arXiv subjects

Akane Sano

Publications and source records attributed to Akane Sano.

At least 19 recordsLinked to original sources

arXiv2025

Reflections from Research Roundtables at the Conference on Health, Inference, and Learning (CHIL) 2025

The 6th Annual Conference on Health, Inference, and Learning (CHIL 2025), hosted by the Association for Health Learning and Inference (AHLI), was held in person on June 25-27, 2025, at the University of California, Berkeley, in Berkeley, California, USA. As part of this year's program, we hosted Research Roundtables to catalyze collaborative, small-group dialogue around critical, timely topics at the intersection of machine learning and healthcare. Each roundtable was moderated by a team of senior and junior chairs who fostered open exchange, intellectual curiosity, and inclusive engagement. The sessions emphasized rigorous discussion of key challenges, exploration of emerging opportunities, and collective ideation toward actionable directions in the field. In total, eight roundtables were held by 19 roundtable chairs on topics of "Explainability, Interpretability, and Transparency," "Uncertainty, Bias, and Fairness," "Causality," "Domain Adaptation," "Foundation Models," "Learning from Small Medical Data," "Multimodal Methods," and "Scalable, Translational Healthcare Solutions."

cs.LG↗

arXiv2025

MindBenchAI: An Actionable Platform to Evaluate the Profile and Performance of Large Language Models in a Mental Healthcare Context

Individuals are increasingly utilizing large language model (LLM)based tools for mental health guidance and crisis support in place of human experts. While AI technology has great potential to improve health outcomes, insufficient empirical evidence exists to suggest that AI technology can be deployed as a clinical replacement; thus, there is an urgent need to assess and regulate such tools. Regulatory efforts have been made and multiple evaluation frameworks have been proposed, however,field-wide assessment metrics have yet to be formally integrated. In this paper, we introduce a comprehensive online platform that aggregates evaluation approaches and serves as a dynamic online resource to simplify LLM and LLM-based tool assessment: MindBenchAI. At its core, MindBenchAI is designed to provide easily accessible/interpretable information for diverse stakeholders (patients, clinicians, developers, regulators, etc.). To create MindBenchAI, we built off our work developing MINDapps.org to support informed decision-making around smartphone app use for mental health, and expanded the technical MINDapps.org framework to encompass novel large language model (LLM) functionalities through benchmarking approaches. The MindBenchAI platform is designed as a partnership with the National Alliance on Mental Illness (NAMI) to provide assessment tools that systematically evaluate LLMs and LLM-based tools with objective and transparent criteria from a healthcare standpoint, assessing both profile (i.e. technical features, privacy protections, and conversational style) and performance characteristics (i.e. clinical reasoning skills).

cs.HC↗

arXiv2025

Machine Learning-based Context-Aware EMAs: An Offline Feasibility Study

Mobile health (mHealth) systems help researchers monitor and care for patients in real-world settings. Studies utilizing mHealth applications use Ecological Momentary Assessment (EMAs), passive sensing, and contextual features to develop emotion recognition models, which rely on EMA responses as ground truth. Due to this, it is crucial to consider EMA compliance when conducting a successful mHealth study. Utilizing machine learning is one approach that can solve this problem by sending EMAs based on the predicted likelihood of a response. However, literature suggests that this approach may lead to prompting participants more frequently during emotions associated with responsiveness, thereby narrowing the range of emotions collected. We propose a multi-objective function that utilizes machine learning to identify optimal times for sending EMAs. The function identifies optimal moments by combining predicted response likelihood with model uncertainty in emotion predictions. Uncertainty would lead the function to prioritize time points when the model is less confident, which often corresponds to underrepresented emotions. We demonstrate that this objective function would result in EMAs being sent when participants are responsive and experiencing less commonly observed emotions. The evaluation is conducted offline using two datasets: (1) 91 spousal caregivers of individuals with Alzheimer's Disease and Related dementias (ADRD), (2) 45 healthy participants. Results show that the multi-objective function tends to be higher when participants respond to EMAs and report less commonly observed emotions. This suggests that using the proposed objective function to guide EMA delivery could improve receptivity rates and capture a broader range of emotions.

