Study finds multi-task learning and pre-training can improve healthcare models on EHR data.
problem Improving model performance on diverse EHR tasks using multi-task learning.
method Examined multi-task learning across various EHR tasks and training schemes, using pre-training and fine-tuning.
result Significant gains in model performance achieved via multi-task pre-training and single-task fine-tuning.
MPVAA learns holistic patient representations from mixed healthcare data.
problem Learning personalized patient representations from heterogeneous healthcare data.
method Mixed Pooling Multi-View Attention Autoencoder (MPVAA) that integrates non-linear relationships among multiple data modalities.
result MPVAA generates more effective patient representations than state-of-the-art methods.
Unified model for multiple healthcare tasks using graph structure.
problem Multiple healthcare tasks with shared graph structure.
method Graph-Convolutional Network (GCN) with multiple variational autoencoders.
result Boosted performance across all tasks, outperforming state-of-the-art.
Study improves conformal prediction for EEG classification in healthcare, enhancing coverage.
problem Uncertainty quantification in clinical predictions, especially in distribution-shifted settings.
method Personalized calibration strategies to improve coverage of prediction sets.
result Coverage improved by over 20 percentage points with comparable prediction set sizes.
Unified framework for imputation and prediction in healthcare time series.
problem Time misalignment and data sparsity in healthcare time series.
method MAGIC (Multi-tAsk Gaussian Process for Imputation and Classification) using hierarchical multi-task Gaussian process and functional logistic regression.
result Superior predictive accuracy compared to existing methods in two healthcare applications.
Study identifies what healthcare tasks can and should be automated.
problem Undesired consequences of automation in healthcare.
method Quantitative analysis using machine learning models trained on practitioner and expert ratings.
result Developed an analytical tool (Automatability-Desirability Matrix) for policymakers and leaders.
Enhances understanding of patient healthcare journeys using self-attention.
problem Capturing hidden dependencies in multi-level patient journey data.
method Proposes a multi-level self-attention network (MusaNet) for encoding patient journeys.
result MusaNet produces higher-quality representations than state-of-the-art methods.
Study finds little progress in medical machine learning benchmarks over 3 years.
problem Lack of meaningful progress in medical machine learning benchmarks for structured healthcare data.
method Comprehensive review and meta-analysis of benchmarks in medical machine learning for structured data.
result Deep recurrent models perform only better than logistic regression on certain clinical prediction tasks.
New approach uses under-trained deep ensembles to learn from noisy labels.
problem Improper labelling hinders reliable generalization in supervised learning.
method Under-trained deep ensembles, each trained on a subset of data, combine to form better labels.
result Significant performance improvement in accuracy and kappa for noisy label tasks.
In this paper we present a method for the unsupervised clustering of high-dimensional binary data, with a special focus on electronic healthcare records. We present a robust and efficient heuristic to face this problem using tensor decomposition. We present the reasons why this approach is preferable for tasks such as …
Somed2Vec learns medical concept embeddings from SNOMED-CT, improving healthcare analytics.
problem Lack of effective vector representations for medical concepts in healthcare analytics.
method Graph-based representation learning using random walks and Poincaré embeddings on SNOMED-CT.
result Concept embeddings from SNOMED-CT significantly outperform state-of-the-art embeddings.
Deep learning models exhibit state-of-the-art performance for many predictive healthcare tasks using electronic health records (EHR) data, but these models typically require training data volume that exceeds the capacity of most healthcare systems. External resources such as medical ontologies are used to bridge the da…
A broad spectrum of data from different modalities are generated in the healthcare domain every day, including scalar data (e.g., clinical measures collected at hospitals), tensor data (e.g., neuroimages analyzed by research institutes), graph data (e.g., brain connectivity networks), and sequence data (e.g., digital f…
Developing reliable workload predictive models can affect many aspects of clinical decision making procedure. The primary challenge in healthcare systems is handling the demand uncertainty over the time. This issue becomes more critical for the healthcare facilities that provide service for chronic disease treatment be…
LogGENE uses log-cosh loss for deep learning in gene expression datasets, improving accuracy and interpretability.
problem Mining large gene expression datasets for reliable deep learning predictions.
method Develops a smooth alternative to check loss (log-cosh) for quantile regression in gene expression datasets.
result Achieves state-of-the-art performance in accuracy and provides robust uncertainty estimates.
