Analysis of Specimen Mammography with Artificial Intelligence to Predict Margin Status.

BACKGROUND: Intraoperative specimen mammography is a valuable tool in breast cancer surgery, providing immediate assessment of margins for a resected tumor. However, the accuracy of specimen mammography in detecting microscopic margin positivity is low. We sought to develop an artificial intelligence model to predict the pathologic margin status of resected breast tumors using specimen mammography. METHODS: A dataset of specimen mammography images matched with pathologic margin status was collected from our institution from 2017 to 2020. The dataset was randomly split into training, validation, and test sets. Specimen mammography models pretrained on radiologic images were developed and compared with models pretrained on nonmedical images. Model performance was assessed using sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC). RESULTS: The dataset included 821 images, and 53% had positive margins. For three out of four model architectures tested, models pretrained on radiologic images outperformed nonmedical models. The highest performing model, InceptionV3, showed sensitivity of 84%, specificity of 42%, and AUROC of 0.71. Model performance was better among patients with invasive cancers, less dense breasts, and non-white race. CONCLUSIONS: This study developed and internally validated artificial intelligence models that predict pathologic margins status for partial mastectomy from specimen mammograms. The models' accuracy compares favorably with published literature on surgeon and radiologist interpretation of specimen mammography. With further development, these models could more precisely guide the extent of resection, potentially improving cosmesis and reducing reoperations.

Analysis of patient safety event report categories at one large academic hospital.

Given the persistent safety incidents in operating rooms (ORs) nationwide (approx. 4,000 preventable harmful surgical errors per year), there is a need to better analyze and understand reported patient safety events. This study describes the results of applying the Team Strategies and Tools to Enhance Performance and Patient Safety (TeamSTEPPS) supported by the Teamwork Evaluation of Non-Technical Skills (TENTS) instrument to analyze patient safety event reports at one large academic medical center. Results suggest that suboptimal behaviors stemming from poor communication, lack of situation monitoring, and inappropriate task prioritization and execution were implicated in most reported events. Our proposed methodology offers an effective way of programmatically sorting and prioritizing patient safety improvement efforts.

Outcomes in Obese Adult Veno-Venous Extracorporeal Membrane Oxygenation: A Systematic Review.

Obesity is associated with an overall increased risk of morbidity and mortality. However, in patients with critical illness, sepsis, and acute respiratory distress syndrome, obesity may be protective, termed "the obesity paradox." This is a systematic literature review of articles published from 2000 to 2022 evaluating complications and mortality in adults with respiratory failure on veno-venous extracorporeal membrane oxygenation (VV ECMO) based on body mass index (BMI). Eighteen studies with 517 patients were included. Common complications included acute renal failure (175/377, 46.4%), venous thrombosis (175/293, 59.7%), and bleeding (28/293, 9.6%). Of the six cohort studies, two showed improved mortality among obese patients, two showed a trend toward improved mortality, and two showed no difference. Comparing all patients in the studies with BMI of less than 30 to those with BMI of greater than or equal to 30, we noted decreased mortality with obesity (92, 37.1% of BMI <30 vs. 30, 11% of BMI ≥30, p ≤ 0.0001). Obesity may be protective against mortality in adult patients undergoing VV ECMO. Morbid and super morbid obesity should not be considered a contraindication to cannulation, with patients with BMI ≥ 80 surviving to discharge. Complications may be high, however, with higher rates of continuous renal replacement therapy and thrombosis among obese patients.

The Effect of Area Social Deprivation on Health Behavior and Health Care Utilization in an Adult Trauma Population.

Social determinants of health may mediate health disparities, but these variables are not routinely measured in clinical practice. This is a retrospective, single-institution study that evaluates the effect of area deprivation on outcomes after trauma admission. Adult trauma patients 18 years and older were eligible. Patients were stratified into high-area (HSD) or low-area (LSD) social deprivation cohorts using zip code of residence. Regression modeling was used to explain the association between HSD, sociodemographic characteristics, and clinical outcomes. Patients who resided in HSD areas made up 29.5% of the study population, were more likely to be younger, male, and identify as a non-White race. Patients in the HSD cohort were also less likely to be admitted to the ICU (OR 0.84, CI 0.71-0.98) and discharged with additional services (OR 0.73, CI 0.57-0.94). We found that independently, area social deprivation affects trauma outcomes and the resources a patient is provided after discharge.

Computer Vision Analysis of Specimen Mammography to Predict Margin Status.

Intra-operative specimen mammography is a valuable tool in breast cancer surgery, providing immediate assessment of margins for a resected tumor. However, the accuracy of specimen mammography in detecting microscopic margin positivity is low. We sought to develop a deep learning-based model to predict the pathologic margin status of resected breast tumors using specimen mammography. A dataset of specimen mammography images matched with pathology reports describing margin status was collected. Models pre-trained on radiologic images were developed and compared with models pre-trained on non-medical images. Model performance was assessed using sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC). The dataset included 821 images and 53% had positive margins. For three out of four model architectures tested, models pre-trained on radiologic images outperformed domain-agnostic models. The highest performing model, InceptionV3, showed a sensitivity of 84%, a specificity of 42%, and AUROC of 0.71. These results compare favorably with the published literature on surgeon and radiologist interpretation of specimen mammography. With further development, these models could assist clinicians with identifying positive margins intra-operatively and decrease the rate of positive margins and re-operation in breast-conserving surgery.