A new method for brain tissue segmentation across medical centers using a smoothness prior.
problem Tissue segmentation challenges due to center-specific acquisition protocols.
method Developed a smoothness prior that is fit to segmentations from another medical center, integrated into an unsupervised Bayesian model.
result Segmentations are similarly smooth across centers, improving generalization.
Deep learning predicts readmissions from less structured data.
problem Predicting readmissions from non-standard, unstructured medical records.
method Proposes a deep learning architecture that handles less structured data, including Spanish text.
result Achieves AUROC of 0.76 on a Chilean medical dataset, comparable to US results.
BrainTorrent uses peer-to-peer FL for medical image segmentation without a central server.
problem Lack of sufficient annotated data for personalized medical models.
method Peer-to-peer federated learning framework without a central server.
result BrainTorrent outperforms traditional server-based FL and achieves similar performance to pooled data training.
A method for data encryption makes data look identical to humans but misleading to machine learning.
problem Data leakage in data sharing for medical purposes.
method Proposes a method inspired by adversarial attacks for data encryption.
result Encrypted data look identical to humans but misleading to machine learning methods.
Novel IRL method identifies suboptimal medical decisions in ICU data.
problem Identifying suboptimal medical decisions in clinical settings.
method Incorporates Inverse Reinforcement Learning with a pruning step to identify and remove suboptimal actions.
result Pruning step effectively identifies clinical priorities and values from suboptimal data.
New method generates diverse EHR data types while maintaining privacy.
problem Privacy risks in sharing EHRs across large scales.
method Refined GAN model, feature constraints, and utility measures.
result New model preserves EHR statistics, correlations, and constraints.
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.
MCU-Net combines U-Net and Monte Carlo Dropout for uncertainty in medical image segmentation.
problem Lack of uncertainty representation in deep learning methods for patient-centered healthcare decisions.
method MCU-Net framework using U-Net and Monte Carlo Dropout with four uncertainty metrics.
result MCU-Net maximizes automated performance and refers truly uncertain cases.
Paper proposes a human-algorithm approach to reduce medical device recall risk and workload.
problem High recall rate and regulatory workload in FDA's 510(k) pathway.
method Developed machine learning models to estimate recall risk and proposed a data-driven clearance policy.
result Conservative evaluation of policy shows a 32.9% improvement in recall rate and 40.5% reduction in workload.
Bayesian Federated Inference combines local data analyses to estimate regression models.
problem Estimating accurate parameters with limited data from different centers.
method Bayesian Federated Inference (BFI) for pooling local data analyses.
result Excellent performance of BFI methodology shown in real-life examples.
Bayesian Federated Inference improves survival model analysis without merging data.
problem Accurately estimating survival model parameters requires sufficient data and events, which is often lacking in practice.
method Bayesian Federated Inference (BFI) for survival models, where local centers perform analyses and combine results.
result Results from BFI are similar to those from merged data analyses, demonstrating excellent performance.
Bayesian Federated Inference improves statistical model estimation from multicenter data.
problem Combining data from different medical centers is challenging due to regulatory and logistic issues.
method Bayesian Federated Inference (BFI) framework for multicenter data.
result BFI framework infers additional features of the posterior parameter distribution, capturing more information than Federated Learning.
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…
X-Caps improves medical diagnosis explainability by encoding visual attributes in capsules.
problem Uninterpretable predictions from deep neural networks in healthcare.
method Teaches a novel multi-task capsule network to encode high-level visual attributes and malignancy scores.
result X-Caps outperforms state-of-the-art deep dense 3D CNNs in capturing visually interpretable attributes and malignancy prediction.
Adapts CNN for robust medical image segmentation across different scanners and protocols.
problem Performance degradation of CNNs in medical image segmentation due to mismatch between training and test images.
method Designs a segmentation CNN as a concatenation of a shallow normalization CNN and a deep CNN. At test time, adapts the normalization sub-network for each test image using a denoising autoencoder.
result Consistently improves performance on multi-center MRI datasets of brain, heart, and prostate.
