Model identifies urgent radiology reports with high accuracy.
problem Lack of annotated training data for text analysis.
method Self-supervised contextual language representation using BERT.
result Model achieved 97.0% precision, 93.3% recall, and 95.1% F-measure.
BiLSTM model improves NER and negation detection in radiological reports.
problem Automating medical information extraction from radiological reports.
method Bi-directional Long Short-Term Memory (BiLSTM) neural network architecture.
result BiLSTM outperforms traditional rule-based systems for NER and negation detection.
Logistic regression outperforms other models in radiology report classification.
problem Efficiently labeling radiology reports for model training.
method Simple machine learning models, including logistic regression, for binary and multiclass classification.
result Logistic regression binary classifier achieves above 0.9 average precision in unseen reports.
Infrastructure monitors AI/ML radiology models across multiple sites.
problem Monitoring and improving AI/ML radiology models across multiple sites.
method Interactive radiology reporting, centralized cloud system, post-marketing surveillance.
result Efficient monitoring and iterative development of AI/ML models without radiologist burden.
Deep learning method improves radiographic similarity detection.
problem Learning a distance metric for radiographs to capture radiological similarity.
method Deep convolutional neural networks (DCNs) learn a low-dimensional embedding with a distance metric for radiographs.
result The learned metric effectively distinguishes normal from abnormal radiographs.
Improved radiological abnormality detection using LSTM with time-modulated approach.
problem Detect radiological abnormalities in medical images using CNNs on individual exams.
method Used time-modulated LSTM to model entire sequence of radiographs, including reports.
result Improved detection of radiological abnormalities on chest x-rays.
Gaussian Processes outperform other models in estimating uncertainty for radiology report observation detection.
problem Uncertainty quantification in automatic data labelling for semi-supervised learning in clinical NLP.
method Investigation of uncertainty estimates from various predictive models using NLPP and MMPCL metrics.
result Gaussian Processes provide superior performance in quantifying uncertainty for radiology report observation detection.
Model uses unsupervised learning to classify medical reports with less labeled data.
problem Lack of labeled data for fine-grained disease classification in medical reports.
method Developed a pipeline combining an unsupervised encoder-language model and a supervised classifier model.
result Improved classification accuracy with less labeled data compared to previous methods.
Deep learning model predicts CXR findings from patient scans.
problem Insufficient radiologists for accurate CXR interpretation.
method Tagged 959k studies, trained deep learning model on 2M reports.
result Model performs similarly to radiologists on 12 findings.
Conformal Alignment ensures trustworthy outputs from foundation models.
problem Ensuring outputs from foundation models align with human values in high-stakes tasks.
method A framework that trains an alignment predictor using reference data to select trustworthy outputs.
result Conformal Alignment accurately identifies trustworthy outputs via lightweight training over moderate reference data.
CheXpert++ improves CheXpert's accuracy and usability for medical radiology reports.
problem Infeasibility of obtaining ground truth labels for medical data.
method BERT-based approximation of CheXpert, addressing speed, differentiability, and probabilistic output.
result Achieves 99.81% parity with CheXpert, significantly faster, differentiable, and probabilistic.
Large dataset study improves chest x-ray analysis.
problem Improving accuracy in recognizing thorax diseases from chest x-rays.
method Training and evaluating deep convolutional neural networks (CNNs) on a large dataset (473k images).
result DualNet architecture shows improved performance in recognizing chest x-ray findings.
Automated generation of medical reports from chest x-rays using expert annotations.
problem Generating long, unstructured text from medical images with context and consistency.
method First learn visually-informative medical concepts from raw reports, then use these concepts to auto-generate structured reports from images.
result Validation on OpenI dataset shows auto-generated reports are consistent with manual annotations.
Deep learning improves radiology image analysis.
problem Improving image analysis in radiology.
method Review and survey of deep learning applications in radiology.
result Deep learning algorithms match or exceed human performance in radiology tasks.
The paper introduces sanity tests to detect spurious correlations in AI-guided radiology systems.
problem Detecting when AI systems perform well on development data for the wrong reasons.
method Design and implementation of sanity tests to identify spurious correlations.
result Sanity tests can identify spurious correlations in AI-guided radiology systems.
The study explores statistical methods to interpret radiological models and identify key features.
problem Interpreting complex radiological models for clinical use.
method Exploration of statistical techniques to assess relationships between radiomic features.
result Identification of key relationships and features for improved interpretability.
