Search

Optimizing Cox regression and its neural network variants poses substantial computational challenges in large-scale studies. Stochastic gradient descent (SGD), known for its scalability in model optimization, has recently been adapted to optimize Cox models. Unlike its conventional application, which typically targets a sum of independent individual loss, SGD for Cox models updates parameters based on the partial likelihood of a subset of data. Despite its empirical success, the theoretical foundation for optimizing Cox partial likelihood with SGD is largely underexplored. In this work, we demonstrate that the SGD estimator targets an objective function that is batch-size-dependent. We establish that the SGD estimator for the Cox neural network (Cox-NN) is consistent and achieves the optimal minimax convergence rate up to a polylogarithmic factor. For Cox regression, we further prove the $\sqrt{n}$-consistency and asymptotic normality of the SGD estimator, with variance depending on the batch size. Furthermore, we quantify the impact of batch size on Cox-NN training and its effect on the SGD estimator's asymptotic efficiency in Cox regression. These findings are validated by extensive numerical experiments and provide guidance for selecting batch sizes in SGD applications. Finally, we demonstrate the effectiveness of SGD in a real-world application where GD is unfeasible due to the large scale of data.

Extracting social determinants of health (SDoH) from unstructured medical notes depends heavily on labor-intensive annotations, which are typically task-specific, hampering reusability and limiting sharing. In this study we introduced SDoH-GPT, a simple and effective few-shot Large Language Model (LLM) method leveraging contrastive examples and concise instructions to extract SDoH without relying on extensive medical annotations or costly human intervention. It achieved tenfold and twentyfold reductions in time and cost respectively, and superior consistency with human annotators measured by Cohen's kappa of up to 0.92. The innovative combination of SDoH-GPT and XGBoost leverages the strengths of both, ensuring high accuracy and computational efficiency while consistently maintaining 0.90+ AUROC scores. Testing across three distinct datasets has confirmed its robustness and accuracy. This study highlights the potential of leveraging LLMs to revolutionize medical note classification, demonstrating their capability to achieve highly accurate classifications with significantly reduced time and cost.

Graph Neural Networks (GNNs) have attracted immense attention in the past decade due to their numerous real-world applications built around graph-structured data. On the other hand, Large Language Models (LLMs) with extensive pretrained knowledge and powerful semantic comprehension abilities have recently shown a remarkable ability to benefit applications using vision and text data. In this paper, we investigate how LLMs can be leveraged in a computationally efficient fashion to benefit rich graph-structured data, a modality relatively unexplored in LLM literature. Prior works in this area exploit LLMs to augment every node features in an ad-hoc fashion (not scalable for large graphs), use natural language to describe the complex structural information of graphs, or perform computationally expensive finetuning of LLMs in conjunction with GNNs. We propose E-LLaGNN (Efficient LLMs augmented GNNs), a framework with an on-demand LLM service that enriches message passing procedure of graph learning by enhancing a limited fraction of nodes from the graph. More specifically, E-LLaGNN relies on sampling high-quality neighborhoods using LLMs, followed by on-demand neighborhood feature enhancement using diverse prompts from our prompt catalog, and finally information aggregation using message passing from conventional GNN architectures. We explore several heuristics-based active node selection strategies to limit the computational and memory footprint of LLMs when handling millions of nodes. Through extensive experiments & ablation on popular graph benchmarks of varying scales (Cora, PubMed, ArXiv, & Products), we illustrate the effectiveness of our E-LLaGNN framework and reveal many interesting capabilities such as improved gradient flow in deep GNNs, LLM-free inference ability etc.

Male-dominated contexts pose a dilemma: they increase the benefits of repeated collaboration among women, yet at the same time, make such collaborations less likely. This paper seeks to understand the conditions that foster repeated collaboration among women versus men in male-dominated settings by examining the critical role of status hierarchies. Using collaboration data on 8,232,769 computer science research teams, we found that when a woman holds the top-ranking position in a steep status hierarchy, other women on that team are more likely than men to collaborate again, as compared to when the hierarchy is flat, and compared to when men occupy the top-ranking position. In steep hierarchies, top-ranking women but not top-ranking men foster conditions in which junior women are more likely to collaborate again than junior men of similar status levels. Our research suggests that whereas status hierarchies are especially detrimental to repeated collaboration among underrepresented individuals, top-ranking women in steep status hierarchies mitigate these negative impacts between women in male-dominated settings.

