Accuracy and Consistency of LLMs in the Registered Dietitian Exam: The Impact of Prompt Engineering and Knowledge Retrieval

Large language models (LLMs) are fundamentally transforming human-facing applications in the health and well-being domains: boosting patient engagement, accelerating clinical decision-making, and facilitating medical education. Although state-of-the-art LLMs have shown superior performance in several conversational applications, evaluations within nutrition and diet applications are still insufficient. In this paper, we propose to employ the Registered Dietitian (RD) exam to conduct a standard and comprehensive evaluation of state-of-the-art LLMs, GPT-4o, Claude 3.5 Sonnet, and Gemini 1.5 Pro, assessing both accuracy and consistency in nutrition queries. Our evaluation includes 1050 RD exam questions encompassing several nutrition topics and proficiency levels. In addition, for the first time, we examine the impact of Zero-Shot (ZS), Chain of Thought (CoT), Chain of Thought with Self Consistency (CoT-SC), and Retrieval Augmented Prompting (RAP) on both accuracy and consistency of the responses. Our findings revealed that while these LLMs obtained acceptable overall performance, their results varied considerably with different prompts and question domains. GPT-4o with CoT-SC prompting outperformed the other approaches, whereas Gemini 1.5 Pro with ZS recorded the highest consistency. For GPT-4o and Claude 3.5, CoT improved the accuracy, and CoT-SC improved both accuracy and consistency. RAP was particularly effective for GPT-4o to answer Expert level questions. Consequently, choosing the appropriate LLM and prompting technique, tailored to the proficiency level and specific domain, can mitigate errors and potential risks in diet and nutrition chatbots.

Building Trust in Mental Health Chatbots: Safety Metrics and LLM-Based Evaluation Tools

Objective: This study aims to develop and validate an evaluation framework to ensure the safety and reliability of mental health chatbots, which are increasingly popular due to their accessibility, human-like interactions, and context-aware support. Materials and Methods: We created an evaluation framework with 100 benchmark questions and ideal responses, and five guideline questions for chatbot responses. This framework, validated by mental health experts, was tested on a GPT-3.5-turbo-based chatbot. Automated evaluation methods explored included large language model (LLM)-based scoring, an agentic approach using real-time data, and embedding models to compare chatbot responses against ground truth standards. Results: The results highlight the importance of guidelines and ground truth for improving LLM evaluation accuracy. The agentic method, dynamically accessing reliable information, demonstrated the best alignment with human assessments. Adherence to a standardized, expert-validated framework significantly enhanced chatbot response safety and reliability. Discussion: Our findings emphasize the need for comprehensive, expert-tailored safety evaluation metrics for mental health chatbots. While LLMs have significant potential, careful implementation is necessary to mitigate risks. The superior performance of the agentic approach underscores the importance of real-time data access in enhancing chatbot reliability. Conclusion: The study validated an evaluation framework for mental health chatbots, proving its effectiveness in improving safety and reliability. Future work should extend evaluations to accuracy, bias, empathy, and privacy to ensure holistic assessment and responsible integration into healthcare. Standardized evaluations will build trust among users and professionals, facilitating broader adoption and improved mental health support through technology.

Graph-Augmented LLMs for Personalized Health Insights: A Case Study in Sleep Analysis

Health monitoring systems have revolutionized modern healthcare by enabling the continuous capture of physiological and behavioral data, essential for preventive measures and early health intervention. While integrating this data with Large Language Models (LLMs) has shown promise in delivering interactive health advice, traditional methods like Retrieval-Augmented Generation (RAG) and fine-tuning often fail to fully utilize the complex, multi-dimensional, and temporally relevant data from wearable devices. These conventional approaches typically provide limited actionable and personalized health insights due to their inadequate capacity to dynamically integrate and interpret diverse health data streams. In response, this paper introduces a graph-augmented LLM framework designed to significantly enhance the personalization and clarity of health insights. Utilizing a hierarchical graph structure, the framework captures inter and intra-patient relationships, enriching LLM prompts with dynamic feature importance scores derived from a Random Forest Model. The effectiveness of this approach is demonstrated through a sleep analysis case study involving 20 college students during the COVID-19 lockdown, highlighting the potential of our model to generate actionable and personalized health insights efficiently. We leverage another LLM to evaluate the insights for relevance, comprehensiveness, actionability, and personalization, addressing the critical need for models that process and interpret complex health data effectively. Our findings show that augmenting prompts with our framework yields significant improvements in all 4 criteria. Through our framework, we can elicit well-crafted, more thoughtful responses tailored to a specific patient.

