Feasibility of intra-operative image guidance in burn excision surgery with multispectral imaging and deep learning.

BACKGROUND: Exposing a healthy wound bed for skin grafting is an important step during burn surgery to ensure graft take and maintain good functional outcomes. Currently, the removal of non-viable tissue in the burn wound bed during excision is determined by expert clinician judgment. Using a porcine model of tangential burn excision, we investigated the effectiveness of an intraoperative multispectral imaging device combined with artificial intelligence to aid clinician judgment for the excision of non-viable tissue. METHODS: Multispectral imaging data was obtained from serial tangential excisions of thermal burn injuries and used to train a deep learning algorithm to identify the presence and location of non-viable tissue in the wound bed. Following algorithm development, we studied the ability of two surgeons to estimate wound bed viability, both unaided and aided by the imaging device. RESULTS: The deep learning algorithm was 87% accurate in identifying the viability of a burn wound bed. When paired with the surgeons, this device significantly improved their abilities to determine the viability of the wound bed by 25% (p = 0.03). Each time a surgeon changed their decision after seeing the AI model output, it was always a change from an incorrect decision to excise more tissue to a correct decision to stop excision. CONCLUSION: This study provides insight into the feasibility of image-guided burn excision, its effect on surgeon decision making, and suggests further investigation of a real-time imaging system for burn surgery could reduce over-excision of burn wounds.

Defining team membership in primary care: Qualitative analysis.

Primary healthcare is recognized as a team-based activity. Traditionally, a primary care team is considered to be a group of individuals that work together to satisfy patients' needs for primary care services. Past studies show wide variation in the scope and structure of teams across primary care organizations, indicating ambiguity in the definition of primary care teams. In addition, it remains unclear why certain healthcare professionals are included/excluded from another professional's "team". This study explored the question: "How do healthcare professionals in primary care clinics define who is on their team?" Qualitative content analysis was performed on interview data from clinicians and staff in eight primary care clinics regarding team definitions. All participants acknowledged the importance of working in a team, yet they had very different perspectives on how their teams were defined. Multiple themes emerged including borrowing the expertise of another professional, sharing of patient panel, and policy requirements. This study can inform healthcare professionals and administrators, as well as health IT designers, consultants, architects and researchers interested in primary care teams and how they function in a clinic environment.

EHR-related medication errors in two ICUs.

The objective of this study was to describe the frequency, potential harm, and nature of electronic health record (EHR)-related medication errors in intensive care units (ICUs). Using a secondary data analysis of a large database of medication safety events collected in a study on EHR technology in ICUs, we assessed the EHR relatedness of a total of 1622 potential preventable adverse drug events (ADEs) identified in a sample of 624 patients in 2 ICUs of a medical center. Thirty-four percent of the medication events were found to be EHR related. The EHR-related medication events had greater potential for more serious patient harm and occurred more frequently at the ordering stage as compared to non-EHR-related events. Examples of EHR-related events included orders with omitted information and duplicate orders. The list of EHR-related medication errors can be used by health care delivery organizations to monitor implementation and use of the technology and its impact on patient safety. Health information technology (IT) vendors can use the list to examine whether their technology can mitigate or reduce EHR-related medication errors.