An important aspect of precision medicine focuses on characterizing diverse responses to treatment due to unique patient characteristics, also known as heterogeneous treatment effects (HTE), and identifying beneficial subgroups with enhanced treatment effects. Estimating HTE with right-censored data in observational studies remains challenging. In this paper, we propose a pseudo-outcome-based framework for analyzing HTE in survival data, which includes a list of meta-learners for estimating HTE, a variable importance metric for identifying predictive variables to HTE, and a data-adaptive procedure to select subgroups with enhanced treatment effects. We evaluate the finite sample performance of the framework under various settings of observational studies. Furthermore, we applied the proposed methods to analyze the treatment heterogeneity of a Written Asthma Action Plan (WAAP) on time-to-ED (Emergency Department) return due to asthma exacerbation using a large asthma electronic health records dataset with visit records expanded from pre- to post-COVID-19 pandemic. We identified vulnerable subgroups of patients with poorer asthma outcomes but enhanced benefits from WAAP and characterized patient profiles. Our research provides valuable insights for healthcare providers on the strategic distribution of WAAP, particularly during disruptive public health crises, ultimately improving the management and control of pediatric asthma.

Recent advancements in large language models (LLMs) have achieved promising performances across various applications. Nonetheless, the ongoing challenge of integrating long-tail knowledge continues to impede the seamless adoption of LLMs in specialized domains. In this work, we introduce DALK, a.k.a. Dynamic Co-Augmentation of LLMs and KG, to address this limitation and demonstrate its ability on studying Alzheimer's Disease (AD), a specialized sub-field in biomedicine and a global health priority. With a synergized framework of LLM and KG mutually enhancing each other, we first leverage LLM to construct an evolving AD-specific knowledge graph (KG) sourced from AD-related scientific literature, and then we utilize a coarse-to-fine sampling method with a novel self-aware knowledge retrieval approach to select appropriate knowledge from the KG to augment LLM inference capabilities. The experimental results, conducted on our constructed AD question answering (ADQA) benchmark, underscore the efficacy of DALK. Additionally, we perform a series of detailed analyses that can offer valuable insights and guidelines for the emerging topic of mutually enhancing KG and LLM. We will release the code and data at https://github.com/David-Li0406/DALK., Comment: Under Review; Incorrect author name revised

Data accuracy is essential for scientific research and policy development. The National Violent Death Reporting System (NVDRS) data is widely used for discovering the patterns and causes of death. Recent studies suggested the annotation inconsistencies within the NVDRS and the potential impact on erroneous suicide-cause attributions. We present an empirical Natural Language Processing (NLP) approach to detect annotation inconsistencies and adopt a cross-validation-like paradigm to identify problematic instances. We analyzed 267,804 suicide death incidents between 2003 and 2020 from the NVDRS. Our results showed that incorporating the target state's data into training the suicide-crisis classifier brought an increase of 5.4% to the F-1 score on the target state's test set and a decrease of 1.1% on other states' test set. To conclude, we demonstrated the annotation inconsistencies in NVDRS's death investigation notes, identified problematic instances, evaluated the effectiveness of correcting problematic instances, and eventually proposed an NLP improvement solution., Comment: 19 pages, 6 figures

We present the Thought Graph as a novel framework to support complex reasoning and use gene set analysis as an example to uncover semantic relationships between biological processes. Our framework stands out for its ability to provide a deeper understanding of gene sets, significantly surpassing GSEA by 40.28% and LLM baselines by 5.38% based on cosine similarity to human annotations. Our analysis further provides insights into future directions of biological processes naming, and implications for bioinformatics and precision medicine., Comment: 4 pages. Accepted by Web Conf 2024

Purpose: Limited studies exploring concrete methods or approaches to tackle and enhance model fairness in the radiology domain. Our proposed AI model utilizes supervised contrastive learning to minimize bias in CXR diagnosis. Materials and Methods: In this retrospective study, we evaluated our proposed method on two datasets: the Medical Imaging and Data Resource Center (MIDRC) dataset with 77,887 CXR images from 27,796 patients collected as of April 20, 2023 for COVID-19 diagnosis, and the NIH Chest X-ray (NIH-CXR) dataset with 112,120 CXR images from 30,805 patients collected between 1992 and 2015. In the NIH-CXR dataset, thoracic abnormalities include atelectasis, cardiomegaly, effusion, infiltration, mass, nodule, pneumonia, pneumothorax, consolidation, edema, emphysema, fibrosis, pleural thickening, or hernia. Our proposed method utilizes supervised contrastive learning with carefully selected positive and negative samples to generate fair image embeddings, which are fine-tuned for subsequent tasks to reduce bias in chest X-ray (CXR) diagnosis. We evaluated the methods using the marginal AUC difference ($\delta$ mAUC). Results: The proposed model showed a significant decrease in bias across all subgroups when compared to the baseline models, as evidenced by a paired T-test (p<0.0001). The $\delta$ mAUC obtained by our method were 0.0116 (95\% CI, 0.0110-0.0123), 0.2102 (95% CI, 0.2087-0.2118), and 0.1000 (95\% CI, 0.0988-0.1011) for sex, race, and age on MIDRC, and 0.0090 (95\% CI, 0.0082-0.0097) for sex and 0.0512 (95% CI, 0.0512-0.0532) for age on NIH-CXR, respectively. Conclusion: Employing supervised contrastive learning can mitigate bias in CXR diagnosis, addressing concerns of fairness and reliability in deep learning-based diagnostic methods., Comment: 23 pages, 5 figures

