Proof connects Gittins indices to Bayesian upper confidence bounds for patient agents.
problem Connecting Gittins indices to Bayesian upper confidence bounds for patient agents.
method Proof using Gaussian multi-armed bandit problem with discount factor γ.
result Gittins index equals γ-quantile of posterior mean plus vanishing error term.
Study dynamic matching in heterogeneous networks using ODE model.
problem Dynamic matching in heterogeneous networks with compatibility restrictions.
method Introduced an ODE model to evaluate matching algorithms.
result Demonstrated trade-off between quick matching and optimal matching.
Model predicts HU response for sickle cell patients.
problem Predicting which sickle cell patients will respond to Hydroxyurea.
method Developed Deep Artificial Neural Network models.
result 92.6% accuracy in predicting HbF response.
Due to physiological variation, patients diagnosed with the same condition may exhibit divergent, but related, responses to the same treatments. Hidden Parameter Markov Decision Processes (HiP-MDPs) tackle this transfer-learning problem by embedding these tasks into a low-dimensional space. However, the original formul…
AI model identifies chemical agents in MCI with high accuracy.
problem Identifying chemical agents in mass casualty incidents.
method Reverse engineered signs/symptoms, trained using ANN, BDT, and WISER.
result WISER outperformed ANN and BDT in identifying chemical agents.
Machine learning predicts biologic therapy outcomes in psoriasis patients.
problem Predicting long-term biologic therapy outcomes in psoriasis patients.
method Machine learning algorithms were used to predict drug discontinuation and treatment duration.
result Machine learning models accurately predict outcomes with high diagnostic accuracy and low MAE.
We consider a reinforcement learning (RL) setting in which the agent interacts with a sequence of episodic MDPs. At the start of each episode the agent has access to some side-information or context that determines the dynamics of the MDP for that episode. Our setting is motivated by applications in healthcare where ba…
Privacy-preserving inference for clinical trials using differential privacy.
problem Balancing knowledge sharing and privacy in healthcare data.
method Differential privacy (DP) applied to log-linear belief updates in distributed settings.
result Differentially private, distributed inference methods outperform existing techniques.
Improves medication name inference for telemedicine and conversational agents.
problem Challenges in mapping user-friendly medication names to standardized ones.
method Entity-boosted two-tower neural network for ranking SMN to DMP.
result State-of-the-art results achieved with improved attention-based ranking.
Agent-based model compares different COVID-19 testing policies and their effectiveness.
problem Understanding how different testing policies reveal the true number of infected cases.
method Developed an agent-based simulation framework in Python to model various testing policies and interventions.
result Contact Tracing consistently captures more positive cases than Random Symptomatic Testing, and LBT performs similarly.
Deep reinforcement learning improves medical test suggestions.
problem Improving accuracy of disease diagnosis through better medical test recommendations.
method Formulated as a stage-wise Markov decision process, trained using reinforcement learning with a new action policy representation and exploration scheme.
result Significant improvement in disease diagnosis accuracy with better medical test suggestions.
Agent learns reward function from demonstrations in contextual MDPs.
problem Learn reward function from demonstrations in unseen contexts.
method Formulated as convex optimization, proposed algorithm computes subgradients.
result Zero-shot transfer demonstrated in dynamic treatment regime.
Objective: Anemia is a frequent comorbidity in hemodialysis patients that can be successfully treated by administering erythropoiesis-stimulating agents (ESAs). ESAs dosing is currently based on clinical protocols that often do not account for the high inter- and intra-individual variability in the patient's response. …
Develops new methods for risk-aware decision-making in medical bandits.
problem Risk-averse decision-making in medical contexts with limited data.
method Safe, anytime-valid concentration bounds, risk-aware contextual bandits, nonparametric algorithms.
result Improved decision-making algorithms for postoperative patient follow-up.
Improved forecasting of suicide attempts using LSGPs for patients with little data.
problem Challenges in predicting suicide attempts due to their rarity and patient heterogeneity.
method Introduced Latent Similarity Gaussian Processes (LSGPs) to capture patient heterogeneity.
result LSGPs outperform baseline models, even without kernel-design, and offer new insights into patient similarity.
Efficiently fine-tunes patient-independent seizure detection models with tensor kernel machine.
problem Improving seizure detection accuracy for wearable devices.
method Transfer learning with tensor kernel machine using canonical polyadic decomposition.
result Patient fine-tuned model achieves high performance with smaller model size.
Personalized models explain TB treatment outcomes considering patient context.
problem Heterogeneity in TB treatment outcomes due to co-morbidities.
method Multi-task learning approach encoding patient context into personalized models.
result Identifies anemia, age of onset, and HIV as influential for treatment efficacy.
Simulates patient pathways to detect delayed rare disease diagnoses.
problem Delayed rare disease diagnoses in France, causing health system and patient harm.
method Probabilistic modelling of patient pathways to create an alert system.
result Alert system detects and refers wandering patients to CRMRs.
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.
The paper presents a method to score patient engagement in care programs and predicts their response.
problem Improving health outcomes of high-need patients through better patient engagement.
method Data-driven behavioral engagement scoring pipeline for two aspects of patient engagement.
result The scoring method successfully predicts patient engagement and provides interpretable insights.
Study analyzes sensitivity of RL algorithm for ICU hemodynamic management.
problem Evaluating safety and reliability of RL in clinical settings.
method Sensitivity analysis of Duel-DDQN on ICU sepsis patients.
result RL policies are sensitive to various implementation factors.
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.
