RESUMEN
Background: Indocyanine green fluorescence angiography (ICGFA) is gaining popularity as an intraoperative tool to assess flap perfusion. However, it needs interpretation and there is concern regarding a potential for over-debridement with its use. Here we describe an artificial intelligence (AI) method that indicates the extent of flap trimming required. Methods: Operative ICGFA recordings from ten consenting patients undergoing flap reconstruction without subsequent partial/total necrosis as part of an approved prospective study (NCT04220242, Institutional Review Board Ref:1/378/2092), provided the training-testing datasets. Drawing from prior similar experience with ICGFA intestinal perfusion signal analysis, five fluorescence intensity and time-related features were analysed (MATLAB R2024a) from stabilised ICGFA imagery. Machine learning model training (with ten-fold cross-validation application) was grounded on the actual trimming by a consultant plastic surgeon (S.P.) experienced in ICGFA. MATLAB classification learner app was used to identify the most important feature and generate partial dependence plots for interpretability during training. Testing involved post-hoc application to unseen videos blinded to surgeon ICGFA interpretation. Results: Training:testing datasets comprised 7:3 ICGFA videos with 28 and 3 sampled lines respectively. Validation and testing accuracy were 99.9 % and 99.3 % respectively. Maximum fluorescence intensity identified as the most important predictive curve feature. Partial dependence plotting revealed a threshold of 22.1 grayscale units and regions with maximum intensity less then threshold being more likely to be predicted as "excise". Conclusion: The AI method proved discriminative regarding indicating whether to retain or excise peripheral flap portions. Additional prospective patients and expert references are needed to validate generalisability.
RESUMEN
BACKGROUND: The main purpose of this study was to investigate the cleanliness and microbial burden of a veterinary hospital to establish the extent of cross-contamination with faecal bacteria as an aid to reducing nosocomial infections. Enterococci and Escherichia coli were used as faecal indicator organisms as they can survive on inanimate surfaces for months and pose a threat to animal health. The study consisted of several elements: (i) a cross-sectional study to identify sites currently contaminated with faecal organisms that could be usefully included in a longitudinal study, (ii) a 3-week longitudinal study to identify sites from which faecal bacteria were repeatedly recovered, (iii) once-off monitoring of hand hygiene, (iv) a review of all hospitalised cases with confirmed E. coli or enterococcal infection during the 8-week study period to investigate possible hospital-acquired (HAI) infection and relationship with environmental contamination. Environmental surface and hand hygiene were assessed using 3M™ Clean-Trace™ ATP test, 3M™ Petrifilm™ plates and bacteriological culture of Enterococcus species and E. coli. Cross contamination was assessed using results of antimicrobial susceptibility testing. RESULTS: In the cross-sectional study, 26 of 113 (24.5%) of sites sampled exceeded the accepted microbial threshold (2.5 CFU/cm2) and Enterococcus species were isolated from 31 (27.4%) and E. coli from 9 (7.9%) of 113 samples. Organic residue and microbial levels were high in the dog kennels even after cleaning and faecal organisms were also recovered from sites such as the dispensary, a student computer and staff common room. Four of 51 (7.8%) hand samples were contaminated with faecal bacteria. Nine sites were monitored on three occasions in the longitudinal study and a total of 23 Escherichia coli and 6 Enterococcus species were recovered. Seven of the nine sites were positive for faecal organisms on more than one occasion. There was no change in cleanliness or microbial burden over 3 weeks. Twenty-one of the 73 isolates (28.8%) recovered during all parts of the study were multi-drug resistant. Enterococci and E. coli isolates with similar resistance patterns were recovered from the environment in the large and small animal hospitals and from a small number of patients during the same timeframe, suggesting possible hospital acquired infections. CONCLUSIONS: Results suggested that movement between the small and large animal hospital areas may have been responsible for cross-contamination and possible hospital-acquired infections. The data show that cross-sectional and longitudinal monitoring of faecal contamination across all hospital areas can play an important role in informing review of infection control protocols in veterinary hospital settings. Changes in practices in the hospital based on results generated are outlined.