Prognostic factors, prediction of chronic wound healing and electrical stimulation

The aim of the study was to determine the effects of wound, patient and treatment attributes on wound healing rate and to propose a system for wound healing rate prediction. Predicting the wound healing rate from initial wound, patient and treatment data collected in our database of 300 chronic wounds was not possible. After considering weekly follow-ups, we determined that the best prognostic factors were weekly follow-ups of wound healing process, which alone were found to accurately predict the wound healing rate after minimal follow-up period of four weeks (at least five measurements of wound area). After combining them with wound, patient and treatment attributes, minimal follow-up period was reduced to two weeks (at least three measurements of wound area). After follow-up period of two weeks, we were able to predict the wound healing rate of an independent test set of chronic wounds with relative squared error 0.347, and after three weeks with relative squared error 0.181 (using regression trees with linear equations in its leaves). Results show that the type of treatment is just one of many prognostic factors. Arranged in the order of decreasing prediction capability, prognostic factors are: wound size, patient's age, elapsed time from wound appearance to the beginning of the treatment, width-to-length ratio, location and type of treatment. The data collected up to now strongly support our former findings that the biphasic and direct current stimulation contributes to faster healing of chronic wounds. Presented regression trees in combination with the mathematical model of the wound healing process dynamics represent a core of a prognostic system for the chronic wound healing rate prediction. If the wound healing rate is known, then the provided information can help to formulate appropriate treatment decisions.