Single-arm trials (SATs) may be used to support regulatory submissions in settings where there is a high unmet medical need and highly promising early efficacy data undermine the equipoise needed for randomization. In this context, patient-level real-world data (RWD) may be used to create an external control arm (ECA) to contextualize the SAT results. However, naive comparisons of the SAT with its ECA will yield biased estimates of causal effects if groups are imbalanced with regards to (un)measured prognostic factors. Several methods are available to adjust for measured confounding, but the interpretation of such analyses is challenging unless the causal question of interest is clearly defined, and the estimator is aligned with the estimand. Additional complications arise when patients in the ECA are eligible for the SAT at multiple timepoints. In this paper, we use a case-study of a pivotal SAT of a novel CAR-T therapy for heavily pre-treated patients with follicular lymphoma to illustrate how a combination of the target trial and the ICH E9(R1) estimand frameworks can be used to define the target estimand and avoid common methodological pitfalls related to the design of the ECA and comparisons with the SAT. We also propose an approach to address the challenge of how to define an appropriate time zero for external controls who meet the SAT inclusion/exclusion criteria at several timepoints. Use of the target trial and estimand frameworks facilitates discussions amongst internal and external stakeholders, as well as an early assessment of the adequacy of the available RWD.
相關內容
SAT是研究者關注命題可滿足性問題的理論與應用的第一次年度會議。除了簡單命題可滿足性外，它還包括布爾優化（如MaxSAT和偽布爾（PB）約束）、量化布爾公式（QBF）、可滿足性模理論（SMT）和約束規劃（CP），用于與布爾級推理有明確聯系的問題。官網鏈接： ·
Machine Learning
·
學成
·
Better
·
講稿
·
Interactive machine learning (IML) is a field of research that explores how to leverage both human and computational abilities in decision making systems. IML represents a collaboration between multiple complementary human and machine intelligent systems working as a team, each with their own unique abilities and limitations. This teamwork might mean that both systems take actions at the same time, or in sequence. Two major open research questions in the field of IML are: "How should we design systems that can learn to make better decisions over time with human interaction?" and "How should we evaluate the design and deployment of such systems?" A lack of appropriate consideration for the humans involved can lead to problematic system behaviour, and issues of fairness, accountability, and transparency. Thus, our goal with this work is to present a human-centred guide to designing and evaluating IML systems while mitigating risks. This guide is intended to be used by machine learning practitioners who are responsible for the health, safety, and well-being of interacting humans. An obligation of responsibility for public interaction means acting with integrity, honesty, fairness, and abiding by applicable legal statutes. With these values and principles in mind, we as a machine learning research community can better achieve goals of augmenting human skills and abilities. This practical guide therefore aims to support many of the responsible decisions necessary throughout the iterative design, development, and dissemination of IML systems.
Software reliability estimation is one of the most active areas of research in software testing. Since time between failures (TBF) has often been challenging to record, software testing data are commonly recorded as test-case-wise in a discrete set up. We have developed a Bayesian generalised linear mixed model (GLMM) based on software testing detection data and a size-biased strategy which not only estimates the software reliability, but also estimates the total number of bugs present in the software. Our approach provides a flexible, unified modelling framework and can be adopted to various real-life situations. We have assessed the performance of our model via simulation study and found that each of the key parameters could be estimated with a satisfactory level of accuracy. We have also applied our model to two empirical software testing data sets. While there can be other fields of study for application of our model (e.g., hydrocarbon exploration), we anticipate that our novel modelling approach to estimate software reliability could be very useful for the users and can potentially be a key tool in the field of software reliability estimation.
In the peg insertion task, human pays attention to the seam between the peg and the hole and tries to fill it continuously with visual feedback. By imitating the human behavior, we design architectures with position and orientation estimators based on the seam representation for pose alignment, which proves to be general to the unseen peg geometries. By putting the estimators into the closed-loop control with reinforcement learning, we further achieve a higher or comparable success rate, efficiency, and robustness compared with the baseline methods. The policy is trained totally in simulation without any manual intervention. To achieve sim-to-real, a learnable segmentation module with automatic data collecting and labeling can be easily trained to decouple the perception and the policy, which helps the model trained in simulation quickly adapt to the real world with negligible effort. Results are presented in simulation and on a physical robot. Code, videos, and supplemental material are available at //github.com/xieliang555/SFN.git
The number of information systems (IS) studies dealing with explainable artificial intelligence (XAI) is currently exploding as the field demands more transparency about the internal decision logic of machine learning (ML) models. However, most techniques subsumed under XAI provide post-hoc-analytical explanations, which have to be considered with caution as they only use approximations of the underlying ML model. Therefore, our paper investigates a series of intrinsically interpretable ML models and discusses their suitability for the IS community. More specifically, our focus is on advanced extensions of generalized additive models (GAM) in which predictors are modeled independently in a non-linear way to generate shape functions that can capture arbitrary patterns but remain fully interpretable. In our study, we evaluate the prediction qualities of five GAMs as compared to six traditional ML models and assess their visual outputs for model interpretability. On this basis, we investigate their merits and limitations and derive design implications for further improvements.
In a sports competition, a team might lose a powerful incentive to exert full effort if its final rank does not depend on the outcome of the matches still to be played. Therefore, the organiser should reduce the probability of such a situation to the extent possible. Our paper provides a classification scheme to identify these weakly (where one team is indifferent) or strongly (where both teams are indifferent) stakeless games. A statistical model is estimated to simulate the UEFA Champions League groups and compare the candidate schedules used in the 2021/22 season according to the competitiveness of the matches played in the last round(s). The option followed in four of the eight groups is found to be optimal under a wide set of parameters. Minimising the number of strongly stakeless matches is verified to be a likely goal in the computer draw of the fixture that remains hidden from the public.
