Search

In AI-assisted decision-making, humans often passively review AI's suggestion and decide whether to accept or reject it as a whole. In such a paradigm, humans are found to rarely trigger analytical thinking and face difficulties in communicating the nuances of conflicting opinions to the AI when disagreements occur. To tackle this challenge, we propose Human-AI Deliberation, a novel framework to promote human reflection and discussion on conflicting human-AI opinions in decision-making. Based on theories in human deliberation, this framework engages humans and AI in dimension-level opinion elicitation, deliberative discussion, and decision updates. To empower AI with deliberative capabilities, we designed Deliberative AI, which leverages large language models (LLMs) as a bridge between humans and domain-specific models to enable flexible conversational interactions and faithful information provision. An exploratory evaluation on a graduate admissions task shows that Deliberative AI outperforms conventional explainable AI (XAI) assistants in improving humans' appropriate reliance and task performance. Based on a mixed-methods analysis of participant behavior, perception, user experience, and open-ended feedback, we draw implications for future AI-assisted decision tool design.

In AI-assisted decision-making, it is crucial but challenging for humans to achieve appropriate reliance on AI. This paper approaches this problem from a human-centered perspective, "human self-confidence calibration". We begin by proposing an analytical framework to highlight the importance of calibrated human self-confidence. In our first study, we explore the relationship between human self-confidence appropriateness and reliance appropriateness. Then in our second study, We propose three calibration mechanisms and compare their effects on humans' self-confidence and user experience. Subsequently, our third study investigates the effects of self-confidence calibration on AI-assisted decision-making. Results show that calibrating human self-confidence enhances human-AI team performance and encourages more rational reliance on AI (in some aspects) compared to uncalibrated baselines. Finally, we discuss our main findings and provide implications for designing future AI-assisted decision-making interfaces.

Artificial Intelligence (AI) is increasingly employed in various decision-making tasks, typically as a Recommender, providing recommendations that the AI deems correct. However, recent studies suggest this may diminish human analytical thinking and lead to humans' inappropriate reliance on AI, impairing the synergy in human-AI teams. In contrast, human advisors in group decision-making perform various roles, such as analyzing alternative options or criticizing decision-makers to encourage their critical thinking. This diversity of roles has not yet been empirically explored in AI assistance. In this paper, we examine three AI roles: Recommender, Analyzer, and Devil's Advocate, and evaluate their effects across two AI performance levels. Our results show each role's distinct strengths and limitations in task performance, reliance appropriateness, and user experience. Notably, the Recommender role is not always the most effective, especially if the AI performance level is low, the Analyzer role may be preferable. These insights offer valuable implications for designing AI assistants with adaptive functional roles according to different situations.

The two-phase sampling design is a cost-effective sampling strategy that has been widely used in public health research. The conventional approach in this design is to create subsample specific weights that adjust for probability of selection and response in the second phase. However, these weights can be highly variable which in turn results in unstable weighted analyses. Alternatively, we can use the rich data collected in the first phase of the study to improve the survey inference of the second phase sample. In this paper, we use a Bayesian tree-based multiple imputation (MI) approach for estimating population means using a two-phase survey design. We demonstrate how to incorporate complex survey design features, such as strata, clusters, and weights, into the imputation procedure. We use a simulation study to evaluate the performance of the tree-based MI approach in comparison to the alternative weighted analyses using the subsample weights. We find the tree-based MI method outperforms weighting methods with smaller bias, reduced root mean squared error, and narrower 95\% confidence intervals that have closer to the nominal level coverage rate. We illustrate the application of the proposed method by estimating the prevalence of diabetes among the United States non-institutionalized adult population using the fasting blood glucose data collected only on a subsample of participants in the 2017-2018 National Health and Nutrition Examination Survey.

Federated learning (FL) has gained popularity in clinical research in recent years to facilitate privacy-preserving collaboration. Structured data, one of the most prevalent forms of clinical data, has experienced significant growth in volume concurrently, notably with the widespread adoption of electronic health records in clinical practice. This review examines FL applications on structured medical data, identifies contemporary limitations and discusses potential innovations. We searched five databases, SCOPUS, MEDLINE, Web of Science, Embase, and CINAHL, to identify articles that applied FL to structured medical data and reported results following the PRISMA guidelines. Each selected publication was evaluated from three primary perspectives, including data quality, modeling strategies, and FL frameworks. Out of the 1160 papers screened, 34 met the inclusion criteria, with each article consisting of one or more studies that used FL to handle structured clinical/medical data. Of these, 24 utilized data acquired from electronic health records, with clinical predictions and association studies being the most common clinical research tasks that FL was applied to. Only one article exclusively explored the vertical FL setting, while the remaining 33 explored the horizontal FL setting, with only 14 discussing comparisons between single-site (local) and FL (global) analysis. The existing FL applications on structured medical data lack sufficient evaluations of clinically meaningful benefits, particularly when compared to single-site analyses. Therefore, it is crucial for future FL applications to prioritize clinical motivations and develop designs and methodologies that can effectively support and aid clinical practice and research.

In AI-assisted decision-making, it is critical for human decision-makers to know when to trust AI and when to trust themselves. However, prior studies calibrated human trust only based on AI confidence indicating AI's correctness likelihood (CL) but ignored humans' CL, hindering optimal team decision-making. To mitigate this gap, we proposed to promote humans' appropriate trust based on the CL of both sides at a task-instance level. We first modeled humans' CL by approximating their decision-making models and computing their potential performance in similar instances. We demonstrated the feasibility and effectiveness of our model via two preliminary studies. Then, we proposed three CL exploitation strategies to calibrate users' trust explicitly/implicitly in the AI-assisted decision-making process. Results from a between-subjects experiment (N=293) showed that our CL exploitation strategies promoted more appropriate human trust in AI, compared with only using AI confidence. We further provided practical implications for more human-compatible AI-assisted decision-making.

