Data-Driven and Statistical Models

2015 ◽  
pp. 89-98
Author(s):  
Yoram Vodovotz ◽  
Gary An
Keyword(s):  
Statistical Models ◽  
Data Driven

scholarly journals The power of modeling in emergency preparedness for COVID-19: a moonshot moment for hospitals

2021 ◽  
pp. 1-10
Author(s):  
Kyan C. Safavi ◽  
Ann L. Prestipino ◽  
Ana Cecilia Zenteno Langle ◽  
Martin Copenhaver ◽  
Michael Hu ◽  
...  
Keyword(s):  
New England ◽  
Emergency Preparedness ◽  
Statistical Models ◽  
Operational Planning ◽  
Data Driven ◽  
Major Objective ◽  
Response Models ◽  
Specific Data ◽  
Clinical Leadership ◽  
Future Patient

Abstract Prior to COVID-19, few hospitals had fully tested emergency surge plans. Uncertainty in the timing and degree of surge complicates planning efforts, putting hospitals at risk of being overwhelmed. Many lack access to hospital-specific, data-driven projections of future patient demand to guide operational planning. Our hospital experienced one of the largest surges in New England. We developed statistical models to project hospitalizations during the first wave of the pandemic. We describe how we used these models to meet key planning objectives. To build the models successfully, we emphasize the criticality of having a team that combines data scientists with frontline operational and clinical leadership. While modeling was a cornerstone of our response, models currently available to most hospitals are built outside of their institution and are difficult to translate to their environment for operational planning. Creating data-driven, hospital-specific, and operationally relevant surge targets and activation triggers should be a major objective of all health systems.

scholarly journals Inferring reaction network structure from single-cell, multiplex data, using toric systems theory

2019 ◽  
Author(s):  
Shu Wang ◽  
Jia-Ren Lin ◽  
Eduardo D. Sontag ◽  
Peter K. Sorger
Keyword(s):  
Single Cell ◽  
Chemical Reaction ◽  
Network Structure ◽  
Statistical Models ◽  
Control Cell ◽  
Toric Varieties ◽  
Chemical Reaction Networks ◽  
Data Driven ◽  
Cell Subpopulation ◽  
Reaction Networks

AbstractThe goal of many single-cell studies on eukaryotic cells is to gain insight into the biochemical reactions that control cell fate and state. In this paper we introduce the concept of effective stoichiometric space (ESS) to guide the reconstruction of biochemical networks from multiplexed, fixed time-point, single-cell data. In contrast to methods based solely on statistical models of data, the ESS method leverages the power of the geometric theory of toric varieties to begin unraveling the structure of chemical reaction networks (CRN). This application of toric theory enables a data-driven mapping of covariance relationships in single cell measurements into stoichiometric information, one in which each cell subpopulation has its associated ESS interpreted in terms of CRN theory. In the development of ESS we reframe certain aspects of the theory of CRN to better match data analysis. As an application of our approach we process cytomery- and image-based single-cell datasets and identify differences in cells treated with kinase inhibitors. Our approach is directly applicable to data acquired using readily accessible experimental methods such as Fluorescence Activated Cell Sorting (FACS) and multiplex immunofluorescence.Author summaryWe introduce a new notion, which we call the effective stoichiometric space (ESS), that elucidates network structure from the covariances of single-cell multiplexed data. The ESS approach differs from methods that are based on purely statistical models of data: it allows a completely new and data-driven translation of the theory of toric varieties in geometry and specifically their role in chemical reaction networks (CRN). In the process, we reframe certain aspects of the theory of CRN. As illustrations of our approach, we find stoichiometry in different single-cell datasets, and pinpoint dose-dependence of network perturbations in drug-treated cells.