Scientific novelty is the essential driving force for research breakthroughs and innovation. However, little is known about how early-career scientists pursue novel research paths, and the gender disparities in this process. To address this research gap, this study investigates a comprehensive dataset of 279,424 doctoral theses in biomedical sciences authored by US Ph.D. graduates. Spanning from 1980 to 2016, the data originates from the ProQuest Dissertations & Theses Database. This study aims to shed light on Ph.D. students' pursuit of scientific novelty in their doctoral theses and assess gender-related differences in this process. Using a combinatorial approach and a pre-trained Bio-BERT model, we quantify the scientific novelty of doctoral theses based on bio-entities. Applying fractional logistic and quantile regression models, this study reveals a decreasing trend in scientific novelty over time and heterogeneous gender disparities in doctoral theses. Specifically, female students consistently exhibited lower scientific novelty levels than their male peers. When supervised by female advisors, students' theses are found to be less novel than those under male advisors. The significant interaction effect of female students and female advisors suggests that female advisors may amplify the gender disparity in scientific novelty. Moreover, heterogeneous gender disparities in scientific novelty are identified, with non-top-tier universities displaying more pronounced disparities, while the differences at higher percentile ranges were comparatively more minor. These findings indicate a potential underrepresentation of female scientists pursuing novel research during the early stages of their careers. Notably, the outcomes of this study hold significant policy implications for advancing the careers of female scientists.

Josephson tunneling in twisted cuprate junctions provides a litmus test for the pairing symmetry, which is fundamental for understanding the microscopic mechanism of high temperature superconductivity. This issue is rekindled by experimental advances in van der Waals stacking and the proposal of an emergent d+id-wave. So far, all experiments have been carried out on Bi$_2$Sr$_2$CaCu$_2$O$_{8+x}$ (Bi-2212) with double CuO$_2$ planes but show controversial results. Here, we investigate junctions made of Bi$_2$Sr$_{2-x}$La$_x$CuO$_{6+y}$ (Bi-2201) with single CuO$_2$ planes. Our on-site cold stacking technique ensures uncompromised crystalline quality and stoichiometry at the interface. Junctions with carefully calibrated twist angles around 45{\deg} show strong Josephson tunneling and conventional temperature dependence. Furthermore, we observe standard Fraunhofer diffraction patterns and integer Fiske steps in a junction with a twist angle of 45.0$\pm$0.2{\deg}. Together, these results pose strong constraints on the d or d+id-wave pairing and suggest an indispensable isotropic pairing component., Comment: 32 pages, 5 figures

Same-race mentorship preference refers to mentors or mentees forming connections significantly influenced by a shared race. Although racial diversity in science has been well-studied and linked to favorable outcomes, the extent and effects of same-race mentorship preferences remain largely underexplored. Here, we analyze 465,355 mentor-mentee pairs from more than 60 research areas over the last 70 years to investigate the effect of same-race mentorship preferences on mentees' academic performance and survival. We use causal inference and statistical matching to measure same-race mentorship preferences while accounting for racial demographic variations across institutions, time periods, and research fields. Our findings reveal a pervasive same-race mentorship propensity across races, fields, and universities of varying research intensity. We observe an increase in same-race mentorship propensity over the years, further reinforced inter-generationally within a mentorship lineage. This propensity is more pronounced for minorities (Asians, Blacks, and Hispanics). Our results reveal that mentees under the supervision of mentors with high same-race propensity experience significantly lower productivity, impact, and collaboration reach during and after training, ultimately leading to a 27.6% reduced likelihood of remaining in academia. In contrast, a mentorship approach devoid of racial propensity appears to offer the best prospects for academic performance and persistence. These findings underscore the importance of mentorship diversity for academic success and shed light on factors contributing to minority underrepresentation in science., Comment: 1. After further evaluating the race prediction method, we observed unsatisfactory accuracy and F1 scores. The study's findings could be impacted by these subpar predictions. 2. Our study incorporates both US and non-US samples, revealing that non-US samples may introduce outliers and distort the results. We recognize that the study's findings and conclusions might be affected by data quality

Pruning has emerged as a powerful technique for compressing deep neural networks, reducing memory usage and inference time without significantly affecting overall performance. However, the nuanced ways in which pruning impacts model behavior are not well understood, particularly for long-tailed, multi-label datasets commonly found in clinical settings. This knowledge gap could have dangerous implications when deploying a pruned model for diagnosis, where unexpected model behavior could impact patient well-being. To fill this gap, we perform the first analysis of pruning's effect on neural networks trained to diagnose thorax diseases from chest X-rays (CXRs). On two large CXR datasets, we examine which diseases are most affected by pruning and characterize class "forgettability" based on disease frequency and co-occurrence behavior. Further, we identify individual CXRs where uncompressed and heavily pruned models disagree, known as pruning-identified exemplars (PIEs), and conduct a human reader study to evaluate their unifying qualities. We find that radiologists perceive PIEs as having more label noise, lower image quality, and higher diagnosis difficulty. This work represents a first step toward understanding the impact of pruning on model behavior in deep long-tailed, multi-label medical image classification. All code, model weights, and data access instructions can be found at https://github.com/VITA-Group/PruneCXR., Comment: Early accepted to MICCAI 2023

