Medical question answering systems face deployment challenges including hallucinations, bias, computational demands, privacy concerns, and the need for specialized expertise across diverse domains. Here, we present SOLVE-Med, a multi-agent architecture combining domain-specialized small language models for complex medical queries. The system employs a Router Agent for dynamic specialist selection, ten specialized models (1B parameters each) fine-tuned on specific medical domains, and an Orchestrator Agent that synthesizes responses. Evaluated on Italian medical forum data across ten specialties, SOLVE-Med achieves superior performance with ROUGE-1 of 0.301 and BERTScore F1 of 0.697, outperforming standalone models up to 14B parameters while enabling local deployment. Our code is publicly available on GitHub: https://github.com/PRAISELab-PicusLab/SOLVE-Med.

Full-process clinical diagnosis in the real world encompasses the entire diagnostic workflow that begins with only an ambiguous chief complaint. While artificial intelligence (AI), particularly large language models (LLMs), is transforming clinical diagnosis, its role remains largely as an assistant to physicians. This AI-assisted working pattern makes AI can only answer specific medical questions at certain parts within the diagnostic process, but lack the ability to drive the entire diagnostic process starting from an ambiguous complaint, which still relies heavily on human physicians. This gap limits AI's ability to fully reduce physicians' workload and enhance diagnostic efficiency. To address this, we propose a paradigm shift that reverses the relationship between physicians and AI: repositioning AI as the primary director, with physicians serving as its assistants. So we present DxDirector-7B, an LLM endowed with advanced deep thinking capabilities, enabling it to drive the full-process diagnosis with minimal physician involvement. Furthermore, DxDirector-7B establishes a robust accountability framework for misdiagnoses, delineating responsibility between AI and human physicians. In evaluations across rare, complex, and real-world cases under full-process diagnosis setting, DxDirector-7B not only achieves significant superior diagnostic accuracy but also substantially reduces physician workload than state-of-the-art medical LLMs as well as general-purpose LLMs. Fine-grained analyses across multiple clinical departments and tasks validate its efficacy, with expert evaluations indicating its potential to serve as a viable substitute for medical specialists. These findings mark a new era where AI, traditionally a physicians' assistant, now drives the entire diagnostic process to drastically reduce physicians' workload, indicating an efficient and accurate diagnostic solution.

The ability to summarize and organize knowledge into abstract concepts is key to learning and reasoning. Many industrial applications rely on the consistent and systematic use of concepts, especially when dealing with decision-critical knowledge. However, we demonstrate that, when methodically questioned, large language models (LLMs) often display and demonstrate significant inconsistencies in their knowledge. Computationally, the basic aspects of the conceptualization of a given domain can be represented as Is-A hierarchies in a knowledge graph (KG) or ontology, together with a few properties or axioms that enable straightforward reasoning. We show that even simple ontologies can be used to reveal conceptual inconsistencies across several LLMs. We also propose strategies that domain experts can use to evaluate and improve the coverage of key domain concepts in LLMs of various sizes. In particular, we have been able to significantly enhance the performance of LLMs of various sizes with openly available weights using simple knowledge-graph (KG) based prompting strategies.

Aidoc, a provider of artificial intelligence (AI) solutions for medical imaging, has announced a $66 million investment, bringing its total funding to $140 million. This Series C round, led by General Catalyst, follows a surge in demand for Aidoc's AI-driven solutions, including the largest clinical deployment of AI in healthcare through its partnership with Radiology Partners. Aidoc co-founder and CEO Elad Walach, said: "This investment comes after significant milestones; expanding our product lines, doubling our FDA clearances and quadrupling our customer base. We are experiencing a huge expansion, which is also a direct result of C-level executives adopting an AI strategy and integrating our platform as a must-have solution across clinical pathways. It is truly rewarding – and a great responsibility – to be the trusted partner of the most innovative health systems and physician practices across the globe." A pioneer in healthcare AI, Aidoc's FDA-cleared solutions analyse medical images for critical conditions and trigger actionable alerts directly in the imaging workflow supporting medical specialists in reducing turnaround time and improving quality of care.

It's hard to imagine what scenes Florence Nightingale witnessed when she arrived at the British military hospitals during the wars in her time. Armed with only a notebook and lamp, Nightingale redefined the problem she was trying to solve. She did not believe soldiers were simply succumbing to their wounds and was determined to curb any avoidable deaths. By recording and visualizing data she uncovered that poor sanitary practices were the main culprit of fatality in hospitals. Put simply, she used data to save lives.

Aidence, an Amsterdam-based start-up applying Artificial Intelligence to the interpretation of medical images, today announced its raise of €2.25M in seed funding from notable investors Northzone, HenQ, Health Innovations, and the medical specialists of the Haaglanden hospital group. The investment will be used to strengthen its sales and technical teams and expand international reach. Aidence is improving healthcare using Computer-Aided Diagnostics, with a first application in lung cancer. Aidence's software enables faster, cheaper, and more accurate diagnoses of X-ray, MRI and CT images. The key enabling technology is Deep Learning, a revolutionary type of Artificial Intelligence that is capable of analysing medical images with human-level accuracy.

Aiming to tackle the severe shortage of specialist doctors in India, the 27-year olds behind the DocsApp platform promise a consultation with a doctor within 30 minutes of logging on to their app (with a little AI help). DocsApp cofounders Satish Kannan and Enbasekar D graduated from IIT Madras in 2012, both on a fast track, completing undergraduate and graduate degrees in engineering. While Kannan went off to work as an engineer for Philips Healthcare, where he says he witnessed how the medical industry works from the inside, Enbasekar cut his teeth working on machines to diagnose diabetic retinopathy. The university friends quickly realized that there was a problem with the healthcare system in India. India faces a severe shortage of doctors, with around 150,000 specialists available to meet the needs of a billion strong population.

Ambient activity monitoring systems produce large amounts of data, which can be used for health monitoring.The problem is that patterns in this data reflecting health status are not identified yet. In this paper the possibility is explored of predicting the functional health status (the motor score of AMPS = Assessment of Motor and Process Skills) of a person from data of binary ambient sensors. Data is collected of five independently living elderly people. Based on expert knowledge, features are extracted from the sensor data and several subsets are selected. We use standard linear regression and Gaussian processes for mapping the features to the functional status and predict the status of a test person using a leave-one-person-out cross validation. The results show that Gaussian processes perform better than the linear regression model, and that both models perform better with the basic feature set than with location or transition based features.Some suggestions are provided for better feature extraction and selection for the purpose of health monitoring.These results indicate that automated functional health assessment is possible, but some challenges lie ahead. The most important challenge is eliciting expert knowledge and translating that into quantifiable features.