Study on privacy-preserving health care models that sacrifice accuracy for data protection.
problem Privacy-preserving models in health care neglect data from the tails, reducing accuracy for small groups.
method Used state-of-the-art differentially private learning methods for clinical prediction tasks.
result Privacy-preserving models in health care exhibit steep tradeoffs between privacy and utility, and disproportionately influence large demographic groups.
Neural network de-identification improved with EHR features.
problem De-identify patient notes while preserving sensitive information.
method Incorporated human-engineered and EHR-derived features into neural networks.
result State-of-the-art de-identification improved with EHR features.
Review of automatic de-identification systems for EHR, highlighting challenges beyond accuracy.
problem Challenges in surrogate generation and patient privacy in de-identification of EHR.
method Comprehensive review of 18 recently published systems, focusing on accuracy and challenges.
result Despite accuracy improvements, challenges remain in surrogate generation and patient privacy.
Objective: Patient notes in electronic health records (EHRs) may contain critical information for medical investigations. However, the vast majority of medical investigators can only access de-identified notes, in order to protect the confidentiality of patients. In the United States, the Health Insurance Portability a…
This paper improves fairness in PCA and kernel PCA.
problem Fairness in unsupervised learning, specifically PCA.
method Develops convex optimization formulations for fair PCA and kernel PCA.
result Shows how to perform fair clustering of health data.
Privacy-preserving algorithm for sensory data protects sensitive information.
problem Protecting sensitive information from discovery through access to sensory data.
method Replacement AutoEncoder learns to transform sensitive features into less sensitive ones.
result The algorithm retains recognition accuracy while preserving privacy.
The paper develops a valuation framework for GLWB-LTC contracts with Levy dynamics and stochastic interest rates.
problem Valuation of GLWB-LTC contracts with financial guarantees, longevity protection, and health-contingent LTC payments.
method Coupling a recombining Hull-White trinomial tree with an IMEX finite difference scheme, incorporating a seven-state health model.
result Hybrid tree-IMEX method delivers stable long-maturity prices consistent with simulation benchmarks.
Research uses Twitter to study transgender health issues.
problem Lack of information on transgender health needs.
method Collect and analyze tweets from transgender users.
result Identified 54 health topics, 7 categories, linguistic and topical differences between TM and TW.
System detects power grid health using AI and machine learning.
problem Detecting and preventing power grid malfunctions.
method Artificial intelligence, machine learning, recurrent neural networks, SVM, LSTM.
result High accuracy in detecting grid health, scalable for complex architectures.
Proposes a new method for subgroup analysis using optimal trees with parameter fusion.
problem Challenges of greedy heuristics and overfitting in tree-based recursive partitioning methods.
method Fused optimal causal tree method leveraging mixed integer optimization (MIO) for globally optimal partitions and parameter fusion.
result Substantial improvement in subgroup discovery accuracy and statistical efficiency.
Supervised learning improves disease outbreak detection accuracy.
problem Early detection of infectious disease outbreaks to protect public health.
method Developed a supervised learning approach based on hidden Markov models for disease outbreak detection.
result Reduces false positive rate by up to 50% while maintaining sensitivity.
The study examines how investor protection and past information affect stock returns and interest rates.
problem Empirical regularities related to investor protection and past information in asset pricing models.
method Developed a dynamic asset pricing model with a controlling shareholder and good/bad memory in budget dynamics.
result Good/bad memory of investors on historical market information affects stock returns and interest rates, strengthening investor protection in high ownership concentration.
The paper introduces a health-informed policy gradient method for multi-agent reinforcement learning.
problem Optimizing joint reward functions in multi-agent systems with varying agent health.
method Health-informed credit assignment in a multi-agent proximal policy optimization algorithm.
result Significant improvement in learning performance compared to traditional methods.
New method learns fair representations by separating out protected attributes.
problem Learning fair representations invariant to protected attributes.
method FD-VAE: disentangles latent space into target, protected, and mutual attributes.
result FD-VAE outperforms previous methods in fairness metrics.
Paper proposes a new approach to GDPR compliance using data protection analytics.
problem Lack of research on data protection risk management and difficulty in GDPR compliance.
method Quantitative approach to data protection risk-based compliance.
result Improves data protection impact assessments by integrating analytics and expert opinions.
