Document Detail

Neural network adapted to wound cell analysis in surgical patients.
MedLine Citation:
PMID:  21362082     Owner:  NLM     Status:  In-Data-Review    
Assessment of the real state of wound healing of closed surgical wounds is uncertain both clinically and from conventional laboratory tests. Therefore, a novel approach based on early analysis of exactly timed wound cells, computerized further with an artificial neural network, was developed. At the end of routine surgery performed on 481 children under 18 years of age, a specific wound drain Cellstick(™) was inserted subcutaneously between the wound edges to harvest wound cells. The Cellsticks(™) were removed from 1 to 50 hours, mainly at hour 3 or 24 postsurgery. Immediately, the cellular contents were washed out using a pump constructed for the purpose. After cytocentrifugation, the cells were stained and counted differentially. Based on their relative proportions at selected time intervals, an artificial self-organizing neural map was developed. This was further transformed to a unidirectional linear graph where each node represents one set of relative cell quantities. As early as 3 hours, but more precisely 24 hours after surgery, the location of the nodes on this graph showed individually the patients' initial speed of wound inflammatory cell response. Similarly, timed Cellstick(™) specimens from new surgical patients could be analyzed, computerized, and compared with these node values to assess their initial speed in wound inflammatory cell response. Location of the node on the graph does not express the time lapse after surgery but the speed of wound inflammatory cell response in relation to that of other patients.
Jouko Viljanto; Antti Koski
Publication Detail:
Type:  Journal Article    
Journal Detail:
Title:  Wound repair and regeneration : official publication of the Wound Healing Society [and] the European Tissue Repair Society     Volume:  19     ISSN:  1524-475X     ISO Abbreviation:  Wound Repair Regen     Publication Date:  2011 Mar 
Date Detail:
Created Date:  2011-03-02     Completed Date:  -     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  9310939     Medline TA:  Wound Repair Regen     Country:  United States    
Other Details:
Languages:  eng     Pagination:  162-7     Citation Subset:  IM    
Copyright Information:
© 2011 by the Wound Healing Society.
Departments of Pediatric Surgery and Surgery, Turku University Central Hospital, Turku, Finland, and Department of Computer Science, University of Turku, Turku, Finland.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine

Previous Document:  Vasculogenic stem cell mobilization and wound recruitment in diabetic patients: increased cell numbe...
Next Document:  Increased Lipoprotein (a) concentrations in patients with chronic venous leg ulcers: a study on pati...