Frequent pandemics of infectious diseases have had devastating global consequences. A central epidemiological metric for guiding effective public health interventions is the basic reproduction number, R0. Although mathematical models are commonly used to characterize transmission dynamics and derive R0, accurately computing this quantity remains challenging when models incorporate multiple transmission routes, time-varying parameters driven by seasonal or behavioral changes, or mobility-induced diffusion processes. In this work, we develop a unified framework—Math-model Informed Neural Network (MINN)—that integrates machine learning with mechanistic disease models to estimate R0. Our approach leverages a neural network representation of the linearized infection subsystem, allowing for the computation of R0 without explicitly solving the system. We apply MINN to spatiotemporally homogeneous, spatially heterogeneous, temporally homogeneous, and fully spatiotemporally heterogeneous models of infectious diseases, including those with direct, environmental, and vector-borne transmission. Across all scenarios, MINN accurately estimates R0 and closely recovers previously established analytical or numerical benchmarks. This AI-augmented modeling framework provides a generalizable and efficient approach for estimating basic reproduction numbers, with potential utility in informing timely and effective pandemic-prevention policies.
Purpose Scaphoid fractures, the most common carpal fractures, are prone to nonunion because of their retrograde blood supply. Delayed presentation increases the risk of nonunion and progression to scaphoid nonunion advanced collapse. Social determinants of health, as measured by Area Deprivation Index (ADI), Social Vulnerability Index (SVI), and Child Opportunity Index (COI), can influence timely presentation, increasing the risk of nonunion. This study aims to develop a novel artificial intelligence model to predict scaphoid nonunion rates using socioeconomic indices alone. Methods A retrospective review identified 107 patients with suspected scaphoid fractures (January 2018–June 2025) who presented within 5 years of injury. National ADI, SVI, and COI scores were obtained. A binomial regression was used to validate ADI, SVI, and COI scores to predict nonunion status. A multilayer neural network was trained on the indices to predict nonunion status. Model performance was evaluated with area under the curve, and Youden’s J statistic was maximized to determine sensitivity and specificity. Results Higher ADI (OR = 1.029; 95% CI, 1.009–1.049) and SVI (OR = 1.020; 95% CI, 1.006–1.035), and lower COI (OR = 0.986; 95% CI, 0.974–0.998) were independent predictors of nonunion on presentation, validating their usage. The neural network had an area under the curve of 0.879, and at a threshold of 0.21 (J = 0.707), the model achieved a sensitivity of 95.7%, specificity of 75.0%, precision of 0.512, and an F1 score of 0.667. Conclusions Our artificial intelligence model predicts nonunion status based purely on social determinants of health, emphasizing their influence on scaphoid fractures. Addressing these disparities is essential to improve timely access to care for injuries such as scaphoid fractures and may be crucial to other timely orthopedic fractures. Type of study/level of evidence Prevalence IIIb.
During extreme weather events, transportation networks-modeled as graphs G(V, E ) consisting of a set of vertices Vand a set of edges E-can be disrupted by bridge failures and wind-thrown trees, increasing the likelihood of disconnection between critical locations. Evaluating connectivity reliability between two vertices under probabilistic edge failures is a #P-complete problem, where exact analysis is generally limited to small graphs only. Quantum computing offers potential to accelerate these computations. While prior studies have formulated quantum approaches for undirected networks, the anticipated computational speedup has not been fully realized due to irreversibility of the connectivity computation. This study develops a quantum computational framework with a novel reversible computation technique for evaluating connectivity reliability in mixed graph networks-containing both one-way and two-way roads-commonly encountered in real transportation systems. The reversible logic enables the use of quantum amplitude estimation and phase estimation algorithms to achieve quadratic query-complexity improvement over crude Monte Carlo sampling. The corresponding query complexity scales as O(& varepsilon;- 1), and qubit requirement for modeling and computation is on the order of O(V log V), where & varepsilon; and V denote the precision of the reliability estimate and number of vertices, respectively. Validation of the proposed framework is performed on representative example graphs using Qiskit's Aer simulator. The proposed approach establishes a quantum framework for hazard-induced connectivity reliability in mixed transportation networks and supports planning-oriented continuity assessment, although practical advantage awaits further hardware advances.
Scaphotrapeziotrapezoidal fracture-dislocations are extremely rare injuries, requiring early recognition and treatment. We present a case of a 54-year-old man with scaphotrapeziotrapezoidal fracture/dislocation following a motor vehicle accident, resulting in dorsal dislocation of the first and second carpal-metacarpal joints through the trapezium and trapezoid. The identification of the dislocation was delayed, and a month after the initial injury, fixation was attempted elsewhere but had redislocated at the first postoperative visit. Subsequent fixation was successful, using both radial and ulnar buried Kirschner wires. The clinical outcome was excellent with stable reduction maintained at 21 weeks postop.
