Hardway, Heather

BACKGROUND Implementing Mohs case complexity grading systems is critical due to inherent complexities of Mohs workflow coordination. Precise scheduling can improve wait times and resource allocation. OBJECTIVE To predict Mohs number of stages and reconstruction type as surrogates of case complexity and to use information derived from model training and practice to develop scheduling recommendations. METHODS Machine learning models were trained to predict number of Mohs stages and complex reconstruction across multiple practices and surgeons in an institutional enterprise, using information available on pathology reports. A workflow analysis by health systems engineering was conducted to identify improvement areas for efficiency. Information from modeling and workflow analysis was combined to develop fixed rules for scheduling recommendations. RESULTS In total, 18,473 Mohs cases were used for training/validation and 2,053 for testing. Models achieved an AUC-ROC of 0.83 (95% CI: 0.81–0.85) for prediction of complex reconstruction and 0.62 (0.60–0.66) for number of stages (1 vs 2 vs 3 or more). Anatomical location was the most valuable feature, with midface locations predicting higher case complexity and longer surgical time. CONCLUSION We demonstrated feasibility for prediction of Mohs surgery case complexity. Combining machine and human-derived knowledge provides complementary insights that can assist with improving scheduling and workflow.

ABSTRACTBackgroundIntercellular IgG4 deposition is variably present on DIF in patients with pemphigus. Whether this feature has clinical, serologic, or histopathologic correlates was unknown.MethodsWe identified 34 patients with pemphigus who had 55 DIF specimens reported to show intercellular IgG, IgG4, and/or C3 deposition (8/22/2017–11/30/2023). Patients and biopsies were stratified by intercellular IgG4 status. Clinical and serologic data were extracted from electronic records, and corresponding biopsy slides were reviewed for histopathologic findings.ResultsAmong the 34 patients with pemphigus, patients with positive IgG4 were significantly more likely to have detectable serum anti‐desmoglein 1/3 antibodies by ELISA (p = 0.014 and p = 0.030, respectively). Paraneoplastic pemphigus (PNP) was more frequent in the IgG4‐negative group (p = 0.037), particularly among patients with ocular involvement. Of 55 DIF biopsy specimens meeting inclusion criteria, 52 (94.5%) had intercellular IgG deposition and 42 (76.4%) had intercellular IgG4 on DIF. Compared to IgG4‐negative specimens, IgG4‐positive specimens were significantly more likely to represent a vesiculobullous lesion (p = 0.024), to be derived from the trunk (p = 0.047), to show histologic acantholysis (p = 0.019) and to lack lichenoid inflammation (p = 0.0004).ConclusionFor pemphigus, DIF IgG4 status correlated with ocular involvement, the clinical morphology selected for biopsy, the likelihood of detecting circulating desmoglein antibodies, the presence of specific histopathologic features such as acantholysis and lichenoid inflammation, and the likelihood of having a final diagnosis of PNP. Further studies are needed to determine whether the presence of tissue‐bound intercellular IgG4 antibodies correlates with particular disease variants or lesion‐specific characteristics.

ABSTRACTBackground/ObjectivesImmune‐mediated skin disorders, such as immunobullous dermatoses and leukocytoclastic vasculitis, rarely affect children. While direct immunofluorescence (DIF) biopsy is a standard diagnostic tool, limited data exist on pediatric DIF patterns, rates of positivity, pretest diagnostic concordance, and the relevance of biopsy site. This study sought to address these gaps.MethodsDIF data from all skin and mucosal specimens interpreted at Mayo Clinic's reference immunodermatology laboratory for patients aged 0–18 years (August 22, 2017 to November 30, 2023) were reviewed. DIF results were classified as positive if a characteristic pattern was seen and negative if the findings were negative or nondiagnostic.ResultsOf 986 pediatric DIF studies, 153 (15.5%) were positive and comparable to adult positivity rates (20.9%) during the same period. The most frequent DIF patterns were IgA‐predominant vasculitis (N = 85/153; 55.5%) and lichenoid tissue reaction (N = 21/153;13.7%). Concordance between pretest diagnosis and positive DIF results was highest for linear IgA bullous dermatosis (N = 7/7; 100%) and dermatitis herpetiformis (N = 6/6; 100%). Excluding these entities, DIF changed the pretest diagnosis in 16.7% (N = 19/114) of cases. While lower extremity biopsies were initially more likely to yield positive DIF results, this association disappeared when IgA vasculitis cases were excluded.ConclusionThe most frequent DIF pattern in children was that of IgA‐predominant vasculitis. Pediatric DIF positivity rates closely mirrored those of adults, supporting similar biopsy thresholds. DIF results differed from the pretest impression in a substantial percentage, supporting the value of DIF in select situations in the pediatric population. After controlling for IgA vasculitis, biopsy site was not associated with DIF positivity.