The Coronavirus disease 2019 (COVID-19) outbreak quickly spread around the world, resulting in over 240 million infections and 4 million deaths by Oct 2021. While the virus is spreading from person to person silently, fear has also been spreading around the globe. The COVID-19 information from the Australian Government is convincing but not timely or detailed, and there is much information on social networks with both facts and rumors. As software engineers, we have spontaneously and rapidly constructed a COVID-19 information dashboard aggregating reliable information semi-automatically checked from different sources for providing one-stop information sharing site about the latest status in Australia. Inspired by the John Hopkins University COVID-19 Map, our dashboard contains the case statistics, case distribution, government policy, latest news, with interactive visualization. In this paper, we present a participant's in-person observations in which the authors acted as founders of //covid-19-au.com/ serving more than 830K users with 14M page views since March 2020. According to our first-hand experience, we summarize 9 lessons for developers, researchers and instructors. These lessons may inspire the development, research and teaching in software engineer aspects for coping with similar public crises in the future.
We design and implement LEGOStore, an erasure coding (EC) based linearizable data store over geo-distributed public cloud data centers (DCs). For such a data store, the confluence of the following factors opens up opportunities for EC to be latency-competitive with replication: (a) the necessity of communicating with remote DCs to tolerate entire DC failures and implement linearizability; and (b) the emergence of DCs near most large population centers. LEGOStore employs an optimization framework that, for a given object, carefully chooses among replication and EC, as well as among various DC placements to minimize overall costs. To handle workload dynamism, LEGOStore employs a novel agile reconfiguration protocol. Our evaluation using a LEGOStore prototype spanning 9 Google Cloud Platform DCs demonstrates the efficacy of our ideas. We observe cost savings ranging from moderate (5-20\%) to significant (60\%) over baselines representing the state of the art while meeting tail latency SLOs. Our reconfiguration protocol is able to transition key placements in 3 to 4 inter-DC RTTs ($<$ 1s in our experiments), allowing for agile adaptation to dynamic conditions.
The local reference frame (LRF), as an independent coordinate system generated on a local 3D surface, is widely used in 3D local feature descriptor construction and 3D transformation estimation which are two key steps in the local method-based surface matching. There are numerous LRF methods have been proposed in literatures. In these methods, the x- and z-axis are commonly generated by different methods or strategies, and some x-axis methods are implemented on the basis of a z-axis being given. In addition, the weight and disambiguation methods are commonly used in these LRF methods. In existing evaluations of LRF, each LRF method is evaluated with a complete form. However, the merits and demerits of the z-axis, x-axis, weight and disambiguation methods in LRF construction are unclear. In this paper, we comprehensively analyze the z-axis, x-axis, weight and disambiguation methods in existing LRFs, and obtain six z-axis and eight x-axis, five weight and two disambiguation methods. The performance of these methods are comprehensively evaluated on six standard datasets with different application scenarios and nuisances. Considering the evaluation outcomes, the merits and demerits of different weight, disambiguation, z- and x-axis methods are analyzed and summarized. The experimental result also shows that some new designed LRF axes present superior performance compared with the state-of-the-art ones.
In this paper we study the finite sample and asymptotic properties of various weighting estimators of the local average treatment effect (LATE), several of which are based on Abadie (2003)'s kappa theorem. Our framework presumes a binary endogenous explanatory variable ("treatment") and a binary instrumental variable, which may only be valid after conditioning on additional covariates. We argue that one of the Abadie estimators, which we show is weight normalized, is likely to dominate the others in many contexts. A notable exception is in settings with one-sided noncompliance, where certain unnormalized estimators have the advantage of being based on a denominator that is bounded away from zero. We use a simulation study and three empirical applications to illustrate our findings. In applications to causal effects of college education using the college proximity instrument (Card, 1995) and causal effects of childbearing using the sibling sex composition instrument (Angrist and Evans, 1998), the unnormalized estimates are clearly unreasonable, with "incorrect" signs, magnitudes, or both. Overall, our results suggest that (i) the relative performance of different kappa weighting estimators varies with features of the data-generating process; and that (ii) the normalized version of Tan (2006)'s estimator may be an attractive alternative in many contexts. Applied researchers with access to a binary instrumental variable should also consider covariate balancing or doubly robust estimators of the LATE.
Structural data well exists in Web applications, such as social networks in social media, citation networks in academic websites, and threads data in online forums. Due to the complex topology, it is difficult to process and make use of the rich information within such data. Graph Neural Networks (GNNs) have shown great advantages on learning representations for structural data. However, the non-transparency of the deep learning models makes it non-trivial to explain and interpret the predictions made by GNNs. Meanwhile, it is also a big challenge to evaluate the GNN explanations, since in many cases, the ground-truth explanations are unavailable. In this paper, we take insights of Counterfactual and Factual (CF^2) reasoning from causal inference theory, to solve both the learning and evaluation problems in explainable GNNs. For generating explanations, we propose a model-agnostic framework by formulating an optimization problem based on both of the two casual perspectives. This distinguishes CF^2 from previous explainable GNNs that only consider one of them. Another contribution of the work is the evaluation of GNN explanations. For quantitatively evaluating the generated explanations without the requirement of ground-truth, we design metrics based on Counterfactual and Factual reasoning to evaluate the necessity and sufficiency of the explanations. Experiments show that no matter ground-truth explanations are available or not, CF^2 generates better explanations than previous state-of-the-art methods on real-world datasets. Moreover, the statistic analysis justifies the correlation between the performance on ground-truth evaluation and our proposed metrics.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191