skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.


Title: Evidence-driven spatiotemporal COVID-19 hospitalization prediction with Ising dynamics
Abstract In this work, we aim to accurately predict the number of hospitalizations during the COVID-19 pandemic by developing a spatiotemporal prediction model. We propose HOIST, an Ising dynamics-based deep learning model for spatiotemporal COVID-19 hospitalization prediction. By drawing the analogy between locations and lattice sites in statistical mechanics, we use the Ising dynamics to guide the model to extract and utilize spatial relationships across locations and model the complex influence of granular information from real-world clinical evidence. By leveraging rich linked databases, including insurance claims, census information, and hospital resource usage data across the U.S., we evaluate the HOIST model on the large-scale spatiotemporal COVID-19 hospitalization prediction task for 2299 counties in the U.S. In the 4-week hospitalization prediction task, HOIST achieves 368.7 mean absolute error, 0.6$${R}^{2}$$ R 2 and 0.89 concordance correlation coefficient score on average. Our detailed number needed to treat (NNT) and cost analysis suggest that future COVID-19 vaccination efforts may be most impactful in rural areas. This model may serve as a resource for future county and state-level vaccination efforts.  more » « less
Award ID(s):
2034479
PAR ID:
10416645
Author(s) / Creator(s):
; ; ; ; ;
Publisher / Repository:
Nature Publishing Group
Date Published:
Journal Name:
Nature Communications
Volume:
14
Issue:
1
ISSN:
2041-1723
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract In this paper we prove a higher dimensional analogue of Carleson’s$$\varepsilon ^{2}$$ ε 2 conjecture. Given two arbitrary disjoint Borel sets$$\Omega ^{+},\Omega ^{-}\subset \mathbb{R}^{n+1}$$ Ω + , Ω R n + 1 , and$$x\in \mathbb{R}^{n+1}$$ x R n + 1 ,$$r>0$$ r > 0 , we denote$$ \varepsilon _{n}(x,r) := \frac{1}{r^{n}}\, \inf _{H^{+}} \mathcal{H}^{n} \left ( ((\partial B(x,r)\cap H^{+}) \setminus \Omega ^{+}) \cup (( \partial B(x,r)\cap H^{-}) \setminus \Omega ^{-})\right ), $$ ε n ( x , r ) : = 1 r n inf H + H n ( ( ( B ( x , r ) H + ) Ω + ) ( ( B ( x , r ) H ) Ω ) ) , where the infimum is taken over all open affine half-spaces$$H^{+}$$ H + such that$$x \in \partial H^{+}$$ x H + and we define$$H^{-}= \mathbb{R}^{n+1} \setminus \overline{H^{+}}$$ H = R n + 1 H + . Our first main result asserts that the set of points$$x\in \mathbb{R}^{n+1}$$ x R n + 1 where$$ \int _{0}^{1} \varepsilon _{n}(x,r)^{2} \, \frac{dr}{r}< \infty $$ 0 1 ε n ( x , r ) 2 d r r < is$$n$$ n -rectifiable. For our second main result we assume that$$\Omega ^{+}$$ Ω + ,$$\Omega ^{-}$$ Ω are open and that$$\Omega ^{+}\cup \Omega ^{-}$$ Ω + Ω satisfies the capacity density condition. For each$$x \in \partial \Omega ^{+} \cup \partial \Omega ^{-}$$ x Ω + Ω and$$r>0$$ r > 0 , we denote by$$\alpha ^{\pm }(x,r)$$ α ± ( x , r ) the characteristic constant of the (spherical) open sets$$\Omega ^{\pm }\cap \partial B(x,r)$$ Ω ± B ( x , r ) . We show that, up to a set of$$\mathcal{H}^{n}$$ H n measure zero,$$x$$ x is a tangent point for both$$\partial \Omega ^{+}$$ Ω + and$$\partial \Omega ^{-}$$ Ω if and only if$$ \int _{0}^{1} \min (1,\alpha ^{+}(x,r) + \alpha ^{-}(x,r) -2) \frac{dr}{r} < \infty . $$ 0 1 min ( 1 , α + ( x , r ) + α ( x , r ) 2 ) d r r < . The first result is new even in the plane and the second one improves and extends to higher dimensions the$$\varepsilon ^{2}$$ ε 2 conjecture of Carleson. 
