Search AI Products and News

Recently, the Evo2 bio AI model, jointly developed by Arc Institute and Nvidia, was officially released. This foundational model is based on DNA data from over 100,000 species and aims to deeply decode various complex phenomena in biology. Evo2 can identify patterns in the genetic sequences of different organisms that researchers would typically take years to discover, significantly enhancing the ability to identify disease-related mutations, and can design entirely new genomes comparable to simple bacteria.

Singapore General Hospital (SGH) is developing an artificial intelligence solution called 'Augmented Intelligent Infectious Diseases' (AI2D), aimed at determining the necessity of prescribing antibiotics, reducing antibiotic usage, and identifying the most appropriate antibiotic for each patient. The project is in collaboration with DXC Technology and currently covers pneumonia cases. The AI2D model is built on de-identified clinical data of approximately 8,000 SGH patients from 2019 to 2020, including X-rays, clinical symptoms, vital signs, and infection responses.

Google is leveraging artificial intelligence technology to analyze sound data, aiming to predict and detect health issues early, particularly tuberculosis. In partnership with Indian startup Salcit Technologies, the plan is to integrate this innovative technology into smartphones for easier use in resource-limited areas. This method can assist in diagnosing health conditions through simple audio like cough sounds. Google's ongoing exploration in the health sector, including disease detection through olfactory technology, demonstrates its commitment to enhancing health management capabilities through technological means.

Baichuan Intelligence and the National Children's Medical Center Beijing Children's Hospital have signed a strategic cooperation agreement aimed at utilizing artificial intelligence technology to improve the quality and coverage of pediatric medical services. The scope of cooperation includes home healthcare, auxiliary diagnosis and treatment, and scientific research innovation, with the goal of launching an 'A Big Four Small' AI smart child health service product. This initiative focuses on constructing a comprehensive child health model, including a family digital consultant, grassroots doctor assistant, expert clinical research assistant, and chronic disease management robot. This cooperation marks a new attempt in the technological development of pediatrics, leveraging AI technology.

Google's HeAR bioacoustic model detects various diseases such as tuberculosis, COVID-19, and chronic obstructive pulmonary disease by analyzing sounds, trained on 313 million audio clips, demonstrating exceptional diagnostic capabilities. HeAR outperforms existing models in multiple health acoustic events, cough, and lung function inference tasks, particularly excelling in detecting COVID-19 and tuberculosis. Salcit Technologies has applied HeAR in its product Swaasa® for lung assessment.

The study shows that ChatGPT has limitations in providing nutritional consultations for patients with various non-communicable diseases. Researchers found that ChatGPT's performance declined in handling overlapping conditions, potentially leading to conflicting or inappropriate advice. While it performs well in general dietary recommendations, its effectiveness diminishes in complex situations, necessitating customized strategies. The findings highlight that ChatGPT cannot replace consultations with healthcare professionals, especially when dealing with complex medical conditions.

["Google DeepMind has released AlphaMissense, focusing on analyzing the impact of DNA mutations, providing new tools for medical research.","AlphaMissense combines natural language processing with biological knowledge, aiding in the diagnosis and treatment of hereditary diseases.","The model predicts the pathogenicity of missense gene variants with high accuracy, achieving an astonishing accuracy rate of 90%.","AlphaMissense operates more like a language model trained in biology."]