A computational model for BMP movement in sea urchin embryos.

Bone morphogen proteins (BMPs) are distributed along a dorsal-ventral (DV) gradient in many developing embryos. The spatial distribution of this signaling ligand is critical for correct DV axis specification. In various species, BMP expression is spatially localized, and BMP gradient formation relies on BMP transport, which in turn requires interactions with the extracellular proteins Short gastrulation/Chordin (Chd) and Twisted gastrulation (Tsg). These binding interactions promote BMP movement and concomitantly inhibit BMP signaling. The protease Tolloid (Tld) cleaves Chd, which releases BMP from the complex and permits it to bind the BMP receptor and signal. In sea urchin embryos, BMP is produced in the ventral ectoderm, but signals in the dorsal ectoderm. The transport of BMP from the ventral ectoderm to the dorsal ectoderm in sea urchin embryos is not understood. Therefore, using information from a series of experiments, we adapt the mathematical model of Mizutani et al. (2005) and embed it as the reaction part of a one-dimensional reaction-diffusion model. We use it to study aspects of this transport process in sea urchin embryos. We demonstrate that the receptor-bound BMP concentration exhibits dorsally centered peaks of the same type as those observed experimentally when the ternary transport complex (Chd-Tsg-BMP) forms relatively quickly and BMP receptor binding is relatively slow. Similarly, dorsally centered peaks are created when the diffusivities of BMP, Chd, and Chd-Tsg are relatively low and that of Chd-Tsg-BMP is relatively high, and the model dynamics also suggest that Tld is a principal regulator of the system. At the end of this paper, we briefly compare the observed dynamics in the sea urchin model to a version that applies to the fly embryo, and we find that the same conditions can account for BMP transport in the two types of embryos only if Tld levels are reduced in sea urchin compared to fly.

Utilization and Outcomes of Multigene Panel Testing in Patients With Pancreatic Ductal Adenocarcinoma.

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.

Artificial intelligence-based screening for cardiomyopathy in an obstetric population: A pilot study.

Background: Cardiomyopathy is a leading cause of pregnancy-related mortality and the number one cause of death in the late postpartum period. Delay in diagnosis is associated with severe adverse outcomes. Objective: To evaluate the performance of an artificial intelligence-enhanced electrocardiogram (AI-ECG) and AI-enabled digital stethoscope to detect left ventricular systolic dysfunction in an obstetric population. Methods: We conducted a single-arm prospective study of pregnant and postpartum women enrolled at 3 sites between October 28, 2021, and October 27, 2022. Study participants completed a standard 12-lead ECG, digital stethoscope ECG and phonocardiogram recordings, and a transthoracic echocardiogram within 24 hours. Diagnostic performance was evaluated using the area under the curve (AUC). Results: One hundred women were included in the final analysis. The median age was 31 years (Q1: 27, Q3: 34). Thirty-eight percent identified as non-Hispanic White, 32% as non-Hispanic Black, and 21% as Hispanic. Five percent and 6% had left ventricular ejection fraction (LVEF) <45% and <50%, respectively. The AI-ECG model had near-perfect classification performance (AUC: 1.0, 100% sensitivity; 99%-100% specificity) for detection of cardiomyopathy at both LVEF categories. The AI-enabled digital stethoscope had an AUC of 0.98 (95% CI: 0.95, 1.00) and 0.97 (95% CI: 0.93, 1.00), for detection of LVEF <45% and <50%, respectively, with 100% sensitivity and 90% specificity. Conclusion: We demonstrate an AI-ECG and AI-enabled digital stethoscope were effective for detecting cardiac dysfunction in an obstetric population. Larger studies, including an evaluation of the impact of screening on clinical outcomes, are essential next steps.

Predicting Penicillin Allergy: A United States Multicenter Retrospective Study.