This paper presents the first deep reinforcement learning (DRL) framework to estimate the optimal Dynamic Treatment Regimes from observational medical data. This framework is more flexible and adaptive for high dimensional action and state spaces than existing reinforcement learning methods to model real-life complexit…
Viewing the trajectory of a patient as a dynamical system, a recurrent neural network was developed to learn the course of patient encounters in the Pediatric Intensive Care Unit (PICU) of a major tertiary care center. Data extracted from Electronic Medical Records (EMR) of about 12000 patients who were admitted to the…
This paper introduces a deep-learning based efficient classifier for common dermatological conditions, aimed at people without easy access to skin specialists. We report approximately 80% accuracy, in a situation where primary care doctors have attained 57% success rate, according to recent literature. The rationale of…
Improves medication name inference for telemedicine and conversational agents.
problem Challenges in mapping user-friendly medication names to standardized ones.
method Entity-boosted two-tower neural network for ranking SMN to DMP.
result State-of-the-art results achieved with improved attention-based ranking.
Medical deconfounder uses EHRs to estimate treatment effects without confounders.
problem Bias in assessing treatment effects from EHRs due to unobserved confounders.
method Develops a machine learning algorithm (medical deconfounder) to adjust for confounders.
result Medical deconfounder produces more accurate treatment effect estimates and identifies effective medications.
Two large medical dialogue datasets for improving healthcare.
problem Improving healthcare through better dialogue systems.
method Building two large-scale medical dialogue datasets: MedDialog-EN and MedDialog-CN.
result The datasets are the largest medical dialogue datasets to date.
Proposes guidelines for developing medical AI products.
problem Lack of clear pathways for regulating medical AI.
method Statistical risk perspective and deep understanding of machine learning methodologies.
result Enhanced development of medical AI products and regulations.
Paper tackles medical question similarity using domain-relevant embeddings.
problem Identifying same-question pairs in medical contexts.
method Semi-supervised pre-training of a neural network on medical question-answer pairs.
result Our model achieves 82.6% accuracy on medical question similarity task.
Automated system extracts medication regimens from medical conversations.
problem Extract relevant medication information from medical conversations.
method QA task approach, combined QA and Information Extraction, data augmentation, public embeddings, pretraining.
result Improved accuracy in extracting dosage and frequency from 54.28 and 37.13 to 89.57 and 45.94.
Critically ill patients in regular wards are vulnerable to unanticipated clinical dete- rioration which requires timely transfer to the intensive care unit (ICU). To allow for risk scoring and patient monitoring in such a setting, we develop a novel Semi- Markov Switching Linear Gaussian Model (SSLGM) for the inpatient…
The study compares different scRNA sequencing methods using a high-dimensional dataset.
problem To identify unique characteristics of different scRNA sequencing methods.
method Quantitative comparison through clustering analysis of a high-dimensional dataset.
result Identifies unique characteristics associated with different scRNA sequencing methods.
MedGCN uses graph convolutional networks to recommend medications and estimate lab tests.
problem Automatically recommend medications and estimate lab tests for cost savings and better patient care.
method Integrates heterogeneous graph relations, learns node embeddings with graph convolutional networks, and uses cross regularization for multi-task learning.
result MedGCN outperforms state-of-the-art models in both medication recommendation and lab test imputation on real-world datasets.
The k-means++ algorithm is generalized by choosing the most distant point from the nearest center.
problem Improving the initialization of k-means clustering.
method Generalizing the center initialization process by selecting the most distant point from the nearest center.
result Choosing the most distant point from the nearest center achieves similar clustering quality to k-means++.
A new method centers outliers in robust PCA without manual intervention.
problem Outliers in robust PCA require manual centering, complicating the analysis.
method Introduces a 'bias trick' to automatically center non-outliers.
result First optimal RPCA algorithm with automatic centering.
A GMM-based method generates new 3D structures from medical images.
problem Generating new medical images from limited data and different modalities.
method Gaussian Mixture Model (GMM) for point-cloud generation.
result Generated point-clouds closely match training samples from the same class.
Strong baseline for medical imaging domain adaptation.
problem Improving generalization in medical imaging across different datasets.
method Training on diverse chest X-ray datasets.
result Empirical demonstration of model generalization to out-of-sample domains.
The medical field stands to see significant benefits from the recent advances in deep learning. Knowing the uncertainty in the decision made by any machine learning algorithm is of utmost importance for medical practitioners. This study demonstrates the utility of using Bayesian LSTMs for classification of medical time…
Center identified in stated skein algebra for quantum traces.
problem Understanding the center of the stated skein algebra.
method Analyzing the algebra as a generalization of Kauffman bracket skein algebra, focusing on the case when the quantum parameter is a root of unity.
result Simple description and dimension calculation of the center over the center module.