Empathy Through Multimodality in Conversational Interfaces

Agents represent one of the most emerging applications of Large Language Models (LLMs) and Generative AI, with their effectiveness hinging on multimodal capabilities to navigate complex user environments. Conversational Health Agents (CHAs), a prime example of this, are redefining healthcare by offering nuanced support that transcends textual analysis to incorporate emotional intelligence. This paper introduces an LLM-based CHA engineered for rich, multimodal dialogue-especially in the realm of mental health support. It adeptly interprets and responds to users' emotional states by analyzing multimodal cues, thus delivering contextually aware and empathetically resonant verbal responses. Our implementation leverages the versatile openCHA framework, and our comprehensive evaluation involves neutral prompts expressed in diverse emotional tones: sadness, anger, and joy. We evaluate the consistency and repeatability of the planning capability of the proposed CHA. Furthermore, human evaluators critique the CHA's empathic delivery, with findings revealing a striking concordance between the CHA's outputs and evaluators' assessments. These results affirm the indispensable role of vocal (soon multimodal) emotion recognition in strengthening the empathetic connection built by CHAs, cementing their place at the forefront of interactive, compassionate digital health solutions.

ALCM: Autonomous LLM-Augmented Causal Discovery Framework

To perform effective causal inference in high-dimensional datasets, initiating the process with causal discovery is imperative, wherein a causal graph is generated based on observational data. However, obtaining a complete and accurate causal graph poses a formidable challenge, recognized as an NP-hard problem. Recently, the advent of Large Language Models (LLMs) has ushered in a new era, indicating their emergent capabilities and widespread applicability in facilitating causal reasoning across diverse domains, such as medicine, finance, and science. The expansive knowledge base of LLMs holds the potential to elevate the field of causal reasoning by offering interpretability, making inferences, generalizability, and uncovering novel causal structures. In this paper, we introduce a new framework, named Autonomous LLM-Augmented Causal Discovery Framework (ALCM), to synergize data-driven causal discovery algorithms and LLMs, automating the generation of a more resilient, accurate, and explicable causal graph. The ALCM consists of three integral components: causal structure learning, causal wrapper, and LLM-driven causal refiner. These components autonomously collaborate within a dynamic environment to address causal discovery questions and deliver plausible causal graphs. We evaluate the ALCM framework by implementing two demonstrations on seven well-known datasets. Experimental results demonstrate that ALCM outperforms existing LLM methods and conventional data-driven causal reasoning mechanisms. This study not only shows the effectiveness of the ALCM but also underscores new research directions in leveraging the causal reasoning capabilities of LLMs.

Integrating Wearable Sensor Data and Self-reported Diaries for Personalized Affect Forecasting

Emotional states, as indicators of affect, are pivotal to overall health, making their accurate prediction before onset crucial. Current studies are primarily centered on immediate short-term affect detection using data from wearable and mobile devices. These studies typically focus on objective sensory measures, often neglecting other forms of self-reported information like diaries and notes. In this paper, we propose a multimodal deep learning model for affect status forecasting. This model combines a transformer encoder with a pre-trained language model, facilitating the integrated analysis of objective metrics and self-reported diaries. To validate our model, we conduct a longitudinal study, enrolling college students and monitoring them over a year, to collect an extensive dataset including physiological, environmental, sleep, metabolic, and physical activity parameters, alongside open-ended textual diaries provided by the participants. Our results demonstrate that the proposed model achieves predictive accuracy of 82.50% for positive affect and 82.76% for negative affect, a full week in advance. The effectiveness of our model is further elevated by its explainability.

Knowledge-Infused LLM-Powered Conversational Health Agent: A Case Study for Diabetes Patients

Effective diabetes management is crucial for maintaining health in diabetic patients. Large Language Models (LLMs) have opened new avenues for diabetes management, facilitating their efficacy. However, current LLM-based approaches are limited by their dependence on general sources and lack of integration with domain-specific knowledge, leading to inaccurate responses. In this paper, we propose a knowledge-infused LLM-powered conversational health agent (CHA) for diabetic patients. We customize and leverage the open-source openCHA framework, enhancing our CHA with external knowledge and analytical capabilities. This integration involves two key components: 1) incorporating the American Diabetes Association dietary guidelines and the Nutritionix information and 2) deploying analytical tools that enable nutritional intake calculation and comparison with the guidelines. We compare the proposed CHA with GPT4. Our evaluation includes 100 diabetes-related questions on daily meal choices and assessing the potential risks associated with the suggested diet. Our findings show that the proposed agent demonstrates superior performance in generating responses to manage essential nutrients.

