Raphael Sonabend

Raphael Sonabend
Imperial College London | Imperial · Department of Infectious Disease Epidemiology

PhD
Research Associate @ Imperial College London|Postdoctoral Fellow @ University of Kaiserslautern|Tech Manager @ Wellcome

About

25
Publications
4,087
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
980
Citations
Education
September 2018 - September 2021
University College London
Field of study
  • Statistics
September 2015 - June 2018
University College London
Field of study
  • Statistics

Publications

Publications (25)
Preprint
Full-text available
Algorithmic fairness is an increasingly important field concerned with detecting and mitigating biases in machine learning models. There has been a wealth of literature for algorithmic fairness in regression and classification however there has been little exploration of the field for survival analysis. Survival analysis is the prediction task in w...
Preprint
Full-text available
In this paper we consider how to evaluate survival distribution predictions with measures of discrimination. This is a non-trivial problem as discrimination measures are the most commonly used in survival analysis and yet there is no clear method to derive a risk prediction from a distribution prediction. We survey methods proposed in literature an...
Preprint
Full-text available
The SARS-CoV-2 Gamma variant spread rapidly across Brazil, causing substantial infection and death waves. We use individual-level patient records following hospitalisation with suspected or confirmed COVID-19 to document the extensive shocks in hospital fatality rates that followed Gamma’s spread across 14 state capitals, and in which more than hal...
Article
Background: Specialized Rehabilitation Services (SRSs) are designed to offer intensive multidisciplinary rehabilitation to patients with complex needs, who are expected to make significant functional gains in their ADLs over a relatively limited period of time. Although national guidelines offer a guidance on how to band patients by complexity, th...
Article
Full-text available
Background England's COVID-19 roadmap out of lockdown policy set out the timeline and conditions for the stepwise lifting of non-pharmaceutical interventions (NPIs) as vaccination roll-out continued, with step one starting on March 8, 2021. In this study, we assess the roadmap, the impact of the delta (B.1.617.2) variant of SARS-CoV-2, and potentia...
Article
While craft apprenticeship can be understood as socially mediated individual learning, the ensuing prediction of individual and cultural object traits within craft communities has not been investigated. Here we provide an assessment of vessel shape variations occurring through cultural transmission and their visual perception by the craftsmen. To t...
Preprint
Full-text available
Background: England's COVID-19 'roadmap out of lockdown' set out the timeline and conditions for the stepwise lifting of non-pharmaceutical interventions (NPIs) as vaccination roll-out continued. Here we assess the roadmap, the impact of the Delta variant, and potential future epidemic trajectories. Methods: We extended a model of SARS-CoV-2 transm...
Article
Full-text available
Background: The multiple efficacious vaccines authorised for emergency use worldwide represent the first preventative intervention against coronavirus disease 2019 (COVID-19) that does not rely on social distancing measures. The speed at which data are emerging and the heterogeneities in study design, target populations, and implementation make it...
Thesis
Full-text available
Survival analysis is an important field of Statistics concerned with making time-to-event predictions with ‘censored’ data. Machine learning, specifically supervised learning, is the field of Statistics concerned with using state-of-the-art algorithms in order to make predictions on unseen data. This thesis looks at unifying these two fields as cur...
Article
distr6 is an object-oriented (OO) probability distributions interface leveraging the extensibil ity and scalability of R6 and the speed and efficiency of Rcpp. Over 50 probability distributions are currently implemented in the package with ‘core’ methods, including density, distribution, and gener ating functions, and more ‘exotic’ ones, including...
Article
Full-text available
Cases of SARS-CoV-2 infection in Manaus, Brazil, resurged in late 2020, despite previously high levels of infection. Genome sequencing of viruses sampled in Manaus between November 2020 and January 2021 revealed the emergence and circulation of a novel SARS-CoV-2 variant of concern. Lineage P.1, acquired 17 mutations, including a trio in the spike...
Article
Background: Health-related quality of life (HRQL) is important for evaluating the impact of a disease in the longer term across the physical and psychological domains of human functioning. The aim of this study is to evaluate HRQL in COVID-19 survivors in Italy using the short form 36-items questionnaire (SF-36). Methods: This is an observational s...
Preprint
Full-text available
Cases of SARS-CoV-2 infection in Manaus, Brazil, resurged in late 2020, despite high levels of previous infection there. Through genome sequencing of viruses sampled in Manaus between November 2020 and January 2021, we identified the emergence and circulation of a novel SARS-CoV-2 variant of concern, lineage P.1, that acquired 17 mutations, includi...
Article
Full-text available
Motivation As machine learning has become increasingly popular over the last few decades, so too has the number of machine learning interfaces for implementing these models. Whilst many R libraries exist for machine learning, very few offer extended support for survival analysis. This is problematic considering its importance in fields like medicin...
Preprint
Full-text available
Machine learning (ML) and AI toolboxes such as scikit-learn or Weka are workhorses of contemporary data scientific practice -- their central role being enabled by usable yet powerful designs that allow to easily specify, train and validate complex modeling pipelines. However, despite their universal success, the key design principles in their const...
Article
Background: Executive dysregulation and impulsivity can both predispose individuals to risk-prone actions. Although the risk of falls is well established in people with poor executive function, its association to impulsivity is less clear. Purpose: To describe and assess the prognostic capabilities of the relationship between impulsivity, execut...
Article
Objective: To describe the relationship between type 2 diabetes and all-cause mortality among adults with coronavirus disease 2019 (COVID-19) in the critical care setting. Research design and methods: This was a nationwide retrospective cohort study in people admitted to hospital in England with COVID-19 requiring admission to a high dependency...
Article
Full-text available
Studies have documented that traditional motor skills (i.e. motor habits) are part of the cultural way of life that characterises each society. Yet, it is still unclear to what extent motor skills are inherited through culture. Drawing on ethnology and motor behaviour, we addressed this issue through a detailed description of traditional pottery sk...
Preprint
Full-text available
distr6 is an object-oriented (OO) probability distributions interface leveraging the extensibility and scalability of R6, and the speed and efficiency of Rcpp. Over 50 probability distributions are currently implemented in the package with `core' methods including density, distribution, and generating functions, and more `exotic' ones including haz...
Preprint
Full-text available
As machine learning has become increasingly popular over the last few decades, so too has the number of machine learning interfaces for implementing these models. Whilst many R libraries exist for machine learning, very few offer extended support for survival analysis. This is problematic considering its importance in fields like medicine, bioinfor...
Article
Full-text available
Bilal Mateen and Raphael Sonabend are searching for Santa Claus, armed only with a statistical model to predict ear size based on age. The plan sounds ridiculous, but there's a serious lesson here about the limits of predictive models Bilal Mateen and Raphael Sonabend are searching for Santa Claus, armed only with a statistical model to predict ear...
Preprint
Full-text available
Objective: To determine the completeness of argumentative steps necessary to conclude effectiveness of an algorithm in a sample of current ML/AI supervised learning literature. Data Sources: Papers published in the Neural Information Processing Systems (NeurIPS, n\'ee NIPS) journal where the official record showed a 2017 year of publication. Eligib...

Network

Cited By

Projects

Project (1)
Project
Methods and Tools for Machine Learning based Survival Analysis