PURPOSE Guidelines recommend germline genetic testing (GT) for patients with pancreatic ductal adenocarcinoma (PDAC). This study aims to evaluate the utilization and outcomes of multigene panel GT in patients with PDAC. METHODS This retrospective, multisite study included patients with PDAC diagnosed between May 2018 and August 2020 at Mayo Clinic Arizona, Florida, and Minnesota. Discussion, uptake, and outcomes of GT were compared before (May 1, 2018-May 1, 2019) and after (August 1, 2019-August 1, 2020) the guideline update, accounting for a transition period. RESULTS The study identified 533 patients with PDAC, with 321 (60.2%) preguideline and 212 (39.8%) postguideline. Patient characteristics did not differ between the preguideline and postguideline periods. GT was discussed in 34.3% (110 of 321) of preguideline and 39.6% (84 of 212) of postguideline patients (odds ratio [OR], 1.26 [95% CI, 0.88 to 1.80]) and subsequently performed in 80.9% (89 of 110) of preguideline and 75.0% (63 of 84) of postguideline patients (OR, 1.10 [95% CI, 0.75 to 1.61]). Of 152 tested patients, 26 (17.1%) had a pathogenic variant (PV), of whom 17 (11.2%; 17 of 152) were PDAC-associated. Over the entire study period, GT was more likely in younger patients (65 v 70 years; P < .001), those seen by a medical oncologist (82.9% v 69.0%; P < .001), and those surviving more than 12 months from diagnosis (70.4% v 43.4%; P < .001). Demographics and personal/family cancer history were comparable between patients with and without a PDAC PV. CONCLUSION GT remains underutilized despite National Comprehensive Cancer Network guideline recommendations. Given the poor prognosis of PDAC and potential implications of GT, efforts to increase utilization are needed to provide surveillance and support to both patients with PDAC and at-risk family members.

Abstract Background Cardiomyopathy is a leading cause of pregnancy-related mortality and represents the number one cause of death in the late postpartum period. Purpose The goal of this study was to prospectively evaluate the effectiveness of an artificial intelligence-based electrocardiogram (AI-ECG) and a point-of-care artificial intelligence-enhanced digital stethoscope for cardiomyopathy screening among pregnant and postpartum women. Methods We conducted a single-arm prospective study of pregnant and postpartum women (up to 12 months following delivery) enrolled at three sites between October 2021 and October 2022. Study participants completed a standard 12-lead ECG, ECG + phonocardiogram recordings with a digital stethoscope, a demographic questionnaire, and a transthoracic echocardiogram (TTE) within a 24-hour period. Diagnostic performance of the AI-ECG and digital stethoscope for cardiomyopathy detection, defined as left ventricular ejection fraction (LVEF) &lt; 45%, was evaluated using the area under the curve (AUC) and standard measures of diagnostic performance. Results We included 100 consecutive pregnant and postpartum women who provided informed consent and had at least one ECG recorded, completed the questionnaire, and had an echocardiogram performed. All participants self-identified as female, and 41% were recruited from a federally qualified health center. The median age of participants was 31 years (Q1: 27, Q3: 34). Thirty-eight percent identified as non-Hispanic White, 32% as non-Hispanic Black, 21% as Hispanic or Latino, 6% as Asian, and 3% as Other (1 Native Hawaiian and 2 multiracial). Five percent (5/100) had LVEF &lt;45%. The 12-lead AI-ECG model demonstrated close to perfect discrimination (accuracy 99%; AUC 1.00, sensitivity 100%) for detection of cardiomyopathy with 1 false positive screen (LVEF 49%), Figure 1A. The digital stethoscope (angled position) had an AUC of 0.99 (95% CI: 0.97, 1.00) for detection of LVEF &lt;45%. Sensitivity, specificity, positive predictive value, and negative predictive value for the digital stethoscope were 60%, 98%, 60% and 98%, respectively for detection of LVEF &lt;45% (Figure 1B & 1C). Conclusions In this small prospective study, we found that 5% of pregnant and postpartum women had cardiomyopathy, a potentially life-threatening condition, and that a rapid, inexpensive, ubiquitous, massively scalable point-of-care test - the ECG - showed promising results, identifying it with an AUC &gt; 0.98 with the application of artificial intelligence.Figure 1

