arXiv subjects

Ronald Moore

Publications and source records attributed to Ronald Moore.

6 recordsLinked to original sources

arXiv2024

Robust Meta-Model for Predicting the Need for Blood Transfusion in Non-traumatic ICU Patients

Objective: Blood transfusions, crucial in managing anemia and coagulopathy in ICU settings, require accurate prediction for effective resource allocation and patient risk assessment. However, existing clinical decision support systems have primarily targeted a particular patient demographic with unique medical conditions and focused on a single type of blood transfusion. This study aims to develop an advanced machine learning-based model to predict the probability of transfusion necessity over the next 24 hours for a diverse range of non-traumatic ICU patients. Methods: We conducted a retrospective cohort study on 72,072 adult non-traumatic ICU patients admitted to a high-volume US metropolitan academic hospital between 2016 and 2020. We developed a meta-learner and various machine learning models to serve as predictors, training them annually with four-year data and evaluating on the fifth, unseen year, iteratively over five years. Results: The experimental results revealed that the meta-model surpasses the other models in different development scenarios. It achieved notable performance metrics, including an Area Under the Receiver Operating Characteristic (AUROC) curve of 0.97, an accuracy rate of 0.93, and an F1-score of 0.89 in the best scenario. Conclusion: This study pioneers the use of machine learning models for predicting blood transfusion needs in a diverse cohort of critically ill patients. The findings of this evaluation confirm that our model not only predicts transfusion requirements effectively but also identifies key biomarkers for making transfusion decisions.

cs.LG↗

arXiv2023

Meta-learning in healthcare: A survey

As a subset of machine learning, meta-learning, or learning to learn, aims at improving the model's capabilities by employing prior knowledge and experience. A meta-learning paradigm can appropriately tackle the conventional challenges of traditional learning approaches, such as insufficient number of samples, domain shifts, and generalization. These unique characteristics position meta-learning as a suitable choice for developing influential solutions in various healthcare contexts, where the available data is often insufficient, and the data collection methodologies are different. This survey discusses meta-learning broad applications in the healthcare domain to provide insight into how and where it can address critical healthcare challenges. We first describe the theoretical foundations and pivotal methods of meta-learning. We then divide the employed meta-learning approaches in the healthcare domain into two main categories of multi/single-task learning and many/few-shot learning and survey the studies. Finally, we highlight the current challenges in meta-learning research, discuss the potential solutions, and provide future perspectives on meta-learning in healthcare.

cs.LG↗

arXiv2023

Transfer Learning for Causal Effect Estimation

We present a Transfer Causal Learning (TCL) framework when target and source domains share the same covariate/feature spaces, aiming to improve causal effect estimation accuracy in limited data. Limited data is very common in medical applications, where some rare medical conditions, such as sepsis, are of interest. Our proposed method, named \texttt{$\ell_1$-TCL}, incorporates $\ell_1$ regularized TL for nuisance models (e.g., propensity score model); the TL estimator of the nuisance parameters is plugged into downstream average causal/treatment effect estimators (e.g., inverse probability weighted estimator). We establish non-asymptotic recovery guarantees for the \texttt{$\ell_1$-TCL} with generalized linear model (GLM) under the sparsity assumption in the high-dimensional setting, and demonstrate the empirical benefits of \texttt{$\ell_1$-TCL} through extensive numerical simulation for GLM and recent neural network nuisance models. Our method is subsequently extended to real data and generates meaningful insights consistent with medical literature, a case where all baseline methods fail.

cs.LG↗

arXiv2022

ALRt: An Active Learning Framework for Irregularly Sampled Temporal Data

Sepsis is a deadly condition affecting many patients in the hospital. Recent studies have shown that patients diagnosed with sepsis have significant mortality and morbidity, resulting from the body's dysfunctional host response to infection. Clinicians often rely on the use of Sequential Organ Failure Assessment (SOFA), Systemic Inflammatory Response Syndrome (SIRS), and the Modified Early Warning Score (MEWS) to identify early signs of clinical deterioration requiring further work-up and treatment. However, many of these tools are manually computed and were not designed for automated computation. There have been different methods used for developing sepsis onset models, but many of these models must be trained on a sufficient number of patient observations in order to form accurate sepsis predictions. Additionally, the accurate annotation of patients with sepsis is a major ongoing challenge. In this paper, we propose the use of Active Learning Recurrent Neural Networks (ALRts) for short temporal horizons to improve the prediction of irregularly sampled temporal events such as sepsis. We show that an active learning RNN model trained on limited data can form robust sepsis predictions comparable to models using the entire training dataset.

cs.LG↗

arXiv2020

A Solar Magnetic-fan Flaring Arch Heated by Non-thermal Particles and Hot Plasma from an X-ray Jet Eruption

We have investigated an M1.3 limb flare, which develops as a magnetic loop/arch that fans out from an X-ray jet. Using Hinode/EIS, we found that the temperature increases with height to a value of over 10$^{7}$ K at the loop-top during the flare. The measured Doppler velocity (redshifts of 100$-$500 km s$^{-1}$) and the non-thermal velocity ($\geq$100 km s$^{-1}$) from Fe XXIV also increase with loop height. The electron density increases from $0.3\times10^{9}$ cm$^{-3}$ early in the flare rise to $1.3\times10^{9}$ cm$^{-3}$ after the flare peak. The 3-D structure of the loop derived with STEREO/EUVI indicates that the strong redshift in the loop-top region is due to upflowing plasma originating from the jet. Both hard X-ray and soft X-ray emission from RHESSI were only seen as footpoint brightenings during the impulsive phase of the flare, then, soft X-ray emission moves to the loop-top in the decay phase. Based on the temperature and density measurements and theoretical cooling models, the temperature evolution of the flare arch is consistent with impulsive heating during the jet eruption followed by conductive cooling via evaporation and minor prolonged heating in the top of the fan loop. Investigating the magnetic field topology and squashing factor map from SDO/HMI, we conclude that the observed magnetic-fan flaring arch is mostly heated from low atmospheric reconnection accompanying the jet ejection, instead of from reconnection above the arch as expected in the standard flare model.

astro-ph.SR↗

arXiv2019

Magnetic Flux Cancellation as the Trigger Mechanism of Solar Coronal Jets

Coronal jets are transient narrow features in the solar corona that originate from all regions of the solar disk: active regions, quiet sun, and coronal holes. Recent studies indicate that at least some coronal jets in quiet regions and coronal holes are driven by the eruption of a minifilament following flux cancellation at a magnetic neutral line. We have tested the veracity of that view by examining 60 random jets in quiet regions and coronal holes using multithermal (304 A, 171 A, 193 A, and 211 A) extreme ultraviolet (EUV) images from the Solar Dynamics Observatory (SDO)/Atmospheric Imaging Assembly (AIA) and line-of-sight magnetograms from the SDO/Helioseismic and Magnetic Imager (HMI). By examining the structure and changes in the magnetic field before, during, and after jet onset, we found that 85% of these jets resulted from a minifilament eruption triggered by flux cancellation at the neutral line. The 60 jets have a mean base diameter of 8800 +/- 3100 km and a mean duration of 9 +/-3.6 minutes. These observations confirm that minifilament eruption is the driver and magnetic flux cancellation is the primary trigger mechanism for most coronal hole and quiet region coronal jets.

astro-ph.SR↗