    more » « less
  2. Abstract In this paper, we present counterexamples to maximal$$L^p$$ L p -regularity for a parabolic PDE. The example is a second-order operator in divergence form with space and time-dependent coefficients. It is well-known from Lions’ theory that such operators admit maximal$$L^2$$ L 2 -regularity on$$H^{-1}$$ H - 1 under a coercivity condition on the coefficients, and without any regularity conditions in time and space. We show that in general one cannot expect maximal$$L^p$$ L p -regularity on$$H^{-1}(\mathbb {R}^d)$$ H - 1 ( R d ) or$$L^2$$ L 2 -regularity on$$L^2(\mathbb {R}^d)$$ L 2 ( R d )
    more » « less
  3. Abstract A model based on a$$U(1)_{T^3_R}$$ U ( 1 ) T R 3 extension of the Standard Model can address the mass hierarchy between generations of fermions, explain thermal dark matter abundance, and the muon$$g - 2$$ g - 2 ,$$R_{(D)}$$ R ( D ) , and$$R_{(D^*)}$$ R ( D ) anomalies. The model contains a light scalar boson$$\phi '$$ ϕ and a heavy vector-like quark$$\chi _\textrm{u}$$ χ u that can be probed at CERN’s large hadron collider (LHC). We perform a phenomenology study on the production of$$\phi '$$ ϕ and$${\chi }_u$$ χ u particles from proton–proton$$(\textrm{pp})$$ ( pp ) collisions at the LHC at$$\sqrt{s}=13.6$$ s = 13.6 TeV, primarily through$$g{-g}$$ g - g and$$t{-\chi _\textrm{u}}$$ t - χ u fusion. We work under a simplified model approach and directly take the$$\chi _\textrm{u}$$ χ u and$$\phi '$$ ϕ masses as free parameters. We perform a phenomenological analysis considering$$\chi _\textrm{u}$$ χ u final states to b-quarks, muons, and neutrinos, and$$\phi '$$ ϕ decays to$$\mu ^+\mu ^-$$ μ + μ - . A machine learning algorithm is used to maximize the signal sensitivity, considering an integrated luminosity of 3000$$\text {fb}^{-1}$$ fb - 1 . The proposed methodology can be a key mode for discovery over a large mass range, including low masses, traditionally considered difficult due to experimental constraints. 
    more » « less
  4. Abstract This article revisits the problem of global well-posedness for the generalized parabolic Anderson model on$$\mathbb {R}^+\times \mathbb {T}^2$$ R + × T 2 within the framework of paracontrolled calculus (Gubinelli et al. in Forum Math, 2015). The model is given by the equation:$$\begin{aligned} (\partial _t-\Delta ) u=F(u)\eta \end{aligned}$$ ( t - Δ ) u = F ( u ) η where$$\eta \in C^{-1-\kappa }$$ η C - 1 - κ with$$1/6>\kappa >0$$ 1 / 6 > κ > 0 , and$$F\in C_b^2(\mathbb {R})$$ F C b 2 ( R ) . Assume that$$\eta \in C^{-1-\kappa }$$ η C - 1 - κ and can be lifted to enhanced noise, we derive new a priori bounds. The key idea follows from the recent work by Chandra et al. (A priori bounds for 2-d generalised Parabolic Anderson Model,,2024), to represent the leading error term as a transport type term, and our techniques encompass the paracontrolled calculus, the maximum principle, and the localization approach (i.e. high-low frequency argument). 
    more » « less
  5. Abstract Physical experiments and numerical simulations have observed a remarkable stabilizing phenomenon: a background magnetic field stabilizes and dampens electrically conducting fluids. This paper intends to establish this phenomenon as a mathematically rigorous fact on a magnetohydrodynamic (MHD) system with anisotropic dissipation in$$\mathbb R^3$$ R 3 . The velocity equation in this system is the 3D Navier–Stokes equation with dissipation only in the$$x_1$$ x 1 -direction, while the magnetic field obeys the induction equation with magnetic diffusion in two horizontal directions. We establish that any perturbation near the background magnetic field (0, 1, 0) is globally stable in the Sobolev setting$$H^3({\mathbb {R}}^3)$$ H 3 ( R 3 ) . In addition, explicit decay rates in$$H^2({\mathbb {R}}^3)$$ H 2 ( R 3 ) are also obtained. For when there is no presence of a magnetic field, the 3D anisotropic Navier–Stokes equation is not well understood and the small data global well-posedness in$$\mathbb R^3$$ R 3 remains an intriguing open problem. This paper reveals the mechanism of how the magnetic field generates enhanced dissipation and helps to stabilize the fluid. 
    more » « less