cs.HC↗

arXiv2025

Uncovering Bias Paths with LLM-guided Causal Discovery: An Active Learning and Dynamic Scoring Approach

Ensuring fairness in machine learning requires understanding how sensitive attributes like race or gender causally influence outcomes. Existing causal discovery (CD) methods often struggle to recover fairness-relevant pathways in the presence of noise, confounding, or data corruption. Large language models (LLMs) offer a complementary signal by leveraging semantic priors from variable metadata. We propose a hybrid LLM-guided CD framework that extends a breadth-first search strategy with active learning and dynamic scoring. Variable pairs are prioritized for querying using a composite score combining mutual information, partial correlation, and LLM confidence, enabling more efficient and robust structure discovery. To evaluate fairness sensitivity, we introduce a semi-synthetic benchmark based on the UCI Adult dataset, embedding domain-informed bias pathways alongside noise and latent confounders. We assess how well CD methods recover both global graph structure and fairness-critical paths (e.g., sex-->education-->income). Our results demonstrate that LLM-guided methods, including our active, dynamically scored variant, outperform baselines in recovering fairness-relevant structure under noisy conditions. We analyze when LLM-driven insights complement statistical dependencies and discuss implications for fairness auditing in high-stakes domains.

cs.LG↗

arXiv2025

GRAIL: A Benchmark for GRaph ActIve Learning in Dynamic Sensing Environments

Graph-based Active Learning (AL) leverages the structure of graphs to efficiently prioritize label queries, reducing labeling costs and user burden in applications like health monitoring, human behavior analysis, and sensor networks. By identifying strategically positioned nodes, graph AL minimizes data collection demands while maintaining model performance, making it a valuable tool for dynamic environments. Despite its potential, existing graph AL methods are often evaluated on static graph datasets and primarily focus on prediction accuracy, neglecting user-centric considerations such as sampling diversity, query fairness, and adaptability to dynamic settings. To bridge this gap, we introduce GRAIL, a novel benchmarking framework designed to evaluate graph AL strategies in dynamic, real-world environments. GRAIL introduces novel metrics to assess sustained effectiveness, diversity, and user burden, enabling a comprehensive evaluation of AL methods under varying conditions. Extensive experiments on datasets featuring dynamic, real-life human sensor data reveal trade-offs between prediction performance and user burden, highlighting limitations in existing AL strategies. GRAIL demonstrates the importance of balancing node importance, query diversity, and network topology, providing an evaluation mechanism for graph AL solutions in dynamic environments.

cs.LG↗

arXiv2025

Fairness-Driven LLM-based Causal Discovery with Active Learning and Dynamic Scoring

Causal discovery (CD) plays a pivotal role in numerous scientific fields by clarifying the causal relationships that underlie phenomena observed in diverse disciplines. Despite significant advancements in CD algorithms that enhance bias and fairness analyses in machine learning, their application faces challenges due to the high computational demands and complexities of large-scale data. This paper introduces a framework that leverages Large Language Models (LLMs) for CD, utilizing a metadata-based approach akin to the reasoning processes of human experts. By shifting from pairwise queries to a more scalable breadth-first search (BFS) strategy, the number of required queries is reduced from quadratic to linear in terms of variable count, thereby addressing scalability concerns inherent in previous approaches. This method utilizes an Active Learning (AL) and a Dynamic Scoring Mechanism that prioritizes queries based on their potential information gain, combining mutual information, partial correlation, and LLM confidence scores to refine the causal graph more efficiently and accurately. This BFS query strategy reduces the required number of queries significantly, thereby addressing scalability concerns inherent in previous approaches. This study provides a more scalable and efficient solution for leveraging LLMs in fairness-driven CD, highlighting the effects of the different parameters on performance. We perform fairness analyses on the inferred causal graphs, identifying direct and indirect effects of sensitive attributes on outcomes. A comparison of these analyses against those from graphs produced by baseline methods highlights the importance of accurate causal graph construction in understanding bias and ensuring fairness in machine learning systems.

cs.LG↗

arXiv2024

Exploration of LLMs, EEG, and behavioral data to measure and support attention and sleep