Can tongue be recovered from face? the answer of data-driven statistical models

2010 ◽  
Author(s):  
Atef Ben Youssef ◽  
Pierre Badin ◽  
Gérard Bailly
Keyword(s):  
Statistical Models ◽  
Data Driven

scholarly journals Character Constellations

2021 ◽  
Author(s):  
Roel Smeets
Keyword(s):  
Network Analysis ◽  
Social Mobility ◽  
Statistical Models ◽  
Social Impact ◽  
Social Groups ◽  
Class Struggle ◽  
Cultural Representation ◽  
Data Driven ◽  
Race Ethnicity ◽  
Dutch Language

Fiction has a major social impact, not least because it co-shapes the image that society has of various social groups. Drawing on a collection of 170 contemporary Dutch-language novels, Character Constellations presents a range of data-driven, statistical models to study depictions of characters in terms of gender, race, ethnicity, class, age, sexuality, and other identity categories. Incorporating the tools of network analysis, each chapter highlights an aspect of fictional social networks that affects the representation of social groups: their centrality, their communities, and their conflicts. While reading individual novels in light of emerging statistical patterns, combining the formal methods of social network analysis with the interpretive tools of narratology, this study shows how central societal themes such as (in)equality and emancipation, integration and segregation, and social mobility and class struggle are foregrounded, replicated, or distorted in the Dutch novel. Showcasing what character-based critiques of literary representation gain by integrating data-driven methods into the practice of critical close reading, Character Constellations contributes to societal debates on cultural representation and identity and the role fiction and art have in those debates.

scholarly journals The future of digital health with federated learning

2020 ◽  
Vol 3 (1) ◽  
Author(s):  
Nicola Rieke ◽  
Jonny Hancox ◽  
Wenqi Li ◽  
Fausto Milletarì ◽  
Holger R. Roth ◽  
...  
Keyword(s):  
Statistical Models ◽  
Digital Health ◽  
Healthcare Systems ◽  
Medical Data ◽  
Data Driven ◽  
Full Potential ◽  
Sufficient Data ◽  
Key Factors ◽  
Privacy Concerns ◽  
The Future

Abstract Data-driven machine learning (ML) has emerged as a promising approach for building accurate and robust statistical models from medical data, which is collected in huge volumes by modern healthcare systems. Existing medical data is not fully exploited by ML primarily because it sits in data silos and privacy concerns restrict access to this data. However, without access to sufficient data, ML will be prevented from reaching its full potential and, ultimately, from making the transition from research to clinical practice. This paper considers key factors contributing to this issue, explores how federated learning (FL) may provide a solution for the future of digital health and highlights the challenges and considerations that need to be addressed.

scholarly journals The Ionic Liquid Property Explorer: An Extensive Library of Task-Specific Solvents

Data ◽  
2019 ◽  
Vol 4 (2) ◽  
pp. 88
Author(s):  
Vishwesh Venkatraman ◽  
Sigvart Evjen ◽  
Kallidanthiyil Chellappan Lethesh
Keyword(s):  
Ionic Liquids ◽  
Statistical Models ◽  
Data Driven ◽  
Virtual Library ◽  
Equilibrium Thermodynamics ◽  
Data Set ◽  
Using Data ◽  
Liquid Property ◽  
Selection Of ◽  
Transition Heat

Ionic liquids have a broad spectrum of applications ranging from gas separation to sensors and pharmaceuticals. Rational selection of the constituent ions is key to achieving tailor-made materials with functional properties. To facilitate the discovery of new ionic liquids for sustainable applications, we have created a virtual library of over 8 million synthetically feasible ionic liquids. Each structure has been evaluated for their-task suitability using data-driven statistical models calculated for 12 highly relevant properties: melting point, thermal decomposition, glass transition, heat capacity, viscosity, density, cytotoxicity, CO 2 solubility, surface tension, and electrical and thermal conductivity. For comparison, values of six properties computed using quantum chemistry based equilibrium thermodynamics COSMO-RS methods are also provided. We believe the data set will be useful for future efforts directed towards targeted synthesis and optimization.

Sign in / Sign up

Export Citation Format

Share Document