Currently, approximately 30% of epileptic patients treated with antiepileptic drugs (AEDs) remain resistant to treatment (known as refractory patients). This project seeks to understand the underlying similarities in refractory patients vs. other epileptic patients, identify features contributing to drug resistance acr…
System detects multiple patients' behaviors in real-time using mmWave radar and CNN.
problem Real-time patient behavior monitoring in hospitals.
method Used mmWave radar for tracking and collecting Doppler patterns. Created a three-layer CNN model for behavior classification.
result System achieved very good inference accuracy in predicting patient behaviors in real-time.
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.
In the modern healthcare system, rapidly expanding costs/complexity, the growing myriad of treatment options, and exploding information streams that often do not effectively reach the front lines hinder the ability to choose optimal treatment decisions over time. The goal in this paper is to develop a general purpose (…
Characterizing a patient's progression through stages of sepsis is critical for enabling risk stratification and adaptive, personalized treatment. However, commonly used sepsis diagnostic criteria fail to account for significant underlying heterogeneity, both between patients as well as over time in a single patient. W…
Proposes a deep learning framework for evaluating patient similarities from EHRs.
problem Evaluating clinical similarities between patients for various healthcare applications.
method A deep learning framework with medical concept embedding, preserving temporal information.
result Significant improvement in patient similarity evaluation over baselines.
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…
Longitudinal patient data has the potential to improve clinical risk stratification models for disease. However, chronic diseases that progress slowly over time are often heterogeneous in their clinical presentation. Patients may progress through disease stages at varying rates. This leads to pathophysiological misalig…
Study automates detection of visitation disruptions in ICU patients.
problem Difficulty in detecting frequent visitation disruptions in ICU patients.
method Used DensePose R-CNN model to count people in video frames, analyzed disruptions and patient outcomes.
result Automated method detects visitation disruptions, impacts on pain and length of stay examined.
Model predicts treatment initiation from clinical data using patient-clinician relations.
problem Predicting treatment initiation from clinical time series data considering patient-clinician relations.
method Graph-Augmented Time-Sensitive Model using top eigenvectors of graph Laplacian.
result Relational similarity improves prediction over baselines, e.g., 5% improvement in AUPRC.
A new model uses GPs and latent force models to predict patient responses to drugs.
problem Challenges in modeling short-term effects of drugs on patient physiology.
method Hybrid Gaussian process with latent force model for joint modeling of patient physiology and drug effects.
result The model accurately predicts patient responses to three common drugs, showing competitive performance.
Bayesian methods improve group testing for identifying infected patients.
problem Identifying infected patients from group testing results with false positives.
method Bayesian inference and belief propagation algorithm, combined with expectation-maximization method.
result True-positive rate improved by considering credible intervals.
Paper predicts IVF pregnancy rates from basic patient info.
problem Predicting IVF pregnancy rates from patient characteristics.
method Clustering patients into groups, then SVM models for each group.
result Support vector machine models achieve best overall performance.
This study uses bandit algorithms to predict Warfarin dosages more accurately.
problem Determining the correct initial Warfarin dosage is challenging due to patient variability and adverse effects.
method Developed and evaluated linear bandit algorithms on real data from PharmGKB.
result Proposed algorithms outperformed fixed-dose and clinical algorithms.
Model identifies key problems in HIV patients' records.
problem Complex and time-consuming task of identifying patient problems from electronic health records.
method Unsupervised phenotyping approach that jointly learns phenotypes from structured and unstructured data.
result Learned phenotypes and their relatedness are clinically valid and surpass existing methods.
Study develops electronic phenotypes of ICU patient acuity.
problem Limited time for patient acuity assessments and imprecise clinical trajectory prediction.
method Developed electronic phenotypes using automated variable retrieval in electronic health records.
result Identified three phenotypes: persistently stable, persistently unstable, and transitioning from unstable to stable.
Deep learning clusters patient time-series data for better prognosis.
problem Clustering time-series data for patient phenotyping and prognosis.
method Deep predictive clustering with novel loss functions for future outcome distribution.
result Model achieves superior clustering performance and identifies meaningful patient subgroups.
Over the past decades, both critical care and cancer care have improved substantially. Due to increased cancer-specific survival, we hypothesized that both the number of cancer patients admitted to the ICU and overall survival have increased since the millennium change. MIMIC-III, a freely accessible critical care data…
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.
Mild cognitive impairment (MCI) is a prodromal phase in the progression from normal aging to dementia, especially Alzheimers disease. Even though there is mild cognitive decline in MCI patients, they have normal overall cognition and thus is challenging to distinguish from normal aging. Using transcribed data obtained …
The paper tracks patient recovery using graphs of joint movement data.
problem Tracking individual patient recovery trajectories in physical therapy.
method Bayesian learning of Random Geometric Graphs from joint movement data.
result Optimal exercise routines can be recommended based on patient recovery data.
Enhances understanding of patient healthcare journeys using self-attention.
problem Capturing hidden dependencies in multi-level patient journey data.
method Proposes a multi-level self-attention network (MusaNet) for encoding patient journeys.
result MusaNet produces higher-quality representations than state-of-the-art methods.
Deep RL controls anesthesia more accurately than traditional methods.
problem Controlling the level of unconsciousness during anesthesia.
method Deep Reinforcement Learning (DRL) to map patient state to propofol dosage.
result Deep RL model outperformed traditional controllers (1.7% vs 3.4% median absolute performance error).
Paper proposes a new method for more accurate group testing of infected patients.
problem Identifying infected patients efficiently with reduced tests and corrected errors.
method Adaptive design of pools based on Bayesian posterior prediction using belief propagation algorithm.
result The proposed method results in more accurate identification of infected patients.
New model identifies patient-specific disease root causes.
problem Identifying root causes of complex diseases varying between patients.
method Generalized Root Causal Inference (GRCI) algorithm for heteroscedastic noise model.
result GRCI accurately extracts patient-specific root causes.
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.