We explore the application of large language models (LLMs), pre-trained models with massive textual data for detecting and improving attention and sleep. We investigate the use of LLMs to estimate attention states, sleep stages, and sleep quality and generate sleep improvement suggestions and adaptive guided imagery scripts based on electroencephalogram (EEG) and physical activity data (e.g., waveforms, power spectrogram images, numerical features). Our results show that LLMs can estimate sleep quality based on human textual behavioral features and provide personalized sleep improvement suggestions and guided imagery scripts; however, detecting attention, sleep stages, and sleep quality based on EEG and activity data requires further training data and domain-specific knowledge.

eess.SP↗

arXiv2024

ECG Semantic Integrator (ESI): A Foundation ECG Model Pretrained with LLM-Enhanced Cardiological Text

The utilization of deep learning on electrocardiogram (ECG) analysis has brought the advanced accuracy and efficiency of cardiac healthcare diagnostics. By leveraging the capabilities of deep learning in semantic understanding, especially in feature extraction and representation learning, this study introduces a new multimodal contrastive pretaining framework that aims to improve the quality and robustness of learned representations of 12-lead ECG signals. Our framework comprises two key components, including Cardio Query Assistant (CQA) and ECG Semantics Integrator(ESI). CQA integrates a retrieval-augmented generation (RAG) pipeline to leverage large language models (LLMs) and external medical knowledge to generate detailed textual descriptions of ECGs. The generated text is enriched with information about demographics and waveform patterns. ESI integrates both contrastive and captioning loss to pretrain ECG encoders for enhanced representations. We validate our approach through various downstream tasks, including arrhythmia detection and ECG-based subject identification. Our experimental results demonstrate substantial improvements over strong baselines in these tasks. These baselines encompass supervised and self-supervised learning methods, as well as prior multimodal pretraining approaches.

eess.SP↗

arXiv2024

AdaWaveNet: Adaptive Wavelet Network for Time Series Analysis

Time series data analysis is a critical component in various domains such as finance, healthcare, and meteorology. Despite the progress in deep learning for time series analysis, there remains a challenge in addressing the non-stationary nature of time series data. Traditional models, which are built on the assumption of constant statistical properties over time, often struggle to capture the temporal dynamics in realistic time series, resulting in bias and error in time series analysis. This paper introduces the Adaptive Wavelet Network (AdaWaveNet), a novel approach that employs Adaptive Wavelet Transformation for multi-scale analysis of non-stationary time series data. AdaWaveNet designed a lifting scheme-based wavelet decomposition and construction mechanism for adaptive and learnable wavelet transforms, which offers enhanced flexibility and robustness in analysis. We conduct extensive experiments on 10 datasets across 3 different tasks, including forecasting, imputation, and a newly established super-resolution task. The evaluations demonstrate the effectiveness of AdaWaveNet over existing methods in all three tasks, which illustrates its potential in various real-world applications.

cs.LG↗

arXiv2024

Enhancing Fairness and Performance in Machine Learning Models: A Multi-Task Learning Approach with Monte-Carlo Dropout and Pareto Optimality

Bias originates from both data and algorithmic design, often exacerbated by traditional fairness methods that fail to address the subtle impacts of protected attributes. This study introduces an approach to mitigate bias in machine learning by leveraging model uncertainty. Our approach utilizes a multi-task learning (MTL) framework combined with Monte Carlo (MC) Dropout to assess and mitigate uncertainty in predictions related to protected labels. By incorporating MC Dropout, our framework quantifies prediction uncertainty, which is crucial in areas with vague decision boundaries, thereby enhancing model fairness. Our methodology integrates multi-objective learning through pareto-optimality to balance fairness and performance across various applications. We demonstrate the effectiveness and transferability of our approach across multiple datasets and enhance model explainability through saliency maps to interpret how input features influence predictions, thereby enhancing the interpretability of machine learning models in practical applications.

