Harini Suresh
Relevante Arbeiten
Meistzitierte Publikationen im Bereich Gesundheit & MedTech
A Framework of Potential Sources of Harm Throughout the Machine Learning Life Cycle
2021 · 415 Zit. · DSpace@MIT (Massachusetts Institute of Technology)
Do as AI say: susceptibility in deployment of clinical decision-aids
2021 · 393 Zit. · npj Digital Medicine
A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle
2021 · 84 Zit.
Non-task expert physicians benefit from correct explainable AI advice when reviewing X-rays
2023 · 83 Zit. · Scientific Reports
Clinical Intervention Prediction and Understanding using Deep Networks
2017 · 78 Zit. · arXiv (Cornell University)
Development and preliminary testing of Health Equity Across the AI Lifecycle (HEAAL): A framework for healthcare delivery organizations to mitigate the risk of AI solutions worsening health inequities
2024 · 37 Zit. · PLOS Digital Health
Understanding Potential Sources of Harm throughout the Machine Learning Life Cycle
2021 · 28 Zit.
Intuitively Assessing ML Model Reliability through Example-Based Explanations and Editing Model Inputs
2022 · 18 Zit.
Using Large Language Models to Promote Health Equity
2025 · 14 Zit. · NEJM AI
Saliency Cards: A Framework to Characterize and Compare Saliency Methods
2023 · 11 Zit.
Development and preliminary testing of Health Equity Across the AI Lifecycle (HEAAL): A framework for healthcare delivery organizations to mitigate the risk of AI solutions worsening health inequities
2023 · 6 Zit.
Who should do as AI say? Only non-task expert physicians benefit from correct explainable AI advice
2022 · 3 Zit.
Sociotechnical AI Governance: Challenges and Opportunities for HCI
2025 · 2 Zit.
Audit Trails for Accountability in Large Language Models
2026 · 0 Zit. · arXiv (Cornell University)
Audit Trails for Accountability in Large Language Models
2026 · 0 Zit. · ArXiv.org