Risk-stratify improves risk stratification for cardiovascular disease.
problem Accurately stratify patients for cardiovascular disease prognosis.
method Two-phase algorithm: tree partitioning followed by graph decomposition.
result Significant reduction in false discovery rate (33%) compared to state-of-the-art methods.
Hidden Markov model predicts sepsis progression stages.
problem Sepsis diagnostic criteria fail to account for patient heterogeneity.
method Introduced a hidden Markov model to account for heterogeneity.
result Model uncovers patient's latent sepsis trajectory.
Copula-based fusion improves breast cancer risk stratification.
problem Combining clinical and genomic risk scores using simple rules fails to capture their joint relationship.
method Used copulas to model the joint relationship between clinical and genomic risk scores.
result Copula-based fusion improves risk stratification, identifying subgroups with the worst prognosis.
Improved patient risk stratification with relaxed parameter sharing in clinical time-series data.
problem Learning time-varying relationships in clinical time-series data with limited training data.
method Proposed a novel RNN formulation based on a mixture model with relaxed parameter sharing over time.
result Relaxed parameter sharing leads to improved patient risk stratification performance in settings with limited data.
New method measures patient similarity over time, improving disease risk prediction.
problem Chronic diseases' varying progression rates and heterogeneous clinical presentations make patient comparison difficult.
method Subsequence alignment to account for pathophysiological misalignment and varying patient presentation times.
result Subsequence alignment outperforms global alignment in predicting disease progression.
New method improves prediction accuracy for low-risk patients in healthcare.
problem Machine learning models often focus on high-risk patients, ignoring low-risk ones.
method Proposed a new log-likelihood formulation to minimize proportional rate error.
result Improved prediction accuracy for low-risk patients in EHR data.
Clusters of ACS patients identified for better therapeutic stratification.
problem Data-driven classification and subtyping of ACS patients for improved treatment.
method Outcome-driven clustering using a multi-task neural network with attention.
result Seven patient clusters with distinct characteristics and risk profiles identified.
Deep learning model creates patient representations for scalable EHR-based stratification.
problem Challenges in summarizing and representing patient data from EHRs prevent scalable stratification analysis.
method Unsupervised framework based on deep learning (ConvAE) using word embeddings, CNNs, and autoencoders.
result ConvAE significantly outperformed baselines in clustering diverse patient cohorts, identifying clinically relevant subtypes.
ECG signal learning predicts cardiovascular death risk.
problem Scarce positive ECG event examples and class imbalance.
method Multiple instance learning framework for raw ECG signals.
result Learned risk score outperforms existing metrics.
Models predict patients at risk of uncontrolled hypertension.
problem Identifying patients at risk of uncontrolled hypertension.
method Developed machine learning models (logistic regression and recurrent neural networks) using EHR data.
result Best model achieved AUROC of 0.719, outperforming baseline.
New model detects postoperative complications early after surgery.
problem Early detection of postoperative complications in patients.
method Hidden Markov Model sequence classifier analyzing postoperative temperature sequences.
result Improved classification performance compared to other machine learning classifiers.
The paper defines and learns credible models that are both accurate and interpretable.
problem Models may be interpretable but lack credibility when their reasoning does not align with established knowledge.
method Formally defines credibility, proposes EYE penalty that incorporates expert knowledge.
result Models learned with EYE penalty are significantly more credible than those learned with other penalties.
Develops fair ASCVD risk models reducing group disparities.
problem Inconsistent performance of risk stratification models across race and gender groups.
method Adversarial learning and large observational cohort from EHRs.
result Reduced variability in error rates across groups.
Combines neural networks and logic circuits for interpretable, accurate, and cost-effective learning.
problem Lack of generalizability and interpretability in neural networks and high hardware cost in logic circuits.
method Trains a neural network, then translates it to random forests, and finally to AND-Inverter logic.
result The pipeline maintains greater accuracy and minimizes logic complexity.
Hidden stratification causes machine learning models to fail on rare but important patient subgroups.
problem Machine learning models fail on rare patient subgroups not identified during training or testing.
method Assessed techniques for measuring and describing hidden stratification effects on multiple medical imaging datasets.
result Evidence of hidden stratification leading to over 20% performance differences on clinically important subsets.
Study develops a dynamic risk model for COVID-19 mortality using UK Biobank data.
problem Developing tools to monitor high-risk patients during the COVID-19 pandemic.
method Data-driven random forest classification model using baseline characteristics and symptoms.
result Model predicts COVID-19 mortality with excellent performance (AUC: 0.91), identifying novel predictors.
DeepHeart predicts multiple medical conditions from wearable heart rate data.
problem Predicting multiple medical conditions from wearable heart rate data.
method Semi-supervised LSTM trained on 57,675 person-weeks of data.
result Semi-supervised sequence learning and heuristic pretraining outperform hand-engineered biomarkers.
New method tests risk measures for various distortions.
problem Testing risk measures for different distortions.
method Stratification and randomization of risk levels.
result Method performs well in numerical case studies.
New method improves compatibility of risk stratification models without sacrificing accuracy.
problem Compatibility issues arise when updating clinical machine learning models.
method Proposes rank-based compatibility measure and new loss function.
result Increased compatibility of models by 0.019 with no loss in discriminative performance.
A new method boosts survival analysis by stratifying patients and removing noise covariates.
problem Weak detection of treatment differences in randomized clinical trials due to patient heterogeneity.
method 5-Step Stratified Testing and Amalgamation Routine (5-STAR) using elastic net Cox regression and conditional inference trees.
result The 5-STAR routine significantly improves power in detecting treatment effects compared to traditional methods.
Deep learning predicts personalized drug responses from medical data.
problem Predicting personalized drug responses from medical data.
method Deep learning algorithms applied to large datasets.
result Deep learning improves prediction of personalized drug responses.
Study improves mortality prediction in hospital patients using comprehensive feature engineering.
problem Accurate prediction of all-cause in-hospital mortality in healthcare.
method Comprehensive feature engineering approach using vital signs, laboratory results, and demographic data.
result Random Forest model achieved highest performance with AUC of 0.94, significantly outperforming other models.
The paper offers simple, near-optimal algorithms for multi-group learning.
problem Learning predictors within subgroups of a population, addressing fairness and hidden stratification.
method Studies the structure of solutions and provides simple, near-optimal algorithms.
result Simple and near-optimal algorithms for multi-group learning.
Study predicts risk of true-lumen narrowing after ATAAD surgery using CT data.
problem Early post-surgery risk assessment for aortic dissection patients.
method Retrospective study with CT data, derived cross-sectional shapes, form factor (FF) for morphology assessment, linear discriminant analysis (LDA) for risk classification, LOPO-CV for prediction.
result Machine-learning model accurately predicts risk for all high-risk patients and low-risk patients, potentially reducing hospital visits.
Model predicts wound and episode-level readmission risk and time to re-admit.
problem Identify patients at high risk of re-admission to prevent wound recurrences and reduce healthcare costs.
method Data-driven analysis of wound care and episode-level patient data.
result Model achieves high recall and precision for predicting re-admission risk and time.
We develop a personalized real time risk scoring algorithm that provides timely and granular assessments for the clinical acuity of ward patients based on their (temporal) lab tests and vital signs. Heterogeneity of the patients population is captured via a hierarchical latent class model. The proposed algorithm aims t…
StageNet improves health risk prediction by integrating disease stage information.
problem Improving health risk prediction for patients with chronic conditions.
method StageNet uses a stage-aware LSTM and stage-adaptive convolutional modules to extract and integrate disease stage information.
result StageNet achieves up to 12% higher AUPRC for risk prediction and over 58% higher Calinski-Harabasz score for patient subtyping compared to state-of-the-art models.
We propose a new active learning algorithm for parametric linear regression with random design. We provide finite sample convergence guarantees for general distributions in the misspecified model. This is the first active learner for this setting that provably can improve over passive learning. Unlike other learning se…
In many healthcare settings, intuitive decision rules for risk stratification can help effective hospital resource allocation. This paper introduces a novel variant of decision tree algorithms that produces a chain of decisions, not a general tree. Our algorithm, α-Carving Decision Chain (ACDC), sequentially carves o…
We develop a neural network model to classify liver cancer patients into high-risk and low-risk groups using genomic data. Our approach provides a novel technique to classify big data sets using neural network models. We preprocess the data before training the neural network models. We first expand the data using wavel…
Machine learning detects NASH patients from medical claims data.
problem Detecting undiagnosed NASH patients for screening and management.
method Gradient-boosted decision trees trained on administrative medical claims data.
result Model precision for NASH detection is significantly higher than NASH incidence.
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.
Develops a risk score to assist ECMO planning for critically ill patients with viral or unspecified pneumonia.
problem Lack of a risk score to guide ECMO planning for critically ill patients.
method Leverages machine learning to develop the PEER score.
result PEER score predicts mortality and decompensation in patients eligible for ECMO.
SUBIC detects patient subgroups for personalized treatment of HTN in African-Americans.
problem Developing tailored treatment schemes for different patient subgroups.
method Supervised Biclustering using convex optimization.
result Identifies and prioritizes risk factors for HTN in African-Americans.
The paper shows how the timing of prediction impacts model performance in healthcare.
problem The timing of prediction affects model performance in healthcare.
method The paper compares two prediction schemes: outcome-dependent and outcome-independent.
result An outcome-independent scheme outperforms an outcome-dependent scheme.
Italy's daily COVID-19 cases stratified by age groups.
problem Analyzing the spread and impact of COVID-19 across different age groups.
method Stratified daily data of COVID-19 cases by age classes.
result Detailed insights into how age affects COVID-19 outcomes.
Deep learning model predicts severe COVID-19 outcomes.
problem Predicting severe COVID-19 outcomes in ED patients.
method Deep feature fusion model using EHR data and CXR images.
result CO-RISK score achieved AUC of 0.95 and 0.92 for 24 and 72 hours predictions, superior to human performance.
Study develops a predictive model to reduce hospital readmissions.
problem Inaccurate readmission risk prediction models in clinical settings.
method Used Genetic Algorithm and Greedy Ensemble to optimize a readmission risk prediction model.
result Developed a useful risk prediction model for reducing unplanned readmissions.
LMM predicts healthcare costs and risks with improved accuracy.
problem Wasteful healthcare spending and inefficiencies in risk prediction.
method Generative pre-trained transformer trained on patient event sequences.
result Improves cost prediction by 14.1% and chronic conditions prediction by 1.9%.
DBN improves sepsis mortality risk prediction in ICU patients.
problem Early sepsis detection in ICU patients with infection.
method Data-driven, semantically enhanced dynamic Bayesian network.
result DBN AUROC 0.91, outperforming other scoring tools.
Research uses activity analysis to identify mental health symptoms.
problem Identifying mental health symptoms using objective activity metrics.
method Proposes a framework for mHealth monitoring of psychiatric patients based on physical activity time series.
result Identifies distinct behavioural phenotypes and measures for mood assessment.
Machine learning predicts trauma patient mortality risk.
problem Predicting mortality risk in trauma patients using traditional regression models.
method Transfer learning-based machine learning algorithm applied to trauma patient data.
result Machine learning model achieved similar performance to contemporary models without restrictive criteria.
MetaPred uses meta-learning to improve clinical risk prediction from limited EHR data.
problem Clinical risk prediction from sparse patient EHR data.
method Meta-learning approach to train a meta-learner from related tasks, then fine-tune for target risk prediction.
result MetaPred achieves better performance for target risk prediction with limited data.
Framework predicts patient risk progression over time.
problem Predicting how patient risk changes over time.
method Supervised contrastive learning framework with embedding properties.
result Framework outperforms baselines in mortality and cognitive impairment datasets.
SAPSAM trains CNNs on lung CTs with binary labels, improving CPA detection and localization.
problem Chronic Pulmonary Aspergillosis (CPA) detection and localization on CT scans using binary labels.
method Binary labels, average intensity projections, 2D RGB-like images, hierarchical CNN architectures.
result High classification accuracy, precise localization, predictive power of 2-year survival.
Study predicts AKI risk in rehospitalized patients using EHR data.
problem Predicting AKI in rehospitalized patients to improve outcomes.
method Gradient boosting, logistic regression, and recurrent neural network trained on EHR data.
result Developed a risk score for AKI at hospital re-entry.
Generates synthetic health data from patient visits.
problem Lack of longitudinal, event-based medical data.
method Transformed longitudinal data into summary statistics, trained GAN.
result Synthetic data closely resembles real data univariately.
Study uses machine learning to predict heart failure in cancer patients.
problem Early detection of cancer patients at risk for cardiotoxicity.
method Examined four machine learning algorithms on 143,199 cancer patients.
result Gradient boosting model achieved best AUC score of 0.9077.