Study tackles database variability in medical data using ensemble models and CNNs.
problem Achieving robust generalization in machine learning models across multiple medical databases.
method Ensemble of local models based on convolutional neural networks (CNNs) and various data preprocessing techniques.
result Improved inter-database generalization performance and scalability of models.
Federated learning enables secure meta-analysis of large medical brain datasets.
problem Privacy and legal concerns prevent direct sharing of brain imaging data across different institutions.
method Developed a federated learning framework to securely access and analyze brain data from multiple databases.
result The framework successfully analyzed brain structural relationships across various diseases and cohorts.
This paper predicts registration error in medical images using a random regression forest.
problem Predicting registration error in medical images without a ground truth.
method Random regression forest trained on features related to transformation model and dissimilarity after registration.
result The method achieves good performance in automatic quality control of large-scale image analysis.
We propose using canonical correlation analysis (CCA) to generate features from sequences of medical billing codes. Applying this novel use of CCA to a database of medical billing codes for patients with diverticulitis, we first demonstrate that the CCA embeddings capture meaningful relationships among the codes. We th…
Eigenrank selects images for deep learning training and predicts segmentation failures.
problem Challenges in automating deep learning for medical image segmentation.
method Eigenrank selects images for training and predicts failures using Von Neumann information.
result U-Net trained on Eigenrank-selected images outperforms one trained on random images.
Paper tackles dataset bias in medical imaging studies, proposing a method to unlearn study membership.
problem Dataset bias limits model generalization across different medical imaging studies.
method Proposes a framework to unlearn study membership by transforming data to an intermediate space indistinguishable by study membership.
result Models learn general properties of etiology under study, not dataset-specific peculiarities.
Introduction. Case Based Reasoning (CBR) is an emerg- ing decision making paradigm in medical research where new cases are solved relying on previously solved similar cases. Usually, a database of solved cases is provided, and every case is described through a set of attributes (inputs) and a label (output). Extracting…
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.
ZiMM model predicts long-term blurry relapses from non-clinical claims data.
problem Predicting long-term blurry relapses after medical acts.
method Introduces ZiMM (Zero-inflated Mixture of Multinomial distributions) and a deep-learning architecture (ZiMM Encoder-Decoder) to learn from sparse, irregular patterns in claims data.
result ZiMM ED improves predictions over various baselines, including non-deep learning and deep-learning approaches.
Word embeddings are a popular approach to unsupervised learning of word relationships that are widely used in natural language processing. In this article, we present a new set of embeddings for medical concepts learned using an extremely large collection of multimodal medical data. Leaning on recent theoretical insigh…
Topology-based information retrieval improves query accuracy.
problem Query accuracy in databases with complex structures.
method Dilation-invariant comparative measures of persistent homology.
result Topology-based retrieval outperforms standard methods.
Paper proposes a new method to handle missing data in medical records using sequential variational autoencoders.
problem Missing data in medical records due to sensor off-times and uneven data collection.
method Sequential variational autoencoders (VAEs) with a new methodology called Shi-VAE.
result Shi-VAE achieves the best performance in terms of both metrics compared to state-of-the-art methods.
ChatGPT's medical response accuracy is 56%, but studies vary widely.
problem Lack of standard guidelines for evaluating ChatGPT's performance in medicine.
method Systematic review and meta-analysis of 17 studies.
result ChatGPT's overall integrated accuracy in medical queries is 56%.
There is a growing interest in using a longitudinal observational databases to detect drug safety signal. In this paper we present a novel method, which we used online during the OMOP Cup. We consider homogeneous ensembling, which is based on random re-sampling (known, also, as bagging) as a main innovation compared to…
Reliable microaneurysm detection in digital fundus images is still an open issue in medical image processing. We propose an ensemble-based framework to improve microaneurysm detection. Unlike the well-known approach of considering the output of multiple classifiers, we propose a combination of internal components of mi…
With the improvement of medical data capturing, vast amount of continuous patient monitoring data, e.g., electrocardiogram (ECG), real-time vital signs and medications, become available for clinical decision support at intensive care units (ICUs). However, it becomes increasingly challenging to model such data, due to …
Graph-based framework predicts ADR signals from clinical data.
problem Detecting ADRs in post-market surveillance using clinical data.
method Developed a Drug-disease graph with Graph Neural Network for ADR signal prediction.
result Improved AUROC and AUPRC performance (0.795 and 0.775) compared to other algorithms.