Artificial Intelligence (AI), a cornerstone of 21st-century technology, has seen remarkable growth in China. In this paper, we examine China's AI development process, demonstrating that it is characterized by rapid learning and differentiation, surpassing the export-oriented growth propelled by Foreign Direct Investment seen in earlier Asian industrializers. Our data indicates that China currently leads the USA in the volume of AI-related research papers. However, when we delve into the quality of these papers based on specific metrics, the USA retains a slight edge. Nevertheless, the pace and scale of China's AI development remain noteworthy. We attribute China's accelerated AI progress to several factors, including global trends favoring open access to algorithms and research papers, contributions from China's broad diaspora and returnees, and relatively lax data protection policies. In the vein of our research, we have developed a novel measure for gauging China's imitation of US research. Our analysis shows that by 2018, the time lag between China and the USA in addressing AI research topics had evaporated. This finding suggests that China has effectively bridged a significant knowledge gap and could potentially be setting out on an independent research trajectory. While this study compares China and the USA exclusively, it's important to note that research collaborations between these two nations have resulted in more highly cited work than those produced by either country independently. This underscores the power of international cooperation in driving scientific progress in AI.

The aim of dynamic prediction is to provide individualized risk predictions over time, which are updated as new data become available. In pursuit of constructing a dynamic prediction model for a progressive eye disorder, age-related macular degeneration (AMD), we propose a time-dependent Cox survival neural network (tdCoxSNN) to predict its progression using longitudinal fundus images. tdCoxSNN builds upon the time-dependent Cox model by utilizing a neural network to capture the non-linear effect of time-dependent covariates on the survival outcome. Moreover, by concurrently integrating a convolutional neural network (CNN) with the survival network, tdCoxSNN can directly take longitudinal images as input. We evaluate and compare our proposed method with joint modeling and landmarking approaches through extensive simulations. We applied the proposed approach to two real datasets. One is a large AMD study, the Age-Related Eye Disease Study (AREDS), in which more than 50,000 fundus images were captured over a period of 12 years for more than 4,000 participants. Another is a public dataset of the primary biliary cirrhosis (PBC) disease, where multiple lab tests were longitudinally collected to predict the time-to-liver transplant. Our approach demonstrates commendable predictive performance in both simulation studies and the analysis of the two real datasets.

Leadership is evolving dynamically from an individual endeavor to shared efforts. This paper aims to advance our understanding of shared leadership in scientific teams. We define three kinds of leaders, junior (10-15), mid (15-20), and senior (20+) based on career age. By considering the combinations of any two leaders, we distinguish shared leadership as heterogeneous when leaders are in different age cohorts and homogeneous when leaders are in the same age cohort. Drawing on 1,845,351 CS, 254,039 Sociology, and 193,338 Business teams with two leaders in the OpenAlex dataset, we identify that heterogeneous shared leadership brings higher citation impact for teams than homogeneous shared leadership. Specifically, when junior leaders are paired with senior leaders, it significantly increases team citation ranking by 1-2%, in comparison with two leaders of similar age. We explore the patterns between homogeneous leaders and heterogeneous leaders from team scale, expertise composition, and knowledge recency perspectives. Compared with homogeneous leaders, heterogeneous leaders are more adaptive in large teams, have more diverse expertise, and trace both the newest and oldest references.

Background: The predictive Intensive Care Unit (ICU) scoring system plays an important role in ICU management because it predicts important outcomes, especially mortality. Many scoring systems have been developed and used in the ICU. These scoring systems are primarily based on the structured clinical data in the electronic health record (EHR), which may suffer the loss of important clinical information in the narratives and images. Methods: In this work, we build a deep learning based survival prediction model with multi-modality data to predict ICU mortality. Four sets of features are investigated: (1) physiological measurements of Simplified Acute Physiology Score (SAPS) II, (2) common thorax diseases pre-defined by radiologists, (3) BERT-based text representations, and (4) chest X-ray image features. We use the Medical Information Mart for Intensive Care IV (MIMIC-IV) dataset to evaluate the proposed model. Results: Our model achieves the average C-index of 0.7829 (95% confidence interval, 0.7620-0.8038), which substantially exceeds that of the baseline with SAPS-II features (0.7470 (0.7263-0.7676)). Ablation studies further demonstrate the contributions of pre-defined labels (2.00%), text features (2.44%), and image features (2.82%)., Comment: 21 pages, 5 figures, 7 tables

