Empirical Derivation of an Electronic Clinically Useful Problem Statement System

Abstract

Problem lists are tools to improve patient management. In the medical record, they connect diagnoses to therapy, prognosis, and psychosocial issues. Computer-based problem lists enhance paper-based approaches by enabling cost-containment and quality assurance applications, but they require clinically expressive controlled vocabularies. Because existing controlled vocabularies do not represent problem statements at a clinically useful level, we derived a new canonical problem statement vocabulary through semi-automated analysis and distillation of provider-entered problem lists collected over 6 years from 74,696 patients. We combined automated and manual methods to condense 891,770 problem statements entered by 1961 care providers at Grady Memorial Hospital in Atlanta, Georgia, to 15,534 Canonical Clinical Problem Statement System (CCPSS) terms. The nature and frequency of problem statements were characterized, interrelations among them were enumerated, and a database capturing the epidemiology of problems was created. The authors identified 23,503 problem relations (co-occurrences, sign-symptom complexes, and differential diagnoses) and 22,690 modifier words that further categorized "canonical" problems. To assess completeness, CCPSS content was compared with that of the 1997 Unified Medical Language System Metathesaurus (containing terms from 44 clinical vocabularies). Unified Medical Language System terms expressed 25% of individual CCPSS terms exactly (71% of problems by frequency), 27% partially, and 48% poorly or not at all. Clinicians judged that CCPSS terms completely captured their clinical intent for 84% of 686 randomly selected free-text problem statements. The CCPSS represents clinical concepts at a level exceeding that of previous approaches. A similar national approach could create a standardized, useful, shared resource for clinical practice.

Awareness of Osteoporosis and Compliance with Management Guidelines in Patients with Newly Diagnosed Low-Impact Fractures

“…It is conceivable that inclusion of osteoporosis in problem lists or discharge diagnoses would lead to investigation and therapeutic steps [20]. In addition, the omission of past medical histories in referral letters of patients with low-impact fractures and lack of direct reference to the possibility of osteoporosis as the cause of the fracture may imply that many physicians do not perceive osteoporosis as a metabolic condition and thus fail to associate it with other medical conditions.…”

Benchmarking Ontologies: Bigger or Better?

“…To demonstrate our approach to the comparison of biomedical ontologies, we identified concepts associated with disease phenotypes and relations in four medical ontologies: ICD9-CM [48], [54], CCPSS [55], SNOMED CT [56] and MeSH (see Table 1 and Figure 2). Comparing each medical ontology concept-by-concept (as assessed with UMLS MetaMap—see Materials and Methods), we found that despite a reasonable overlap in biomedical terms and concepts, different ontologies intersect little in their relations (see Figure 2 A and B).…”

“…CCPSS , the C anonical C linical P roblem S tatement S ystem [55], is a knowledge base that encodes clinical problems encountered by ailing humans. It is specifically designed to encode clinical knowledge regarding relations between medical conditions.…”

Health Care Transformation Through Collaboration on Open-Source Informatics Projects: Integrating a Medical Applications Platform, Research Data Repository, and Patient Summarization

“…One knowledge base utilizes probabilistic linkages in the medical record, an approach first suggested more than a decade ago [36]. This approach is able to detect correct linkage very accurately on medications used for one very specific purpose (eg, glycopyrrolate) and for non-clinical problems (eg, tube feeding, taking medication).…”