paper-with-me

홈 › Papers

When accurate prediction models yield harmful self-fulfilling prophecies

2023-12-02 · Wouter A. C. van Amsterdam, Nan van Geloven, Jesse H. Krijthe, Rajesh Ranganath, Giovanni Ciná

Prediction models are popular in medical research and practice. By predicting an outcome of interest for specific patients, these models may help inform difficult treatment decisions, and are often hailed as the poster children for personalized, data-driven healthcare. We show however, that using prediction models for decision making can lead to harmful decisions, even when the predictions exhibit good discrimination after deployment. These models are harmful self-fulfilling prophecies: their deployment harms a group of patients but the worse outcome of these patients does not invalidate the predictive power of the model. Our main result is a formal characterization of a set of such prediction models. Next we show that models that are well calibrated before and after deployment are useless for decision making as they made no change in the data distribution. These results point to the need to revise standard practices for validation, deployment and evaluation of prediction models that are used in medical decisions.

📄 PDF Abstract BibTeX arXiv:2312.01210

Code (0)

등록된 구현이 없습니다.

Tasks

Decision MakingPrediction

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Improving Open-Set Semi-Supervised Learning with Self-Supervision

2023-01-24 · Erik Wallin, Lennart Svensson, Fredrik Kahl, Lars Hammarstrand

Open-set semi-supervised learning (OSSL) embodies a practical scenario within semi-supervised learning, wherein the unlabeled training set encompasses classes absent from the labeled set. Many existing OSSL methods assum…

Open Set Learning

Self-HarmLLM: Can Large Language Model Harm Itself?

2025-10-31 · Heehwan Kim, Sungjune Park, Daeseon Choi arxiv

Large Language Models (LLMs) are generally equipped with guardrails to block the generation of harmful responses. However, existing defenses always assume that an external attacker crafts the harmful query, and the possi…

Estimating Tail Risks in Language Model Output Distributions

2026-04-24 · Rico Angell, Raghav Singhal, Zachary Horvitz, Zhou Yu 외 arxiv

Language models are increasingly capable and are being rapidly deployed on a population-level scale. As a result, the safety of these models is increasingly high-stakes. Fortunately, advances in alignment have significan…

From algorithms to action: improving patient care requires causality

2022-09-15 · Wouter A. C. van Amsterdam, Pim A. de Jong, Joost J. C. Verhoeff, Tim Leiner 외

In cancer research there is much interest in building and validating outcome predicting outcomes to support treatment decisions. However, because most outcome prediction models are developed and validated without regard …

Decision MakingPrediction

Self-Destructive Language Model

2025-05-18 · Yuhui Wang, Rongyi Zhu, Ting Wang

Harmful fine-tuning attacks pose a major threat to the security of large language models (LLMs), allowing adversaries to compromise safety guardrails with minimal harmful data. While existing defenses attempt to reinforc…

Language ModelingLanguage Modellingmodel