Graphs are omnipresent and GNNs are a powerful family of neural networks for learning over graphs. Despite their popularity, scaling GNNs either by deepening or widening suffers from prevalent issues of unhealthy gradients, over-smoothening, information squashing, which often lead to sub-standard performance. In this work, we are interested in exploring a principled way to scale GNNs capacity without deepening or widening, which can improve its performance across multiple small and large graphs. Motivated by the recent intriguing phenomenon of model soups, which suggest that fine-tuned weights of multiple large-language pre-trained models can be merged to a better minima, we argue to exploit the fundamentals of model soups to mitigate the aforementioned issues of memory bottleneck and trainability during GNNs scaling. More specifically, we propose not to deepen or widen current GNNs, but instead present a data-centric perspective of model soups tailored for GNNs, i.e., to build powerful GNNs. By dividing giant graph data, we build multiple independently and parallelly trained weaker GNNs (soup ingredient) without any intermediate communication, and combine their strength using a greedy interpolation soup procedure to achieve state-of-the-art performance. Compared to concurrent distributed GNN training works such as Jiong et. al. 2023, we train each soup ingredient by sampling different subgraphs per epoch and their respective sub-models are merged only after being fully trained (rather than intermediately so). Moreover, we provide a wide variety of model soup preparation techniques by leveraging state-of-the-art graph sampling and graph partitioning approaches that can handle large graphs. Codes are available at: \url{https://github.com/VITA-Group/graph_ladling}., Comment: Accepted in ICML 2023. Included comparison with a concurrent work (Jiong et. al. 2023) which independently presents similar ideas, among other SOTA distributed GNN training works

Large pre-trained transformers have been receiving explosive attention in the past few years, due to their wide adaptability for numerous downstream applications via fine-tuning, but their exponentially increasing parameter counts are becoming a primary hurdle to even just fine-tune them without industry-standard hardware. Recently, Lottery Ticket Hypothesis (LTH) and its variants, have been exploited to prune these large pre-trained models generating subnetworks that can achieve similar performance as their dense counterparts, but LTH pragmatism is enormously inhibited by repetitive full training and pruning routine of iterative magnitude pruning (IMP) which worsens with increasing model size. Motivated by the recent observations of model soups, which suggest that fine-tuned weights of multiple models can be merged to a better minima, we propose Instant Soup Pruning (ISP) to generate lottery ticket quality subnetworks, using a fraction of the original IMP cost by replacing the expensive intermediate pruning stages of IMP with computationally efficient weak mask generation and aggregation routine. More specifically, during the mask generation stage, ISP takes a small handful of iterations using varying training protocols and data subsets to generate many weak and noisy subnetworks, and superpose them to average out the noise creating a high-quality denoised subnetwork. Our extensive experiments and ablation on two popular large-scale pre-trained models: CLIP (unexplored in pruning till date) and BERT across multiple benchmark vision and language datasets validate the effectiveness of ISP compared to several state-of-the-art pruning methods. Codes are available at: \url{https://github.com/VITA-Group/instant_soup}, Comment: Accepted in ICML 2023

A human decision-maker benefits the most from an AI assistant that corrects for their biases. For problems such as generating interpretation of a radiology report given findings, a system predicting only highly likely outcomes may be less useful, where such outcomes are already obvious to the user. To alleviate biases in human decision-making, it is worth considering a broad differential diagnosis, going beyond the most likely options. We introduce a new task, "less likely brainstorming," that asks a model to generate outputs that humans think are relevant but less likely to happen. We explore the task in two settings: a brain MRI interpretation generation setting and an everyday commonsense reasoning setting. We found that a baseline approach of training with less likely hypotheses as targets generates outputs that humans evaluate as either likely or irrelevant nearly half of the time; standard MLE training is not effective. To tackle this problem, we propose a controlled text generation method that uses a novel contrastive learning strategy to encourage models to differentiate between generating likely and less likely outputs according to humans. We compare our method with several state-of-the-art controlled text generation models via automatic and human evaluations and show that our models' capability of generating less likely outputs is improved., Comment: Accepted to ACL (Findings) 2023

Large pre-trained language models (LLMs) have been shown to have significant potential in few-shot learning across various fields, even with minimal training data. However, their ability to generalize to unseen tasks in more complex fields, such as biology, has yet to be fully evaluated. LLMs can offer a promising alternative approach for biological inference, particularly in cases where structured data and sample size are limited, by extracting prior knowledge from text corpora. Our proposed few-shot learning approach uses LLMs to predict the synergy of drug pairs in rare tissues that lack structured data and features. Our experiments, which involved seven rare tissues from different cancer types, demonstrated that the LLM-based prediction model achieved significant accuracy with very few or zero samples. Our proposed model, the CancerGPT (with $\sim$ 124M parameters), was even comparable to the larger fine-tuned GPT-3 model (with $\sim$ 175B parameters). Our research is the first to tackle drug pair synergy prediction in rare tissues with limited data. We are also the first to utilize an LLM-based prediction model for biological reaction prediction tasks.