Dynamic treatment regimes (DTRs) are sequences of decision rules that recommend treatments based on patients' time-varying clinical conditions. The sequential multiple assignment randomized trial (SMART) is an experimental design that can provide high-quality evidence for constructing optimal DTRs. In a conventional SMART, participants are randomized to available treatments at multiple stages with balanced randomization probabilities. Despite its relative simplicity of implementation and desirable performance in comparing embedded DTRs, the conventional SMART faces inevitable ethical issues including assigning many participants to the empirically inferior treatment or the treatment they dislike, which might slow down the recruitment procedure and lead to higher attrition rates, ultimately leading to poor internal and external validities of the trial results. In this context, we propose a SMART under the Experiment-as-Market framework (SMART-EXAM), a novel SMART design that holds the potential to improve participants' welfare by incorporating their preferences and predicted treatment effects into the randomization procedure. We describe the steps of conducting a SMART-EXAM and evaluate its performance compared to the conventional SMART. The results indicate that the SMART-EXAM can improve the welfare of the participants enrolled in the trial, while also achieving a desirable ability to construct an optimal DTR when the experimental parameters are suitably specified. We finally illustrate the practical potential of the SMART-EXAM design using data from a SMART for children with attention-deficit/hyperactivity disorder (ADHD).

Mobile technology enables unprecedented continuous monitoring of an individual's behavior, social interactions, symptoms, and other health conditions, presenting an enormous opportunity for therapeutic advancements and scientific discoveries regarding the etiology of psychiatric illness. Continuous collection of mobile data results in the generation of a new type of data: entangled multivariate time series of outcome, exposure, and covariates. Missing data is a pervasive problem in biomedical and social science research, and the Ecological Momentary Assessment (EMA) using mobile devices in psychiatric research is no exception. However, the complex structure of multivariate time series introduces new challenges in handling missing data for proper causal inference. Data imputation is commonly recommended to enhance data utility and estimation efficiency. The majority of available imputation methods are either designed for longitudinal data with limited follow-up times or for stationary time series, which are incompatible with potentially non-stationary time series. In the field of psychiatry, non-stationary data are frequently encountered as symptoms and treatment regimens may experience dramatic changes over time. To address missing data in possibly non-stationary multivariate time series, we propose a novel multiple imputation strategy based on the state space model (SSMmp) and a more computationally efficient variant (SSMimpute). We demonstrate their advantages over other widely used missing data strategies by evaluating their theoretical properties and empirical performance in simulations of both stationary and non-stationary time series, subject to various missing mechanisms. We apply the SSMimpute to investigate the association between social network size and negative mood using a multi-year observational smartphone study of bipolar patients, controlling for confounding variables.

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

We build a Cu-MoTe2-Cu device model and use first-principles density functional theory to study the transport properties of single-layer Td-MoTe2. We obtained the effect of strain on the energy band structure, transport properties, and photocurrent. The strain-induced photocurrent shows an anisotropy that reflects the modulation of the energy bands, including the Weyl point, by strain. The photocurrent can be suppressed to almost zero when the strain is applied along the vacuum direction. In contrast, the photocurrent can be significantly increased when the strain is applied along the transport direction. The transport properties and magnitude of the photocurrent in the MoTe2-based device can be effectively modulated by adjusting the strength and direction of the strain., Comment: 6 pages, 6 figures

We study the effect of the strain on the band structure and the valley-dependent transport property of graphene heterojunctions. It is found that valley-dependent separation of electrons can be achieved by utilizing the strain and on-site energies. In the presence of the strain, the values of the transmission can be effectively adjusted by changing the strengths of the strain, while the transport angle basically keeps unchanged. When an extra on-site energy is simultaneously applied to the central scattering region, not only are the electrons of valleys K and K' separated into two distinct transmission lobes in opposite transverse directions, but the transport angles of two valleys can be significantly changed. Therefore, one can realize an effective modulation of valley-dependent transport by changing the strength and stretch angle of the strain and on-site energies, which can be exploited for graphene-based valleytronics devices., Comment: 7 pages, 10 figures

By using the tight-binding model and non-equilibrium Green's function method (NEGF), we study the band structures and transport properties of a silicene nanoribbon with a line defect where a bulk energy gap is opened due to the sublattice symmetry breaking. The flat subband bends downwards or upwards due to the effect of the line defect. The spin-orbit coupling induces quantum spin Hall states. Especially, the energy band depends on the distance between the line defect and the edge of the nanoribbon. The effects of the on-site energies on the band spectra of the two defect configurations are different. There always exists one band gap for different on-site energies for the defect configuration of case 1. However, a gapless state and a band gap can be modulated by changing the on-site energy, the sublattice potential and spin-orbit couplings for the defect configuration of case 2. Accordingly, the variation trends of the conductance including zero conductance can be well understood in terms of the combined effect of the sublattice potential, the on-site energy and spin-orbit couplings on the band structures. Thus it is easy and effective to modulate the transport property of the silicene nanoribbon with the defect configuration of case 2 by utilizing the sublattice potential, the on-site energy and spin-orbit couplings. This study is of great significance for the fabrication and the modulation of the transport property of silicene-based devices., Comment: 7 pages, 10 figures