ABSTRACT
Background Clinical trial matching, essential for advancing medical research, involves detailed screening of potential participants to ensure alignment with specific trial requirements. Research staff face challenges due to the high volume of eligible patients and the complexity of varying eligibility criteria. The traditional manual process, both time-consuming and error-prone, often leads to missed opportunities. Recently, large language models (LLMs), specifically generative pre-trained transformers (GPTs), have become impressive and impactful tools. Utilizing such tools from artificial intelligence (AI) and natural language processing (NLP) may enhance the accuracy and efficiency of this process through automated patient screening against established criteria. Methods Utilizing data from the National NLP Clinical Challenges (n2c2) 2018 Challenge, we utilized 202 longitudinal patient records. These records were annotated by medical professionals and evaluated against 13 selection criteria encompassing various health assessments. Our approach involved embedding medical documents into a vector database to determine relevant document sections and then using an LLM (OpenAI's GPT-3.5 Turbo and GPT-4) in tandem with structured and chain-of-thought prompting techniques for systematic document assessment against the criteria. Misclassified criteria were also examined to identify classification challenges. Results This study achieved an accuracy of 0.81, sensitivity of 0.80, specificity of 0.82, and a micro F1 score of 0.79 using GPT-3.5 Turbo, and an accuracy of 0.87, sensitivity of 0.85, specificity of 0.89, and micro F1 score of 0.86 using GPT-4. Notably, some criteria in the ground truth appeared mislabeled, an issue we couldn't explore further due to insufficient label generation guidelines on the website. Conclusion Our findings underscore the potential of AI and NLP technologies, including LLMs, in the clinical trial matching process. The study demonstrated strong capabilities in identifying eligible patients and minimizing false inclusions. Such automated systems promise to alleviate the workload of research staff and improve clinical trial enrollment, thus accelerating the process and enhancing the overall feasibility of clinical research. Further work is needed to determine the potential of this approach when implemented on real clinical data.
ABSTRACT
Previous studies have linked peripheral microvascular dysfunction measured by arterial tonometry to high residual risk in on-statin patients. Digital thermal monitoring (DTM) of microvascular function is a new and simplified technique based on fingertip temperature measurements that has been correlated with the burden of atherosclerosis and its risk factors. Here, we report analyses of DTM data from two large US registries: Registry-I (6,084 cases) and Registry-II (1,021 cases) across 49 US outpatient clinics. DTM tests were performed using a VENDYS device during a 5-minute arm-cuff reactive hyperemia. Fingertip temperature falls during cuff inflation and rebounds after deflation. Adjusted maximum temperature rebound was reported as vascular reactivity index (VRI). VRI distributions were similar in both registries, with mean ± SD of 1.58 ± 0.53 in Registry-I and 1.52 ± 0.43 in Registry-II. In the combined dataset, only 18% had optimal VRI (≥2.0) and 82% were either poor (<1.0) or intermediate (1.0-2.0). Women had slightly higher VRI than men (1.62 ± 0.56 vs. 1.54 ± 0.47, p < 0.001). VRI was inversely but mildly correlated with age (r = -0.19, p < 0.001). Suboptimal VRI was found in 72% of patients <50 years, 82% of 50-70 years, and 86% of ≥70 years. Blood pressure was not correlated with VRI. In this largest registry of peripheral microvascular function measurements, suboptimal scores were highly frequent among on-treatment patients, possibly suggesting a significant residual risk. Prospective studies are warranted to validate microvascular dysfunction as an indicator of residual risk.
ABSTRACT
It has been reported in the literature that the perception of crime at the neighbourhood level inversely affects the walking behaviour of individuals. On the other hand, the gated neighbourhoods are considered safe from crime, however, there is a lack of research on the association of the perception of crime and walking in gated neighbourhoods. Therefore, the objectives of the study reported in this paper were to investigate the association between the perception of crime and walking in gated and non-gated neighbourhoods. A questionnaire was used to collect the data on walking and the perception of crime in 16 neighbourhoods of Karachi Pakistan, 8 out of which were gated. Independent sample t-test and gamma tests were used for the data analysis. The results show that although there is a lower perception of crime in the gated neighbourhoods, yet the inhabitants of gated neighbourhoods engage in less physical activity comprising of walking. In spite of a greater perception of crime in non-gated neighbourhoods, higher values of walking were reported by the residents of those neighbourhoods. Therefore, it has been concluded that there does not exist a definite relationship between the perception of crime and walking behaviour at the neighbourhood level and the perceived safety from crime claimed by the proponents of the gated neighbourhoods does not encourage walking among the residents.