Leveraging machine learning and artificial intelligence to improve peripheral artery disease detection, treatment, and outcomes

AM Flores, F Demsas, NJ Leeper, EG Ross - Circulation research, 2021 - Am Heart Assoc
Peripheral artery disease is an atherosclerotic disorder which, when present, portends poor
patient outcomes. Low diagnosis rates perpetuate poor management, leading to limb loss …

Model inversion attacks that exploit confidence information and basic countermeasures

M Fredrikson, S Jha, T Ristenpart - … of the 22nd ACM SIGSAC conference …, 2015 - dl.acm.org
Machine-learning (ML) algorithms are increasingly utilized in privacy-sensitive applications
such as predicting lifestyle choices, making medical diagnoses, and facial recognition. In a …

Racial and ethnic disparities in radiology: a call to action

JR Betancourt, A Tan-McGrory, E Flores… - Journal of the American …, 2019 - Elsevier
The US health care system is in the midst of incredible transformation. High-value, high-
quality health care is the ultimate goal. Guided by the Institute of Medicine report “Crossing …

Early predictions of movie success: The who, what, and when of profitability

MT Lash, K Zhao - Journal of Management Information Systems, 2016 - Taylor & Francis
We focus on predicting the profitability of a movie to support movie-investment decisions at
early stages of film production. By leveraging data from various sources, and using social …

Objective metrics and gradient descent algorithms for adversarial examples in machine learning

U Jang, X Wu, S Jha - Proceedings of the 33rd Annual Computer …, 2017 - dl.acm.org
Fueled by massive amounts of data, models produced by machine-learning (ML) algorithms
are being used in diverse domains where security is a concern, such as, automotive …

A health decision support system for disease diagnosis based on wearable medical sensors and machine learning ensembles

H Yin, NK Jha - IEEE Transactions on Multi-Scale Computing …, 2017 - ieeexplore.ieee.org
Even with an annual expenditure of more than $3 trillion, the US healthcare system is far
from optimal. For example, the third leading cause of death in the US is preventable medical …

Constrained optimization of objective functions determined from random forests

M Biggs, R Hariss, G Perakis - Production and Operations …, 2023 - journals.sagepub.com
In this paper, we examine a data‐driven optimization approach to making optimal decisions
as evaluated by a trained random forest, where these decisions can be constrained by an …

Defending against membership inference attacks with high utility by GAN

L Hu, J Li, G Lin, S Peng, Z Zhang… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
The success of machine learning (ML) depends on the availability of large-scale datasets.
However, recent studies have shown that models trained on such datasets are vulnerable to …

A self-inspected adaptive SMOTE algorithm (SASMOTE) for highly imbalanced data classification in healthcare

T Kosolwattana, C Liu, R Hu, S Han, H Chen, Y Lin - BioData Mining, 2023 - Springer
In many healthcare applications, datasets for classification may be highly imbalanced due to
the rare occurrence of target events such as disease onset. The SMOTE (Synthetic Minority …

Socioeconomic and demographic predictors of missed opportunities to provide advanced imaging services

MK Glover IV, D Daye, O Khalilzadeh, O Pianykh… - Journal of the American …, 2017 - Elsevier
Purpose The extent to which racial and socioeconomic disparities exist in accessing
clinically appropriate, advanced diagnostic imaging has not been well studied. This study …