OMTL uses ontology to learn from imbalanced EHR data.
problem Imbalanced and small usable data for phenotypes in EHRs.
method Ontology-driven multi-task learning framework.
result Improved learning performance on phenotypes.
Project extends emotion recognition database and trains neural networks for categorical and dimensional emotions.
problem Understanding and recognizing emotions for human-computer interaction, safety, and medical research.
method Training CNN + RNN models with emotion category and valence/arousal representations, comparing three model types.
result Categorical emotion recognition performance improves with combined model training.
New method predicts Parkinson's using deep neural network latent info.
problem Medical diagnosis of Parkinson's disease.
method Transfer learning, k-means clustering, k-Nearest Neighbour classification of DNN representations.
result Improved prediction of Parkinson's disease based on MRI and DaT Scan data.
With the increased availability of large databases of electronic health records (EHRs) comes the chance of enhancing health risks screening. Most post-marketing detections of adverse drug reaction (ADR) rely on physicians' spontaneous reports, leading to under reporting. To take up this challenge, we develop a scalable…
This study interprets machine learning models to identify biomarkers for severe COVID-19 infection.
problem The black-box nature of machine learning models makes it difficult for medical researchers to understand and trust their predictions.
method The study uses permutation feature importance, Partial Dependence Plot, Individual Conditional Expectation, Accumulated Local Effects, Local Interpretable Model-agnostic Explanations, and Shapley Additive Explanation to interpret four machine learning models.
result The study identifies NTproBNP, CRP, LDH, LYM, leukocytes, eosinophils, and platelets as biomarkers associated with severe COVID-19 infection.
Privacy-preserving deep learning for clinical data across multiple sites.
problem Training deep neural networks on sensitive clinical data requires privacy protection.
method Distributed training with differential privacy to protect patient data.
result Proven privacy guarantees for training neural networks on clinical data.
MedCAT extracts valuable medical information from unstructured text.
problem Extracting structured information from unstructured biomedical documents.
method Unsupervised machine learning for disambiguation of entities.
result Improved entity detection and linking compared to existing tools.
Proposes DeepSDRF for continuous treatment recommendation from clinical survival data.
problem Continuous treatment recommendation in medical settings with survival data.
method Deep Survival Dose Response Function (DeepSDRF) for learning conditional average dose response (CADR) function.
result Similar performance of recommender algorithms based on random search and reinforcement learning.
A new method for deep multiple instance learning using self-attention.
problem Classifying bags of instances with dependencies.
method Introducing Self-Attention-based aggregation operation for bags of instances.
result SA-AbMILP outperforms other models in various datasets.
Hi-RES framework extracts medical relations from articles and EHRs.
problem Manual annotation bottleneck in relation extraction.
method Labeling sentences, creating improved negative samples, using pretrained language models, and combining EHR embeddings.
result Significant accuracy increases in relation extraction, up to 0.998 for disorder-location relations.
Bayesian method transfers knowledge between brain tumor datasets.
problem Applying deep learning to small medical datasets.
method Generative Bayesian Prior network for knowledge transfer.
result Best results in Dice Similarity Coefficient for BRATS2018.
Framework assesses treatment effects by risk groups in observational studies.
problem Evaluating treatment effects in observational studies with risk stratification.
method Five-step framework for risk-based assessment of treatment effect heterogeneity.
result Low-risk patients received negligible absolute benefits, while high-risk patients had pronounced effects.
Bayesian method transfers knowledge between brain tumor datasets for MRI segmentation.
problem Limited applicability of deep learning methods for small medical datasets.
method Generative Bayesian Prior network for knowledge transfer.
result Best results in Dice Similarity Coefficient metric for BRATS2018.
Deep neural network predicts ECG abnormalities from short-duration exams.
problem Improving accuracy of ECG diagnosis from short-duration exams.
method Residual neural network with 9 convolutional layers trained on large dataset.
result Model outperformed medical doctors on ECG abnormalities.
