arXiv research

New model predicts ICU patient stays more accurately.

New model predicts ICU patients' stay duration efficiently.

With the improvement of medical data capturing, vast amount of continuous patient monitoring data, e.g., electrocardiogram (ECG), real-time vital signs and medications, become available for clinical decision support at intensive care units (ICUs). However, it becomes increasingly challenging to model such data, due to …

Research shows a significant increase in stay lengths for digital nomads in the U.S. during and after the pandemic.

A novel approach combines interpretability and performance in machine learning models.

When training clinical prediction models from electronic health records (EHRs), a key concern should be a model's ability to sustain performance over time when deployed, even as care practices, database systems, and population demographics evolve. Due to de-identification requirements, however, current experimental pra…

Monitoring patients in ICU is a challenging and high-cost task. Hence, predicting the condition of patients during their ICU stay can help provide better acute care and plan the hospital's resources. There has been continuous progress in machine learning research for ICU management, and most of this work has focused on…

Inpatient care is a large share of total health care spending, making analysis of inpatient utilization patterns an important part of understanding what drives health care spending growth. Common features of inpatient utilization measures include zero inflation, over-dispersion, and skewness, all of which complicate st…

While the volume of electronic health records (EHR) data continues to grow, it remains rare for hospital systems to capture dense physiological data streams, even in the data-rich intensive care unit setting. Instead, typical EHR records consist of sparse and irregularly observed multivariate time series, which are wel…

Though black-box predictors are state-of-the-art for many complex tasks, they often fail to properly quantify predictive uncertainty and may provide inappropriate predictions for unfamiliar data. Instead, we can learn more reliable models by letting them either output a prediction set or abstain when the uncertainty is…

Let $N$ be a complete manifold with bounded geometry, such that $\sec_N\le -σ< 0$ for some positive constant $σ$. We investigate the mean curvature flow of the graphs of smooth length-decreasing maps $f:\mathbb{R}^m\to N$. In this case, the solution exists for all times and the evolving submanifold stays the graph of a…

Acute kidney injury (AKI) commonly occurs in hospitalized patients and can lead to serious medical complications. In order to optimally predict AKI before it develops at any time during a hospital stay, we present a novel framework in which AKI is continually predicted automatically from EHR data over the entire hospit…

This study aims to predict vessel stay and delay times at ports to optimize logistics.

Proposes proactive bed requests to reduce ED boarding and patient wait times.

Study compares federated and centralized learning for patient data privacy.

Deep learning models (aka Deep Neural Networks) have revolutionized many fields including computer vision, natural language processing, speech recognition, and is being increasingly used in clinical healthcare applications. However, few works exist which have benchmarked the performance of the deep learning models with…

The paper studies the correlation of Hilbert lengths for convex projective surfaces.

Machine learning for healthcare often trains models on de-identified datasets with randomly-shifted calendar dates, ignoring the fact that data were generated under hospital operation practices that change over time. These changing practices induce definitive changes in observed data which confound evaluations which do…

We prove that the curvature flow of an embedded planar network of three curves connected through a triple junction, with fixed endpoints on the boundary of a given strictly convex domain, exists smooth until the lengths of the three curves stay far from zero. If this is the case for all times, then the evolution exists…

Health care is one of the most exciting frontiers in data mining and machine learning. Successful adoption of electronic health records (EHRs) created an explosion in digital clinical data available for analysis, but progress in machine learning for healthcare research has been difficult to measure because of the absen…

The use of machine learning systems to support decision making in healthcare raises questions as to what extent these systems may introduce or exacerbate disparities in care for historically underrepresented and mistreated groups, due to biases implicitly embedded in observational data in electronic health records. To …

The paper tackles distribution-free prediction intervals for multi-source data.

Progress of machine learning in critical care has been difficult to track, in part due to absence of public benchmarks. Other fields of research (such as computer vision and natural language processing) have established various competitions and public benchmarks. Recent availability of large clinical datasets has enabl…

Study predicts antimicrobial resistance in ICU patients quickly.

X-CAL improves survival model calibration without sacrificing predictive power.

Study finds little progress in medical machine learning benchmarks over 3 years.

Geodesic envelopes stay uniformly bounded in specific Teichmüller spaces.

We consider a regular embedded network composed by two curves, one of them closed, in a convex domain $Ω$. The two curves meet only in one point, forming angle of $120$ degrees. The non-closed curve has a fixed end point on $\partialΩ$. We study the evolution by curvature of this network. We show that the maximal exist…

Stratifying patients at risk for postoperative complications may facilitate timely and accurate workups and reduce the burden of adverse events on patients and the health system. Currently, a widely-used surgical risk calculator created by the American College of Surgeons, NSQIP, uses 21 preoperative covariates to asse…

Study evaluates approaches to improve worst-case model performance across patient subpopulations.

Recurrent neural networks and sequence to sequence models require a predetermined length for prediction output length. Our model addresses this by allowing the network to predict a variable length output in inference. A new loss function with a tailored gradient computation is developed that trades off prediction accur…

Acute Kidney Injury (AKI), a sudden decline in kidney function, is associated with increased mortality, morbidity, length of stay, and hospital cost. Since AKI is sometimes preventable, there is great interest in prediction. Most existing studies consider all patients and therefore restrict to features available in the…

Develops CPL for optimal prediction set length and validity.

DeepONets enhance spatial-temporal surrogates for structural dynamics.

Neural model predicts survival outcomes and reveals feature relationships.

The paper develops a method to predict ICU mortality risk across diverse patient populations.

Random curves on surfaces have predictable properties as they grow.

We analyse the structure of the distribution of eigenvalues of the stock market correlation matrix with increasing length of the time series representing the price changes. We use 100 highly-capitalized stocks from the American market and relate result to the corresponding ensemble of Wishart random matrices. It turns …

Artin-Tits groups act on a certain delta-hyperbolic complex, called the "additional length complex". For an element of the group, acting loxodromically on this complex is a property analogous to the property of being pseudo-Anosov for elements of mapping class groups. By analogy with a well-known conjecture about mappi…

This work challenges the assumption that shorter conformal prediction intervals are always better.

Projected random forests improve circular data prediction with adaptive arc length and finite-sample coverage.

The paper proves stability of critical points for conformally invariant Lagrangians.

Generative model predicts menstrual cycle lengths accounting for self-tracking artifacts.

Traditional methods for assessing illness severity and predicting in-hospital mortality among critically ill patients require time-consuming, error-prone calculations using static variable thresholds. These methods do not capitalize on the emerging availability of streaming electronic health record data or capture time…

Effective representation learning of electronic health records is a challenging task and is becoming more important as the availability of such data is becoming pervasive. The data contained in these records are irregular and contain multiple modalities such as notes, and medical codes. They are preempted by medical co…

Optimizing storage assignment is a central problem in warehousing. Past literature has shown the superiority of the Duration-of-Stay (DoS) method in assigning pallets, but the methodology requires perfect prior knowledge of DoS for each pallet, which is unknown and uncertain under realistic conditions. The dynamic natu…

Markov's theorem classifies the worst irrational numbers with respect to rational approximation and the indefinite binary quadratic forms whose values for integer arguments stay farthest away from zero. The main purpose of this paper is to present a new proof of Markov's theorem using hyperbolic geometry. The main ingr…

Opioid addiction is a severe public health threat in the U.S, causing massive deaths and many social problems. Accurate relapse prediction is of practical importance for recovering patients since relapse prediction promotes timely relapse preventions that help patients stay clean. In this paper, we introduce a Generati…