Implementation of clinical algorithms in complex wound care: a pilot study on feasibility and professional acceptance

Purpose: Mobile applications that integrate clinical algorithms have the potential to standardize wound assessment and to support clinical decision-making across assessment, diagnostic support, and therapeutic planning in complex wound care. This pilot study explored the feasibility of implementing such algorithms in a mobile application and examined concordance with nurse assessments and professional acceptance. Methods: A prospective multicenter pilot cohort study was conducted between June and October 2023 in rehabilitation units, outpatient clinics, primary healthcare, homecare, and hospitals. Adults aged ≥ 18 years with pressure injuries/pressure ulcers, venous leg ulcers, arterial ulcers, or diabetic foot ulcers were eligible. Nurses recorded data using the CWS_Validation application at three time points over 4 weeks. Agreement between algorithm-generated classifications and nurse assessments was analyzed using Cohen’s kappa, Fleiss’ kappa, and Krippendorff’s alpha. Nurse adherence to therapeutic recommendations and perceptions of the alert system were also evaluated. Results: A total of 49 patients with 56 wounds (mean age = 79 years) were included. Pressure injuries/pressure ulcers were most prevalent (71.4%), particularly categories 3 (25%) and 4 (23.2%). The algorithm provided diagnoses for 46 wounds, with fair overall concordance with nurse assessments (κ = 0.41; 95% CI: 0.24–0.57). Adherence to therapeutic recommendations was high: 85.3% in complete monitoring and 90.3% in partial monitoring. Nurses rated the alert system positively (mean = 4.34, SD = 0.82) in complete monitoring sessions (n = 109). Conclusions: Clinical algorithms can be feasibly integrated into mobile applications and are well accepted by nurses across diverse care contexts. These preliminary findings highlight the potential of algorithm-driven tools to support wound assessment and decision-making, while underscoring the need for larger studies with more robust designs to confirm clinical impact.