Impact of Physical Activity on Quality of Life During Pregnancy: A Causal ML Approach

The concept of Quality of Life (QoL) refers to a holistic measurement of an individual's well-being, incorporating psychological and social aspects. Pregnant women, especially those with obesity and stress, often experience lower QoL. Physical activity (PA) has shown the potential to enhance the QoL. However, pregnant women who are overweight and obese rarely meet the recommended level of PA. Studies have investigated the relationship between PA and QoL during pregnancy using correlation-based approaches. These methods aim to discover spurious correlations between variables rather than causal relationships. Besides, the existing methods mainly rely on physical activity parameters and neglect the use of different factors such as maternal (medical) history and context data, leading to biased estimates. Furthermore, the estimations lack an understanding of mediators and counterfactual scenarios that might affect them. In this paper, we investigate the causal relationship between being physically active (treatment variable) and the QoL (outcome) during pregnancy and postpartum. To estimate the causal effect, we develop a Causal Machine Learning method, integrating causal discovery and causal inference components. The data for our investigation is derived from a long-term wearable-based health monitoring study focusing on overweight and obese pregnant women. The machine learning (meta-learner) estimation technique is used to estimate the causal effect. Our result shows that performing adequate physical activity during pregnancy and postpartum improves the QoL by units of 7.3 and 3.4 on average in physical health and psychological domains, respectively. In the final step, four refutation analysis techniques are employed to validate our estimation.

Differential Private Federated Transfer Learning for Mental Health Monitoring in Everyday Settings: A Case Study on Stress Detection

Mental health conditions, prevalent across various demographics, necessitate efficient monitoring to mitigate their adverse impacts on life quality. The surge in data-driven methodologies for mental health monitoring has underscored the importance of privacy-preserving techniques in handling sensitive health data. Despite strides in federated learning for mental health monitoring, existing approaches struggle with vulnerabilities to certain cyber-attacks and data insufficiency in real-world applications. In this paper, we introduce a differential private federated transfer learning framework for mental health monitoring to enhance data privacy and enrich data sufficiency. To accomplish this, we integrate federated learning with two pivotal elements: (1) differential privacy, achieved by introducing noise into the updates, and (2) transfer learning, employing a pre-trained universal model to adeptly address issues of data imbalance and insufficiency. We evaluate the framework by a case study on stress detection, employing a dataset of physiological and contextual data from a longitudinal study. Our finding show that the proposed approach can attain a 10% boost in accuracy and a 21% enhancement in recall, while ensuring privacy protection.

Robust CNN-based Respiration Rate Estimation for Smartwatch PPG and IMU

Respiratory rate (RR) serves as an indicator of various medical conditions, such as cardiovascular diseases and sleep disorders. These RR estimation methods were mostly designed for finger-based PPG collected from subjects in stationary situations (e.g., in hospitals). In contrast to finger-based PPG signals, wrist-based PPG are more susceptible to noise, particularly in their low frequency range, which includes respiratory information. Therefore, the existing methods struggle to accurately extract RR when PPG data are collected from wrist area under free-living conditions. The increasing popularity of smartwatches, equipped with various sensors including PPG, has prompted the need for a robust RR estimation method. In this paper, we propose a convolutional neural network-based approach to extract RR from PPG, accelerometer, and gyroscope signals captured via smartwatches. Our method, including a dilated residual inception module and 1D convolutions, extract the temporal information from the signals, enabling RR estimation. Our method is trained and tested using data collected from 36 subjects under free-living conditions for one day using Samsung Gear Sport watches. For evaluation, we compare the proposed method with four state-of-the-art RR estimation methods. The RR estimates are compared with RR references obtained from a chest-band device. The results show that our method outperforms the existing methods with the Mean-Absolute-Error and Root-Mean-Square-Error of 1.85 and 2.34, while the best results obtained by the other methods are 2.41 and 3.29, respectively. Moreover, compared to the other methods, the absolute error distribution of our method was narrow (with the lowest median), indicating a higher level of agreement between the estimated and reference RR values.