The COVID 19 pandemic has paused many ongoing research projects and unified researchers' attention to focus on COVID 19 related issues. Our project traces 712294 scientists' publications related to COVID 19 for two years, from January 2020 to December 2021, to detect the dynamic evolution patterns of the COVID 19 collaboration network over time. By studying the collaboration network of COVID 19 scientists, we observe how a new scientific community has been built in preparation for a sudden shock. The number of newcomers grows incrementally, and the connectivity of the collaboration network shifts from loose to tight promptly. Even though every scientist has an equal opportunity to start a study, collaboration disparity still exists. Following the scale-free distribution, only a few top authors are highly connected with other authors. These top authors are more likely to attract newcomers and work with each other. As the collaboration network evolves, the increase rate in the probability of attracting newcomers for authors with higher degrees increases, whereas the increase rates in the likelihood of forming new links among authors with higher degrees decreases. This highlights the interesting trend that the COVID pandemic alters the research collaboration trends that star scientists are starting to collaborate more with newcomers but less with existing collaborators, which, in a certain way, reduces the collaboration disparity.

This paper applies multiple machine learning (ML) algorithms to a dataset of de-identified COVID-19 patients provided by the COVID-19 Research Database. The dataset consists of 20,878 COVID-positive patients, among which 9,177 patients died in the year 2020. This paper aims to understand and interpret the association of socio-economic characteristics of patients with their mortality instead of maximizing prediction accuracy. According to our analysis, a patients households annual and disposable income, age, education, and employment status significantly impacts a machine learning models prediction. We also observe several individual patient data, which gives us insight into how the feature values impact the prediction for that data point. This paper analyzes the global and local interpretation of machine learning models on socio-economic data of COVID patients., Comment: 10 pages, 10 figures, American Medical Informatics Association(AMIA) Annual Conference 2022, Washington DC, USA, Nov 5-9, 2022

This paper applies eXplainable Artificial Intelligence (XAI) methods to investigate the socioeconomic disparities in COVID patient mortality. An Extreme Gradient Boosting (XGBoost) prediction model is built based on a de-identified Austin area hospital dataset to predict the mortality of COVID-19 patients. We apply two XAI methods, Shapley Additive exPlanations (SHAP) and Locally Interpretable Model Agnostic Explanations (LIME), to compare the global and local interpretation of feature importance. This paper demonstrates the advantages of using XAI which shows the feature importance and decisive capability. Furthermore, we use the XAI methods to cross-validate their interpretations for individual patients. The XAI models reveal that Medicare financial class, older age, and gender have high impact on the mortality prediction. We find that LIME local interpretation does not show significant differences in feature importance comparing to SHAP, which suggests pattern confirmation. This paper demonstrates the importance of XAI methods in cross-validation of feature attributions., Comment: AMIA 2023 Informatics Summit, March 13-16, Seattle, WA, USA. 10 pages

Deep neural networks (DNNs) have rapidly become a \textit{de facto} choice for medical image understanding tasks. However, DNNs are notoriously fragile to the class imbalance in image classification. We further point out that such imbalance fragility can be amplified when it comes to more sophisticated tasks such as pathology localization, as imbalances in such problems can have highly complex and often implicit forms of presence. For example, different pathology can have different sizes or colors (w.r.t.the background), different underlying demographic distributions, and in general different difficulty levels to recognize, even in a meticulously curated balanced distribution of training data. In this paper, we propose to use pruning to automatically and adaptively identify \textit{hard-to-learn} (HTL) training samples, and improve pathology localization by attending them explicitly, during training in \textit{supervised, semi-supervised, and weakly-supervised} settings. Our main inspiration is drawn from the recent finding that deep classification models have difficult-to-memorize samples and those may be effectively exposed through network pruning \cite{hooker2019compressed} - and we extend such observation beyond classification for the first time. We also present an interesting demographic analysis which illustrates HTLs ability to capture complex demographic imbalances. Our extensive experiments on the Skin Lesion Localization task in multiple training settings by paying additional attention to HTLs show significant improvement of localization performance by $\sim$2-3\%., Comment: Accepted in WACV 2023

AI-powered Medical Imaging has recently achieved enormous attention due to its ability to provide fast-paced healthcare diagnoses. However, it usually suffers from a lack of high-quality datasets due to high annotation cost, inter-observer variability, human annotator error, and errors in computer-generated labels. Deep learning models trained on noisy labelled datasets are sensitive to the noise type and lead to less generalization on the unseen samples. To address this challenge, we propose a Robust Stochastic Knowledge Distillation (RoS-KD) framework which mimics the notion of learning a topic from multiple sources to ensure deterrence in learning noisy information. More specifically, RoS-KD learns a smooth, well-informed, and robust student manifold by distilling knowledge from multiple teachers trained on overlapping subsets of training data. Our extensive experiments on popular medical imaging classification tasks (cardiopulmonary disease and lesion classification) using real-world datasets, show the performance benefit of RoS-KD, its ability to distill knowledge from many popular large networks (ResNet-50, DenseNet-121, MobileNet-V2) in a comparatively small network, and its robustness to adversarial attacks (PGD, FSGM). More specifically, RoS-KD achieves >2% and >4% improvement on F1-score for lesion classification and cardiopulmonary disease classification tasks, respectively, when the underlying student is ResNet-18 against recent competitive knowledge distillation baseline. Additionally, on cardiopulmonary disease classification task, RoS-KD outperforms most of the SOTA baselines by ~1% gain in AUC score., Comment: Accepted in ICDM 2022

