Weston, Alexander D.

INTRODUCTION: A deeper understanding of the factors influencing survival in patients with pancreatic ductal adenocarcinoma (PDAC) is essential for optimizing treatment strategies. This study investigates the independent association of body composition parameters with overall survival in patients with PDAC. METHODS: This retrospective multisite cohort study included patients diagnosed with PDAC. Diagnostic computed tomography scans were retrieved, and body composition was evaluated using a validated deep learning-based segmentation algorithm that measured tissue volume and density in a 20 cm vertical abdominal section. RESULTS: A total of 1,666 patients with PDAC were included, 938 male (56.3%) and median age 69 years (interquartile range 61–76). In the subgroup of patients who underwent surgical resection (n = 509), myosteatosis (intramuscular infiltration of adipose tissue; hazard ratio [HR] 1.56, 95% confidence interval [CI] 1.16–2.11, P = 0.004), sarcopenic obesity (HR 1.75, 95% CI 1.06–2.91, P = 0.03), and less subcutaneous adipose tissue (HR 1.09, 95% CI 1.03–1.16, P = 0.002) were associated with higher mortality. In patients receiving palliative systemic therapy (n = 439), lower skeletal muscle density (HR 1.43, 95% CI 1.03–1.99, P = 0.03) was associated with higher mortality. In patients who did not undergo tumor-targeted treatment (n = 718), less visceral adipose tissue (HR 1.04, 95% CI 1.01–1.08, P = 0.02) was associated with higher mortality. DISCUSSION: Body composition parameters, derived from computed tomography scans at the time of PDAC diagnosis, particularly low skeletal muscle density, sarcopenic obesity, and low adipose tissue, are independently associated with overall survival in patients with PDAC. Evaluating body composition at diagnosis could enhance clinical decision-making and enable more personalized treatment strategies.

Abstract: Background: Allergic contact dermatitis is a common, pruritic, debilitating skin disease, affecting at least 20% of the population. Objective: To prospectively validate a computer vision algorithm across all Fitzpatrick skin types. Methods: Each participant was exposed to 10 allergens. The reference criterion was obtained 5 days after initial patch placement by a board-certified dermatologist. The algorithm processed photographs of the test site obtained on Day 5. Human performance in reading the photographs was also evaluated. Results: A total of 206 evaluable participants [mean age 39 years, 66% (136/206) female, and 47% with Fitzpatrick skin types IV–VI] completed testing. Forty-two percent (87/206) of participants experienced 1 or more allergic reaction resulting in a total of 132 allergic reactions. The model provided high discrimination (AUROC 0.86, 95% CI: 0.82–0.90) and specificity (93%, 95% CI: 92%–94%) but with lower sensitivity (58%, 95% CI: 49%–67%). Human performance interpreting the photographs ranged from providing similar performance to the algorithm to providing superior performance when combined across readers. There were no serious adverse events. Conclusions: The combination of a smartphone capture of patch testing sites with deep learning yielded high discrimination across a diverse sample.

Background We developed a simplified ABC/2‐derived method to estimate total subarachnoid hemorrhage volume (SAHV) on noncontrast computed tomography in patients with aneurysmal SAH and compared the clinical and radiographic outcomes. Methods and Results In this retrospective observational cohort study, we analyzed 277 patients with SAH admitted to our Comprehensive Stroke Center between 2012 and 2022. We derived a mathematical model (model 1) by measuring SAH basal cisternal blood volume using an ABC/2‐derived ellipsoid formula (A=width/thickness, B=length, C=vertical extension) on head noncontrast computed tomography in 5 major SAH cisternal compartments. We compared model 1 against a manual segmentation method (model 2) on noncontrast computed tomography. Data were analyzed using logistic regression analysis, t test, receiver operator characteristic curves, and area under the curve analysis. There was no significant difference in cisternal SAHV analysis between the 2 models ( P =0.14). Mean SAHV by the simplified method was 7.0 mL (95% CI, 5.89–8.09) for good outcome and 16.6 mL (95% CI, 13.49–19.77) for poor outcome. Patients with delayed cerebral ischemia had higher SAHV, with a cutoff value of 10 mL. Conclusions Our simplified ABC/2‐derived method to estimate SAHV is comparable to manual segmentation and can be performed in low‐resource settings. Higher total SAHV was associated with worse outcomes and higher risk of delayed cerebral ischemia. A potential dose–response relationship was observed, with SAHV >10 mL predicting worse outcomes and higher risk of DCI.

