Background: Simulated patient systems are vital in medical education and research, providing safe, integrative training environments and supporting clinical decision-making. Progressive Artificial Intelligence (AI) technologies, such as Large Language Models (LLM), could advance simulated patient systems by replicating medical conditions and patient-doctor interactions with high fidelity and low cost. However, effectiveness and trustworthiness remain challenging. Methods: We developed AIPatient, a simulated patient system powered by LLM-based AI agents. The system incorporates the Retrieval Augmented Generation (RAG) framework, powered by six task-specific LLM-based AI agents for complex reasoning. For simulation reality, the system is also powered by the AIPatient KG (Knowledge Graph), built with de-identified real patient data from the Medical Information Mart for Intensive Care (MIMIC)-III database. Results: Here we show that the system’s accuracy in Electronic Health Record (EHR)-based medical Question Answering (QA), readability, robustness, and stability. Specifically, the system achieves a QA accuracy of 94.15% when all six agents, surpassing benchmarks with partial or no agent integration. Its knowledgebase demonstrates high validity (F1 score=0.89). Readability scores show median Flesch Reading Ease at 68.77 and median Flesch Kincaid Grade at 6.4, indicating accessibility to all medical professionals. Robustness and stability are confirmed with non-significant variance (ANOVA F-value = 0.6126, p > 0.1; F-value = 0.782, p > 0.1). A user study with medical students shows that AIPatient delivers high fidelity, usability, and educational value, matching or exceeding human-simulated patients in history-taking. Conclusions: Large language model–based simulated patient systems provide accurate, readable, and reliable medical encounters and demonstrates potential to transform medical education.

Background: Cancer remains a global health challenge, characterized not just by uncontrolled cell proliferation but also by the complex metabolic reprogramming that underlies its development and progression. Objectives: This review delves into the intricate relationship between cancer and its metabolic alterations, drawing an innovative comparison with the cosmological concepts of dark matter and dark energy to highlight the pivotal yet often overlooked role of metabolic reprogramming in tumor evolution. Methods: It scrutinizes the Warburg effect and other metabolic adaptations, such as shifts in lipid synthesis, amino acid turnover, and mitochondrial function, driven by mutations in key regulatory genes. Results: This review emphasizes the significance of targeting these metabolic pathways for therapeutic intervention, outlining the potential to disrupt cancer’s energy supply and signaling mechanisms. It calls for an interdisciplinary research approach to fully understand and exploit the intricacies of cancer metabolism, pointing toward metabolic reprogramming as a promising frontier for developing more effective cancer treatments. Conclusion: By equating cancer’s metabolic complexity with the enigmatic nature of dark matter and energy, this review underscores the critical need for innovative strategies in oncology, highlighting the importance of unveiling and targeting the “dark energy” within cancer cells to revolutionize future therapy and research.

People with long COVID are those who still have symptoms, signs, and conditions after the initial phase of infection of SARS-CoV-2. The incidence of long COVID varies among regions-31% in North America, 44% in Europe, and 51% in Asia, which is challenging the healthcare system, but there is limited guidelines for its treatment. With more and more nationwide projects funded by the government such as the RECOVER initiative in the United States and National Institute for Health Research funding in the United Kingdom, an increasing number of ongoing clinical trials are investigating the efficacy of diverse therapies on reversing long COVID. After searching the World Health Organization International Clinical Trial Registry Platform, 587 clinical studies are identified as long COVID studies. Among these, 312 studies (53.2%) are testing potential therapies. Most of the long COVID trials were conducted in the United States (58 trials [18.6%]), followed by India (55 trials [17.6%]), and Spain (20 trials [6.4%]). Interventions in these clinical trials include physical exercise, rehabilitation therapy, behavioral therapy, and pharmacological therapies including herbs, paxlovid, and fluvoxamine. These trials are aiming to deal with these long COVID symptoms and signs including fatigue, decreased pulmonary function, reduced cognitive function, and others. To date, only 11 of these 312 studies have published their results that were not confirmative, unfortunately. Future studies should be designed to address sleep disorders which were seldomly included in registered clinical studies. Moreover, interventions aimed at treating the underlying pathophysiology of long COVID are also necessary but currently lacking.

Assumptions are made about the genetic model of single nucleotide polymorphisms (SNPs) when choosing a traditional genetic encoding: additive, dominant, and recessive. Furthermore, SNPs across the genome are unlikely to demonstrate identical genetic models. However, running SNP-SNP interaction analyses with every combination of encodings raises the multiple testing burden. Here, we present a novel and flexible encoding for genetic interactions, the elastic data-driven genetic encoding (EDGE), in which SNPs are assigned a heterozygous value based on the genetic model they demonstrate in a dataset prior to interaction testing. We assessed the power of EDGE to detect genetic interactions using 29 combinations of simulated genetic models and found it outperformed the traditional encoding methods across 10%, 30%, and 50% minor allele frequencies (MAFs). Further, EDGE maintained a low false-positive rate, while additive and dominant encodings demonstrated inflation. We evaluated EDGE and the traditional encodings with genetic data from the Electronic Medical Records and Genomics (eMERGE) Network for five phenotypes: age-related macular degeneration (AMD), age-related cataract, glaucoma, type 2 diabetes (T2D), and resistant hypertension. A multi-encoding genome-wide association study (GWAS) for each phenotype was performed using the traditional encodings, and the top results of the multi-encoding GWAS were considered for SNP-SNP interaction using the traditional encodings and EDGE. EDGE identified a novel SNP-SNP interaction for age-related cataract that no other method identified: rs7787286 (MAF: 0.041; intergenic region of chromosome 7)–rs4695885 (MAF: 0.34; intergenic region of chromosome 4) with a Bonferroni LRT p of 0.018. A SNP-SNP interaction was found in data from the UK Biobank within 25 kb of these SNPs using the recessive encoding: rs60374751 (MAF: 0.030) and rs6843594 (MAF: 0.34) (Bonferroni LRT p: 0.026). We recommend using EDGE to flexibly detect interactions between SNPs exhibiting diverse action.