Statistical machine learning

We apply statistical modelling and machine learning techniques to analyse data, such as:

  • Time-series forecasting, to predict the evolution of diseases like atopic dermatitis.
  • Bayesian modelling, to learn from small data, quantify uncertainty and develop flexible models that reflect data-generating mechanisms.
  • Clustering, to uncover complex patterns in biological data.
Determining the clinical applicability of machine learning models through assessment of reporting across skin phototypes and rarer skin cancer types: A systematic review
Lloyd Steele, Xiang Li Tan, Bayanne Olabi, Jing Mia Gao, Reiko Tanaka, Hywel C. Williams
Cite DOI
EczemaPred: A computational framework for personalised prediction of eczema severity dynamics
Prediction of the patient-pecific dynamic evolution of AD severity by EczemaPred will help manage and anticipate fluctuating disease symptoms, contributing to personalised medicine.
Guillem Hurault, Jean François Stalder, Sophie Mery, Alain Delarue, Markéta Saint Aroman, Gwendal Josse, Reiko Tanaka
Cite Code DOI R Package
Data-driven research on eczema: systematic characterization of the field and recommendations for the future
Ariane Duverdier, Adnan Custovic, Reiko Tanaka
Cite Code DOI MedRxiv
Can serum biomarkers predict the outcome of systemic immunosuppressive therapy in adult atopic dermatitis patients?
Guillem Hurault, Evelien Roekevisch, Mandy .E. Schram, Krisztina Szegedi, Sanja Kezic, Maritza A. Middelkamp-Hup, Phyllis I. Spuls, Reiko Tanaka
Cite Code DOI MedRxiv
Impact of environmental factors in predicting daily severity scores of atopic dermatitis
Guillem Hurault, Valentin Delorieux, Young‐Min Kim, Kangmo Ahn, Hywel C. Williams, Reiko Tanaka
Cite Code DOI MedRxiv
Personalised prediction of daily eczema severity scores using a mechanistic machine learning model
Guillem Hurault, Elisa Domínguez-Hüttinger, Sinead M. Langan, Hywel C. Williams, Reiko Tanaka
Cite Code DOI MedRxiv