Optical Coherence Tomography (OCT) is a widely adopted imaging technique in ophthalmology, yet its clinical interpretation remains prone to inconsistency and subjectivity. This study presents a retrieval-augmented generation (RAG) framework aimed at improving both diagnostic accuracy and interpretability in OCT-based analysis. The pipeline integrates a dual-headed convolutional neural network with a case-based retrieval system and a language model capable of generating structured clinical summaries. A ResNet-50 model was trained to classify diabetic retinopathy (DR), diabetic macular edema (DME), and key retinal biomarkers using a public OCT dataset. Feature embeddings generated by the model were indexed into a similarity-search database to enable retrieval of clinically relevant cases. Retrieved scans, along with classification outputs, were used to prompt a large language model to generate concise diagnostic reports that reflect both the model’s predictions and visually aligned precedents. The system achieved 89% accuracy in distinguishing DR from DME in a hold-out test set. Interpretability was also demonstrated through consistent retrieval of semantically similar cases. Generated reports were found to be readable and aligned with clinical reasoning. By combining classification performance with transparent, case-grounded explanations, the RAG approach enhances clinical confidence and supports decision-making. This work highlights the potential of retrieval-augmented pipelines to reduce variability in OCT interpretation and to serve as a scalable, explainable foundation for future AI-driven diagnostic support in ophthalmology.

Improving Optical Coherence Tomography Interpretation With Retrieval-Guided Diagnosis and Text Generation

As populations age globally, older adults are increasingly affected by chronic physical and mental health challenges, including frailty, cognitive impairment, depression, and social isolation. Artificial intelligence (AI) tools such as chatbots, wearable monitors, predictive models, and socially assistive robots have been proposed as scalable solutions to support aging populations. This literature review systematically examined 28 peer-reviewed studies to evaluate the efficacy and usability of current AI interventions designed to enhance health and well-being in adults aged 65 and older. Methods included supervised machine learning for diagnosis and prediction, large language models for health communication, and co-designed systems for home-based care and emotional support. Results suggest that AI applications can improve physical activity, emotional regulation, and early detection of cognitive decline and depression, with user feedback indicating positive perceptions of usability and engagement. However, most studies had small, homogeneous samples, lacked long-term follow-up, and were conducted in simulated or non-clinical settings. Ethical and implementation challenges were common, including data privacy concerns, unclear algorithmic decision-making, limited digital literacy, and underrepresentation of diverse older adult populations. Despite these limitations, the evidence indicates that AI holds promise in augmenting and streamlining older adult care when tools are transparent, inclusive, and tailored to user needs. Broader adoption will require rigorous evaluation in real-world environments, equitable design practices, and sustained attention to ethical risks.

Artificial Intelligence for Care for Older Adults with Chronic Health Conditions

Large language models are a fascinating and powerful technology, but are not faultless. Iteratively selecting the most probable next word can result in a sentence that sounds coherent, but contains content that is fabricated, taken out of context, or in self-conflict. This can create particular danger when end users rely on LLMs for information on critical issues. Many countries lack equal or affordable access to healthcare. This can lead to some viewing popular LLM chatbots such as ChatGPT as being an online doctor; available to answer their healthcare needs. People with chronic diseases are particularly vulnerable to this, as the chronicity of their disease presents a consistent healthcare cost. Our research seeks to take the first step of many in creating a framework within which LLMs can self-check for hallucinations, resulting in more reliable information. We worked in reference to an existing paper to create a dataset containing pairs of questions and hallucinated answers, specifically in reference to chronic disease. We also conduct an experiment on our dataset in which we determine whether LLMs can accurately detect their own hallucinations. We find that, while some LLMs can identify a hallucinated answer with incredible accuracy, it is highly inconsistent from model to model. We endorse the future research of hallucination detection technologies in LLMs in order to mitigate risk of harm caused by the dissemination of inaccurate information by LLMs.

A Reflection on Hallucinations in LLM Responses to Chronic Disease Queries

Chronic kidney disease (CKD) is a progressive and irreversible loss of kidney function that affected about 753 million people globally in 2016. There are often no noticeable symptoms until it reaches later stages which makes early identification important for prevention. Diabetes mellitus is among the leading causes of chronic kidney disease worldwide, with an estimated 40\% of diabetic patients developing diabetic kidney disease. This project applies machine learning techniques to predict self-reported kidney disease risk in older diabetic individuals (ages 55+) using data from the U.S. National Health and Nutrition Examination Survey (NHANES). I used survey- based variables such as blood pressure, glycohemoglobin, body mass index (BMI), physical activity, and demographics to create a classification model. After preprocessing and engineering features related to age, blood pressure, and activity levels, I trained logistic regression and random forest classifiers to identify individuals at higher risk. The random forest model achieved an area under the receiver operating characteristic (ROC) curve (AUC) of 0.93, while the logistic regression model achieved an ROC AUC of 0.87. These results show that both models can effectively identify high-risk individuals. Feature importance analysis identified blood pressure, age, BMI, and diabetes status as leading predictors. This study demonstrates that machine learning can be used to improve early detection of CKD risk in aging diabetic populations.