Deep learning improves MRI analysis of MSK disorders.
problem Accurate and rapid analysis of musculoskeletal disorders from MRI scans.
method Convolutional neural networks (CNN) for automatic classification of knee abnormalities.
result Multi-view deep learning showed promising performance in classifying MSK abnormalities.
Model learns to focus on key areas of chest X-rays.
problem Detecting abnormalities in chest X-rays.
method Recurrent visual attention model using reinforcement learning.
result Model can focus on informative areas of X-rays.
Models extract relevant EHR snippets to aid radiologists in diagnosis.
problem Difficulty in identifying relevant patient record information for diagnosis.
method Distantly supervised transformer-based neural model for extractive summarization.
result Models yield better extractive summaries than unsupervised approaches.
Unified model identifies and locates thoracic abnormalities with limited annotations.
problem Accurate identification and localization of thoracic abnormalities require large annotated datasets, which are expensive to acquire.
method Unified model that simultaneously identifies and localizes abnormalities using limited location annotations.
result Unified model significantly outperforms baseline in classification and localization tasks.
Study improves deep learning chest X-ray models by incorporating lateral views.
problem Lack of lateral views in training datasets limits deep learning performance.
method Used PadChest dataset with multiple views to explore merging methods.
result Incorporating lateral views increases model performance for 32 labels.
Study proposes a multimodal model for cardiovascular risk prediction using EHRs.
problem Lack of comprehensive risk prediction from EHRs due to unstructured text.
method Proposes a multimodal BiLSTM model integrating structured and unstructured EHR data.
result Proposed BiLSTM model outperforms other DNN architectures in cardiovascular risk prediction.
MAMMO reduces radiologist workload by triaging mammograms, improving accuracy.
problem Reducing radiologist workload while maintaining diagnostic accuracy.
method Developed a clinical decision support system with a multi-task learning CNN and triage network.
result Reduced radiologist workload by 42.8% with improved overall diagnostic accuracy.
QC methods improve reliability of machine learning-based image segmentation.
problem Inaccuracies in machine learning algorithms limit their clinical applicability.
method Analysis and validation of QC approaches for automatic segmentation.
result Aggregation of uncertainty and Dice prediction methods improved segmentation reliability.
OptCS optimizes model selection after conformal inference, controlling FDR and power loss.
problem Challenges in model selection for conformal inference, especially when limited labeled data and many model choices are available.
method OptCS framework that allows valid statistical testing after flexible data-driven model optimization, using novel multiple testing procedures.
result Valid conformal p-values constructed despite substantial data reuse, maintaining FDR control.
CNNs trained on one hospital's x-rays perform poorly on x-rays from other hospitals.
problem Generalization of radiological deep learning models across different hospitals.
method Cross-sectional design using x-rays from three hospitals (NIH, Mount Sinai, Indiana).
result CNNs trained on one hospital's x-rays perform significantly worse on x-rays from other hospitals.
New models compare mammograms to improve cancer diagnosis.
problem Improving cancer diagnosis accuracy by comparing recent and prior mammograms.
method Proposed neural network models trained on over 665,000 pairs of images.
result Best model achieves AUC of 0.866 in predicting malignancy.
Study uses weak labels and visual attention networks to detect lung nodules in chest radiographs.
problem Automated detection of lung nodules in chest radiographs requires large amounts of manually annotated images.
method Proposes two network architectures: one using saliency maps and the other a recurrent attention model trained with reinforcement learning.
result Demonstrates promising nodule detection performance using weak labels and visual attention mechanisms.
Deep learning system detects hip fractures as well as radiologists.
problem Automatically identifying hip fractures from x-rays.
method Trained on 53,000 clinical x-rays, system achieves 0.994 ROC curve.
result Equivalent diagnostic performance to human radiologists.
CoroNet detects COVID-19 from chest X-rays with high accuracy.
problem Detecting COVID-19 from chest X-rays using limited testing kits.
method Proposes CoroNet, a deep neural network based on Xception architecture trained on a combined dataset of COVID-19 and pneumonia X-rays.
result CoroNet achieved an overall accuracy of 89.6% and precision/recall rates of 93%/98.2% for 4-class cases (COVID vs Pneumonia bacterial vs pneumonia viral vs normal).
CheXNet detects pneumonia from chest X-rays better than radiologists.
problem Detecting pneumonia from chest X-rays with high accuracy.
method 121-layer convolutional neural network trained on ChestX-ray14 dataset.
result CheXNet outperforms radiologists on F1 metric.
CLARA generates clinical reports from raw inputs, improving accuracy and efficiency.
problem Generating accurate and detailed clinical reports from raw inputs is time-consuming and error-prone.
method Interactive method that generates reports sentence by sentence based on doctors' anchor words and partially completed sentences.
result CLARA achieves significant improvements in report generation accuracy and efficiency.
