The Deep View: AI for Good: Conformal classification

Posted on May 6, 2025 by michelleclarke2015
AI for Good: Conformal classification
Source: Unsplash
The application of machine learning and AI techniques in high-stakes environments, like healthcare, for instance, presents a massive challenge considering the persistent unreliability of the models and systems in question. 
Whether we’re talking about vision models or language models, we’re talking about predicted output; those predictions aren’t always accurate. 
There exists a technique, called conformal classification, that can, to a degree, remedy the uncertainty problem. Conformal classification replaces a single prediction with a range of probabilities that come with a guarantee that the correct probability — in this case, a diagnosis — is somewhere within that range. 
Think of a doctor using a medical imaging model to analyze chest X-rays — that doctor would want to be sure to actively rule out lung cancer and any other possible diagnoses before accepting a single prediction as true. The challenge here is compounded by the fact that many conditions show up with remarkable similarities on medical imaging. The problem with this technique is that, in order to ensure the correct probability gets included in the final output, models tend to output too many predictions for it to be useful. 
A team of MIT researchers recently applied a technique called Test Time Augmentation to conformal classification, a simple method that massively reduces the final output size without requiring researchers to retrain a given model. 
Why it matters: More accurate, more actionable sets of predictions — outputted with confidence scores — could make the technology more genuinely accessible and usable in the medical field. Importantly, it could also reduce some of the risk associated with implementing a system that is inherently unreliable. 
Unknown's avatar

About michelleclarke2015

Life event that changes all: Horse riding accident in Zimbabwe in 1993, a fractured skull et al including bipolar anxiety, chronic fatigue …. co-morbidities (Nietzche 'He who has the reason why can deal with any how' details my health history from 1993 to date). 17th 2017 August operation for breast cancer (no indications just an appointment came from BreastCheck through the Post). Trinity College Dublin Business Economics and Social Studies (but no degree) 1997-2003; UCD 1997/1998 night classes) essays, projects, writings. Trinity Horizon Programme 1997/98 (Centre for Women Studies Trinity College Dublin/St. Patrick's Foundation (Professor McKeon) EU Horizon funded: research study of 15 women (I was one of this group and it became the cornerstone of my journey to now 2017) over 9 mth period diagnosed with depression and their reintegration into society, with special emphasis on work, arts, further education; Notes from time at Trinity Horizon Project 1997/98; Articles written for Irishhealth.com 2003/2004; St Patricks Foundation monthly lecture notes for a specific period in time; Selection of Poetry including poems written by people I know; Quotations 1998-2017; other writings mainly with theme of social justice under the heading Citizen Journalism Ireland. Letters written to friends about life in Zimbabwe; Family history including Michael Comyn KC, my grandfather, my grandmother's family, the O'Donnellan ffrench Blake-Forsters; Moral wrong: An acrimonious divorce but the real injustice was the Catholic Church granting an annulment – you can read it and make your own judgment, I have mine. Topics I have written about include annual Brain Awareness week, Mashonaland Irish Associataion in Zimbabwe, Suicide (a life sentence to those left behind); Nostalgia: Tara Hill, Co. Meath.
This entry was posted in Uncategorized. Bookmark the permalink.

Leave a comment