Background National guidelines recommend that waist circumference (WC) be measured in patients with a body mass index (BMI) 27–35 kg/m2. Unfortunately, perhaps due to logistical reasons, WC is seldom measured in clinical settings. Herein, we describe the performance of a self-operated waist measurement device (SOWMD) as a potential means to overcome barriers to measuring WC. Materials and methods Ten volunteers underwent WC measures by professionals and SOWMD on 5 separate days to assess the reproducibility and accuracy. We then compared SOWMD measures with CT-derived fat content by recruiting 81 patients scheduled for a diagnostic abdominal CT scan. Results There was no difference between professionally measured and SOWMD-measured WC; the intraindividual coefficient of variation over the 5 days was between 0.4% and 2.2%. The WC measured manually, by SOWMD and CT scan were highly correlated (r=0.90–0.92, all p<0.001). The minimal WC measured by SOWMD was a better predictor (r=0.81 for all patients, r=0.87 for men, both p<0.001) of CT-measured visceral adipose tissue volume than other approaches. The minimal WC measured by SOWMD was correlated with fasting plasma glucose (r=0.40, p<0.05), triglyceride (r=0.41, p<0.01) and high-density cholesterol (r=−0.49, p<0.001) concentrations. Conclusion SOWMD is a reproducible, accurate and convenient way to measure WC that can provide added value for health care providers when combined with BMI information.

Abstract Background Body composition can be accurately quantified from abdominal computed tomography (CT) exams and is a predictor for the development of aging-related conditions and for mortality. However, reference ranges for CT-derived body composition measures of obesity, sarcopenia, and bone loss have yet to be defined in the general population. Methods We identified a population-representative sample of 4 900 persons aged 20 to 89 years who underwent an abdominal CT exam from 2010 to 2020. The sample was constructed using propensity score matching an age and sex stratified sample of persons residing in the 27-county region of Southern Minnesota and Western Wisconsin. The matching included race, ethnicity, education level, region of residence, and the presence of 20 chronic conditions. We used a validated deep learning based algorithm to calculate subcutaneous adipose tissue area, visceral adipose tissue area, skeletal muscle area, skeletal muscle density, vertebral bone area, and vertebral bone density from a CT abdominal section. Results We report CT-based body composition reference ranges on 4 649 persons representative of our geographic region. Older age was associated with a decrease in skeletal muscle area and density, and an increase in visceral adiposity. All chronic conditions were associated with a statistically significant difference in at least one body composition biomarker. The presence of a chronic condition was generally associated with greater subcutaneous and visceral adiposity, and lower muscle density and vertebrae bone density. Conclusions We report reference ranges for CT-based body composition biomarkers in a population-representative cohort of 4 649 persons by age, sex, body mass index, and chronic conditions.

Abstract Aims The current guidelines recommend aortic valve intervention in patients with severe aortic regurgitation (AR) with the onset of symptoms, left ventricular enlargement, or systolic dysfunction. Recent studies have suggested that we might be missing the window of early intervention in a significant number of patients by following the guidelines. Methods and results The overarching goal was to determine if machine learning (ML)-based algorithms could be trained to identify patients at risk for death from AR independent of aortic valve replacement (AVR). Models were trained with five-fold cross-validation on a dataset of 1035 patients, and performance was reported on an independent dataset of 207 patients. Optimal predictive performance was observed with a conditional random survival forest model. A subset of 19/41 variables was selected for inclusion in the final model. Variable selection was performed with 10-fold cross-validation using random survival forest model. The top variables included were age, body surface area, body mass index, diastolic blood pressure, New York Heart Association class, AVR, comorbidities, ejection fraction, end-diastolic volume, and end-systolic dimension, and the relative variable importance averaged across five splits of cross-validation in each repeat were evaluated. The concordance index for predicting survival of the best-performing model was 0.84 at 1 year, 0.86 at 2 years, and 0.87 overall, respectively. Conclusion Using common echocardiographic parameters and patient characteristics, we successfully trained multiple ML models to predict survival in patients with severe AR. This technique could be applied to identify high-risk patients who would benefit from early intervention, thereby improving patient outcomes.

