Objectives/Goals: This research aims to harness electronic health records (EHR) combined with machine learning (ML) to predict necrotizing enterocolitis (NEC) in preterm infants using data up to their first 14 days of life. We aim to provide interpretable results for clinical decisions that can reduce infant mortality rates and complications from NEC. Methods/Study Population: Through a retrospective cohort study using data from the University of Florida Integrated Data Repository and One Florida, we will develop machine learning models suitable for sequential data to predict NEC. Our inclusion criteria include very low birth weight (VLBW; <1500g) infants born <32 weeks gestation and EHR data availability from the first 14 days of life. We will include infants with NEC and infants without NEC to train our ML model. Exclusion criteria include infants diagnosed with spontaneous intestinal perforation and severe congenital anomalies/defects requiring surgery. Results/Anticipated Results: We anticipate that our model will provide an accurate and dynamic prediction for the risk of NEC in neonates using data up to the first 14 days of life. Our model will be interpretable to identify key risk factors and can integrate real-world clinical insights to increase early detection and improve patient outcomes. Discussion/Significance of Impact: The development of a model to predict NEC could be used in neonatal intensive care guidelines and protocols and could ultimately decrease mortality, reduce complications, improve the overall quality of care, and lower healthcare costs associated with NEC.

Objectives/Goals: Knowledge about predictive factors for immune-related endocrinopathies can help identify appropriate populations for specific screening approaches, provide recommendations for ICI therapy selection, guide clinical monitoring strategies to improve patient outcomes, and guide research efforts to provide equitable healthcare for all patients. Methods/Study Population: This is an analysis of the demographic and clinical data available of patients from DiRECT Cohort, a longitudinal study that prospectively follows adult cancer patients who self-identify as Black or White and undergo anti-PD-(L)1 ICI therapy. Endocrinopathies were graded using the CTCAE criteria. Kaplan–Meier method was used to calculate the incidence within the first year of treatment. Bivariate analysis (Chi-square and log-rank test) examined the associations between patient demographics, clinical characteristics, and endocrinopathies. Results/Anticipated Results: Among 955 patients, 13.20% developed endocrinopathies of any grade, most commonly hyper-/hypothyroidism and adrenal insufficiency, and 5.97% were at grade ≥2. Younger age (7.59% in age 30 vs. 4.72% in BMI ≤30, p = 0.022) showed significant associations. No significant difference was found in the incidence of grade ≥2 endocrinopathies by race (13.3 % in White and 10.79% in Black patients, p = 0.732). No association was found with cancer stage or comorbidities. Discussion/Significance of Impact: ICIs can lead to (irAEs). Endocrinopathies are a common type of irAEs, presenting a unique challenge. However, the current literature lacks real-time data and a comprehensive comparative analysis of variables like race. Identifying and understanding these variables ensures equatable access to safe and effective healthcare for all patients.

Objectives/Goals: This research aims to harness electronic health records (EHR) combined with machine learning (ML) to predict necrotizing enterocolitis (NEC) in preterm infants using data up to their first 14 days of life. We aim to provide interpretable results for clinical decisions that can reduce infant mortality rates and complications from NEC. Methods/Study Population: Through a retrospective cohort study using data from the University of Florida Integrated Data Repository and One Florida, we will develop machine learning models suitable for sequential data to predict NEC. Our inclusion criteria include very low birth weight (VLBW; < 1500g) infants born < 32 weeks gestation and EHR data availability from the first 14 days of life. We will include infants with NEC and infants without NEC to train our ML model. Exclusion criteria include infants diagnosed with spontaneous intestinal perforation and severe congenital anomalies/defects requiring surgery. Results/Anticipated Results: We anticipate that our model will provide an accurate and dynamic prediction for the risk of NEC in neonates using data up to the first 14 days of life. Our model will be interpretable to identify key risk factors and can integrate real-world clinical insights to increase early detection and improve patient outcomes. Discussion/Significance of Impact: The development of a model to predict NEC could be used in neonatal intensive care guidelines and protocols and could ultimately decrease mortality, reduce complications, improve the overall quality of care, and lower healthcare costs associated with NEC.