Early Detection of Kidney Disease in Aging Diabetic Populations Using Machine Learning

This research leverages deep learning techniques to investigate the connectivity between social determinants of health (SDoH) and chronic disease-related mortality and life expectancy globally. We integrated multiple datasets, including World Bank socioeconomic indicators, WHO global health estimates, and income inequality measures, spanning from 2000 to 2021. Using exploratory data analysis, we identified global trends and significant correlations between five chronic disease outcomes, Alzheimer’s, asthma, cardiovascular diseases, diabetes, and kidney diseases, and various socioeconomic factors. We implemented multiple predictive models, including linear regression, XGBoost, and recurrent neural networks, including Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM), validated using 3-fold cross- validation. The parameters are selected using hyperparameter tuning techniques. XGBoost consistently outperformed other methods across diseases, achieving superior accuracy as measured by mean squared error (MSE) and coefficient of determination (R²). To ensure interpretability, SHAP (SHapley Additive exPlanations) values were applied, highlighting influential socioeconomic factors like income inequality, diabetes prevalence, and life expectancy. Our analysis revealed distinct patterns based on income groups and geographic regions, emphasizing the necessity of specific public health strategies. This research uniquely contributes by integrating interpretable AI techniques, providing actionable insights into the socioeconomic drivers of chronic diseases, and guiding effective policy and intervention design aimed at promoting healthier aging populations worldwide.

Deep Learning Insights into Social Determinants of Chronic Disease and Longevity

The global rise in the elderly population is putting an increasing strain on healthcare systems, particularly due to the increased chance of chronic illness, polypharmacy, and healthcare utilization. The traditional one-size-fits-all treatment approach often fails to address the unique and evolving needs of older adults, leading to adverse drug reactions, diminished quality of life, and inefficient use of medical resources. This study investigated the potential of personalized medicine — augmented by artificial intelligence (AI) — to improve elderly care through data-driven, individualized treatment plans. By integrating data from electronic health records, genomics, wearable devices, and lifestyle factors, we developed AI-enhanced models capable of tailoring treatments to each patient’s specific profile. These models allow for real-time treatment adjustments, predictive risk assessments, and optimized drug regimens. Our findings suggest that AI-driven personalized care can reduce adverse outcomes, enhance clinical effectiveness, and support proactive, scalable, and patient-centered healthcare for aging populations.

Improving Prediction of ADR in Elderly Patients Using Machine Learning Algorithms

AAAI/EAAI Patrick Henry Winston Outstanding Educator Award: T(w)eaching AI in the Age of LLMs

Mechanistic interpretability is one of the most exciting and important research programs in current AI. My aim is to build some philosophical foundations for the program, along with setting out some concrete challenges and assessing progress to date. I will argue for the importance of propositional interpretability, which involves interpreting a system’s mechanisms and behavior in terms of propositional attitudes: attitudes (such as belief, desire, or subjective probability) to propositions (e.g. the proposition that it is hot outside). Propositional attitudes are the central way that we interpret and explain human beings and they are likely to be central in AI too. A central challenge is what I call thought logging: creating systems log all of the relevant propositional attitudes in an AI system over time. I will examine currently popular methods of interpretability (such as probing, sparse auto-encoders, and chain of thought methods) as well as philosophical methods of interpretation (including psychosemantics and representation theorems) to assess their strengths and weaknesses as methods of propositional interpretability.

Propositional Interpretability in Humans and AI Systems

We focus on the medication recommendation problem aiming to recommend accurate medications for a patient’s current visit. Most existing methods for this problem utilize the patient’s current health status, medications prescribed at her past visits, and an Electronic Health Records (EHR) graph which represents whether medications have been co-prescribed. However, we point out their two limitations: (1) they have difficulty in utilizing only the medications which have been prescribed in health status similar to the patient’s current health status, regardless of whether they are prescribed at her past visits or at other patients’ visits; (2) for two medications that have ever been co-prescribed, their EHR graph does not consider the degree to which one medication is prescribed together when the other is prescribed. To address these two limitations, we propose a novel medication recommendation framework, named HI-DR (pronounced as ‘Hi Doctor’), composed of following two core ideas: (Idea 1) Health status-aware attentIon; (Idea 2) an electronic health recorDs gRaph+. Extensive experiments on real-world datasets demonstrate the significant superiority of HI-DR (up to 18.69% higher accuracy than the best competitor) and the effectiveness of two core ideas in HI-DR.