Introduction: Conduction disturbance after transcatheter aortic valve replacement (TAVR) remains a common complication. Predictive tools to identify conduction disturbance requiring pacing are limited. Our main objective was to develop a deep learning model to predict the need for a permanent pacemaker. Hypothesis: An electrocardiogram (ECG) based deep learning algorithm can predict the need for permanent pacemaker post TAVR. Methods: We evaluated patients who had TAVR at Mayo Clinic between June 2010 and May 2021. Digital ECGs done on the TAVR date or within 24 hours post procedure were partitioned into training, validation, and testing datasets. We trained a deep learning algorithm on the training data and optimized hyperparameters against the validation data. All model performance metrics are based on the reserved test data that were estimated once model architecture was optimized. Need for permanent pacemaker, defined as pacemaker placement due to development of conduction disturbance post TAVR and at least 1% ventricular pacing on device interrogation done at least 2 weeks post pacemaker implantation, was the training target. Results: A total of 3021 patients were evaluated for inclusion and 2,407 cases were available for modeling (exclusions: prior pacemaker (n=419), unsuccessful TAVR (n=27) and no ECG within the pre-specified period (n=168)). Overall, the median age was 82 (Q1: 76, Q3: 86) and 41% were female. In the withheld test data, 15% had a permanent pacemaker with at least 1% ventricular pacing. The algorithm detected the need for pacemaker in the test set with an AUC of 0.83 (95% CI: 0.73 to 0.92). Accuracy, sensitivity, specificity, positive and negative predictive were 80%, 72%, 81%, 41% and 94%, respectively. Conclusions: This study demonstrates the ability of a deep learning model based on ECG data to assist in making the decision to implant a pacemaker following TAVR with a high negative predictive value. Larger validation studies are warranted.

Abstract IntroductionLiver disease such as cirrhosis is known to cause changes in the composition of volatile organic compounds (VOC) present in patient breath samples. Previous studies have demonstrated the diagnosis of liver cirrhosis from these breath samples, but studies are limited to a handful of discrete, well-characterized compounds.MethodsWe utilized VOC profiles from breath samples from 46 individuals, 35 with cirrhosis and 11 healthy controls. A deep-neural network was optimized to discriminate between healthy controls and individuals with cirrhosis.ResultsA 1D convolutional neural network (CNN) was accurate in predicting which patients had cirrhosis with an AUC of 0.90 (95% CI: 0.75, 0.99). Shapley Additive Explanations characterized the presence of discrete, observable peaks which were implicated in prediction, and the top peaks (based on the average SHAP profiles on the test dataset) were noted.ConclusionCNNs demonstrate the ability to predict the presence of cirrhosis based on a full volatolomics profile of patient breath samples. SHAP values indicate the presence of discrete, detectable peaks in the VOC signal.

PurposeOrgan segmentation of computed tomography (CT) imaging is essential for radiotherapy treatment planning. Treatment planning requires segmentation not only of the affected tissue, but nearby healthy organs‐at‐risk, which is laborious and time‐consuming. We present a fully automated segmentation method based on the three‐dimensional (3D) U‐Net convolutional neural network (CNN) capable of whole abdomen and pelvis segmentation into 33 unique organ and tissue structures, including tissues that may be overlooked by other automated segmentation approaches such as adipose tissue, skeletal muscle, and connective tissue and vessels. Whole abdomen segmentation is capable of quantifying exposure beyond a handful of organs‐at‐risk to all tissues within the abdomen.MethodsSixty‐six (66) CT examinations of 64 individuals were included in the training and validation sets and 18 CT examinations from 16 individuals were included in the test set. All pixels in each examination were segmented by image analysts (with physician correction) and assigned one of 33 labels. Segmentation was performed with a 3D U‐Net variant architecture which included residual blocks, and model performance was quantified on 18 test cases. Human interobserver variability (using semiautomated segmentation) was also reported on two scans, and manual interobserver variability of three individuals was reported on one scan. Model performance was also compared to several of the best models reported in the literature for multiple organ segmentation.ResultsThe accuracy of the 3D U‐Net model ranges from a Dice coefficient of 0.95 in the liver, 0.93 in the kidneys, 0.79 in the pancreas, 0.69 in the adrenals, and 0.51 in the renal arteries. Model accuracy is within 5% of human segmentation in eight of 19 organs and within 10% accuracy in 13 of 19 organs.ConclusionsThe CNN approaches the accuracy of human tracers and on certain complex organs displays more consistent prediction than human tracers. Fully automated deep learning‐based segmentation of CT abdomen has the potential to improve both the speed and accuracy of radiotherapy dose prediction for organs‐at‐risk.