BACKGROUND: Using the reaction history in logistic regression and machine learning (ML) models to predict penicillin allergy has been reported based on non-US data. OBJECTIVE: We developed ML positive penicillin allergy testing prediction models from multisite US data. METHODS: Retrospective data from 4 US-based hospitals were grouped into 4 datasets: enriched training (1:3 case-control matched cohort), enriched testing, nonenriched internal testing, and nonenriched external testing. ML algorithms were used for model development. We determined area under the curve (AUC) and applied the Shapley Additive exPlanations (SHAP) framework to interpret risk drivers. RESULTS: Of 4777 patients (mean age 60 [standard deviation: 17] years; 68% women, 91% White, and 86% non-Hispanic) evaluated for penicillin allergy labels, 513 (11%) had positive penicillin allergy testing. Model input variables were frequently missing: immediate or delayed onset (71%), signs or symptoms (13%), and treatment (31%). The gradient-boosted model was the strongest model with an AUC of 0.67 (95% confidence interval [CI]: 0.57-0.77), which improved to 0.87 (95% CI: 0.73-1) when only cases with complete data were used. Top SHAP drivers for positive testing were reactions within the last year and reactions requiring medical attention; female sex and reaction of hives/urticaria were also positive drivers. CONCLUSIONS: An ML prediction model for positive penicillin allergy skin testing using US-based retrospective data did not achieve performance strong enough for acceptance and adoption. The optimal ML prediction model for positive penicillin allergy testing was driven by time since reaction, seek medical attention, female sex, and hives/urticaria.

Non-invasive detection of cardiac allograft rejection among heart transplant recipients using an electrocardiogram based deep learning model.

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.

Modeling the precision and robustness of Hunchback border during Drosophila embryonic development.

During anterior-posterior axis specification in the Drosophila embryo, the Hunchback (Hb) protein forms a sharp boundary at the mid-point of the embryo with great positional precision. While Bicoid (Bcd) is a known upstream regulator for hb expression, there is evidence to suggest that Hb effectively filters out "noisy" data received from varied Bcd gradients. We use mathematical models to explore simple regulatory networks which filter out such noise to produce a precise Hb boundary. We find that in addition to Bcd and Hb, at least one freely evolving protein is necessary. An automated search yields a number of examples of three-protein networks exhibiting the desired precision. In all such networks, Hb diffuses much slower than the third protein. In addition, the action of Hb on the third protein is the opposite of the action of the third protein on hb (i.e. if Hb activates the third protein, then the third protein inhibits hb expression, and vice versa). Most of the discovered systems satisfy the known biological properties, that Bcd activates hb, and that Hb activates its own expression. We find that all network topologies satisfying these constraints arise among the networks exhibiting the desired precision. Investigating the dynamics of these networks, we find that under a general class of non-uniform initial conditions, Bcd can be eliminated from the system and the spatiotemporal evolution of these two proteins alone is sufficient to recapture the dynamics. We hypothesize that Bcd is needed only to spatially disturb the gradient of the third protein, and then becomes unnecessary in the further evolution of the Hb border. This provides a possible explanation as to why the Hb dynamics are robust under perturbations of the Bcd gradient. Under this hypothesis, other proteins would be able to assume the role of Bcd in our simulations (possibly in the case of evolutionary divergences or a redundancy in the process), with the only constraint that they act to positively regulate hb.

Gene network models robust to spatial scaling and noisy input.

Many biological systems are inherently noisy, yet demonstrate robustness to perturbations and changes in external influences. Such is the case in the Bicoid-Hunchback (Bcd-Hb) system, which is critical to axis specification in the developing Drosophila embryo. We use this system as motivation to explore the larger problem of how precise patterning can be achieved under imprecise conditions. While evidence suggests Bicoid gradients are uncorrelated with respect to embryo length, downstream genes, such as Hb, are expressed in a precise manner with regard to position along the anterior-posterior (AP)-axis. In addition to precision under variability of embryo length, Hb also exhibits robustness to perturbations to the regulatory network, gene dosage, and temperature. Understanding the reduced variability of patterns in this system is of interest to both experimentalists and theoreticians, lending itself well to the field of mathematical modeling. In this paper, a class of reaction-diffusion models is presented, which produce precise patterns, despite receiving noisy input and other perturbations to the system. An essential property of the network includes the existence of a strong inhibitor for the Hb representative, where the strength of the inhibition is directly related to the amount of variation that can be tolerated. With a higher inhibitory effect, larger perturbations of Bcd can be made with relatively small changes to the location of the Hb boundary. Network topology and interaction strength are the essential properties of the minimal model giving rise to the robust features, and possible interpretations are made with regard to the Bcd-Hb system.