The object of our investigation is a point that gives the maximum value of a potential with a strictly decreasing radially symmetric kernel. It defines a center of a body in Rm. When we choose the Riesz kernel or the Poisson kernel as the kernel, such centers are called a radial center or an illuminating center, respec…
This paper benchmarks privacy-preserving machine learning on medical images.
problem Ensuring privacy in medical image analysis while maintaining model accuracy.
method Comparing Local-DP and DP-SGD for differential privacy in medical imagery.
result Theoretical privacy guarantees do not fully align with real-world performance.
Machine learning constructs problem-based medical records from electronic health records.
problem Difficulty in finding relevant medical information for clinical questions.
method Knowledge base completion using machine learning on electronic health records.
result Automatic construction of problem-based groupings of medications, procedures, and lab tests.
ME2Vec learns medical entity vectors from EHR data.
problem Learning structured information from EHR data.
method Graph-based medical entity embedding using diverse graph embedding techniques.
result ME2Vec outperforms baselines in disease diagnosis prediction.
Refines geometric center of mass analysis for Einstein field equations.
problem Analyzing the geometric center of mass of Willmore surfaces in initial data for Einstein field equations.
method Refined Lyapunov-Schmidt analysis to study geometric center of mass of area-constrained Willmore surfaces.
result The geometric center of mass agrees with the Hamiltonian center of mass under specific conditions.
Enhances medical code predictions for multi-morbidity patients using text classification.
problem Improving accuracy in predicting medical codes for patients with multiple illnesses.
method Used machine learning techniques, including multi-label medical text classification, to enhance predictions.
result High dimensional embeddings pre-trained on health data significantly improve multi-label classification performance.
Paper detects bias in AI medical models using CART.
problem Ensuring fairness in AI medical decision support systems.
method Uses Classification and Regression Trees (CART) algorithm to identify bias.
result Validated the CART approach in both synthetic and real-world data.
Inpatient2Vec learns representations for inpatients with multi-layer self-attention.
problem Lack of specialized RL methods for inpatient data with strong temporal relations and consistent diagnoses.
method Inpatient2Vec uses a multi-layer self-attention mechanism with two training tasks to learn medical activity, hospital day, and diagnosis representations for inpatients.
result Inpatient2Vec outperforms baselines on semantic similarity and clinical events prediction tasks.
Deep reinforcement learning improves medical test suggestions.
problem Improving accuracy of disease diagnosis through better medical test recommendations.
method Formulated as a stage-wise Markov decision process, trained using reinforcement learning with a new action policy representation and exploration scheme.
result Significant improvement in disease diagnosis accuracy with better medical test suggestions.
Let f:M->M be a partially hyperbolic diffeomorphism such that all of its center leaves are compact. We prove that Sullivan's example of a circle foliation that has arbitrary long leaves cannot be the center foliation of f. This is proved by thorough study of the accessible boundaries of the center-stable and the center…
We investigate centers of a body (the closure of a bounded open set) defined as maximum points of potentials. In particular, we study centers defined by the Riesz potential and by Poisson's integral. These centers, in general, depend on parameters and move with respect to the parameters. We give a necessary and suffici…
Diabetic eye disease is one of the fastest growing causes of preventable blindness. With the advent of anti-VEGF (vascular endothelial growth factor) therapies, it has become increasingly important to detect center-involved diabetic macular edema (ci-DME). However, center-involved diabetic macular edema is diagnosed us…
This study applies neural models to automatically recognize medical entities from natural language.
problem Automated recognition of medical entities from natural language is complex and time-consuming.
method Utilizes deep neural sequence models trained on a large dataset of death certificates.
result Deep neural models can efficiently recognize medical entities from natural language.
Survey of deep learning methods for medical anomaly detection.
problem Medical anomaly detection using machine learning.
method Thorough review of deep learning techniques across various medical domains.
result Comparison and contrast of deep learning models and their limitations.
We prove the existence of a center, or continuous selection of a point, in the relative interior of C1 embedded k-disks in Riemannian n-manifolds. If k≤3 the center can be made equivariant with respect to the isometries of the manifold, and under mild assumptions the same holds for k=4=n. By contrast, for…