Despite the enormous success of Graph Convolutional Networks (GCNs) in modeling graph-structured data, most of the current GCNs are shallow due to the notoriously challenging problems of over-smoothening and information squashing along with conventional difficulty caused by vanishing gradients and over-fitting. Previous works have been primarily focused on the study of over-smoothening and over-squashing phenomena in training deep GCNs. Surprisingly, in comparison with CNNs/RNNs, very limited attention has been given to understanding how healthy gradient flow can benefit the trainability of deep GCNs. In this paper, firstly, we provide a new perspective of gradient flow to understand the substandard performance of deep GCNs and hypothesize that by facilitating healthy gradient flow, we can significantly improve their trainability, as well as achieve state-of-the-art (SOTA) level performance from vanilla-GCNs. Next, we argue that blindly adopting the Glorot initialization for GCNs is not optimal, and derive a topology-aware isometric initialization scheme for vanilla-GCNs based on the principles of isometry. Additionally, contrary to ad-hoc addition of skip-connections, we propose to use gradient-guided dynamic rewiring of vanilla-GCNs} with skip connections. Our dynamic rewiring method uses the gradient flow within each layer during training to introduce on-demand skip-connections adaptively. We provide extensive empirical evidence across multiple datasets that our methods improve gradient flow in deep vanilla-GCNs and significantly boost their performance to comfortably compete and outperform many fancy state-of-the-art methods. Codes are available at: https://github.com/VITA-Group/GradientGCN., Comment: Advances in Neural Information Processing Systems (NeurIPS), 2022

We study the band structure and transport properties of ferromagnetic tetragonal silicene nanoribbons by using the non-equilibrium Green's function method. The band structure and spin-dependent conductance are discussed under the combined effect of the external electric field, potential energy, exchange field and the spin-orbit coupling. One can easily realize a phase transition from a semimetallic to a semiconducting state by changing the transverse width of the nanoribbon. Separation of spin-dependent conductances arises from the effect of exchange field and the spin-orbit coupling, while zero-conductance behaviors exhibit spin-dependent band gaps induced by the electric field. We propose a device configuration of four-terminal tetragonal silicene nanoribbon with two central channels. It is found that spin current can be controlled by utilizing two switches. The switch with a high potential barrier can block electrons flowing from the central scattering region into other terminals. Interestingly, applying only one switch can realize spin-dependent zero conductance and large spin polarization. Two switches can provide multiple operations for controlling spin-dependent transport properties. The two-channel ferromagnetic tetragonal silicene nanoribbon can realize an effective separation of spin current, which may be a potential candidate for spintronic devices., Comment: 11 pages, 15 figures

Before the recent success of deep learning methods for automated medical image analysis, practitioners used handcrafted radiomic features to quantitatively describe local patches of medical images. However, extracting discriminative radiomic features relies on accurate pathology localization, which is difficult to acquire in real-world settings. Despite advances in disease classification and localization from chest X-rays, many approaches fail to incorporate clinically-informed domain knowledge. For these reasons, we propose a Radiomics-Guided Transformer (RGT) that fuses \textit{global} image information with \textit{local} knowledge-guided radiomics information to provide accurate cardiopulmonary pathology localization and classification \textit{without any bounding box annotations}. RGT consists of an image Transformer branch, a radiomics Transformer branch, and fusion layers that aggregate image and radiomic information. Using the learned self-attention of its image branch, RGT extracts a bounding box for which to compute radiomic features, which are further processed by the radiomics branch; learned image and radiomic features are then fused and mutually interact via cross-attention layers. Thus, RGT utilizes a novel end-to-end feedback loop that can bootstrap accurate pathology localization only using image-level disease labels. Experiments on the NIH ChestXRay dataset demonstrate that RGT outperforms prior works in weakly supervised disease localization (by an average margin of 3.6\% over various intersection-over-union thresholds) and classification (by 1.1\% in average area under the receiver operating characteristic curve). We publicly release our codes and pre-trained models at \url{https://github.com/VITA-Group/chext}.

