Deep learning improves skin disease diagnosis for primary care.
problem Limited dermatological expertise in primary care settings.
method Supervised deep learning for nine dermatological conditions.
result 80% accuracy compared to 57% by human doctors.
VAE detects skin disease anomalies with high accuracy.
problem Anomaly detection in skin disease images.
method Variational Autoencoder (VAE) for deep learning.
result 0.779 AUCROC overall, 0.864 for melanoma, 0.872 for actinic keratosis.
Study evaluates deep learning methods for dermatology, finding they perform poorly under non-ideal conditions.
problem Lack of robustness of deep learning methods in dermatology under real-world conditions.
method Simulated non-ideal conditions on user-submitted dermatology images.
result Deep learning methods show significant drop in accuracy and prediction changes under non-ideal conditions.
The paper investigates skin tone estimation and its impact on dermatology model performance.
problem The impact of skin tone on dermatology model performance is not well understood.
method The authors use individual typology angle (ITA) to estimate skin tone in dermatology datasets and analyze model performance.
result There is no measurable correlation between model performance and ITA values.
A hybrid deep learning model improves ESD diagnosis accuracy.
problem Automated diagnosis of Erythemato-Squamous Disease (ESD) is challenging.
method Proposes Derm2Vec, a hybrid model combining Autoencoders and Deep Neural Networks.
result Derm2Vec outperforms other methods in real-world dermatology dataset.
Discriminative neural networks address class imbalance in coronary heart disease risk analysis.
problem Class imbalance in medical test data, especially in binary classification problems.
method Use of discriminative neural networks and contrastive loss with a Siamese network structure.
result The method effectively handles class imbalance, improving predictive models for coronary heart disease risk.
BIN and CBN models infer health variables from symptoms and signals.
problem Inferring health variables from symptoms and signals.
method Bidirectional inference networks (BIN) and composite BIN (CBIN).
result CBIN achieves state-of-the-art performance and better accuracy.
Deep learning skin lesion classifier explained using CAVs.
problem Limited acceptance of deep learning CAD systems due to opaque decision-making.
method Mapped human understandable concepts to RECOD model using CAVs.
result Classifier learns and encodes disease-related concepts in its latent representation.
DPVis integrates HMMs into visualizations for disease progression analysis.
problem Challenges in interpreting HMMs for disease progression modeling.
method Design study with clinical experts, visualizations of HMM parameters and outcomes.
result DPVis successfully evaluates and summarizes disease progression models.
SS3M learns disease phenotypes from few labels.
problem Lack of supervised data for disease phenotyping.
method Semi-Supervised Mixed Membership Model (SS3M).
result SS3M learns interpretable disease phenotypes.
Bayesian hypergraph inference models disease pathways from EHR data.
problem Modeling rare diseases influenced by shared risk factors.
method Bayesian hypergraph inference framework reframing multi-disease modeling.
result Interpretable disease pathways and well-calibrated uncertainty quantification.
Model predicts disease progression by leveraging multi-resolution data.
problem Personalized prediction of disease trajectories.
method Hierarchical latent variable model sharing statistical strength across different resolutions.
result Significant improvements in predictive accuracy compared to state-of-the-art methods.
System recommends disease treatments based on big data and cloud computing.
problem Inaccurate disease classification and treatment recommendations due to complex symptoms and multi-pathogenesis.
method DPCA for disease-symptom clustering, Apriori for D-D and D-T rules, parallel Apache Spark implementation.
result Effective disease-symptom clustering and accurate treatment recommendations for inexperienced doctors.
Model learns disease self-representations for drug repositioning.
problem Drug repositioning for disease treatment.
method Enforces proximity in disease self-representations to preserve human phenome network structure.
result Method outperforms state-of-the-art approaches and produces biologically interpretable disease self-representations.
Bayesian model identifies health disparities in disease progression.
problem Health disparities bias disease progression models.
method Interpretable Bayesian model accounting for three disparities.
result Model identifies and corrects for health disparities.
DKT transfers biomarker information between neurodegenerative diseases.
problem Estimating biomarker trajectories in rare neurodegenerative diseases with limited data.
method DKT is a joint-disease generative model that transfers biomarker progressions from common neurodegenerative diseases to rare ones.
result DKT estimates plausible multimodal biomarker trajectories in rare diseases like PCA using only unimodal data.
