EFFICACY OF ARTIFICIAL NEURAL NETWORK APPROACH FOR INPATIENT DIABETES MANAGEMENT BY INSULIN ADMINISTRATION; A RETROSPECTIVE STUDY

Q: How can I download an article?

To download an article from SID, first log in to the site, search for the article title, and click on the 'Download Article' option.

Q: How can I download an ISI article?

To download an ISI article on SID, enter the keyword or article title in the search bar, view the relevant results, click on the desired article, and select the 'Download Article' option.

Q: How can I access the SID database?

To access the SID database, visit SID.ir, create an account, and log in to access scientific resources.

Q: Is downloading articles from SID free?

Some articles on SID are available for free, while others require payment. Details are specified on the article's page.

REZAEI GHALEH N.A.; SIADAT F.; MOSHAYEDI P.; SIADAT N.

مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resources

Journal Paper

Paper Information

Journal: IRANIAN JOURNAL OF ENDOCRINOLOGY AND METABOLISM (IJEM) Year:2005 | Volume:7 | Issue:SUPPLEMENT 4 Page(s): 423-426

Download Full-Text

Persian Verion

View:

890

Download:

Cites:

Information Journal Paper

Title

EFFICACY OF ARTIFICIAL NEURAL NETWORK APPROACH FOR INPATIENT DIABETES MANAGEMENT BY INSULIN ADMINISTRATION; A RETROSPECTIVE STUDY

Author(s)

REZAEI GHALEH N.A. | SIADAT F. | MOSHAYEDI P. | SIADAT N. | Issue Writer Certificate

Keywords

ARTIFICIAL NEURAL NETWORKQ3

DIABETESQ3

INSULINQ3

Abstract

Introduction: Appropriate DIABETES management by INSULIN administration is mainly based on clinical judgment and is usually achieved through a relatively time consuming trial and error process. ARTIFICIAL NEURAL NETWORKs may offer a useful opportunity for prediction of final controlling INSULIN dosage and hence, faster achievement of good control among hospitalized and poorly controlled diabetics. Materials and Methods: To design such a system, we first prepared a list of variables probably affecting appropriate INSULIN dosage. We designed a 3 layer feedforward ARTIFICIAL NEURAL NETWORK with backpropagation as the training algorithm using MatLab 6.0. The system was trained and the convergence was achieved using 150 cases. Thereafter the capability of the neural network to predict the final controlling total INSULIN doses was tested on 50 cases. Results: In 74% of tested cases, the trained system could predict total INSULIN dose within ±5% of actual controlling dose. Conclusion: This study indicates that ARTIFICIAL NEURAL NETWORKs may assist medical experts to achieve optimal and/or acceptable blood glucose level more rapidly among hospitalized diabetic patients.

Cites

No record.

References

No record.

Cite

APA: Copy

REZAEI GHALEH, N.A., SIADAT, F., MOSHAYEDI, P., & SIADAT, N.. (2005). EFFICACY OF ARTIFICIAL NEURAL NETWORK APPROACH FOR INPATIENT DIABETES MANAGEMENT BY INSULIN ADMINISTRATION; A RETROSPECTIVE STUDY. IRANIAN JOURNAL OF ENDOCRINOLOGY AND METABOLISM (IJEM), 7(SUPPLEMENT 4), 423-426. SID. https://sid.ir/paper/27799/en

Vancouver: Copy

REZAEI GHALEH N.A., SIADAT F., MOSHAYEDI P., SIADAT N.. EFFICACY OF ARTIFICIAL NEURAL NETWORK APPROACH FOR INPATIENT DIABETES MANAGEMENT BY INSULIN ADMINISTRATION; A RETROSPECTIVE STUDY. IRANIAN JOURNAL OF ENDOCRINOLOGY AND METABOLISM (IJEM)[Internet]. 2005;7(SUPPLEMENT 4):423-426. Available from: https://sid.ir/paper/27799/en

IEEE: Copy

N.A. REZAEI GHALEH, F. SIADAT, P. MOSHAYEDI, and N. SIADAT, “EFFICACY OF ARTIFICIAL NEURAL NETWORK APPROACH FOR INPATIENT DIABETES MANAGEMENT BY INSULIN ADMINISTRATION; A RETROSPECTIVE STUDY,” IRANIAN JOURNAL OF ENDOCRINOLOGY AND METABOLISM (IJEM), vol. 7, no. SUPPLEMENT 4, pp. 423–426, 2005, [Online]. Available: https://sid.ir/paper/27799/en

Related Journal Papers