New method prevents cherry-picking in machine learning reports.
problem Selection bias in reporting machine learning innovations.
method Post-reporting solution to verify bias using another set of results.
result False reports of innovation can be prevented even if no actual improvement exists.
Study classifies pathology reports using TF-IDF features and machine learning.
problem Classifying pathology reports for cancer surveillance and diagnostic workflow.
method Extracted TF-IDF features from pathology reports and classified them using SVM, XGBoost, and Logistic Regression.
result XGBoost achieved 92% accuracy in classifying pathology reports.
This study uses NLP to predict stock performance based on analyst reports.
problem Predicting stock performance using textual information from analyst reports.
method Natural language processing (NLP) and a customized BERT deep learning model for Chinese text.
result Strong positive sentiment in analyst reports increases excess return and intraday volatility, while strong negative sentiment increases volatility and trading volume but decreases excess return.
Deep learning model improves corporate distress prediction using text data.
problem Predicting corporate distress using only financial data is insufficient.
method Convolutional recurrent neural network trained on auditors' and managers' reports.
result Unstructured textual data significantly enhances distress prediction, especially for large firms.
Predictive policing models can be biased by differential crime reporting rates.
problem Bias in predictive policing models due to differential crime reporting.
method Simulation based on Bogotá, Colombia's victimization and crime reporting data.
result Differential crime reporting rates can lead to misallocation of police patrols.
Study improves risk evaluation timing with right-censored reporting delays.
problem Improving risk evaluation under short observation windows due to administrative censoring.
method Jointly models parametric hazards for event and reporting processes, uses Monte Carlo expectation-maximization algorithm, and proposes transfer-learning procedure.
result Improves accuracy of timely risk evaluation under administrative censoring.
Report assesses Edinburgh tram project's risk management.
problem Projects often exceed costs and timelines, underperforming intended benefits.
method Describes and evaluates risk assessment and management for the Edinburgh tram.
result Careful consideration of cost, schedule, and benefit risks is crucial for megaprojects.
Private anchors affect how information is communicated and can improve or distort transmission.
problem How private anchors influence strategic communication and information transmission.
method Analyzed a sender-receiver game with costly reports and privately observed anchors.
result Small positive reporting costs can lead to full revelation, even with zero costs.
Paper develops a BERT-based classifier to reduce pathology report annotation workload.
problem Manual annotation of pathology reports is labor-intensive and time-consuming.
method Developed an automatic text classifier using BERT and introduced a human-centric metric to identify low-confidence cases.
result The model reduces manual annotation workload by 80% to 98%.
Typically, operational risk losses are reported above a threshold. Fitting data reported above a constant threshold is a well known and studied problem. However, in practice, the losses are scaled for business and other factors before the fitting and thus the threshold is varying across the scaled data sample. A report…
Deep learning classifies railroad accident causes from narrative reports.
problem Classifying accident causes from narrative reports is challenging.
method Applied deep learning with word embeddings to classify accident causes.
result Deep learning accurately classifies accident causes from narratives and identifies inconsistencies.
New method protects whistleblowers from retaliation by ensuring their reports remain private.
problem Whistleblowers face retaliation, and current protections are insufficient.
method Formalizes protection against strong-adversary threat model as per-report (0,δ)-differential privacy, and provides a generic mechanism to reduce private auditing to private continual counting. result Demonstrates a reduction in selection error and improved utility over randomized response.
Sell-side analysts' reports explain 10% of stock returns, with income statement analyses most impactful.
problem The value of sell-side analysts' information in predicting stock returns.
method Analysis of large language model embeddings and Shapley value decomposition.
result Income statement analyses contribute most to explaining stock returns.
Deep learning predicts vascular disease from medical history.
problem Predicting high-risk vascular diseases from medical records.
method Medical History-based Prediction using Attention Network (MeHPAN) models.
result MeHPAN models outperform standard classification models.
Framework integrates financial and annual report data for better corporate credit ratings.
problem Lack of insights from non-financial data in credit rating models.
method Uses FinBERT to extract features from annual reports and combines them with financial data.
result Improves credit rating accuracy by 8-12%.
Paper uses LLMs to analyze annual reports for stock investment, improving efficiency.
problem Manual analysis of annual reports is time-consuming and requires expertise.
method Leverages Large Language Models to extract and analyze annual reports.
result Machine Learning model trained on LLM outputs outperforms S&P500 returns.