Nursing Diagnosis by Computers: An Application of Neural Networks

Abstract

In a pilot-test application of the neural network, test case diagnoses made by the ART-2 neural network agreed with those made independently by nurses. The main conclusion is that the ART-2 neural network is promising as a decision-making aid. It can handle probabilistic and ill-defined data through a process of pattern recognition without programming rules. A disadvantage is that the ART-2 neural network requires “training” by the nurse using at least one example to define a diagnosis. In practice, however, this requirement does not affect its usefulness. Moreover, providing the ART-2 neural network with several training examples enables it to identify new patterns that are “close” to the textbook case but vary in one or more characteristics.

Keywords

nursing diagnosis neural network ART-2 bowel elimination computer

Get full access to this article

View all access options for this article.

References

Bulkeley

(1991, February 28). Technology, The Wall Street Journal, p. B1.

Erickson

Tomlin

Swain

(1983). Modeling and role-modeling: A theory and paradigm for nursing. Englewood Cliffs, NJ: Prentice Hall.

Goodwin

Edwards

(1975). Developing a computer program to assist the nursing process: Phase 1-From systems analysis to an expandable program. Nursing Research, 24, 299–305.

Gordon

(1980). Predictive strategies in diagnostic tests. Nursing Research, 29, 39–46.

Gordon

(1987). Nursing diagnosis process and application. New York: McGraw-Hill.

Gordon

(1989). Manual of nursing diagnoses 1988–1989. St. Louis, MO: Mosby.

Grossberg

(1988). Nonlinear neural networks: Principles, mechanisms, and architectures. Neural Networks, 1, 17–61.

Hirsch

Chang

Gilbert

(1989). A computer program to sup port patient assessment and clinical decision making in nursing education. Computers in Nursing, 7, 157–160.

Lagina

(1971) A computer program to diagnose anxiety levels. Nursing Research, 20, 484–492.

10.

Lippmann

(1987). An introduction to computing with neural nets IEEE ASSP Magazine, 4, 4–22.

11.

Lourence

(1989). Nursing diagnoses in renal transplant patients. Unpublished masters research project, Boston College School of Nursing, Boston, MA.

12.

McCain

(1965). Nursing by assessment-not by intuition. American Journal of Nursing, 65, 82–84.

13.

McLane

(ed). (1987). Classification of nursing diagnoses: Proceedings of the seventh conference (pp. 469–473). St. Louis, MOMosby.

14.

NANDA (1992). Taxonomy I Revised 1992. St. Louis, MO: Author.

15.

Orem

(1981). Nursing: Concepts of practice (2d ed.) New York: McGraw-Hill.

16.

Ozbolt

(1982). A prototype information system to aid nursing decisions. Computer Applications in Medical Care: Proceedings of the Sixth Symposium (pp. 653–657). Los Angeles: IEEF Computer Society.

17.

Ozbolt

(1987). Developing decision support systems for nursing. Computers in Nursing, 3, 105–111.

18.

Ozbolt

(1988). Knowledge-based systems for supporting clinical nursing decisions. In Ball

Hannah

Gerdin Jeler

Peterson

(eds)., Nursing informatics: Where caring and technology meet (pp. 274–285). New York: Springer-Verlag.

19.

Pinkley

(1991). Exploring NANDA's definition of nursing diagnosis: Linking diagnostic judgements with the selection of outcomes and interventions. Nursing Diagnosis, 2, 26–32.

20.

Ryan

S. A.

(1985). An expert system for nursing practice-Clinical decision support. Computers in Nursing, 3, 77–84.