cs.LG↗

arXiv2024

Balanced Mixed-Type Tabular Data Synthesis with Diffusion Models

Diffusion models have emerged as a robust framework for various generative tasks, including tabular data synthesis. However, current tabular diffusion models tend to inherit bias in the training dataset and generate biased synthetic data, which may influence discriminatory actions. In this research, we introduce a novel tabular diffusion model that incorporates sensitive guidance to generate fair synthetic data with balanced joint distributions of the target label and sensitive attributes, such as sex and race. The empirical results demonstrate that our method effectively mitigates bias in training data while maintaining the quality of the generated samples. Furthermore, we provide evidence that our approach outperforms existing methods for synthesizing tabular data on fairness metrics such as demographic parity ratio and equalized odds ratio, achieving improvements of over $10\%$. Our implementation is available at https://github.com/comp-well-org/fair-tab-diffusion.

cs.LG↗

arXiv2024

SleepNet: Attention-Enhanced Robust Sleep Prediction using Dynamic Social Networks

Sleep behavior significantly impacts health and acts as an indicator of physical and mental well-being. Monitoring and predicting sleep behavior with ubiquitous sensors may therefore assist in both sleep management and tracking of related health conditions. While sleep behavior depends on, and is reflected in the physiology of a person, it is also impacted by external factors such as digital media usage, social network contagion, and the surrounding weather. In this work, we propose SleepNet, a system that exploits social contagion in sleep behavior through graph networks and integrates it with physiological and phone data extracted from ubiquitous mobile and wearable devices for predicting next-day sleep labels about sleep duration. Our architecture overcomes the limitations of large-scale graphs containing connections irrelevant to sleep behavior by devising an attention mechanism. The extensive experimental evaluation highlights the improvement provided by incorporating social networks in the model. Additionally, we conduct robustness analysis to demonstrate the system's performance in real-life conditions. The outcomes affirm the stability of SleepNet against perturbations in input data. Further analyses emphasize the significance of network topology in prediction performance revealing that users with higher eigenvalue centrality are more vulnerable to data perturbations.

cs.LG↗

arXiv2023

ECG-SL: Electrocardiogram(ECG) Segment Learning, a deep learning method for ECG signal

Electrocardiogram (ECG) is an essential signal in monitoring human heart activities. Researchers have achieved promising results in leveraging ECGs in clinical applications with deep learning models. However, the mainstream deep learning approaches usually neglect the periodic and formative attribute of the ECG heartbeat waveform. In this work, we propose a novel ECG-Segment based Learning (ECG-SL) framework to explicitly model the periodic nature of ECG signals. More specifically, ECG signals are first split into heartbeat segments, and then structural features are extracted from each of the segments. Based on the structural features, a temporal model is designed to learn the temporal information for various clinical tasks. Further, due to the fact that massive ECG signals are available but the labeled data are very limited, we also explore self-supervised learning strategy to pre-train the models, resulting significant improvement for downstream tasks. The proposed method outperforms the baseline model and shows competitive performances compared with task-specific methods in three clinical applications: cardiac condition diagnosis, sleep apnea detection, and arrhythmia classification. Further, we find that the ECG-SL tends to focus more on each heartbeat's peak and ST range than ResNet by visualizing the saliency maps.

cs.LG↗

arXiv2023

Empirical Study of Mix-based Data Augmentation Methods in Physiological Time Series Data

Data augmentation is a common practice to help generalization in the procedure of deep model training. In the context of physiological time series classification, previous research has primarily focused on label-invariant data augmentation methods. However, another class of augmentation techniques (\textit{i.e., Mixup}) that emerged in the computer vision field has yet to be fully explored in the time series domain. In this study, we systematically review the mix-based augmentations, including mixup, cutmix, and manifold mixup, on six physiological datasets, evaluating their performance across different sensory data and classification tasks. Our results demonstrate that the three mix-based augmentations can consistently improve the performance on the six datasets. More importantly, the improvement does not rely on expert knowledge or extensive parameter tuning. Lastly, we provide an overview of the unique properties of the mix-based augmentation methods and highlight the potential benefits of using the mix-based augmentation in physiological time series data.

cs.LG↗

arXiv2023

Towards the Understanding of Receptivity and Affect in EMAs using Physiological based Machine Learning Method: Analysis of Receptivity and Affect