Little is known about the association between iodine nutrition status and bone health. The present study aimed to explore the connection between iodine nutrition status, bone metabolism parameters, and bone disease (osteopenia and osteoporosis). A cross-sectional survey was conducted involving 391, 395, and 421 adults from iodine fortification areas (IFA), iodine adequate areas (IAA), and iodine excess areas (IEA) of China. Iodine nutrition status, bone metabolism parameters and BMD were measured. Our results showed that, in IEA, the urine iodine concentrations (UIC) and serum iodine concentrations (SIC) were significantly higher than in IAA. BMD and Ca2+ levels were significantly different under different iodine nutrition levels and the BMD were negatively correlated with UIC and SIC. Univariate linear regression showed that gender, age, BMI, menopausal status, smoking status, alcohol consumption, UIC, SIC, free thyroxine, TSH, and alkaline phosphatase were associated with BMD. The prevalence of osteopenia was significantly increased in IEA, UIC ≥ 300µg/L and SIC > 90µg/L groups. UIC ≥ 300µg/L and SIC > 90µg/L were risk factors for BMD T value < -1.0 SD. In conclusion, excess iodine can not only lead to changes in bone metabolism parameters and BMD, but is also a risk factor for osteopenia and osteoporosis.

We revisit the communication primitive in ambient calculi. Previously, such communication was confined to first-order (FO) mode (e.g., merely names or capabilities of ambients can be sent), local mode (e.g., the communication only occurs inside an ambient), or particular cross-hierarchy mode (e.g., parent-child communication). In this work, we explore further higher-order (HO) communication in ambient calculi. Specifically, such a communication mechanism allows sending a whole piece of a program across the borders of ambients and is the only form of communication that can happen exactly between ambients. Since ambients are basically of HO nature (i.e., those being moved may be ambients themselves), in a sense, it appears more natural to have HO communication than FO communication. We stipulate that communications merely occur between equally positioned ambients in a peer-to-peer fashion (e.g., between sibling ambients). Following this line, we drop the local or other forms of communication that violate this criterion. As the workbench, we work on a variant of Fair Ambients extended with HO communication, FAHO. This variant also strengthens the original version in that entirely real-identity interaction is guaranteed. We study the semantics, bisimulation, and expressiveness of FAHO. Particularly, we provide the operational semantics using a labeled transition system. Over the semantics, we define the bisimulation in line with the standard notion of bisimulation for ambients and prove that the bisimulation equivalence (i.e., bisimilarity) is a congruence. In addition, we demonstrate that bisimilarity coincides with observational congruence (i.e., barbed congruence). Moreover, we show that FAHO can encode a minimal Turing-complete HO calculus and thus is computationally complete.

In this paper, by means of upper approximation operators in rough set theory, we study representations for sL-domains and its special subclasses. We introduce the concepts of sL-approximation spaces, L-approximation spaces, and bc-approximation spaces, which are special types of CF-approximation spaces. We prove that the collection of CF-closed sets in an sL-approximation space (resp., an L-approximation space, a bc-approximation space) ordered by set-theoretic inclusion is an sL-domain (resp., an L-domain, a bc-domain); conversely, every sL-domain (resp., L-domain, bc-domain) is order-isomorphic to the collection of CF-closed sets of an sL-approximation space (resp., an L-approximation space, a bc-approximation space). Consequently, we establish an equivalence between the category of sL-domains (resp., L-domains) with Scott continuous mappings and that of sL-approximation spaces (resp., L-approximation spaces) with CF-approximable relations.

Machine learning (ML) models have been developed to identify randomised controlled trials (RCTs) to accelerate systematic reviews (SRs). However, their use has been limited due to concerns about their performance and practical benefits. We developed a high-recall ensemble learning model using Cochrane RCT data to enhance the identification of RCTs for rapid title and abstract screening in SRs and evaluated the model externally with our annotated RCT datasets. Additionally, we assessed the practical impact in terms of labour time savings and recall improvement under two scenarios: ML-assisted double screening (where ML and one reviewer screened all citations in parallel) and ML-assisted stepwise screening (where ML flagged all potential RCTs, and at least two reviewers subsequently filtered the flagged citations). Our model achieved twice the precision compared to the existing SVM model while maintaining a recall of 0.99 in both internal and external tests. In a practical evaluation with ML-assisted double screening, our model led to significant labour time savings (average 45.4%) and improved recall (average 0.998 compared to 0.919 for a single reviewer). In ML-assisted stepwise screening, the model performed similarly to standard manual screening but with average labour time savings of 74.4%. In conclusion, compared with existing methods, the proposed model can reduce workload while maintaining comparable recall when identifying RCTs during the title and abstract screening stages, thereby accelerating SRs. We propose practical recommendations to effectively apply ML-assisted manual screening when conducting SRs, depending on reviewer availability (ML-assisted double screening) or time constraints (ML-assisted stepwise screening).

