BERT-XML automates ICD coding from EHR notes using BERT pretraining.
problem Manual ICD coding is time-consuming and expensive in hospitals.
method Trained a BERT model on EHR notes, adapting it for multi-label attention.
result First large-scale ICD-10 classification model using millions of EHR notes.
Deep learning predicts ICD codes with high accuracy for patient phenotyping.
problem Variability in ICD code assignment by coders.
method Deep learning model trained on demographics, lab results, and medications.
result Model predictions outperform coder assigned ICD codes in accuracy.
Reducing ICD-10 code granularity improves cost model accuracy and stability.
problem High-dimensional regression with ICD-10 codes leads to unstable coefficient estimates.
method Log-linear analytics approach to cost model regularization through diagnostic code merging.
result Reducing ICD-10 code granularity from 7 characters to 6 or fewer improves model interpretability and consistency.
Study uses multimodal machine learning to predict ICD-10 codes.
problem Improving accuracy and interpretability of ICD-10 code predictions.
method Developed separate models for text and tabular data, integrated using an ensemble method.
result Best-performing model achieved micro-F1 of 0.7633 and micro-AUC of 0.9541.
Learn embeddings from EHRs to predict ICD codes.
problem Predicting ICD codes from patient visits in EHRs.
method Deep neural network trained to predict ICD codes, capturing clinical information.
result Embeddings capture relevant clinical information and can be used in machine learning models.
Deep learning predicts procedures from diagnoses in EHRs.
problem Manual procedure coding is time-consuming and error-prone.
method Multi-label classification using distributed representations.
result Model outperforms existing methods with high recall.
Categorical Co-Frequency Analysis clusters diagnoses to predict hospital readmissions.
problem Predicting patients' risk of 30-day hospital readmission.
method Categorical Co-Frequency Analysis (CoFA) measures diagnosis similarity using random forests.
result Identified three groups of diagnoses with varying readmission risk.
Method augments CTNs for ICD coding with neural network imputation.
problem Time-consuming manual annotation of CTNs for ICD coding.
method Semi-self-supervised neural network imputation of clinical features.
result Data augmentation improves ICD coding performance significantly.
AI generates a sequence of death causes from hospital records.
problem Accurate death reporting for vital statistics and policy formulation.
method Neural machine translation models to generate causal chains, incorporating medical domain knowledge.
result Achieved 16.04 BLEU score for generating accurate causal chains.
Algorithm recovers causal graphs in presence of latent confounders and selection bias.
problem Recovering causal graphs in the presence of latent confounders and selection bias.
method Iterative causal discovery (ICD) algorithm that relies on causal Markov and faithfulness assumptions.
result Sound and complete algorithm that recovers the equivalence class of the underlying causal graph.
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.
Deep learning improves cancer report classification accuracy.
problem Automatically assigning ICD-O3 codes to cancer reports.
method State-of-the-art deep learning techniques, including hierarchical and flat models, with attention mechanisms.
result Best model achieves 90.3% accuracy on topography site assignment and 84.8% on morphology type assignment.
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.
Improved predictions for rare labels using neural networks and ontologies.
problem Long-tailed frequency distribution in multi-label prediction problems.
method Modified neural network output layer with a Bayesian network of sigmoids leveraging ontology relationships.
result Significant improvements in per-label AUROC and average precision for less common labels.
Personalized deep learning reduces inappropriate shocks in VA detection.
problem High inappropriate shock rate in traditional VA detection methods.
method Personalized deep learning framework using CNN for real-time VA detection and collaborative inference.
result 6.6% reduction in inappropriate shock rate compared to traditional methods.
Study finds AI can predict diverse cardiac and non-cardiac diagnoses from a single ECG.
problem Narrow focus of ECG analysis models for diverse medical conditions.
method Exploratory study using a single AI model to predict multiple ICD codes.
result Model achieved AUROC scores > 0.8 for 253 cardiac and 172 non-cardiac diagnoses.