Research predicts healthcare index movements using historical OHLC data.
problem Predicting the directional movement of healthcare indices based on historical data.
method Supervised classification task with a one-step-ahead rolling window, using a diverse feature set including OHLC ratios.
result Robust predictive performance with accuracy exceeding 0.8 and Matthews correlation coefficients above 0.6, highlighting the importance of nowcasting features.
DMIDAS improves long-term forecasting accuracy in healthcare and electricity data.
problem Challenging long-term forecasting accuracy and computational complexity.
method Smoothness regularization and mixed data sampling techniques integrated into NBEATS architecture.
result Improves prediction accuracy by 5% on long forecasting horizons (1000 timestamps) compared to state-of-the-art models.
Deep learning models (aka Deep Neural Networks) have revolutionized many fields including computer vision, natural language processing, speech recognition, and is being increasingly used in clinical healthcare applications. However, few works exist which have benchmarked the performance of the deep learning models with…
Novel framework for Bayesian neural networks incorporating task-specific constraints.
problem Task-specific constraints in supervised model deployment.
method Introduces Output-Constrained BNN (OC-BNN) framework.
result OC-BNNs effectively incorporate prior expert knowledge and desiderata like safety and fairness.
TAPER learns unified patient EHR representations for healthcare tasks.
problem Irregular and multimodal data in electronic health records.
method Transformer networks and BERT for embedding structured and unstructured data.
result TAPER model outperforms on mortality, readmission, and length of stay tasks.
Adding data can sometimes hurt model performance in multi-source healthcare tasks.
problem Identifying when adding more data helps or hinders model outcomes in multi-source healthcare tasks.
method Identified the Data Addition Dilemma, demonstrated empirically observed trade-offs, introduced distribution shift heuristics.
result Adding data can sometimes reduce model performance due to distribution shift.
MIMIC-Extract transforms EHR data for reproducible healthcare machine learning.
problem Lack of accessible, standardized healthcare data for machine learning.
method Open-source pipeline for converting raw EHR data into usable dataframes.
result Demonstrates utility through benchmark tasks and baseline results.
The Temporal Group LASSO is an example of a multi-task, regularized regression approach for the prediction of response variables that vary over time. The aim of this work is to introduce the reader to the concepts behind the Temporal Group LASSO and its related methods, as well as to the type of potential applications …
New findings show increased exploration needed in non-stationary RL tasks.
problem Task non-stationarity leads to conflicting goals in RL.
method Analyzes the trade-off between cumulative and simple regret in non-stationary environments.
result Increased exploration is necessary to balance CR and SR in non-stationary tasks.
Develops multi-task learning models for ordinal regression with heterogeneous data.
problem Tackling ordinal regression for heterogeneous, non-IID data.
method Sparse and deep multi-task learning approaches.
result Proposed MTOR models improve prediction performance.
Split learning improves deep learning in healthcare by sharing data.
problem Data scarcity in healthcare limits deep learning applications.
method Distributed learning approach for collaborative training of deep neural networks.
result Split learning outperformed non-collaborative methods in both binary and multi-label classification tasks.
Deep learning methods exhibit promising performance for predictive modeling in healthcare, but two important challenges remain: -Data insufficiency:Often in healthcare predictive modeling, the sample size is insufficient for deep learning methods to achieve satisfactory results. -Interpretation:The representations lear…
Framework for imputing time series data with uncertainty measures.
problem Handling missing values in time series data, especially in healthcare.
method Uncertainty-aware multivariate time series imputation framework.
result Selective imputation of less uncertain values improves downstream tasks.
auton-survival simplifies survival analysis for healthcare data.
problem Handling censored time-to-event data in healthcare.
method Open-source package for survival regression, adjustment, counterfactual estimation, phenotyping, and treatment effects.
result Demonstrates auton-survival's ability to support complex health and epidemiological questions.
Probabilistic ML improves healthcare data analysis.
problem Insufficient understanding and incomplete data in healthcare.
method Examination of probabilistic machine learning models for healthcare challenges.
result Probabilistic models enhance healthcare data analysis and model building.
This guide introduces machine learning for medical data analysis.
problem Handling large, complex datasets in healthcare.
method Explains common machine learning algorithms and tasks.
result Illustrates machine learning applications in healthcare.
Improves off-policy evaluation with imperfect annotations.
problem Limited dataset coverage for evaluating new policies.
method Doubly robust estimators combining IS and DM, incorporating counterfactual annotations.
result Using annotations within the DM component yields the most desirable theoretical results.