Pruning large neural networks to create high-quality, independently trainable sparse masks, which can maintain similar performance to their dense counterparts, is very desirable due to the reduced space and time complexity. As research effort is focused on increasingly sophisticated pruning methods that leads to sparse subnetworks trainable from the scratch, we argue for an orthogonal, under-explored theme: improving training techniques for pruned sub-networks, i.e. sparse training. Apart from the popular belief that only the quality of sparse masks matters for sparse training, in this paper we demonstrate an alternative opportunity: one can carefully customize the sparse training techniques to deviate from the default dense network training protocols, consisting of introducing ``ghost" neurons and skip connections at the early stage of training, and strategically modifying the initialization as well as labels. Our new sparse training recipe is generally applicable to improving training from scratch with various sparse masks. By adopting our newly curated techniques, we demonstrate significant performance gains across various popular datasets (CIFAR-10, CIFAR-100, TinyImageNet), architectures (ResNet-18/32/104, Vgg16, MobileNet), and sparse mask options (lottery ticket, SNIP/GRASP, SynFlow, or even randomly pruning), compared to the default training protocols, especially at high sparsity levels. Code is at https://github.com/VITA-Group/ToST, Comment: Accepted by ICML 2022

We study the effect of the strain on the energy bands of TaIrTe4 sheet and the photocurrent in the Cu-TaIrTe4-Cu heterojunction by using the quantum transport simulations. It is found that the Weyl points can be completely broken with increasing of the strain along z dirction. One can obtain a large photocurrent in the Cu-TaIrTe4-Cu heterojunction in the absence of the strain. While the photocurrent can be sharply enhanced by the strain and reach a large value. Accordingly, the maximum values of the photocurrent can be explained in terms of the transitions between peaks of density of states and band structures. The strain-induced energy bands and photocurrent exhibit anisotropic behaviors. Our results provide a novel route to effectively modulate the energy bands and the photocurrent by utilizing mechanical methods for TaIrTe4-based devices., Comment: 5 pages, 7 figures

The double Weyl semimetal (DWSM) is a newly proposed topological material that hosts Weyl points with chiral charge n=2. The disorder effect in DWSM is investigated by adopting the tight-binding Hamiltonian. Using the transfer matrix method and the noncommutative Kubo formula, we numerically calculate the localization length and the Hall conductivity in the presence of the on-site nonmagnetic disorder or orbital (spin-flip) disorders, and give the corresponding global phase diagrams. For the on-site nonmagnetic disorder, the system undergoes the DWSM-3D quantum anomalous hall (3D QAH) and normal insulator (NI)-DWSM phase transitions, and evolves into the diffusive metal (DM) phase before being localized by strong disorders, which is consistent with the Weyl semimetal. For \sigma_x orbital disorder, we find that increasing disorder can generate a pair of Weyl nodes at the boundary of the Brillouin zone and induce a 3D QAH-DWSM phase transition. Then we investigate the combined effect of orbital disorders for both disordered 3D QAH phase and DWSM phase. The disorder-induced transitions can be well understood in terms of an effective medium theory based on self-consistent Born approximation., Comment: 8 pages, 9 figures

Incorporating fresh members in teams is considered a pathway to team creativity. However, whether freshness improves team performance or not remains unclear, as well as the optimal involvement of fresh members for team performance. This study uses a group of authors on the byline of a publication as a proxy for a scientific team. We extend an indicator, i.e., team freshness, to measure the extent to which a scientific team incorporates new members, by calculating the fraction of new collaboration relations established within the team. Based on more than 43 million scientific publications covering more than a half-century of research from Microsoft Academic Graph, this study provides a holistic picture of the current development of team freshness by outlining the temporal evolution of freshness, and its disciplinary distribution. Subsequently, using a multivariable regression approach, we examine the association between team freshness and papers'short-term and long-term citations.The major findings are as follows: (1)team freshness in scientific teams has been increasing in the past half-century; (2)there exists an inverted-U-shaped association between team freshness and papers' citations in all the disciplines and in different periods;(3)the inverted-U-shaped relationship between team freshness and papers' citations is only found in small teams, while, in large teams, team freshness is significantly positively related to papers' citations.

Analyzing radiology reports is a time-consuming and error-prone task, which raises the need for an efficient automated radiology report analysis system to alleviate the workloads of radiologists and encourage precise diagnosis. In this work, we present RadText, an open-source radiology text analysis system developed by Python. RadText offers an easy-to-use text analysis pipeline, including de-identification, section segmentation, sentence split and word tokenization, named entity recognition, parsing, and negation detection. RadText features a flexible modular design, provides a hybrid text processing schema, and supports raw text processing and local processing, which enables better usability and improved data privacy. RadText adopts BioC as the unified interface, and also standardizes the input / output into a structured representation compatible with Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM). This allows for a more systematic approach to observational research across multiple, disparate data sources. We evaluated RadText on the MIMIC-CXR dataset, with five new disease labels we annotated for this work. RadText demonstrates highly accurate classification performances, with an average precision of, a recall of 0.94, and an F-1 score of 0.92. We have made our code, documentation, examples, and the test set available at https://github.com/bionlplab/radtext ., Comment: 9 pages, 2 figures, Accepted by 2022 IEEE 10th International Conference on Healthcare Informatics (ICHI)