Leveraging the potential of synthetic text for AI in mental healthcare

A review on generative AI models for synthetic medical text, time series, and longitudinal data

This paper presents the results of a novel scoping review on the practical models for generating three different types of synthetic health records (SHRs): medical text, time series, and longitudinal data. The innovative aspects of the review, which incorporate study objectives, data modality, and research methodology of the reviewed studies, uncover the importance and the scope of the topic for the digital medicine context. In total, 52 publications met the eligibility criteria for generating medical time series (22), longitudinal data (17), and medical text (13). Privacy preservation was found to be the main research objective of the studied papers, along with class imbalance, data scarcity, and data imputation as the other objectives. The adversarial network-based, probabilistic, and large language models exhibited superiority for generating synthetic longitudinal data, time series, and medical texts, respectively. Finding a reliable performance measure to quantify SHR re-identification risk is the major research gap of the topic.

Synthetic data as an investigative tool in hypertension and renal diseases research

There is a growing body of clinical research on the utility of synthetic data derivatives, an emerging research tool in medicine. In nephrology, clinicians can use machine learning and artificial intelligence as powerful aids in their clinical decision-making while also preserving patient privacy. This is especially important given the epidemiology of chronic kidney disease, renal oncology, and hypertension worldwide. However, there remains a need to create a framework for guidance regarding how to better utilize synthetic data as a practical application in this research.

Open Science at the generative AI turn: An exploratory analysis of challenges and opportunities

Technology influences Open Science (OS) practices, because conducting science in transparent, accessible, and participatory ways requires tools and platforms for collaboration and sharing results. Due to this relationship, the characteristics of the employed technologies directly impact OS objectives. Generative Artificial Intelligence (GenAI) is increasingly used by researchers for tasks such as text refining, code generation/editing, reviewing literature, and data curation/analysis. Nevertheless, concerns about openness, transparency, and bias suggest that GenAI may benefit from greater engagement with OS. GenAI promises substantial efficiency gains but is currently fraught with limitations that could negatively impact core OS values, such as fairness, transparency, and integrity, and may harm various social actors. In this paper, we explore the possible positive and negative impacts of GenAI on OS. We use the taxonomy within the UNESCO Recommendation on Open Science to systematically explore the intersection of GenAI and OS. We conclude that using GenAI could advance key OS objectives by broadening meaningful access to knowledge, enabling efficient use of infrastructure, improving engagement of societal actors, and enhancing dialogue among knowledge systems. However, due to GenAI's limitations, it could also compromise the integrity, equity, reproducibility, and reliability of research. Hence, sufficient checks, validation, and critical assessments are essential when incorporating GenAI into research workflows.

Embracing the uncertainty in human-machine collaboration to support clinical decision-making for mental health conditions

Two significant obstacles exist preventing the widespread usage of Deep Learning (DL) models for predicting healthcare outcomes in general and mental health conditions in particular. Firstly, DL models do not quantify the uncertainty in their predictions, so clinicians are unsure of which predictions they can trust. Secondly, DL models do not triage, i.e., separate which cases could be best handled by the human or the model. This paper attempts to address these obstacles using Bayesian Deep Learning (BDL), which extends DL probabilistically and allows us to quantify the model's uncertainty, which we use to improve human-model collaboration. We implement a range of state-of-the-art DL models for Natural Language Processing and apply a range of BDL methods to these models. Taking a step closer to the real-life scenarios of human-AI collaboration, we propose a Referral Learning methodology for the models that make predictions for certain instances while referring the rest of the instances to a human expert for further assessment. The study demonstrates that models can significantly enhance their performance by seeking human assistance in cases where the model exhibits high uncertainty, which is closely linked to misclassifications. Referral Learning offers two options: (1) supporting humans in cases where the model predicts with certainty, and (2) triaging cases where the model evaluated when it had a better chance of being right than the human by evaluating human disagreement. The latter method combines model uncertainty from BDL and human disagreement from multiple annotations, resulting in improved triaging capabilities.