GPT-4 assesses its confidence in answering USMLE questions with and without feedback.
problem Understanding AI's performance in healthcare applications, especially in sensitive areas like medical education.
method Used a prompting technique to evaluate GPT-4's confidence scores before and after answering USMLE questions, categorized into with and without feedback.
result Feedback influences relative confidence but doesn't consistently increase or decrease it.
A statistical description and model of individual healthcare expenditures in the US has been developed for measuring value in healthcare. We find evidence that healthcare expenditures are quantifiable as an infusion-diffusion process, which can be thought of intuitively as a steady change in the intensity of treatment …
The rapid growth of Electronic Health Records (EHRs), as well as the accompanied opportunities in Data-Driven Healthcare (DDH), has been attracting widespread interests and attentions. Recent progress in the design and applications of deep learning methods has shown promising results and is forcing massive changes in h…
Representation learning improves EHR data for healthcare tasks.
problem Transforming EHR data into useful representations for machine learning.
method Deep learning and disentangling underlying factors from EHR data.
result Better representations improve machine learning performance in healthcare.
Paper analyzes uncertainty metrics in ensemble learning for healthcare AI.
problem Selecting appropriate uncertainty metrics for ensemble learners in healthcare AI.
method Rigorous analysis of two uncertainty metrics: ensemble mean and variance.
result Ensemble mean is preferable to ensemble variance for decision making in healthcare AI.
Big data analytics improves healthcare through early detection and quality life.
problem Limited access to healthcare data hinders evidence-based decision-making.
method Analysis of healthcare data using various tools and techniques.
result Big data analytics enhances healthcare quality and patient outcomes.
A new RL approach learns near-equivalent actions for healthcare decisions.
problem Finding optimal actions in healthcare settings where actions may be near-equivalent.
method Temporal difference learning with a near-greedy heuristic for action selection.
result The proposed algorithm discovers meaningful near-equivalent actions and converges well.
A new reinforcement learning method for medical decisions with limited data.
problem Learning high-performing policies from partially observed data in healthcare.
method Optimization objective that combines policy and generative model quality, suitable for batch off-policy settings.
result Demonstrated improved performance on synthetic and medical decision-making problems.
RETAIN model improves glucose forecasting for diabetics, offering both accuracy and interpretability.
problem Inability of deep learning models to interpret their predictions in healthcare.
method Two-level attention mechanism in a recurrent neural network (RETAIN) architecture.
result RETAIN model achieves comparable accuracy to LSTM and FCN models while being highly interpretable.
In this paper, a Wide Learning architecture is proposed that attempts to automate the feature engineering portion of the machine learning (ML) pipeline. Feature engineering is widely considered as the most time consuming and expert knowledge demanding portion of any ML task. The proposed feature recommendation approach…
Survey on securing ML for healthcare, addressing privacy and robustness issues.
problem Security and robustness challenges in healthcare ML/DL applications.
method Overview of security and privacy methods for ML in healthcare.
result Discussion of current research challenges and future directions.
Deep neural networks have shown promising results for various clinical prediction tasks. However, training deep networks such as those based on Recurrent Neural Networks (RNNs) requires large labeled data, significant hyper-parameter tuning effort and expertise, and high computational resources. In this work, we invest…
OPERA blends multiple OPE estimators to evaluate new policies offline.
problem Lack of reliable offline policy evaluation methods for new policies.
method Adaptive blending of multiple OPE estimators without explicit selection.
result Consistent and reliable policy evaluation framework for offline RL.
New bandit model for healthcare intervention planning.
problem Maximizing patient health with limited monitoring resources.
method Developed Collapsing Bandits model and derived optimal policies.
result 3-order-of-magnitude speedup in algorithm performance.
One of the main issues affecting the Italian NHS is the healthcare deficit: according to current agreements between the Italian State and its Regions, public funding of regional NHS is now limited to the amount of regional deficit and is subject to previous assessment of strict adherence to constraint on regional healt…
Study proposes BFEL framework for privacy-preserving FL in personalized healthcare.
problem Privacy and security concerns in traditional cloud-centric ML, especially in wearable devices.
method Develops a blockchain-enhanced federated edge learning (BFEL) framework based on FedCurv, incorporating fisher information matrix and public key encryption.
result Significant reduction in communication cost and high efficiency for federated training on non-iid and heterogeneous data.