Coherent structures over two distinct, organized wall perturbations – a transverse sinusoidal bump with and without small-scale longitudinal grooves – are studied using direct numerical simulations. Large-scale spanwise rollers (SRs) form via shear layer rollup past the bump peak, enveloping a large separation bubble (SB) for both a smooth wall (SW) and a grooved wall (GW). In a GW, small-scale alternatingly spinning jets emanating from the crests’ corners merge with the shear layer, altering the SRs compared with SRs in a SW. The underlying coherence of the highly turbulent SRs is educed via phase-locked ensemble averaging. Coherent vorticity contours of SRs are ellipses tilted downward, hence causing co-gradient Reynolds stress. The limited streamwise length of SB precludes SR tumbling, unlike in a free shear layer. The coherent field reveals minibubbles attached to the bump’s downstream wall with circulation opposite to that of the SB – they are larger, stronger and more numerous in GW than in SW – reducing skin friction. Compared with SW, the swirling jets in GW increase coherent production while decreasing incoherent production. Additionally, the jets push the SRs to travel faster and farther before reattachment. The SB experiences two different modes of oscillation due to high-frequency advection of the shear layer SR and low-frequency breathing of the SB, where the former dominates in GW and the latter in SW. Negative production is caused by counter-rotating vortex dipoles inducing flow ejections (for both SW and GW) and single vortices penetrating the grooves – both occurring in the region of flow acceleration.

For a continuous-time phase-type (PH) distribution, starting with its Laplace–Stieltjes transform, we obtain a necessary and sufficient condition for its minimal PH representation to have the same order as its algebraic degree. To facilitate finding this minimal representation, we transform this condition equivalently into a non-convex optimization problem, which can be effectively addressed using an alternating minimization algorithm. The algorithm convergence is also proved. Moreover, the method we develop for the continuous-time PH distributions can be used directly for the discrete-time PH distributions after establishing an equivalence between the minimal representation problems for continuous-time and discrete-time PH distributions.

Although it is well established that gestational diabetes mellitus (GDM) is associated with fetal overgrowth in singleton pregnancies, little is known about its role in twins. We aimed to explore the relationship between GDM and the longitudinal fetal growth in twin pregnancies. This was a retrospective matched cohort study of GDM and non-GDM twin pregnancies delivered ≥36 weeks without other complications. All the women performed ≥3 ultrasounds after 22 weeks. Linear mixed models (LMMs) were used to explore the relationships between longitudinal fetal growth trajectories and GDM. Group-based trajectory modeling (GBTM) and generalized estimating equation (GEE) were applied to identify the latent growth patterns and investigate their relationships with GDM. In total, 215 GDM and 645 non-GDM twins were included, the majority of the patients did not require medication therapy (n = 202, GDMA1). LMM revealed that, compared with non-GDM, GDM was associated with an average increase in fetal weight of 4.36 g (95% CI [1.25, 7.48]) per week. GBTM and GEE further revealed that GDM increased the odds of fetal weight trajectory to nearly 40% of the total fetal weight trajectory, classified into the high-speed group (aOR = 1.39, 95% CI [1.03, 1.88]), associating with a 49.44 g (95% CI [11.41, 87.48]) increase in birth weight. Subgroup analysis revealed that all these differences were only significant among the GDMA1 pregnancies (p < .05). GDM (GDMA1) is significantly associated with an increase in fetal weight during gestation in twin pregnancies. However, this acceleration is mild, and its significance requires further exploration.

The operational reliability of large mechanical equipment is typically influenced by the functional effectiveness of key components. Consequently, prompt repair before their failure is necessary to ensure the dependability of mechanical equipment. The prognostic and health management (PHM) technology could track the system’s health state and timely detect faults. Therefore, the remaining useful life (RUL) prediction as one of the key components of PHM is rather important. Accurate RUL prediction results could be the data support for condition-based equipment maintenance plans. Also, it could increase the dependability and safety of mechanical equipment while reducing the loss of human and financial resources and meet the requirements of sustainable manufacturing in the Industry 4.0 era. However, with the widespread use of deep learning in the field of intelligent manufacturing, there is a lack of review on RUL prediction based on deep learning. In this paper, different deep learning-based RUL prediction methods for mechanical components are summarized and classified, along with their pros and cons. Then, the case study on the C-MAPSS dataset is mainly conducted and different methods are compared. And finally, the difficulties and future directions of the RUL prediction in practical scenarios are discussed.

In the contemporary maritime industry, characterised by intense competition, reduced visibility due to heavy fog is a primary cause of accidents, significantly impairing maritime operational efficiency. Consequently, investigating foggy weather navigation safety holds crucial practical significance. This paper, through an analysis and synthesis of various aspects of foggy navigation technology, including foggy navigation regulations at different ports, fog warnings, foggy vessel environmental perception and foggy auxiliary navigation systems, explores the key issues concerning vessel navigation during foggy conditions from a scientific perspective. This discussion encompasses the aspects of regulatory frameworks, standardisation, and the development of intelligent and responsive onboard equipment. Finally, the paper offers a glimpse into potential strategies for fog navigation.