FAA identifies rodent disease carriers for human health.
problem Identifying rodent species that carry zoonotic diseases.
method Applied Formal Concept Analysis to rodent trait data.
result Identified concepts linking rodent traits to zoonotic disease carrier status.
Paper uses GANs for efficient rare disease detection.
problem Efficient detection of rare diseases with limited labeled data.
method Semi-supervised learning with GANs.
result Best precision-recall scores compared to baseline techniques.
This research uses machine learning to identify Alzheimer's disease subtypes and predict progression.
problem Heterogeneity in Alzheimer's disease clinical manifestations and progression rate limit personalized care and treatment planning.
method Unsupervised and supervised machine learning approaches applied to ADNI data.
result Identification of patient subtypes and prediction of disease progression zones.
Bayesian meta-learning predicts Alzheimer's disease progression.
problem Predicting individual Alzheimer's disease progression from limited data.
method Bayesian meta-learning approach that dynamically predicts disease score distributions.
result Bayesian meta-learner outperforms single-task models and deterministic meta-learners, especially for long-term predictions.
VGAE learns gene-disease associations from networks, predicting disease-genes.
problem Predicting gene-disease associations from disease-gene networks.
method Introducing VGAE, a variational graph auto-encoder for disease-gene prediction.
result VGAE and C-VGAE outperform baseline methods in disease-gene prediction.
Elucidating the genetic basis of human diseases is a central goal of genetics and molecular biology. While traditional linkage analysis and modern high-throughput techniques often provide long lists of tens or hundreds of disease gene candidates, the identification of disease genes among the candidates remains time-con…
Discriminative EBM predicts Alzheimer's disease progression timeline more accurately.
problem Estimating the sequence of biomarker abnormalities in Alzheimer's disease.
method Discriminative event-based modeling (EBM) with a generalized Mallows model for central ordering and relative distance between events.
result The proposed method outperformed existing state-of-the-art EBM methods in ADNI and synthetic data.
Deep Belief Network predicts lncRNA-disease associations with high accuracy.
problem Accurately identifying lncRNA-disease associations to understand lncRNA functionality and disease mechanism.
method Proposes a DBN-based model using heterogeneous networks and DBN for feature learning.
result Obtained AUC of 0.96 and AUPR of 0.967 on standard dataset.
DTM learns disease trajectories from EHR data.
problem Understanding disease progression and clinical outcomes.
method Probabilistic model (DTM) using variational inference.
result DTM learns meaningful disease trajectories and their clinical associations.
Enhances disease progression modeling using LLMs for complex brain connectivity.
problem Inaccurate predictions of disease spread due to oversimplified brain connectivity models.
method Uses LLMs to synthesize multi-modal relationships and learn disease trajectories from longitudinal data.
result Superior prediction accuracy and interpretability compared to traditional methods.
Study uses news trends to predict infectious disease outbreaks.
problem Predicting infectious disease outbreaks using news reports.
method Supervised temporal topic models to transform news articles into trends.
result Temporal topic trends from disease news capture outbreak dynamics.
A method to explain disease transformation using biomarker covariance matrices.
problem Understanding disease transformation from a healthy baseline.
method Modeling healthy and disease states of biomarker covariance matrices to characterize perturbations.
result Disease perturbs the biomarker covariance structure, allowing for mechanistic explanations and individual patient prognosis.
Word2vec model captures disease attributes from unstructured text.
problem Augmenting disease surveillance with unstructured data requires accurate taxonomical correlations and trace mapping.
method Developed a disease vocabulary driven word2vec model (Dis2Vec) to model diseases and their attributes.
result Dis2Vec outperforms traditional word2vec methods in capturing taxonomical attributes across different disease classes.
Modeling disease progression in irregularly observed patients.
problem Irregular patient observation in healthcare databases.
method Continuous-time hidden Markov model with generalized linear model.
result Interpretable model of healthcare utilization events.
Medusa detects significant modules in diverse biological data, improving gene-disease association predictions.
problem Ignoring semantic meanings in data modeling limits the value of diverse biological data.
method Medusa combines collective matrix factorization with submodular optimization to detect significant modules.
result Medusa outperforms methods ignoring semantic meanings in predicting gene-disease associations.
Paper predicts multiple types of miRNA-disease associations using tensor decomposition.
problem Predicting miRNA-disease associations, especially multi-type ones.
method Represented miRNA-disease-type triplets as a tensor and used Tensor Decomposition methods.
result Tensor Decomposition methods improve a recent baseline by up to 38% in top-1 F1.
