arXiv subjects

Xiong Liu

Publications and source records attributed to Xiong Liu.

31 records · Page 2Linked to original sources

arXiv2022

A general scheme of differential imaging employing weak measurement

We propose and experimentally realize a general scheme of differential imaging employing the idea of weak measurement. We show that the weak coupling between the system of interest and a two-level ancilla can introduce a two-beam circuit after an arbitrary pre-selection of the ancilla. By choosing the post-selection orthogonal to the pre-selection measurement, an effective imaging platform based on differential operations is shown achieved. Experimental results on both the Sagnac interferometer and ultra-thin Wollaston prism demonstrate that our imaging scheme successfully yields the boundary information of complex geometric configurations.

physics.optics↗

arXiv2021

Clinical Trial Information Extraction with BERT

Natural language processing (NLP) of clinical trial documents can be useful in new trial design. Here we identify entity types relevant to clinical trial design and propose a framework called CT-BERT for information extraction from clinical trial text. We trained named entity recognition (NER) models to extract eligibility criteria entities by fine-tuning a set of pre-trained BERT models. We then compared the performance of CT-BERT with recent baseline methods including attention-based BiLSTM and Criteria2Query. The results demonstrate the superiority of CT-BERT in clinical trial NLP.

q-bio.QM↗

arXiv2021

A Scalable AI Approach for Clinical Trial Cohort Optimization

FDA has been promoting enrollment practices that could enhance the diversity of clinical trial populations, through broadening eligibility criteria. However, how to broaden eligibility remains a significant challenge. We propose an AI approach to Cohort Optimization (AICO) through transformer-based natural language processing of the eligibility criteria and evaluation of the criteria using real-world data. The method can extract common eligibility criteria variables from a large set of relevant trials and measure the generalizability of trial designs to real-world patients. It overcomes the scalability limits of existing manual methods and enables rapid simulation of eligibility criteria design for a disease of interest. A case study on breast cancer trial design demonstrates the utility of the method in improving trial generalizability.

cs.CL↗

arXiv2021

Applications of artificial intelligence in drug development using real-world data

The US Food and Drug Administration (FDA) has been actively promoting the use of real-world data (RWD) in drug development. RWD can generate important real-world evidence reflecting the real-world clinical environment where the treatments are used. Meanwhile, artificial intelligence (AI), especially machine- and deep-learning (ML/DL) methods, have been increasingly used across many stages of the drug development process. Advancements in AI have also provided new strategies to analyze large, multidimensional RWD. Thus, we conducted a rapid review of articles from the past 20 years, to provide an overview of the drug development studies that use both AI and RWD. We found that the most popular applications were adverse event detection, trial recruitment, and drug repurposing. Here, we also discuss current research gaps and future opportunities.

cs.CY↗

arXiv2021

The impact of external innovation on new drug approvals: A retrospective analysis

Pharmaceutical companies are relying more often on external sources of innovation to boost their discovery research productivity. However, more in-depth knowledge about how external innovation may translate to successful product launches is still required in order to better understand how to best leverage the innovation ecosystem. We analyzed the pre-approval publication histories for FDA-approved new molecular entities (NMEs) and new biologic entities (NBEs) launched by 13 top research pharma companies during the last decade (2006-2016). We found that academic institutions contributed the majority of pre-approval publications and that publication subject matter is closely aligned with the strengths of the respective innovator. We found this to also be true for candidate drugs terminated in Phase 3, but the volume of literature on these molecules is substantially less than for approved drugs. This may suggest that approved drugs are often associated with a more robust dataset provided by a large number of institutes. Collectively, the results of our analysis support the hypothesis that a collaborative research innovation environment spanning across academia, industry and government is highly conducive to successful drug approvals.