HI-DR: Exploiting Health Status-Aware Attention and an EHR Graph+ for Effective Medication Recommendation

Next POI recommendation aids users in predicting their destinations of interest and plays an increasingly vital role in location-based social services. Recent works focus on analyzing both long-term and short-term interests in POI recommendation to gain a deeper understanding of user profiles. However, these methods for modeling long-term user's sequences primarily rely on the Transformer model, which functions as a low-pass filter, often leading to the loss of high-frequency information. Additionally, long-term and short-term sequences are typically modeled independently, with short-term sequences often defined solely by the most recent check-ins, overlooking their interactions and dependencies. Therefore, we propose Enhancing Long- and Short-Term Representations for Next POI Recommendations via \textbf{F}requency and \textbf{H}ierarchical \textbf{C}ontrastive Learning (FHCRec). FHCRec captures both high-frequency and low-frequency information in long-term sequences to model richer long-term user's preference representations. Moreover, it harnesses the characteristics of the short-term subsequences embedded within long-term sequences to enhance short-term preference characterization via local and global hierarchical contrastive learning, resulting in more personalized short-term preferences. The enhanced long-term and short-term preferences are integrated to improve model recommendation performance. Extensive experiments on three real-world datasets demonstrate the effectiveness of our method.

Ehancing Long- and Short-Term Representations for Next POI Recommendations via Frequency and Hierarchical Contrastive Learning

In the rapidly evolving landscape of large language models (LLMs) for medical applications, ensuring the reliability and accuracy of these models in clinical settings is paramount. Existing benchmarks often focus on fixed-format tasks like multiple-choice QA, which fail to capture the complexity of real-world clinical diagnostics. Moreover, traditional evaluation metrics and LLM-based evaluators struggle with misalignment, often providing oversimplified assessments that do not adequately reflect human judgment. To address these challenges, we introduce HDCEval, a **H**ierarchical **D**ivide-and-**C**onquer **Eval**uation framework tailored for fine-grained alignment in medical evaluation. HDCEval is built on a set of fine-grained medical evaluation guidelines developed in collaboration with professional doctors, encompassing Patient Question Relevance, Medical Knowledge Correctness, and Expression. The framework decomposes complex evaluation tasks into specialized subtasks, each evaluated by expert models trained through Attribute-Driven Token Optimization (ADTO) on a meticulously curated preference dataset. This hierarchical approach ensures that each aspect of the evaluation is handled with expert precision, leading to a significant improvement in alignment with human evaluators.

Hierarchical Divide-and-Conquer for Fine-Grained Alignment in LLM-Based Medical Evaluation

Understanding how humans cooperatively utilize semantic knowledge to explore unfamiliar environments and decide on navigation directions is critical for house service multi-robot systems. Previous methods primarily focused on single-robot centralized planning strategies, which severely limited exploration efficiency. Recent research has considered decentralized planning strategies for multiple robots, assigning separate planning models to each robot, but these approaches often overlook communication costs. In this work, we propose Multimodal Chain-of-Thought Co-Navigation (MCoCoNav), a modular approach that utilizes multimodal Chain-of-Thought to plan collaborative semantic navigation for multiple robots. MCoCoNav combines visual perception with Vision Language Models (VLMs) to evaluate exploration value through probabilistic scoring, thus reducing time costs and achieving stable outputs. Additionally, a global semantic map is used as a communication bridge, minimizing communication overhead while integrating observational results. Guided by scores that reflect exploration trends, robots utilize this map to assess whether to explore new frontier points or revisit history nodes. Experiments on HM3D_v0.2 and MP3D demonstrate the effectiveness of our approach.

Underline digital video library

Improving Optical Coherence Tomography Interpretation With Retrieval-Guided Diagnosis and Text Generation

Artificial Intelligence for Care for Older Adults with Chronic Health Conditions

A Reflection on Hallucinations in LLM Responses to Chronic Disease Queries

Early Detection of Kidney Disease in Aging Diabetic Populations Using Machine Learning

Deep Learning Insights into Social Determinants of Chronic Disease and Longevity

Improving Prediction of ADR in Elderly Patients Using Machine Learning Algorithms

AAAI/EAAI Patrick Henry Winston Outstanding Educator Award: T(w)eaching AI in the Age of LLMs

Propositional Interpretability in Humans and AI Systems

HI-DR: Exploiting Health Status-Aware Attention and an EHR Graph+ for Effective Medication Recommendation

Ehancing Long- and Short-Term Representations for Next POI Recommendations via Frequency and Hierarchical Contrastive Learning

Hierarchical Divide-and-Conquer for Fine-Grained Alignment in LLM-Based Medical Evaluation

Enhancing Multi-Robot Semantic Navigation Through Multimodal Chain-of-Thought Score Collaboration

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES