Method predicts biomarker trajectories with uncertainty bands for Alzheimer's disease.
problem Uncertainty in biomarker predictions poses risks in clinical deployment.
method Conformal prediction for randomly-timed biomarker trajectories.
result Conformal bands achieve desired coverage and are tighter than baseline.
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.
Proposes a hybrid deep learning network for better heart failure survival prediction.
problem Improving survival prediction in heart failure patients.
method Joint analysis of cardiac motion features and clinical risk factors using a hybrid deep learning network.
result Optimal integration of clinical risk factors into deep prediction networks.
We explain increases in clinical risk predictions over time.
problem Tackling the challenge of explaining dynamic risk increases in clinical settings.
method Developed methods to extend static attribution techniques to dynamic settings, addressing challenges specific to time-series data.
result Identified and addressed challenges specific to dynamic risk estimation, improving clinical alert explanations.
New diagnostics detect variability in individual risk estimates from machine learning models in healthcare.
problem Variability in individual risk estimates from machine learning models in healthcare, leading to unreliable treatment decisions.
method Proposed evaluation framework using empirical prediction interval width and empirical decision flip rate diagnostics.
result Randomness in optimization and initialization can lead to substantial individual-level variability in risk estimates, affecting clinical decisions.
Deepr learns features from medical records to predict patient risk.
problem Feature engineering bottleneck in creating predictive systems from medical records.
method Transforms medical records into sequences, uses convolutional neural nets to detect and combine clinical motifs.
result Deepr achieves superior accuracy in predicting patient risk compared to traditional techniques.
Novel model improves clinical risk prediction by transferring knowledge between tasks over time.
problem Negative transfer in multi-task learning for clinical risk prediction.
method Temporal Probabilistic Asymmetric Multi-Task Learning (TPAMTL).
result Significantly outperforms various deep learning models for time-series prediction.
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.
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.
Natural language processing predicts AKI onset in ICU patients.
problem Early detection of AKI in ICU patients to improve outcomes.
method Clinical notes were processed to generate word and concept embeddings. Five classifiers and a deep learning model were used to predict AKI.
result The best model achieved an AUC of 0.779 for predicting AKI onset.
SAFER improves personalized treatment recommendations for dynamic clinical contexts.
problem Personalized treatment optimization in evolving clinical contexts with safety concerns.
method Integrates structured EHR and clinical notes, uses conformal prediction for safe recommendations.
result SAFER outperforms state-of-the-art baselines in recommendation metrics and mortality rates.
A new framework identifies subgroups with differential model performance in clinical risk prediction models.
problem Differential performance of AI/ML models across subgroups defined by multiple characteristics.
method unfairness tree (utree) framework for identifying subgroups with differential model performance.
result utree identifies subgroup-specific performance patterns in mortality risk models.
Improved model predicts ICU readmission and mortality with interpretable results.
problem Lack of clinically interpretable predictions from deep learning models on clinical notes.
method Augmented a convolutional model with an attention mechanism for clinical note prediction.
result Attention mechanism improves prediction performance while providing interpretable results.
The study develops multimodal models to predict 1-year mortality risk from large clinical datasets.
problem Limited datasets in biomedical studies that do not generalize over large heterogeneous datasets.
method Develops multimodal models using a massive clinical dataset of 25 million videos and 2.9 million ECG traces.
result Extremely low-parameter models with optimized feature selection achieve AUC of 0.89.
Hybrid Bayesian-conformal framework improves uncertainty quantification in healthcare predictions.
problem Jointly satisfying distribution-free coverage guarantees and risk-adaptive precision in clinical decision-making.
method Integrates Bayesian hierarchical random forests with group-aware conformal calibration, using posterior uncertainties to weight conformity scores.
result Achieves target coverage (94.3% vs 95% target) with adaptive precision, 21% narrower intervals for low-uncertainty cases.
Study evaluates how framing affects machine learning models for sepsis prediction.
problem Understanding and reporting framing is crucial for AI technology success.
method Four different approaches applied to AI models of sepsis prediction.
result On-clinical-demand framing showed the lowest missing values and best temporal dependencies.
Study develops models to predict severe COVID-19 progression.
problem Identifying high-risk individuals for severe COVID-19.
method Developed survival models using EHR data, learning clinical concepts to improve accuracy.
result Learned clinical concepts improve model performance, boosting C-index to 0.858.
New method stabilizes deep learning models for clinical risk prediction.
problem Stability issues in deep learning models for clinical risk prediction.
method Bootstrapping-based regularisation framework embedded in deep neural networks.
result Improved prediction stability across multiple datasets.
Develops fair clinical risk prediction models using counterfactual reasoning.
problem Addressing biases in clinical risk prediction models for underrepresented groups.
method Augmented counterfactual fairness criteria applied to electronic health records data.
result Demonstrates the feasibility of fair clinical risk prediction models using counterfactual inference.
Machine learning improves mortality prediction for elderly Medicare patients.
problem Improving mortality prediction for elderly Medicare patients using limited data.
method Developed and tested machine learning classifiers on Medicare claims data.
result Machine learning classifiers outperform logistic regression, especially with improved feature sets.
Study examines impact of fairness penalties on clinical risk prediction models.
problem Widespread health disparities in machine learning-guided clinical decision-making.
method Empirical study across multiple databases, outcomes, and sensitive attributes.
result Penalizing fairness violations nearly universally degrades model performance and fairness metrics.
Predictive models identify patients at risk of severe COVID-19.
problem Identifying patients at risk of severe COVID-19 to ease healthcare strain.
method Machine learning on routinely collected clinical data.
result Models predict positive SARS-CoV-2 tests, hospitalizations, and critical care with high accuracy.
Study creates a multimodal learning framework for CVD risk prediction.
problem Predicting cardiovascular disease risk in diverse populations.
method Combines cross modal transformers, graph neural networks, and causal representation learning.
result Model predicts personalized CVD risk with causal invariance across subpopulations.
Embeddings from EHR diagnoses and procedures predict heart failure risk.
problem Challenges in feature engineering from EHR data due to high dimensionality and heterogeneity.
method Used GloVe to learn word embeddings for diagnoses and procedures in UK EHR data.
result Embeddings enable robust disease risk prediction models for congestive heart failure.
FedRD improves risk difference estimation in federated learning for clinical outcomes.
problem Privacy-preserving model co-training in medical research is hindered by server-dependent architectures and focus on relative effect measures.
method FedRD is a server-independent, communication-efficient framework for federated risk difference estimation in distributed survival data.
result FedRD provides valid confidence intervals and hypothesis testing, and is asymptotically equivalent to pooled individual-level analysis.
New method integrates network knowledge for better clinical risk prediction and biomarker discovery.
problem Improving predictive ability and interpretability of biomarkers using molecular profiling data.
method Introduces a network-regularized sparse Logistic Regression framework with a new penalty term.
result Demonstrates improved performance in simulated and real data compared to existing methods.
Clinical models can be unstable, leading to unreliable predictions.
problem Stability of clinical prediction models developed using statistical or machine learning methods.
method Simulation and case studies of statistical and machine learning approaches to show instability in model predictions.
result Model instability often leads to miscalibration of predictions in new data.
The method learns to partition event time space for better prediction.
problem Improving event time prediction in clinical settings with limited data.
method Develops a method to learn cut points for partitioning event time space.
result Improved prediction performance on real-world datasets.
Paper develops machine learning algorithms to learn optimal integer weights for clinical risk scores.
problem Deriving optimal integer weights for clinical risk scores without computational burden.
method Flexible greedy optimization strategy to directly optimize a value function.
result Constructed an integer-weighted comorbidity score for measuring post-discharge mortality risk.
AdaCare learns health status from biomarkers across multiple time scales.
problem Lack of explicit extraction of historical biomarker variation and adaptability to diverse patient conditions.
method Scale-adaptive feature extraction and recalibration for interpretability.
result AdaCare achieves state-of-the-art prediction accuracy and provides interpretable results.
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.
DeepAISE predicts sepsis onset with high accuracy and low false alarms.
problem Early prediction of sepsis in ICU patients to improve clinical situational awareness.
method Recurrent neural survival model that combines clinical criteria and treatment policies.
result DeepAISE produces the most accurate predictions (AUC=0.90 and 0.87) and lowest false alarm rates (FAR=0.20 and 0.26) compared to baseline models.
SurvLatent ODE predicts VTE risk for cancer patients, outperforming current methods.
problem Predicting clinical outcomes from irregularly sampled EHR data with competing events.
method Neural ODE-based Recurrent Neural Networks (ODE-RNN) for flexible survival time estimation.
result SurvLatent ODE outperforms Khorana Risk scores for VTE risk prediction.
Method predicts ODX scores for breast cancer patients based on clinical data.
problem Predicting ODX scores for breast cancer patients to aid decision-making.
method Distributional random forest approach using 9 clinico-pathological characteristics.
result Correctly predicted 92% of low risk and 40.2% of high risk patients.
Predicting blood lactate levels helps manage ICU patients without invasive tests.
problem Predict blood lactate levels accurately in ICU patients without invasive tests.
method Defined a benchmark problem, evaluated different prediction algorithms, and investigated missing value imputation methods.
result Promising prediction results show the potential of machine learning in ICU care.
Develops a model to predict clinical deterioration in ICU patients.
problem Predicting clinical deterioration in critically ill patients.
method Semi-Markov Switching Linear Gaussian Model (SSLGM) with censored data.
result SSLGM significantly outperforms existing risk scores.
Deep learning predicts heart failure readmission from clinical notes.
problem Predicting and preventing heart failure readmission.
method Convolutional Neural Networks (CNN) trained on clinical notes.
result Deep learning models outperform traditional machine learning methods in readmission prediction.
This research improves uncertainty estimation for medical predictions, enhancing model trust and decision support.
problem Improving model uncertainty estimation for rare medical conditions.
method Developed and refined heuristics for selecting uncertainty estimation techniques, distinguishing them by clinical use-case. Also, compared ensembles vs. auto-encoders for detecting out-of-domain examples.
result Auto-encoders outperform ensembles in detecting out-of-domain examples, highlighting their importance for medical tabular data.
Bayesian logistic regression improves clinical risk prediction models over time.
problem Improving clinical risk prediction models after deployment to adapt to temporal shifts.
method Bayesian logistic regression (BLR) and Markov variant (MarBLR) for online recalibration and revision of prediction models.
result BLR and MarBLR consistently outperform static models and other online revision methods, improving average AUC and calibration index.
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.
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.
The study addresses under-coverage in conformal prediction for Alzheimer's disease biomarkers, especially in high-risk subgroups.
problem Under-coverage of prediction bands in conformal prediction for clinically important subgroups of Alzheimer's disease patients.
method Introduces a framework for auditing and repairing subgroup under-coverage, using mechanisms of rarity and tail-heaviness.
result The proposed corrections restore target coverage for nearly every high-risk subgroup across both cohorts and forecasters.
Proposes a copula-based filter for diabetes risk prediction.
problem Feature selection for robust and interpretable predictive modeling in medicine, especially for extreme patient strata.
method Copula-based supervised filter using Gumbel-copula implied upper-tail concordance score (lambda U).
result The proposed filter outperforms standard filters and provides clinically coherent predictors.
Study predicts antimicrobial resistance in ICU patients quickly.
problem Delayed AMR testing in ICU leads to suboptimal treatment.
method Developed predictive models using clinical and microbiological data.
result Machine learning models predict AMR with higher accuracy than naive model.
Extends nonlinear filtering to predictable jump times.
problem Filtering with jumps in both signal and observation, especially when jump times are known.
method Derive Kushner-Stratonovich and Zakai equations for predictable discontinuities.
result Extends classical nonlinear filtering results to a setting with predictable discontinuities.
Study uses ML to predict cancer patient mortality from FN onset.
problem Predicting mortality in cancer patients with FN to improve survival.
method Multi-domain machine learning models using HCUP data.
result Clinical diagnoses have highest predictive power for FN mortality.
Bayesian neural network improves ICU patient risk prediction and feature selection.
problem Predicting patient outcomes in ICU with limited interpretability.
method Sparse Bayesian neural network with feature selection.
result Model provides interpretable feature importance for mortality prediction.
System predicts HIV patients at risk of dropping out of care.
problem High non-adherence and dropout rates among HIV patients.
method Predictive machine learning model based on resource constraints, stability, and fairness.
result Model performs 3x better than baseline for clinical use and 2.3x better for city-wide use.