Text2Node maps medical phrases to a taxonomy, overcoming coding standard limitations.
problem Limited data interchangeability between EHR systems due to different coding standards.
method Text2Node uses word and node embeddings, along with mapping functions, to generalize from limited training data.
result Text2Node achieves high accuracy in mapping phrases to a taxonomy, even for unseen concepts.
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.
Deep learning models outperform other methods on ICU patient data.
problem Benchmarking deep learning models on healthcare datasets.
method Used MIMIC-III dataset for mortality, length of stay, and ICD-9 code prediction tasks.
result Deep learning models consistently outperform other methods, especially with raw clinical data.
New method generates realistic synthetic healthcare datasets.
problem Creating datasets that mimic real healthcare records.
method Learning latent variable moments for binary datasets.
result Synthetic datasets are harder to distinguish from real ones.
Deep learning text embeddings improve fraud detection in healthcare insurance.
problem Improving fraud detection in healthcare insurance claims.
method Proposed deep learning architectures for text embeddings.
result Our approach outperforms other methods in detecting fraudulent claims.
Paper presents a novel k-means clustering method using two distance measures for Gaussian data.
problem Improving clustering accuracy and robustness for Gaussian data.
method Integrates within cluster distance (WCD) and inter cluster distance (ICD) into k-means clustering.
result The algorithm provides more accurate clustering and better handles outliers.
In this chapter we review the main literature related to kernel spectral clustering (KSC), an approach to clustering cast within a kernel-based optimization setting. KSC represents a least-squares support vector machine based formulation of spectral clustering described by a weighted kernel PCA objective. Just as in th…
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.
ASD-DiagNet uses fMRI data to improve ASD diagnosis accuracy.
problem Difficult diagnosis of Autism Spectrum Disorder (ASD) due to symptom observation.
method Hybrid learning approach combining autoencoder and single layer perceptron.
result Improved classification accuracy up to 80% with 20% increase over state-of-the-art methods.
Model predicts patient outcomes from EHR data by limiting feature interactions.
problem Predicting patient outcomes from noisy, missing EHR data.
method Recurrent neural network with feature interaction restriction.
result Improvement in AU-ROC for mortality prediction (1.1% improvement, p<0.01).
Improves biomedical entity linking with latent type modeling.
problem Lack of fine-grained type information for entity disambiguation.
method Jointly models entity disambiguation and latent type learning without direct supervision.
result Significant performance improvements over state-of-the-art techniques.
Develops deep learning for logical code segmentation.
problem Lack of logically segmented source code.
method Novel deep learning approach to generate logical code segments.
result Improves software analysis tasks like commenting, bug detection, and code synthesis.
Gauss codes help uniquely identify virtual doodles.
problem Identifying virtual doodles uniquely.
method Introduced left canonical Gauss codes.
result Oriented virtual doodles uniquely presented by left canonical Gauss codes.
TreeCaps improves code comprehension for software developers.
problem Processing code efficiently for software developers.
method Tree-based capsule networks for capturing code syntactical structures and dependencies.
result TreeCaps outperforms other approaches in classifying program functionalities.
Study re-evaluates MIMIC-III codes, finding many are under-coded.
problem Validity of MIMIC-III clinical codes is questionable.
method Open-source, reproducible methodology for assessing codes.
result Most frequently assigned codes are under-coded up to 35%
Paper proposes new gradient codes for robust distributed machine learning.
problem Robustness against slow machines (stragglers) in distributed machine learning.
method Constructs gradient codes based on probabilistic and Kronecker product methods.
result Gradient codes exist for a wide range of system parameters with comparable error performance.
Gradient coding improves distributed learning efficiency.
problem Mitigating straggler issues in distributed learning.
method Gradient coding using cyclic MDS codes and expander graphs.
result Approximate gradient codes enable faster convergence and less computation.