Paper uses TDA for automated Parkinson's disease classification and severity assessment.
problem Manual diagnosis of neurological diseases is time-consuming and inaccurate.
method Combines Topological Data Analysis (TDA) with machine learning on postural shift data.
result Proposes a stable and accurate method for classifying Parkinson's disease.
Proposes Ada-Sit method for mortality prediction of rare diseases.
problem Data insufficiency and clinical diversity of rare diseases make mortality prediction hard.
method Initialization-sharing multi-task learning method (Ada-Sit) for fast adaptation to similar tasks.
result Experimental results show the proposed model is effective for mortality prediction of diverse rare diseases.
Graph network predicts circRNA-disease associations using multi-source similarity features.
problem Identifying circRNA-disease associations is challenging and time-consuming.
method Proposes a graph convolution network framework using multi-source similarity information.
result Framework predicts circRNA-disease associations with promising results and outperforms existing methods.
Machine learning classifies medical notes into disease codes.
problem Automatically categorizing patient discharge notes into standard disease labels.
method Used Convolutional Neural Networks with Attention.
result Convolutional Neural Networks with Attention outperform previous methods.
Deep learning detects Crohn's disease in MRI images.
problem Detecting Crohn's disease in MRI images.
method Residual Networks for feature extraction and soft attention mechanisms for interpretability.
result Deep learning algorithms perform comparably to clinical standards with faster inference.
Deep learning improves forecasting of Alzheimer's disease trajectories.
problem Limitations of standard joint models in forecasting disease trajectories over time.
method Adopting a deep learning approach to enhance joint modeling flexibility and scalability.
result Improvements in performance and scalability compared to traditional methods.
Study uses mobile phone data to map Chagas disease risk zones.
problem Identifying geographical spread of Chagas disease.
method Analyzing geolocalized call records and public health information.
result Generated risk maps for public health campaigns.
Deep learning boosts rare disease detection from medical claims.
problem Improving diagnosis and treatment of rare diseases.
method Generative adversarial networks (GANs) and recurrent neural networks for sequence modeling.
result Accurate prediction with 0.56 PR-AUC, outperforming benchmarks.
Study compares machine learning and process-based models for predicting rice blast disease.
problem Predicting rice blast disease to support rice growers in controlling the disease.
method Compared four models: two process-based (Yoshino and WARM) and two machine learning (M5Rules and RNN).
result Machine learning models outperformed process-based models in predicting rice blast disease.
PASS model predicts disease progression with both accuracy and interpretability.
problem Balancing accurate disease prediction with clinically interpretable models.
method Phased LSTM units with attention mechanism for non-stationary state dynamics.
result PASS model achieves superior predictive accuracy and interpretable representations.
Paper proposes a new method for brain disease classification using connectome data.
problem Challenges in classifying brain diseases due to small sample size and high dimensionality.
method Simultaneous approximate diagonalization of adjacency matrices to compute stable eigenstructures.
result The method outperforms simple baselines and state-of-the-art approaches for Alzheimer's disease detection.
Graphical model predicts rare disease physicians, improving accuracy.
problem Identifying rare disease physicians from imbalanced patient data.
method Factor Graph Approach modeling physician and patient features.
result Graphical model outperforms existing targeting methodologies.
Model shows screening for infectious disease is hard but Thompson sampling works well.
problem Optimal screening policy for infectious diseases is hard to find.
method Stochastic-control model with Thompson sampling for optimal performance.
result Thompson sampling provides optimal performance guarantees in screening for infectious diseases.
Automated process links oral health to systemic conditions using machine learning.
problem Correlating oral health with systemic health conditions.
method Intraoral fluorescent biomarker imaging, machine learning segmentation, and clinical examination.
result Machine learning classifier achieved AUC of 0.677, indicating a learned association between disease signatures in images and periodontal disease.
WEST uses EHRs and expert cases to improve rare disease phenotyping.
problem Limited labeled data for rare diseases.
method Weakly supervised transformer model trained on probabilistic silver-standard labels.
result WEST outperforms existing methods in phenotype classification and subphenotyping.
Bayesian approach models neurodegenerative diseases without clinical labels.
problem Personalized, predictive modeling of neurodegenerative diseases.
method Probabilistic programmed deep kernel learning combining Gaussian processes and neural networks.
result Surpasses deep learning in accuracy and timeliness of predicting neurodegeneration.