Burn care management includes assessing the severity of burns accurately, especially distinguishing superficial partial-thickness burns from deep partial-thickness burns, in the context of providing definitive, downstream treatment. Moreover, the healing of the wound in the subacute care setting requires continuous tracking to avoid complications. Artificial intelligence (AI) and computer vision (CV) provide a unique opportunity to build low-cost and accessible tools to classify burn severity and track changes in wound parameters, both in the clinic by physicians and nurses and asynchronously in the remote setting by the patient themselves. Wound assessments can be achieved by AI–CV using the principles of image-guided therapy using high-quality 2D color images. Wound parameters can include wound 2D spatial dimension and the characterization of wound color changes, which demonstrates physiological changes such as the presentation of eschar/necrotic tissue, pustulence, granulation tissue, and scabbing. Here we present the development of AI–CV-based Skin Abnormality Tracking Algorithm pipeline. Additionally, we provide the results on a single localized burn tracked for a 6-week period in the clinic and an additional 2-week period of home monitoring.

Appropriate identification of burn depth and size is paramount. Despite the development of burn depth assessment aids [eg, laser Doppler imaging (LDI)], clinical assessment, which assesses partial-thickness burn depth with 67% accuracy, currently remains the most consistent standard of practice. We sought to develop an image-based artificial intelligence system that predicts burn severity and wound margins for use as a triaging tool in thermal injury management. Modified EfficientNet architecture trained by 1684 mobile-device-captured images of different burn depths was previously used to create a convoluted neural network (CNN). The CNN was modified to a novel boundary attention mapping (BAM) algorithm using elements of saliency mapping, which was used to recognize the boundaries of burns. For validation, 144 patient charts that included clinical assessment, burn location, total body surface area, and LDI assessment were retrieved for a retrospective study. The clinical images underwent CNN-BAM assessment and were directly compared with the LDI assessment. CNN using a 4-level burn severity classification achieved an accuracy of 85% (micro/macro-averaged receiver operating characteristic scores). The CNN-BAM system can successfully highlight burns from surrounding tissue with high confidence. CNN-BAM burn area segmentations attained a 91.6% accuracy, 78.2% sensitivity, and 93.4% specificity, when compared to LDI methodology. Results comparing the CNN-BAM outputs to clinical and LDI assessments have shown a high degree of correlation between the CNN-BAM burn severity predictions to those extrapolated from LDI healing potential (66% agreement). CNN-BAM algorithm gives equivalent burn-depth detection accuracy as LDI with a more economical and accessible application when embedded in a mobile device.

Purpose: An understanding of patient expectations predicts better health outcomes following breast reconstruction. No study to date has examined how patient expectations for breast reconstruction and preoperative health-related quality of life vary with time since breast cancer diagnosis. Methods: Women consulting for breast reconstruction to a single surgeon’s practice over a 13-month period were enrolled in this cross-sectional study. Patients were asked to prospectively complete the BREAST-Q expectations and preoperative reconstruction modules. A retrospective chart review was then performed on eligible patients, and patient demographics, cancer-related factors, and comorbidities were collected. BREAST-Q scores were transformed using the equivalent Rasch method. Multivariate linear regression models were constructed to assess the association between BREAST-Q scores and time since cancer diagnosis. Results: Sixty-five patients met inclusion criteria for analysis and are characterized by a mean age of 53 ± 11 (34-79) years and a mean body mass index of 28 ± 6 (19-49). Most patients were treated by mastectomy (58%) or lumpectomy (23%). At the time of retrospective chart review, 29 (43%) patients had undergone reconstruction, most of which were delayed (59%). The mean latency from cancer diagnosis to reconstruction was 685 ± 867 days (range: 28-3322 days). Latency from cancer diagnosis to reconstruction was associated with a greater expectation of pain (β = 0.5; standard error [SE] = 0.005; 95% confidence interval [CI]: 0.003-0.027; P < .05), and a slower expectation for recovery (β = −0.5; SE = 0.004; 95% CI: −0.021 to −0.001; P < .05) after breast reconstruction. Latency from cancer diagnosis to reconstruction was associated with an increase in preoperative psychosocial well-being (β = 0.578; SE 0.009; 95% CI: 0.002-0.046; P < .05). Conclusion: Delaying breast reconstruction may negatively impact patient expectations of postoperative pain and recovery. Educational interventions aimed at understanding and managing patient expectations in the preoperative period may improve health-related quality of life and patient-related outcomes following initial breast cancer surgery.

Academic communities are increasingly involved in efforts to address the overwhelming burden of disease in low-middle income countries. There is, however, little research dedicated to understanding the best approach to creating a successful and sustainable global healthcare project. Our objective was to review the shared characteristics of successful healthcare partnerships between high- and low-middle income countries. Two independent reviewers conducted a systematic review. Articles, describing collaborative, healthcare partnerships between a high- and low-middle income countries between 1910 and September 2018, were included. Twenty-six articles were included. The majority of collaborations were initiated by either the host institution or as a joint decision between institutions. The primary goal of these collaborations revolved around medical education/training and curriculum development. Two partnerships, after more than a decade of collaboration, had achieved a self-sustaining programme. Lack of funding was identified as a major barrier to sustainability. Successful global healthcare partnerships require true collaboration and equal participation of all partners. Funding should be secured prior to programme development in anticipation of a minimum 10-year project. A minimum list of guidelines has been proposed to improve the chances of both a successful and sustainable collaboration.