New method controls bias in training data for fair outcomes.
problem Ensuring equal treatment between different groups in machine learning.
method Contrastive information estimation to control mutual information between representations and protected attributes.
result Our method provides strong theoretical guarantees on the parity of any downstream algorithm.
Protects user privacy in models using optional personal data.
problem Ensuring fairness for users who opt-out of data sharing.
method Formalizes protection requirements, introduces Protected User Consent (PUC), devises data augmentation strategy.
result PUC-compliant models can improve performance without disadvantaging opt-out users.
Automatically assesses the quality of online health articles.
problem Lack of automated tools to evaluate the quality of online health information.
method Data mining approach using 10 quality criteria and feature selection.
result Classifier achieved 84%-90% accuracy on 10 criteria.
SURI boosts features with high unique relevant information for better health data analysis.
problem Preserving interpretability in health data analysis.
method Mutual information-based feature selection (MIBFS) method called SURI.
result SURI selects more relevant features leading to higher classification performance.
A multi-task network avoids indirect discrimination in insurance pricing.
problem Indirect discrimination in insurance pricing models based on protected characteristics.
method Multi-task neural network architecture trained with partial protected characteristic information.
result Multi-task network produces discrimination-free insurance prices with comparable accuracy to conventional models.
Accurate real-time monitoring systems of influenza outbreaks help public health officials make informed decisions that may help save lives. We show that information extracted from cloud-based electronic health records databases, in combination with machine learning techniques and historical epidemiological information,…
Proposes QNN to protect input privacy in neural networks.
problem Protecting input privacy in neural networks.
method Quaternion-valued neural network (QNN) to hide input information.
result QNN effectively protects input privacy without significant accuracy loss.
Repository tackles fake health news in cancer research.
problem Spread of fake health news over the internet.
method Developed comprehensive FakeHealth repository with rich features and detailed explanations.
result Repository helps in understanding and validating health fake news datasets.
Automated model assesses online health info quality using machine learning.
problem Low quality health information on the internet poses risks to patients.
method Used machine learning models, specifically hierarchical encoder attention-based neural networks (HEA) with BERT and BioBERT embeddings.
result HEA models outperform traditional models in evaluating health info quality.
Bayesian model predicts patient survival from sparse EHR data.
problem Analyzing EHR data with few samples and diverse information.
method Nonparametric probabilistic model using Bayesian trees.
result Improved survival trajectory predictions on patient data.
The paper develops methods for monitoring TPL machine health.
problem Inaccurate and untimely maintenance of TPL systems leads to poor quality and inefficiencies.
method Physics-informed data-driven predictive models integrated with statistical approaches.
result The methods achieve high accuracy across various scenarios and conditions.
PASS protects private attributes by stochastically substituting data.
problem Protecting private attributes in ML services while maintaining data utility.
method PASS uses stochastic data substitution with a novel loss function derived from information theory.
result PASS effectively protects private attributes across various datasets.
Paper studies fairness postprocessing with imperfect attribute information.
problem Ensuring fairness with imperfect protected attribute information.
method Equalized odds postprocessing method with imperfect attribute information.
result Conditions on perturbation ensure reduced bias in classifier.
Paper explores GAN generalization via privacy protection, proving bounds on generalization gap and reducing leakage.
problem Understanding and bounding the generalization gap of GANs.
method Theoretical proof using differential privacy, reinterpreting Bayesian GAN, membership attacks.
result Proven bounds on generalization gap and reduced information leakage.
Study finds macroeconomic indicators predict health workforce and infrastructure measures.
problem Evaluating the predictive value of macroeconomic indicators for public health targets.
method Examined multiple forecasting approaches including neural networks, generalized additive models, random forests, and time series models with exogenous indicators.
result Macroeconomic indicators provide consistent and reproducible predictive signals for health workforce and infrastructure measures, but less so for other targets.
ML4H workshop at NeurIPS 2018 focuses on health applications of machine learning.
problem Improving health outcomes through machine learning.
method Presented health applications and machine learning techniques.
result Demonstrated the potential of machine learning in healthcare.
