Remote wound assessment undertaken by physicians is as effective through an artificial intelligence (AI) medical device as bedside examination, a new study published in the Journal of Wound Care concludes. In an investigation of the non-invasive, AI-powered, portable Wound Viewer device (from Omnidermal), first author Gianluca Zoppo, senior author Jacopo Secco (both Politecnico di Torino, Torino, Italy), and colleagues report that the device was able to assess wounds and provide a precise Wound Bed Protocol (WBP) wound classification without the need for manual data entry, “thereby reducing the risk of human error while preserving high-quality clinical diagnostic data”.
Elia Ricci (head of the department of Electronic Engineering and Telecommunications, Politecnico di Torino, Torino, Italy; president of Associazione Italiana Ulcere Cutanee [AIUC; the Italian Association of Wound Care], and secretary of the World Union of Wound Healing Societies, WUWHS) and Monica Pittarello (Clinica San Luca, Torino, Italy) coordinated the project.
Zoppo et al set out to test the reliability and precision of the Wound Viewer device, as well as its ability to aid health professionals in clinically evaluating wounds as efficiently remotely as at the bedside. They specifically aimed to verify the device’s ability to identify skin ulcers on a patient, acquire the image, and simultaneously provide data on it (surface extension, depth and colouring), while testing the reliability percentage and margin of error, both on individual data acquisitions and statistically relevant samples.
According to the authors’ description, the Wound Viewer uses dedicated sensors and AI algorithms to remotely collect objective and precise clinical data, including three-dimensional (3D) wound measurements, tissue composition, and wound classification through the internationally recognised WBP protocol. These data can then be shared through a secure General Data Protection Regulation (GDPR)- and Health Insurance Portability and Accountability Act (HIPAA)-compliant data transfer system.
To test the device, the investigators conducted a non-randomised, comparative clinical trial, whereby 150 patients were divided into three groups: (i) those with venous and arterial ulcers in the lower limbs; (ii) patients with diabetes and presenting with diabetic foot syndrome; and (iii) patients with pressure ulcers. Each wound was evaluated for area, depth, volume and WBP wound classification. Each patient was examined once and the results, analysed by the AI medical device, were compared against data obtained following visual evaluation by the physician and research team.
The area and depth were compared with a Kruskal–Wallis one-way analysis of variations in the obtained distribution (expected p-value>0.1 for both tests).
The WBP classification and tissue segmentation were analysed by directly comparing the classification obtained by the AI medical device against that of the testing physician.
“The results demonstrated that the AI medical device’s AI algorithm could acquire objective clinical parameters in a completely automated manner,” Zoppo and colleagues state. Wound Viewer reached 97% accuracy against the WBP classification and tissue segmentation analysis compared with that performed in person by the physician.
Moreover, data regarding the measurements of the wounds, as analysed through the Kruskal–Wallis technique, showed that the data distribution proved comparable with the other methods of measurement previously clinically validated in the literature (p=0.9).
Contextualising this work, Zoppo and colleagues write: “Until recently, hospitalisation and inpatient assistance were considered the safest and most effective means to provide wound treatment and to ensure continuous monitoring; this, however, is costly, and so there has been a move toward home care assistance. This has led to the preference for a telemedical approach involving remote monitoring—more suitable both from an economic and patient experience point of view. However, prompt intervention can prove difficult, and health professionals must be able to ensure a high standard of care. Patients treated in home care assistance facilities fall under the responsibility of numerous health professionals, making it vital that all clinical information is shared in a precise and standardised way.”
“As yet, there are few technological support tools for wound care professionals that have provided reliable morphological ulcer measurement, and none are able to provide automatic diagnostic information through a standardised wound classification scale.”
The authors believe Wound Viewer could offer such technical support. They conclude: “The trial demonstrated, with statistical evidence, that the measurements performed by the AI medical device are reliable and precise, and less invasive than some other methods. This trial is the first to test and demonstrate that the AI medical device meets the criteria for which it was designed: constituting a complete, standardised, and non-invasive method for classifying dermatological lesions and monitoring their clinical evolution over a clinician-specified time.”
They claim that this bodes well for the future of telemedicine, which is becoming increasingly common, especially in the era of the COVID-19 pandemic. “Using the device, non-physicians can acquire remote data without compromising quality or clinical standards, enabling physicians to treat and monitor remote wound data efficiently,” Zoppo et al say.
This project was funded by a proof of concept grant from Politecnico di Torino and the Start Cup grant from I3P and Regione Piemonte; the authors report no conflicts of interest.
