AI medical health

Diabetica-7B is a large language model optimized for the diabetes care domain. It excels at a variety of diabetes-related tasks, including diagnosis, treatment recommendations, medication management, lifestyle recommendations, patient education, and more. The model is fine-tuned based on open source models, using disease-specific data sets and fine-tuning techniques, providing a reproducible framework that can accelerate the development of AI-assisted medicine. In addition, it has undergone comprehensive evaluation and clinical trials to verify its effectiveness in clinical applications.

Diabetica-1.5B is a large-scale language model specially customized for the field of diabetes care. It performs well in multiple diabetes-related tasks such as diagnosis, treatment recommendations, medication management, lifestyle recommendations, and patient education. The model is developed based on open source models and fine-tuned using disease-specific data sets, providing a reproducible framework that can accelerate the development of AI-assisted medicine.

Diabetica is a high-level language model developed specifically for diabetes treatment and care. Through deep learning and big data analysis, it is able to provide a variety of services including diagnosis, treatment recommendations, medication management, lifestyle advice and patient education. Diabetica’s models Diabetica-7B and Diabetica-1.5B demonstrate excellent performance on multiple diabetes-related tasks and provide a reproducible framework that allows other medical fields to benefit from such AI technology.

ReMe is a personalized cognitive training framework jointly developed by Microsoft Research Asia and Shanghai Mental Health Center, aiming to provide personalized cognitive training for patients with cognitive impairment. This framework is based on Microsoft Azure OpenAI service and uses multi-modal large model technology to provide users with a cognitive training experience in the form of a conversational robot through input and output of multiple modalities such as text, images, and voice. The innovation of ReMe lies in its personalized and multi-modal interaction capabilities, which can provide customized training programs based on the user's memory content and cognitive level, thereby improving the pertinence and effectiveness of training.

Health Acoustic Representations (HeAR) is a basic bioacoustic model developed by Google's research team that aims to identify early signs of disease by analyzing the sounds made by the human body, such as coughs. The model was trained on 300 million pieces of audio data, and about 100 million pieces of data were used specifically for cough sounds. HeAR is able to identify health-related sound patterns, providing a strong foundation for medical audio analysis. The HeAR model outperforms other models in a variety of tasks and has better generalization capabilities across different microphones. In addition, models trained using HeAR can achieve high performance with less training data, which is crucial in the data-scarce medical research field. HeAR is now available to researchers to accelerate the development of custom bioacoustic models, reducing the need for data, setup, and computation.

MedTrinity-25M is a large-scale multi-modal dataset containing medical annotations at multiple granularities. It was developed by multiple authors to advance research in the field of medical image and text processing. The construction of the data set includes steps such as data extraction and multi-granularity text description generation, and supports a variety of medical image analysis tasks, such as visual question answering (VQA), pathology image analysis, etc.

PeacePulse is a mental health APP designed for iPad. It helps users improve their emotional health and enhance self-care practices through functions such as personalized diary, AI therapist, daily affirmations, mood recording, goal setting and tracking, daily challenges, reminders and notifications. The APP focuses on the security and privacy protection of user data and provides a monthly subscription service priced at US$4.99 per month.

Zest - Longevity is an app designed to help users live longer, healthier lives. It is based on the past decade of scientific research exploring the biological roots of aging, providing a tool that allows users to deal with aging at the core level, and even prevent and reverse the biological aging process. The app was developed by a team of doctors, longevity scientists and researchers and is continually updated to evaluate recommended options. Zest helps users form daily recommended goals by tracking 8 key longevity pillars: mood, sleep, exercise, sun exposure, cold soak, fasting, supplements and blood tests, which are combined to form the user's longevity score. In addition, Zest is compatible with the Vital SDK and passive tracking of digital biomarkers, supports almost all wearable devices, combines behavioral science and longevity science, and uses psychology and neuroscience to help users maintain life-extending habits.

Aloe is a language model in the medical field developed by HPAI, optimized based on the Meta Llama 3 8B model. It achieves state-of-the-art performance commensurate with its size through model fusion and advanced prompting strategies. Aloe scores higher on ethics and factuality metrics, thanks to a combination of red teaming and alignment efforts. The model provides healthcare-specific risk assessments to facilitate the safe use and deployment of these systems.

Polaris is a large language model (LLM) system developed by Hippocratic AI that is highly focused on security and used in healthcare. Through a combination of constellation architecture and professional support agents, Polaris is able to perform multiple medical-related complex tasks. The product is positioned to provide long-term, multi-round voice conversations with patients and provide professional and accurate medical advice. In terms of price, it is billed by the hour, $9 per hour. The main functions include real-time multiple rounds of voice dialogue, medical information provision and interpretation, privacy and compliance checks, medication management and consultation, laboratory and vital sign analysis, nutritional advice, medical record and policy inquiry, patient relationship building, etc.

Benchmark Medical RAG is a Retrieval-Augmented Generation benchmark testing platform focusing on the medical field. It provides a series of datasets and evaluation tools designed to advance research in medical information retrieval and generative models.