Develops methods to measure and reduce fairness in datasets with limited protected attribute labels.
problem Measuring and reducing fairness in datasets with limited protected attribute labels.
method Proposes methods to estimate fairness metrics and train models to limit fairness violations using probabilistic protected attribute labels.
result Our methods provide tighter bounds on true disparity and effectively reduce fairness violations with lesser fairness-accuracy trade-offs.
Research uses Twitter data to identify health issues in gay users.
problem Lack of information on health issues of LGBTQ people.
method Collected and analyzed tweets from gay users on health topics.
result Identified 11 diseases in 7 categories.
The paper tackles fairness in classification by learning fair latent representations.
problem Fairness issues in classification algorithms used in societally critical domains.
method Develops a minimax adversarial framework to learn fair latent representations.
result The framework provides theoretical guarantees for statistical parity and individual fairness.
Proposes GLWB-LTC for enhanced life care annuities with dynamic withdrawal strategies and stochastic interest rates.
problem Improving life care annuity features and pricing methods.
method Introduces GLWB-LTC with dynamic withdrawal strategies and stochastic interest rates. Solves the stochastic control problem using a robust tree method.
result Optimal withdrawal strategies vary over time with policyholder's health status, highlighting the advantage of flexibility.
Proposes a method to balance fairness and utility in ranking models.
problem Systematic disparity across protected groups in ranking models.
method Model-agnostic post-processing framework using dynamic programming.
result Achieves a balance between fairness and utility across various metrics and datasets.
Community-based Question Answering (CQA) sites play an important role in addressing health information needs. However, a significant number of posted questions remain unanswered. Automatically answering the posted questions can provide a useful source of information for online health communities. In this study, we deve…
RENNs protect input privacy by rotating d-ary features.
problem Protecting input privacy from intermediate-layer features.
method Rotation-equivariant neural networks using d-ary vectors/tensors.
result RENNs effectively hide input information without degrading output accuracy.
Differential privacy protects data privacy by adding noise to data.
problem Leakage of sensitive data through common methods like encryption and endpoint protection.
method Randomized response technique to add noise to data collection.
result Differential privacy ensures strong privacy with better utility.
Paper proposes a new method to protect model information in multi-task learning.
problem Protecting model information in multi-task learning from adversaries.
method Proposes a privacy-preserving MTL framework using perturbation of the covariance matrix.
result Our algorithms outperform existing privacy-preserving MTL methods and STL methods.
Risk-based active learning improves SHM decision-making.
problem Lack of prior labels for structural health monitoring.
method Risk-based active learning approach to guide data labeling.
result Improves decision-maker's performance in SHM.
A flexible R package predicts air pollution levels from unmonitored areas.
problem Lack of ambient monitors for PM2.5 and other pollutants.
method Developed a flexible R package using H2O for spatio-temporal modeling.
result Predicts multiple pollutants including PM2.5 from unmonitored areas.
Mobile apps and machine learning improve malaria prevention and treatment.
problem High malaria cases and deaths in low-income countries.
method Adaptive interventions using mobile health apps and machine learning.
result Increased malaria testing, adherence, and provider skills.
New methods ensure fairness in noisy protected groups.
problem Noisy or biased protected group information complicates fairness audits.
method Robust optimization techniques to enforce fairness on true groups.
result Robust approaches achieve better true group fairness guarantees.
Two new algorithms protect distributed SGD from Byzantine attacks.
problem Byzantine attacks on distributed SGD in big data.
method Two asynchronous Byzantine tolerant SGD algorithms.
result The algorithms can handle arbitrary number of Byzantine attackers and are provably convergent.
Method identifies credible medical statements from online health communities.
problem Inaccuracies and misinformation in user-generated medical resources.
method Probabilistic graphical model using linguistic cues and expert supervision.
result Successfully extracts rare or unknown side-effects of medical drugs.
New method trains networks to avoid using protected concepts in decisions.
problem Avoiding use of protected concepts in neural network decisions.
method Domain-Adversarial Neural Network with gradient reversal layer.
result Trains networks to make decisions agnostic to protected concepts.
New method protects sensitive data in deep learning training.
problem Protecting sensitive data in deep learning training.
method Distributed layer-partitioned training with step-wise activation functions.
result Experimental results show the method is simple and effective.