Abstract
Clinical pathology tests generate large volumes of data for critical care clinicians, and ”data overload”, can impede clinical decision making. Bedside arterial blood gas (ABG) analysis is compounding this problem. Expert systems (ES) have great potential to support clinicians' work, but few ES are in routine use. The complexity of knowledge acquisition (KA) leads to poor productivity in the development phase and requires specialist knowledge engineering (KE) skills. This has been termed the knowledge acquisition “bottleneck”. We have devised a novel algorithm, ripple-down rules (RDR), that essentially eliminates the KE bottleneck. The Pathology Expert Interpretative Reporting System (PEIRS), an RDR ES, interprets a broad range of pathology reports (including thyroid function tests, ABG, cardiac enzymes and a range of hormone assays) and has been in routine use for over 4 years. With over 2100 rules, PEIRS is one of the few large medical ES in routine use, and apparently the only large ES built entirely by a pathologist without specialist KE skills or support. A key finding from PEIRS was that its simple KA strategy enabled localisation of its knowledge, e.g. local protocols for interpretation and management. This localisation was essential for gaining the acceptance of the system by the pathologists.
While PEIRS successfully automated the interpretation of ABG reports, extension to bedside decision support was limited by its restriction of a single interpretative comment per report. A new algorithm, multiple-classification RDR (MC-RDR), addresses this issue. We compared conventional RDR and MC-RDR by building prototype ES for ABG interpretation. Data included pH, PCO2, PO2, calculated bicarbonate, base excess and patient's age on up to five sequential specimens. Interpretations such as “resolving respiratory acidosis, metabolic compensation” were based on local criteria, e.g. “severe hypoxaemia” if PO2 is less than 59 mmHg. After 262 cases, MC-RDR was far more compact than RDR (262 vs. 442 total rule conditions), simpler to maintain (109 vs. 184 rules; 22 vs. 129 comments) and matured earlier (84% vs. 30% accuracy for the last 50 cases). The KA task for the local expert was marginally more complex with MC-RDR, but this was more than offset by the substantial overall reduction in KA requirements.
We have shown that MC-RDR is more compact than RDR, and KA is far more efficient. Its rapid maturation supports application in routine clinical care and would suit an embedded decision support system for an ABG analyser. By enabling localisation, we believe that MC-RDR redefines the role of medical ES and that real-time MC-RDR ES will soon be helping critical care clinicians reduce data overload in their daily practice.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Leape L (1994) Error in medicine. JAMA 272: 1851 – 1857
Coiera E (1993) Informatics - the future of laboratory medicine. Oral communication. Presented at the XV International Congress of Clinical Chemistry, Uluru, Australia, 22-24 November
Barro S, Presedo J, Vila J, Ruiz R, Palacios F (1993) Patient management in CCUs: need for an intelligent interpretation of signals. Expert Systems Appl 6: 421 – 432
Coiera E (1993) Intelligent monitoring and control of dynamic physiological systems. Artif Intell Med 5: 1 – 8
Haug P, Gardner R, Tate K et al (1994) Decision support in medicine: examples from the HELP system. Comput Biomed Res 27: 396 – 418
Johnston M, Langton K, Haynes R, Mathieu A (1994) Effects of computer-based clinical decision support systems on clinician performance and patient outcome. Ann Intern Med 120: 135 – 142
Tierney W, Hui S, McDonald C (1986) Delayed feedback of physician performance versus immediate reminders to perform preventative care. Med Care 24: 659
Shapiro B (1995) Clinical and economic performance criteria for intraarterial and extraarterial blood gas monitors, with comparison with in vitro testing. Am J Clin Pathol 104: S100 - S106
Bleich H (1972) Computer-based consultation: electrolyte and acid-base disorders. Am J Med 53: 285 – 291
Patil R, Szolovits P, Schwartz W (1982) Modelling knowledge of the patient in acidbase and electrolyte disorders. In: Szolovits P (ed) Artificial intelligence in medicine. Westview, Boulder, pp 191 – 226
Coiera E (1989) Reasoning with qualitative disease histories for diagnostic patient monitoring. Ph.D. Thesis, University of New South Wales
Gaines B, Shaw M (1991) Foundations of knowledge acquisition. In: Motoda H, Mizoguchi R, Boose J, Gaines B (eds) Knowledge acquisition for knowledge-based systems. Ohmsha, Tokyo, pp 3 – 24
Compton P, Jansen R (1990) A philosophical basis for knowledge acquisition. Knowledge Acquisition 2: 241 – 257
Edwards G, Srinivasan A, Compton P, Malor R, Lazarus L (1991) A user-maintained expert system for the interpretation of chemical pathology reports. Clin Biochem Rev 12: 66
Clancey W (1995) The learning process in the epistemology of medical information. Methods Inform Med 34: 122 – 130
Kang BH, Compton P, Preston P (1995) Multiple classification ripple down rules: evaluation and possibilities. In: Gaines BR, Musen M (eds) 9th Knowledge Acquisition for Knowledge Based Systems Workshop. SRDG Publications, Banff, pp 17.1–17. 20
Kang B (1995) Validating knowledge acquisition: multiple classifications ripple down rules. Ph.D. Thesis, University of New South Wales
Leng W, Pau L (1991) Temporal reasoning in blood gas analysis. Expert Systems 8: 159 – 170
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin · Heidelberg
About this paper
Cite this paper
Edwards, G.A., Compton, P.J., Preston, P.J., Kang, B.H. (1997). Towards Clinically Useful Expert Systems in Critical Care: Locally Managed Interpretation of Arterial Blood Gas Data. In: List, W.F., Müller, M.M., McQueen, M.J. (eds) Advances in Critical Care Testing. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-60735-6_26
Download citation
DOI: https://doi.org/10.1007/978-3-642-60735-6_26
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-62590-2
Online ISBN: 978-3-642-60735-6
eBook Packages: Springer Book Archive