Large language models (LLMs) acquire a breadth of information across various domains. However, their computational complexity, cost, and lack of transparency often hinder their direct application for predictive tasks where privacy and interpretability are paramount. In fields such as healthcare, biology, and finance, specialised and interpretable linear models still hold considerable value. In such domains, labelled data may be scarce or expensive to obtain. Well-specified prior distributions over model parameters can reduce the sample complexity of learning through Bayesian inference; however, eliciting expert priors can be time-consuming. We therefore introduce AutoElicit to extract knowledge from LLMs and construct priors for predictive models. We show these priors are informative and can be refined using natural language. We perform a careful study contrasting AutoElicit with in-context learning and demonstrate how to perform model selection between the two methods. We find that AutoElicit yields priors that can substantially reduce error over uninformative priors, using fewer labels, and consistently outperform in-context learning. We show that AutoElicit saves over 6 months of labelling effort when building a new predictive model for urinary tract infections from sensor recordings of people living with dementia.

Urinary tract infections (UTIs) are a significant health concern, particularly for people living with dementia (PLWD), as they can lead to severe complications if not detected and treated early. This study builds on previous work that utilised machine learning (ML) to detect UTIs in PLWD by analysing in-home activity and physiological data collected through low-cost, passive sensors. The current research focuses on improving the performance of previous models, particularly by refining the Multilayer Perceptron (MLP), to better handle variations in home environments and improve sex fairness in predictions by making use of concepts from multitask learning. This study implemented three primary model designs: feature clustering, loss-dependent clustering, and participant ID embedding which were compared against a baseline MLP model. The results demonstrated that the loss-dependent MLP achieved the most significant improvements, increasing validation precision from 48.92 % to 72.60 % and sensitivity from 27.44 % to 70.52 %, while also enhancing model fairness across sexes. These findings suggest that the refined models offer a more reliable and equitable approach to early UTI detection in PLWD, addressing participant-specific data variations and enabling clinicians to detect and screen for UTI risks more effectively, thereby facilitating earlier and more accurate treatment decisions. The code used in this study is available at the following link: https://github.com/Kexin-Fan/Multi-Source-Analysing.git.

In the field of medical diagnosis and patient monitoring, effective pattern recognition in neurological time-series data is essential. Traditional methods predominantly based on statistical or probabilistic learning and inference often struggle with multivariate, multi-source, state-varying, and noisy data while also posing privacy risks due to excessive information collection and modeling. Furthermore, these methods often overlook critical statistical information, such as the distribution of data points and inherent uncertainties. To address these challenges, we introduce an information theory-based pipeline that leverages specialized features to identify patterns in neurological time-series data while minimizing privacy risks. We incorporate various entropy methods based on the characteristics of different scenarios and entropy. For stochastic state transition applications, we incorporate Shannon's entropy, entropy rates, entropy production, and the von Neumann entropy of Markov chains. When state modeling is impractical, we select and employ approximate entropy, increment entropy, dispersion entropy, phase entropy, and slope entropy. The pipeline's effectiveness and scalability are demonstrated through pattern analysis in a dementia care dataset and also an epileptic and a myocardial infarction dataset. The results indicate that our information theory-based pipeline can achieve average performance improvements across various models on the recall rate, F1 score, and accuracy by up to 13.08 percentage points, while enhancing inference efficiency by reducing the number of model parameters by an average of 3.10 times. Thus, our approach opens a promising avenue for improved, efficient, and critical statistical information-considered pattern recognition in medical time-series data.