• Skip to main content
  • Skip to header right navigation
  • Skip to site footer
CCAIM logo

CCAIM

Novel AI to transform healthcare

  • Home
  • News
    • All News
    • COVID-19 News
    • COVID-19 Research Update
  • About
    • About us
    • Aims
  • Events
    • CCAIM Seminar Series
    • See recording of CCAIM’s Inaugural Event (22 January 2021)
  • Team
  • We’re hiring!
  • Partners
  • Contact
University of Cambridge Logo

‘Clairvoyance’, a breakthrough ML technology for medical time-series data, accepted for ICLR 2021

19 January 2021 by Sean O'Neill

The International Conference on Learning Representations (ICLR) 2021 has accepted a paper representing landmark research from the van der Schaar Lab. The paper is entitled Clairvoyance: A Pipeline Toolkit for Medical Time Series.

ICLR is globally renowned for presenting and publishing cutting-edge research on all aspects of deep learning used in the fields of artificial intelligence, statistics and data science. The Clairvoyance work is one of five conference papers from the van der Schaar Lab already accepted for ICLR 2021.

Clairvoyance is a ground-breaking package, primarily developed to aid clinical research and decision support, that represents the culmination of years of research, development, and real-world testing. As a unified, end-to-end pipeline for time-series data, clairvoyance is unmatched in its capability and versatility: it can also be used to great effect in non-medical contexts, thanks to its ability to facilitate complex inference workflows in a transparent, reproducible and efficient manner.

“Clairvoyance is an enormously important project for our team, and is the result of years of work across a number of different areas,” says CCAIM Director, Mihaela van der Schaar. “It’s the first of its kind: an end-to-end pipeline that can produce personalized and interpretable predictions and recommendations using time-series data. I have no doubt that clairvoyance will prove useful in driving clinical decision-making research, and I also believe it can offer a lot of benefits to the machine learning community.”

For a closer look at Clairvoyance and its enormous potential, see this in-depth explainer on the van der Schaar website.

Or read the paper itself: Clairvoyance: A Pipeline Toolkit for Medical Time Series  

ABSTRACT: Time-series learning is the bread and butter of data-driven clinical decision support, and the recent explosion in ML research has demonstrated great potential in various healthcare settings. At the same time, medical time-series problems in the wild are challenging due to their highly composite nature: They entail design choices and interactions among components that preprocess data, impute missing values, select features, issue predictions, estimate uncertainty, and interpret models. Despite exponential growth in electronic patient data, there is a remarkable gap between the potential and realized utilization of ML for clinical research and decision support. In particular, orchestrating a real-world project lifecycle poses challenges in engineering (i.e. hard to build), evaluation (i.e. hard to assess), and efficiency (i.e. hard to optimize). Designed to address these issues simultaneously, Clairvoyance proposes a unified, end-to-end, autoML-friendly pipeline that serves as a (i) software toolkit, (ii) empirical standard, and (iii) interface for optimization. Our ultimate goal lies in facilitating transparent and reproducible experimentation with complex inference workflows, providing integrated pathways for (1) personalized prediction, (2) treatment-effect estimation, and (3) information acquisition. Through illustrative examples on real-world data in outpatient, general wards, and intensive-care settings, we illustrate the applicability of the pipeline paradigm on core tasks in the healthcare journey. To the best of our knowledge, Clairvoyance is the first to demonstrate viability of a comprehensive and automatable pipeline for clinical time-series ML.

Category: Conference, ICLR, News, Research
Previous Post: ← CCAIM vacancy: Communications Manager
Next Post: Recordings of CCAIM’s Inaugural Event now available →

Sidebar

Cambridge Centre for AI in MedicineFollow112912

Cambridge Centre for AI in Medicine
CC4AIM avatarCambridge Centre for AI in Medicine@CC4AIM·
23 Feb 1364207307446489088

Join us tomorrow for the second instalment in our CCAIM Seminar Series: a talk and Q&A with @harvardMED's Prof. Isaac Kohane! Sign up and get details here: https://www.eventbrite.co.uk/e/ccaim-seminar-series-professor-isaac-zak-kohane-tickets-132944198677

Image for the Tweet beginning: Join us tomorrow for the
Reply on Twitter 1364207307446489088Retweet on Twitter 13642073074464890887Like on Twitter 136420730744648908813Twitter 1364207307446489088
Retweet on TwitterCambridge Centre for AI in Medicine Retweeted
MihaelaVDS avatarMihaela van der Schaar@MihaelaVDS·
8 Feb 1358807945962807296

📌This week I'll share some insights from our major new write-up on individualized treatment effect inference—one of our key research pillars. ITE inference is about understanding the effect of specific treatments on specific patients at specific times. https://www.vanderschaar-lab.com/individualized-treatment-effect-inference/

Reply on Twitter 1358807945962807296Retweet on Twitter 13588079459628072965Like on Twitter 135880794596280729628Twitter 1358807945962807296
Load More...

News

  • Recordings of CCAIM’s Inaugural Event now available
  • ‘Clairvoyance’, a breakthrough ML technology for medical time-series data, accepted for ICLR 2021
  • CCAIM vacancy: Communications Manager
  • Announcing the CCAIM Seminar Series
  • Centre Coordinator and Project Manager (5-year fixed term)

News categories

Discover more about the Centre’s aims, read our latest news, or get in touch.

Follow us

Newsletter

Sign-up for occasional CCAIM news updates

Navigation

Home

News

About

University of Cambridge

  • University A-Z
  • Contact the University
  • Accessibility
  • Data Protection
  • Terms and conditions

CCAIM Logo

Copyright © 2021 CCAIM

Return to top

This website uses cookies to provide you with the best browsing experience.

Find out more or adjust your settings.

CCAIM
Privacy Overview

This website uses cookies so that we can provide you with the best user experience possible. Cookie information is stored in your browser and performs functions such as recognising you when you return to our website and helping our team to understand which sections of the website you find most interesting and useful.

Strictly Necessary Cookies

Strictly Necessary Cookie should be enabled at all times so that we can save your preferences for cookie settings.

If you disable this cookie, we will not be able to save your preferences. This means that every time you visit this website you will need to enable or disable cookies again.

3rd Party Cookies

This website uses Google Analytics to collect anonymous information such as the number of visitors to the site, and the most popular pages.

Keeping this cookie enabled helps us to improve our website.

Please enable Strictly Necessary Cookies first so that we can save your preferences!