As mobile health (mHealth) studies become increasingly productive due to the advancements in wearable and mobile sensor technology, our ability to monitor and model human behavior will be constrained by participant receptivity. The reliance on subjective responses for health constructs poses challenges, especially in populations with lower receptivity rates. Researchers have proposed machine-learning approaches to optimize survey timing and delivery to address this. However, there are concerns regarding potential biases or unintended influences on participant responses. Our study delves into factors impacting receptivity to ecological momentary assessments (EMA) in a 10-day mHealth study, exploring physiological relationships indicative of receptivity and affect. Utilizing data from 45 participants with wearable devices measuring various biometrics, we employ unsupervised (k-means clustering) and supervised (Random Forest and Neural Networks) machine learning methods to infer affect during non-responses. Findings reveal that triggering EMAs based on a receptivity model reduces reported negative affect by over 3 points (0.29 standard deviations). The predicted affect during non-responses exhibits a bimodal distribution, suggesting more frequent initiation during states of higher positive emotions. The study underscores a clear relationship between affect and receptivity, impacting mHealth study efficacy, especially those using machine learning for EMA triggering. Therefore, we propose a smart trigger that promotes EMA receptivity without influencing affect during sampled time points as future work.

cs.HC↗

arXiv2023

PiRL: Participant-Invariant Representation Learning for Healthcare Using Maximum Mean Discrepancy and Triplet Loss

Due to individual heterogeneity, person-specific models are usually achieving better performance than generic (one-size-fits-all) models in data-driven health applications. However, generic models are usually preferable in real-world applications, due to the difficulties of developing person-specific models, such as new-user-adaptation issues and system complexities. To improve the performance of generic models, we propose a Participant-invariant Representation Learning (PiRL) framework, which utilizes maximum mean discrepancy (MMD) loss and domain-adversarial training to encourage the model to learn participant-invariant representations. Further, to avoid trivial solutions in the learned representations, a triplet loss based constraint is used for the model to learn the label-distinguishable embeddings. The proposed framework is evaluated on two public datasets (CLAS and Apnea-ECG), and significant performance improvements are achieved compared to the baseline models.

eess.SP↗

arXiv2022

PiRL: Participant-Invariant Representation Learning for Healthcare

Due to individual heterogeneity, performance gaps are observed between generic (one-size-fits-all) models and person-specific models in data-driven health applications. However, in real-world applications, generic models are usually more favorable due to new-user-adaptation issues and system complexities, etc. To improve the performance of the generic model, we propose a representation learning framework that learns participant-invariant representations, named PiRL. The proposed framework utilizes maximum mean discrepancy (MMD) loss and domain-adversarial training to encourage the model to learn participant-invariant representations. Further, a triplet loss, which constrains the model for inter-class alignment of the representations, is utilized to optimize the learned representations for downstream health applications. We evaluated our frameworks on two public datasets related to physical and mental health, for detecting sleep apnea and stress, respectively. As preliminary results, we found the proposed approach shows around a 5% increase in accuracy compared to the baseline.

cs.LG↗

arXiv2022

Empirical Evaluation of Data Augmentations for Biobehavioral Time Series Data with Deep Learning

Deep learning has performed remarkably well on many tasks recently. However, the superior performance of deep models relies heavily on the availability of a large number of training data, which limits the wide adaptation of deep models on various clinical and affective computing tasks, as the labeled data are usually very limited. As an effective technique to increase the data variability and thus train deep models with better generalization, data augmentation (DA) is a critical step for the success of deep learning models on biobehavioral time series data. However, the effectiveness of various DAs for different datasets with different tasks and deep models is understudied for biobehavioral time series data. In this paper, we first systematically review eight basic DA methods for biobehavioral time series data, and evaluate the effects on seven datasets with three backbones. Next, we explore adapting more recent DA techniques (i.e., automatic augmentation, random augmentation) to biobehavioral time series data by designing a new policy architecture applicable to time series data. Last, we try to answer the question of why a DA is effective (or not) by first summarizing two desired attributes for augmentations (challenging and faithful), and then utilizing two metrics to quantitatively measure the corresponding attributes, which can guide us in the search for more effective DA for biobehavioral time series data by designing more challenging but still faithful transformations. Our code and results are available at Link.

cs.LG↗