cs.CL↗

arXiv2020

Attention-Based LSTM Network for COVID-19 Clinical Trial Parsing

COVID-19 clinical trial design is a critical task in developing therapeutics for the prevention and treatment of COVID-19. In this study, we apply a deep learning approach to extract eligibility criteria variables from COVID-19 trials to enable quantitative analysis of trial design and optimization. Specifically, we train attention-based bidirectional Long Short-Term Memory (Att-BiLSTM) models and use the optimal model to extract entities (i.e., variables) from the eligibility criteria of COVID-19 trials. We compare the performance of Att-BiLSTM with traditional ontology-based method. The result on a benchmark dataset shows that Att-BiLSTM outperforms the ontology model. Att-BiLSTM achieves a precision of 0.942, recall of 0.810, and F1 of 0.871, while the ontology model only achieves a precision of 0.715, recall of 0.659, and F1 of 0.686. Our analyses demonstrate that Att-BiLSTM is an effective approach for characterizing patient populations in COVID-19 clinical trials.

cs.CL↗

arXiv2020

Molecular Decomposition of Anisotropic Hardy Spaces with Variable Exponents

Let $A$ be an expansive dilation on $\mathbb{R}^n$, and $p(\cdot):\mathbb{R}^n\rightarrow(0,\,\infty)$ be a variable exponent function satisfying the globally log-Hölder continuous condition. Let $H^{p(\cdot)}_A({\mathbb {R}}^n)$ be the variable anisotropic Hardy space defined via the non-tangential grand maximal function. In this paper, the authors establish its molecular decomposition, which is still new even in the classical isotropic setting (in the case $A:=2\mathrm I_{n\times n}$). As applications, the authors obtain the boundedness of anisotropic Calderón-Zygmund operators from $H^{p(\cdot)}_{A}(\mathbb{R}^n)$ to $L^{p(\cdot)}(\mathbb{R}^n)$ or from $H^{p(\cdot)}_{A}(\mathbb{R}^n)$ to itself.

math.CA↗

arXiv2019

Predicting Heart Failure Readmission from Clinical Notes Using Deep Learning

Heart failure hospitalization is a severe burden on healthcare. How to predict and therefore prevent readmission has been a significant challenge in outcomes research. To address this, we propose a deep learning approach to predict readmission from clinical notes. Unlike conventional methods that use structured data for prediction, we leverage the unstructured clinical notes to train deep learning models based on convolutional neural networks (CNN). We then use the trained models to classify and predict potentially high-risk admissions/patients. For evaluation, we trained CNNs using the discharge summary notes in the MIMIC III database. We also trained regular machine learning models based on random forest using the same datasets. The result shows that deep learning models outperform the regular models in prediction tasks. CNN method achieves a F1 score of 0.756 in general readmission prediction and 0.733 in 30-day readmission prediction, while random forest only achieves a F1 score of 0.674 and 0.656 respectively. We also propose a chi-square test based method to interpret key features associated with deep learning predicted readmissions. It reveals clinical insights about readmission embedded in the clinical notes. Collectively, our method can make the human evaluation process more efficient and potentially facilitate the reduction of readmission rates.

cs.CL↗

arXiv2018

Estimates for Parametric Marcinkiewicz Integrals on Musielak-Orlicz Hardy Spaces

Let $φ:\mathbb{R}^n\times[0,\,\infty) \rightarrow [0,\,\infty)$ satisfy that $φ(x,\,\cdot)$, for any given $x\in\mathbb{R}^n$, is an Orlicz function and $φ(\cdot\,,t)$ is a Muckenhoupt $A_\infty$ weight uniformly in $t\in(0,\,\infty)$. The Musielak-Orlicz Hardy space $H^φ(\mathbb{R}^n)$ generalizes both of the weighted Hardy space and the Orlicz Hardy space and hence has a wide generality. In this paper, the authors first prove the completeness of both of the Musielak-Orlicz space $L^φ(\mathbb{R}^n)$ and the weak Musielak-Orlicz space $WL^φ(\mathbb{R}^n)$. Then the authors obtain two boundedness criterions of operators on Musielak-Orlicz spaces. As applications, the authors establish the boundedness of parametric Marcinkiewicz integral $μ^ρ_Ω$ from $H^φ(\mathbb{R}^n)$ to $L^φ(\mathbb{R}^n)$ (resp. $WL^φ(\mathbb{R}^n)$) under weaker smoothness condition (resp. some Lipschitz condition) assumed on $Ω$. These results are also new even when $φ(x,\,t):=ϕ(t)$ for all $(x,\,t)\in\mathbb{R}^n\times[0,\,\infty)$, where $ϕ$ is an Orlicz function.

