For continued advancement of PGHD captured via mHealth for SSI surveillance, researchers and health systems should look to other disciplines and non-surgical specialties where technology and programs for mHealth and PGHD are in a more advanced state, including in tele-dermatology, burn care, and chronic wound care.
Although PGHD captured via mHealth for SSI surveillance entails design and implementation considerations that are unique to this use case, capitalizing on evidence and experience around mHealth and PGHD in other domains can advance its use in this setting. Tele-dermatology, chronic wound management, and burn care are examples of non-surgical domains where technology and programs for remote monitoring, including use of PGHD and photography, is more advanced.64 Dermatology practice has long incorporated remote monitoring of patients. The first publications on tele-dermatology began appearing in the mid-1990s65 and has grown to include store-and-forward modalities for collecting and reporting patient-generated data, including patient-generated photos.65-70 Management of chronic wounds is another domain that has advanced the incorporation of PGHD into clinical care. This work encompasses pressure, diabetic, arterial, and venous ulcer wounds, and leverages photography to monitor and treat patients remotely.71-74 Chronic wound management has shown promising advancements in development of 3D modeling of wound depth, and algorithms for assessment of wound color and other features using digital images.75-78 Other examples of domains and technologies that could inform design and development of mHealth tools and programs for SSI surveillance include the use of machine learning methods in tele-radiology and tele-pathology, and predictive analytics in electronic health records systems.
Advancing the use of PGHD captured via mHealth for SSI surveillance should look to gain insights in the following areas:
Specific mHealth technologies and capabilities developed for other clinical domains that can be applied or adapted for SSI surveillance. Remote monitoring of chronic wounds, as outlined above, is an example of a domain where particularly relevant advancements have been made through the application of machine learning computer vision methods. Wang et al and Wu et al report the development of a real-time assessment tools, which apply algorithms to wound photos to assess wound size, color, granulation, and necrosis, using these measures among others to assign a scoring mechanism to quantify would healing.76-78 Although post-operative wounds differ from chronic wounds in significant ways, it may be possible that technologies and techniques used in chronic wound monitoring may be adaptable to the context of SSI surveillance.