Software Validation: Sisped (Diabetic Foot System) As A Diagnostic Support

Abstract

Introduction: Diabetic foot is responsible for 40% to 60% of all non-traumatic amputations. Early and intensive ulcer identification and treatment have been shown to reduce the number of amputations by 45 to 90%. Due to the deficit of low-cost computerized programs and aiming at an improvement in the prevention of diabetic foot complications, the Diabetic Foot System-SISPED was created. Therefore, the present work aims to validate the applicability of this SISPED system. Methods: 117 clinical foot examination records performed by a team of specialists in the detection of the risk foot were evaluated and lauded. Cases were categorized as having or not a risk foot, and the latter, when diagnosed, was classified as described in the literature. These data were then entered into SISPED. The sensitivity, specificity, positive predictive value, negative predictive value and accuracy of the reports were calculated. Results: The mean age of the participants was 55.3 ± 15.5 years, female gender was predominant (71.8%), the meantime of Diabetes Mellitus (DM) diagnosis was 11.9 ± 9.6 years, and the mean glycated hemoglobin was 8.5±1.9%. Patients had type 1 risk foot in 85.5% of cases and only 12% had normal feet. Analysis of the SISPED results indicated a sensitivity of 92.8%, specificity of 99%, positive predictive value (PPV) of 92.8%, negative predictive value (NPV) of 99%, and accuracy of 98.3%. Conclusion: Comparison of the results of SISPED reports, which should be used by general practitioners, with those of a professional specialized in diabetic foot showed equivalence in diagnostic accuracy. The SISPED was valid to be implemented in the Brazil’s National Health System (SUS), in Sergipe, as a diagnostic support tool for health professionals in the assistance to people with diabetes mellitus.