A method and knowledge base for automated inference of patient problems from structured data in an electronic medical record

Abstract

We developed and validated a set of rules for inferring patient problems. These rules have a variety of applications, including clinical decision support, care improvement, augmentation of the problem list, and identification of patients for research cohorts.

Improving completeness of electronic problem lists through clinical decision support: a randomized, controlled trial

“…3e5 In previous research, we showed that problem list completeness in one network ranged from 4.7% for renal insufficiency or failure to 50.7% for hypertension, 61.9% for diabetes, to a maximum of 78.5% for breast cancer, 6 and other institutions have found similar results. 3e5 In addition, we have found in previous qualitative studies that provider attitudes toward, and use of, the problem list vary widely.…”

“…Only three conditions, myasthenia gravis, sickle cell disease, and hyperthyroidism, had similar rates between the two groups; however, even though the difference for hyperthyroidism was not statistically significant with Bonferroni correction, one could infer that there may be a trend for possible statistical significance with a larger sample size. Since our previous research validated the algorithm for the study problems, 6 it is probable Overall acceptance rate (%)* that the overall low prevalence of myasthenia gravis and sickle cell disease is responsible for the lack of any difference in notation between study arms. Our results suggest that problem inference rules such as these are a valuable tool for improving problem list completeness and thus may be beneficial for improving patient care.…”

Use of an Electronic Problem List by Primary Care Providers and Specialists

“…We considered using billing diagnoses to identify potential new clinical diagnoses; however, we previously found that billing codes have a low positive predictive value for clinical problems. 11 Second, notes are an imperfect proxy for visit volume as not all visits result in a note and notes are sometimes written for other purposes. It is possible that the relationship between note volume and visit volume might differ systematically between specialties but we believe that the size of such differences would be insufficient to explain the magnitude of differences seen in problems per note across specialties.…”

“…[6][7][8][9][10] In a previous study, we demonstrated that common problems were frequently omitted from the problem list at one large hospital network-completeness ranged from 4.7% for renal disease to a maximum of 78.5% for breast cancer. 11 In previous qualitative research, we found that provider attitudes towards appropriate use and content varies widely and problem lists are frequently perceived as inaccurate, incomplete and out-of-date. 9,10 In order to shape effective problem list policy and meet "meaningful use goals," it will be necessary to gain an improved understanding of current problem list usage patterns.…”

Health and Clinical Management:

“…This finally leads to a dispersion of information about patients' health condition across many institutions and health workers. Because making the best decisions requires to be well informed, solutions must be found to avoid this fragmentation of information in order to improve each health professional's awareness of all relevant information for his patients [1][2][3][4].…”