Heindl B, Pollwein B, Schleutermann S, Haller M, Finsterer U. Development of a knowledge-base for automatic monitoring of renal function of intensive care patients over time.
Comput Methods Programs Biomed 2000;
62:1-10. [PMID:
10699680 DOI:
10.1016/s0169-2607(99)00044-9]
[Citation(s) in RCA: 1] [Impact Index Per Article: 0.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/23/2023]
Abstract
Renal dysfunction is a major problem in the management of critically ill patients. Monitoring of renal parameters over time is a prerequisite for detection of any significant deterioration of kidney function. Thus, we developed a knowledge-base for the dynamic monitoring of renal function of critically ill patients. A database with renal parameters of 750 intensive care patients was analyzed for distribution of parameters within predefined intervals of the creatinine clearance. Additionally, a subgroup of 11 patients with (quite) normal renal function over 11 days was selected and the daily variability of renal parameters was analyzed. An interdisciplinary expert team selected a set of nine clinically relevant renal parameters and formulated, on the basis of the data analysis and the parameter set, eight definitions of renal function, which represent four levels of renal performance. These definitions were arranged into an hierarchical structure, considering only clinically relevant changes of renal function. A change from one functional state to another inside of 2 days indicates a relevant alteration of renal function. Monitoring of time courses can additionally be performed by statistical analysis of the daily variability of parameters and comparison with their 'normal' variability. Moreover, rules were established for the plausibility check of results and interpretations of single parameters and parameter sets formulated.
Collapse