21 December 2022 in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
There is a growing body of research revealing that longitudinal passive sensing data from smartphones and wearable devices can capture daily behavior signals for human behavior modeling, such as depression detection. Most prior studies build and evaluate machine learning models using data collected from a single population. However, to ensure that a behavior model can work for a larger group of users, its generalizability needs to be verified on multiple datasets from different populations. We present the first work evaluating cross-dataset generalizability of longitudinal behavior models, using depression detection as an application. We collect multiple longitudinal passive mobile sensing datasets with over 500 users from two institutes over a two-year span, leading to four institute-year datasets. Using the datasets, we closely re-implement and evaluated nine prior depression detection algorithms. Our experiment reveals the lack of model generalizability of these methods. We also implement eight recently popular domain generalization algorithms from the machine learning community. Our results indicate that these methods also do not generalize well on our datasets, with barely any advantage over the naive baseline of guessing the majority. We then present two new algorithms with better generalizability. Our new algorithm, Reorder, significantly and consistently outperforms existing methods on most cross-dataset generalization setups. However, the overall advantage is incremental and still has great room for improvement. Our analysis reveals that the individual differences (both within and between populations) may play the most important role in the cross-dataset generalization challenge. Finally, we provide an open-source benchmark platform GLOBEM- short for Generalization of Longitudinal BEhavior Modeling - to consolidate all 19 algorithms. GLOBEM can support researchers in using, developing, and evaluating different longitudinal behavior modeling methods. We call for researchers' attention to model generalizability evaluation for future longitudinal human behavior modeling studies.
28 March 2025 in Science Advances
Advances in artificial intelligence (AI) have achieved expert-level performance in medical imaging applications. Notably, self-supervised vision-language foundation models can detect a broad spectrum of pathologies without relying on explicit training annotations. However, it is crucial to ensure that these AI models do not mirror or amplify human biases, disadvantaging historically marginalized groups such as females or Black patients. In this study, we investigate the algorithmic fairness of state-of-the-art vision-language foundation models in chest x-ray diagnosis across five globally sourced datasets. Our findings reveal that compared to board-certified radiologists, these foundation models consistently underdiagnose marginalized groups, with even higher rates seen in intersectional subgroups such as Black female patients. Such biases present over a wide range of pathologies and demographic attributes. Further analysis of the model embedding uncovers its substantial encoding of demographic information. Deploying medical AI systems with biases can intensify preexisting care disparities, posing potential challenges to equitable healthcare access and raising ethical questions about their clinical applications.
13 May 2024 in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
Passively collected behavioral health data from ubiquitous sensors could provide mental health professionals valuable insights into patient's daily lives, but such efforts are impeded by disparate metrics, lack of interoperability, and unclear correlations between the measured signals and an individual's mental health. To address these challenges, we pioneer the exploration of large language models (LLMs) to synthesize clinically relevant insights from multi-sensor data. We develop chain-of-thought prompting methods to generate LLM reasoning on how data pertaining to activity, sleep and social interaction relate to conditions such as depression and anxiety. We then prompt the LLM to perform binary classification, achieving accuracies of 61.1%, exceeding the state of the art. We find models like GPT-4 correctly reference numerical data 75% of the time. While we began our investigation by developing methods to use LLMs to output binary classifications for conditions like depression, we find instead that their greatest potential value to clinicians lies not in diagnostic classification, but rather in rigorous analysis of diverse self-tracking data to generate natural language summaries that synthesize multiple data streams and identify potential concerns. Clinicians envisioned using these insights in a variety of ways, principally for fostering collaborative investigation with patients to strengthen the therapeutic alliance and guide treatment. We describe this collaborative engagement, additional envisioned uses, and associated concerns that must be addressed before adoption in real-world contexts.
5 January 2024 in Science Advances
Recent respiratory disease screening studies suggest promising performance of cough classifiers, but potential biases in model training and dataset quality preclude robust conclusions. To examine tuberculosis (TB) cough diagnostic features, we enrolled subjects with pulmonary TB (N= 149) and controls with other respiratory illnesses (N= 46) in Nairobi. We collected a dataset with 33,000 passive coughs and 1600 forced coughs in a controlled setting with similar demographics. We trained a ResNet18-based cough classifier using images of passive cough scalogram as input and obtained a fivefold cross-validation sensitivity of 0.70 (±0.11 SD). The smartphone-based model had better performance in subjects with higher bacterial load {receiver operating characteristic–area under the curve (ROC-AUC): 0.87 [95% confidence interval (CI): 0.87 to 0.88],P< 0.001} or lung cavities [ROC-AUC: 0.89 (95% CI: 0.88 to 0.89),P< 0.001]. Overall, our data suggest that passive cough features distinguish TB from non-TB subjects and are associated with bacterial burden and disease severity.