688 Background: Guidelines recommend patients with pancreatic ductal adenocarcinoma (PDAC) undergo genetic testing for germline pathogenic variants (PV). The aim of this study was to evaluate compliance with recently updated guidelines (May 2019) and assess subsequent uptake and outcomes of genetic testing in PDAC patients. In addition, social and clinical factors associated with genetic testing were assessed. Methods: A retrospective chart review of patients diagnosed with PDAC between May 2018 and August 2020 was performed. Discussion and subsequent uptake of genetic testing was reviewed and compared between a 12-month period before (pre-guideline) and a 12-month period after (post-guideline) guidelines were updated, accounting for a three-month transition period. Univariate and multivariate logistic regression analysis was used to assess factors predictive of undergoing genetic testing. Results: In total, 534 patients with PDAC were identified; 321 (60.1%) in the pre-guideline period and 213 (39.9%) in the post-guideline period. The mean age at diagnosis was 68 years and 47% were female. Genetic testing was discussed in 34% (109/321) of pre-guideline and in 39% (84/213) of post-guideline patients ( P = .23). Of those, 82% (89/109) of patients in pre-guideline and 75% (63/84) in post-guideline groups underwent subsequent genetic testing ( P = .71). In 26 (17.1%) of 152 tested patients, a PV was identified, of which 17 (11.2%; 17/152) had a PDAC-associated PV. Age, cancer stage at diagnosis, length of survival, and having a first-degree relative with pancreatic cancer were significant predictors of genetic testing on multivariate analysis. Conclusions: Adherence to recently updated guidelines is poor and germline genetic testing in PDAC patients remains insufficient. Efforts to increase awareness of benefits of testing, which include personalized therapies for patients and cascade testing in family members for subsequent enrollment in pancreatic cancer surveillance programs, could improve future uptake.[Table: see text]

Abstract Aims Current non-invasive screening methods for cardiac allograft rejection have shown limited discrimination and are yet to be broadly integrated into heart transplant care. Given electrocardiogram (ECG) changes have been reported with severe cardiac allograft rejection, this study aimed to develop a deep-learning model, a form of artificial intelligence, to detect allograft rejection using the 12-lead ECG (AI-ECG). Methods and results Heart transplant recipients were identified across three Mayo Clinic sites between 1998 and 2021. Twelve-lead digital ECG data and endomyocardial biopsy results were extracted from medical records. Allograft rejection was defined as moderate or severe acute cellular rejection (ACR) based on International Society for Heart and Lung Transplantation guidelines. The extracted data (7590 unique ECG-biopsy pairs, belonging to 1427 patients) was partitioned into training (80%), validation (10%), and test sets (10%) such that each patient was included in only one partition. Model performance metrics were based on the test set (n = 140 patients; 758 ECG-biopsy pairs). The AI-ECG detected ACR with an area under the receiver operating curve (AUC) of 0.84 [95% confidence interval (CI): 0.78–0.90] and 95% (19/20; 95% CI: 75–100%) sensitivity. A prospective proof-of-concept screening study (n = 56; 97 ECG-biopsy pairs) showed the AI-ECG detected ACR with AUC = 0.78 (95% CI: 0.61–0.96) and 100% (2/2; 95% CI: 16–100%) sensitivity. Conclusion An AI-ECG model is effective for detection of moderate-to-severe ACR in heart transplant recipients. Our findings could improve transplant care by providing a rapid, non-invasive, and potentially remote screening option for cardiac allograft function.

Abstract Background Screening for left ventricular (LV) systolic dysfunction (defined as ejection fraction ≤35%) based on data from a standard 12-lead electrocardiogram (ECG) has become well established when standard digital ECGs are available–8 independent leads sampled at least 250 hertz for 10 seconds. As the algorithm has been incorporated into various clinical scenarios and ancillary research projects, a limitation of the binary classification at 35% has become apparent. Purpose The objective of this study was to develop and validate a deep learning-based algorithm that would classify LVEF into three categories based on only the digital ECG input. Methods After IRB approval, native digital resting ECGs acquired between 1/1/2010 and 12/31/2021 on patients seen in Mayo Clinic in Jacksonville were extracted from the institutional electronic ECG database management system (MUSE, GE Healthcare). These ECGs were matched with transthoracic echocardiograms obtained up to four days prior or 30 days after the ECGs acquisition. A convolutional neural network consisting of 8 layers of convolutions, batch normalization and pooling was trained using Keras and Tensorflow with hyper-parameter optimization for L1 and L2 regularization, learning rate adjustments, and class weights to predict three classes of LVEF: ≤35%, 36–51%, and ≥52% based on clinical relevance. The primary measure of overall performance was the detection of LVEF ≤35%; however, the triad of model predictions was also considered in translating the model output to human interpretable findings. Results A total of 30,153 patients (60,169 ECG pairings; mean age 63 years; 48% male) were randomly split at the patient level into training (24,172 patients), validation (2,973 patients) and testing (3,008 patients). The trained model provided robust discrimination in the withheld testing data – AUROC of 0.941 (95% CI: 0.931 to 0.950). Using the optimal model threshold based on Youden's index from the validation data (0.186), sensitivity and specificity were estimated to be 87.9% (95% CI: 83.8% to 91.2%) and 86.3% (95% CI: 85.4% to 87.2%) in the testing data. In instances where discordant predictions were observed, the posterior distribution of model probabilities provide additional insights into the possible underlying value of LVEF (Figure 1). Conclusions The utilization of a multi-category deep learning classification model for the detection of reduced ejection fraction adds new dimensions to the use of AI technologies on digital ECGs. This work shows high discrimination can still be obtained when using three classes of LVEF. Funding Acknowledgement Type of funding sources: None.