure 1:

Distribution of age in the FH Cohort.

Figure 2:

Distribution of family members in the FH Corpus.

Figure 3:

Heat map of frequencies of co-occurrence of top 10 medical problems and family members.

Figure 4:

Top 5 medical problems for each family member in the FH Corpus.

Figure 5:

Number of years between the diagnosis date of a medical problem and the first date that medical problem mentioned in patient’s family history.

Figure 6:

Timeline charts of two patient cases. X-axis represents the timeline of clinical notes while y-axis the medical problems. A turquoise dot represents a medical problem in diagnosis and a blue dot indicates the first date such medical problem is diagnosed. A yellow diamond represents a medical problem in family history and a red diamond indicates the first date such medical problem occurred in family history.