math.CA↗

arXiv2018

Pre- and post-selected measurements with coupling-strength-dependent modulation

Pre- and post-selected (PPS) measurement, especially the weak PPS measurement, is a useful protocol for amplifying small physical parameters. However, it is difficult to retain both the attainable highest measurement sensitivity and precision with the increase of the parameter to be measured. Here, a modulated PPS measurement scheme based on coupling-strength-dependent modulation is presented with the highest sensitivity and precision retained for an arbitrary coupling strength. This idea is demonstrated by comparing the modulated PPS measurement scheme with standard PPS measurementv scheme, respectively, in the cases of balanced pointer and unbalanced pointer. By using the Fisher information metric, we derive the optimal pre- and post-selected states, as well as the optimal coupling-strength-dependent modulation without any restriction on the coupling strength. We also give the specific strategy of performing the modulated PPS measurement scheme, which may promote practical application of this scheme in precision metrology.

quant-ph↗

arXiv2018

Cell-less Communications in 5G Vehicular Networks Based on Vehicle-Installed Access Points

The development of intelligent transportation systems raises many requirements to the current vehicular networks. For instance, to ensure secure communications between vehicles, low latency, high connectivity and high data rate are required for vehicular networks. To meet such requirements, the 5G communication systems for vehicular networks should be improved accordingly. This article proposes a communication scheme for 5G vehicular networks, in which moving access points are deployed on vehicles to facilitate the access of vehicle users. Moreover, the adjacent vehicle-installed moving access points may cooperatively communicate with the vehicle users by joint transmissions and receptions. In this way, the vehicle users communicate with one or more unspecified cooperative access points in a cell-less manner instead of being associated to a single access point. To manage such cell-less networks, local moving software-defined cloudlets are adopted to perform transmission and scheduling management. Simulation results show that the proposed scheme significantly reduces the latency, while improving the connectivity of the vehicular networks, and can be considered as a research direction for the solution to 5G vehicular networks.

cs.NI↗

arXiv2017

5G Converged Cell-less Communications in Smart Cities

Ubiquitous information service converged by different types of heterogeneous networks is one of fundamental functions for smart cities. Considering the deployment of 5G ultra-dense wireless networks, the 5G converged cell-less communication networks are proposed to support mobile terminals in smart cities. To break obstacles of heterogeneous wireless networks, the 5G converged cell-less communication network is vertically converged in different tiers of heterogeneous wireless networks and horizontally converged in celled architectures of base stations/access points. Moreover, the software defined network controllers are configured to manage the traffic scheduling and resource allocation in 5G converged cell-less communication networks. Simulation results indicate the coverage probability and the energy saving at both base stations and mobile terminals are improved by the cooperative grouping scheme in 5G converged cell-less communication networks.

cs.NI↗

arXiv2016

Energy Saving of Base Stations Sleep Scheduling for Multi-Hop Vehicular Networks

This paper investigates the energy saving of base station (BS) deployed in a 1-D multi-hop vehicular network with sleep scheduling strategy. We consider cooperative BS scheduling strategy where BSs can switch between sleep and active modes to reduce the average energy consumption utilizing the information of vehicular speeds and locations. Assuming a Poisson distribution of vehicles, we derive an appropriate probability distribution function of distance between two adjacent cluster heads, where a cluster is a maximal set of vehicles in which every two adjacent vehicles can communicate directly when their Euclidean distance is less than or equal to a threshold, known as the communication range of vehicles. Furthermore, the expected value of the sojourn time in the sleep mode and energy saving are obtained. The numerical results show that the sleep scheduling strategy significantly reduces the energy consumption of the base stations.

cs.NI↗