New model creates code semantics vectors for better understanding.
problem Improving code understanding and embedding quality.
method Siamese recurrent neural network on Python source code.
result Model significantly outperforms bag-of-tokens embeddings.
New quantum codes improve error correction with local tests.
problem Improving quantum error correction efficiency.
method Introducing hemicubic codes and exploiting their local testability.
result Quantum codes with improved local testability and error correction.
Deep-learning model detects ASD from MRI data with high accuracy.
problem Challenges in diagnosing ASD due to subjective behavioral assessments and informant biases.
method Integrates deep-learning and SVM techniques to classify ASD brain scans.
result Highly accurate classification of ASD brain scans from neurotypical scans.
Deepcode codes outperform traditional ones by 3 orders of magnitude.
problem Designing reliable codes for feedback channels with Gaussian noise.
method Integrating deep learning with information theory for novel codes.
result Deepcode codes outperform known codes by 3 orders of magnitude in reliability.
CoNCRA uses CNN to find code snippets matching developer intent.
problem Finding relevant code snippets using general search engines.
method Convolutional Neural Network approach to code retrieval.
result Improved code retrieval by 5% on average, top 3 positions 80% of the time.
Paper proposes graph-based separable transforms for video coding.
problem Improving video coding efficiency by better capturing residual block statistics.
method Derives graph-based separable transforms (GBSTs) from line graphs with weights determined by parameters.
result GBSTs achieve about 0.4% average coding gain over existing transforms in VVC.
Contrastive Code Representation Learning improves code summarization and type inference.
problem Code representations are sensitive to edits, hindering downstream semantic understanding tasks.
method ContraCode: a contrastive pre-training task that learns code functionality.
result Contrastive pre-training improves code summarization and type inference accuracy.
Adversarial attacks found to be effective on code models.
problem Adversarial robustness of code models.
method Instantiated adversarial attacks for code, demonstrated vulnerability, and improved robustness.
result Neural models for code are vulnerable to adversarial attacks.
Deep neural network predicts semantic labels for source code.
problem Difficulty in labeling and understanding new programming languages and functionalities.
method Language-agnostic deep convolutional neural network trained on Stack Overflow code snippets.
result Mean area under ROC of 0.957 and top-1 accuracy of 86.6% on Github code documents.
This work tackles runtime complexity prediction for code, using machine learning and a new dataset.
problem Predicting runtime complexity of code is hard and mathematically impossible.
method Modelled as a machine learning task, using feature engineering and code embeddings, with a new dataset.
result Achieved state-of-the-art results in runtime complexity prediction.
Transformer model improves source code summarization.
problem Generating readable summaries of source code.
method Transformer model with self-attention mechanism for code representation.
result Transformer model outperforms state-of-the-art techniques.
SLM models code syntax as trees to generate any programming language code.
problem Generating any piece of code in a given language without restrictions.
method Structural language modeling (SLM) decomposes code into ASTs and estimates probabilities over nodes.
result SLM model generates arbitrary code in any language, outperforming previous methods.
Investigates neural codes and their embeddings, proving conjectures and introducing new code types.
problem Analyzing neural codes and their embedding dimensions.
method Combinatorial, topological, and algebraic analysis; proving conjectures; introducing new neural code types.
result Proves conjectures about neural codes and their embeddings, introduces new code types.
Sparse coding approximates the data sample as a sparse linear combination of some basic codewords and uses the sparse codes as new presentations. In this paper, we investigate learning discriminative sparse codes by sparse coding in a semi-supervised manner, where only a few training samples are labeled. By using the m…
Gradient codes use block designs to resist adversarial stragglers in distributed computing.
problem Mitigating slow machines (stragglers) in distributed gradient-based methods.
method Gradient coding based on balanced incomplete block designs (BIBDs) to resist adversarial selection of stragglers.
result Adversarial stragglers have no advantage over random selection, and codes based on symmetric BIBDs maximize the adversarial threshold.