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…
A new model combines VAE and GAN for better anomaly detection in imbalanced datasets.
problem Anomaly detection in imbalanced datasets, especially in medical applications.
method β-VAEGAN model combining VAE and GAN, kernelized SVM for anomaly scores, and deviation from Gaussian prior.
result Improved F1 score from 0.85 to 0.92 on MITBIH Arrhythmia Database. Medical researchers are coming to appreciate that many diseases are in fact complex, heterogeneous syndromes composed of subpopulations that express different variants of a related complication. Time series data extracted from individual electronic health records (EHR) offer an exciting new way to study subtle differen…
We propose a network independent, hand-held system to translate and disambiguate foreign restaurant menu items in real-time. The system is based on the use of a portable multimedia device, such as a smartphones or a PDA. An accurate and fast translation is obtained using a Machine Translation engine and a context-speci…
In the scenario of real-time monitoring of hospital patients, high-quality inference of patients' health status using all information available from clinical covariates and lab tests is essential to enable successful medical interventions and improve patient outcomes. Developing a computational framework that can learn…
Due to advances in sensors, growing large and complex medical image data have the ability to visualize the pathological change in the cellular or even the molecular level or anatomical changes in tissues and organs. As a consequence, the medical images have the potential to enhance diagnosis of disease, prediction of c…
Health care is one of the most exciting frontiers in data mining and machine learning. Successful adoption of electronic health records (EHRs) created an explosion in digital clinical data available for analysis, but progress in machine learning for healthcare research has been difficult to measure because of the absen…
Deep learning predicts opioid use disorder risk in patients.
problem Identifying patients at high risk of opioid use disorder.
method Applied LSTM models to analyze electronic health records of opioid users.
result LSTM model outperformed other methods with F1 score of 0.8023 and AUCROC of 0.9369.
Proposes a VAE for HDLSS data augmentation.
problem Data augmentation in HDLSS settings with small sample sizes.
method Geometry-based variational autoencoder with latent space modeling.
result Significant improvement in classification metrics (e.g., balanced accuracy from 66.3% to 74.3%).
EKG-based models show better stability across patient populations than EHR-based models.
problem Model generalization issues in EHR and EKG-based predictive models.
method Two tests to measure model generalization, comparing EHR and EKG data.
result EKG-based models are more stable across different patient populations.
Deep RL controls anesthesia more accurately than traditional methods.
problem Controlling the level of unconsciousness during anesthesia.
method Deep Reinforcement Learning (DRL) to map patient state to propofol dosage.
result Deep RL model outperformed traditional controllers (1.7% vs 3.4% median absolute performance error).
Existing supervised approaches didn't make use of the low-level features which are actually effective to this task. And another deficiency is that they didn't consider the relation between pixels, which means effective features are not extracted. In this paper, we proposed a novel convolutional neural network which mak…
Aligns databases with Gaussian features using MAP estimation and thresholding.
problem Aligning databases with jointly Gaussian features.
method Two algorithms: MAP estimation and thresholding of log likelihood ratios.
result Conditions on mutual information for reliable performance of algorithms.
Machine learning detects metastatic breast cancer cases from linked EMR and cancer registry data.
problem Lack of metastatic recurrence data in cancer registries and EMRs.
method Semi-supervised machine learning on linked EMR and CCR data.
result Model achieved high accuracy in detecting metastatic breast cancer cases.
Study connects database alignment and planted matching using Gaussian features.
problem Identify matching between correlated user features in anonymized databases.
method Derived results for database alignment and planted matching, showing connections and thresholds.
result Performance thresholds for database alignment converge to planted matching when feature dimensionality is sufficiently high.
Objective: We investigate whether deep learning techniques for natural language processing (NLP) can be used efficiently for patient phenotyping. Patient phenotyping is a classification task for determining whether a patient has a medical condition, and is a crucial part of secondary analysis of healthcare data. We ass…
A2A metric evaluates bias correction methods, reducing ATE estimation errors.
problem Selection biases in non-randomized studies of medical treatments.
method Propensity score matching (PSM) with novel metric A2A.
result Reduces ATE estimation errors by up to 90% across synthetic and real-world datasets.