AI technology now enables single-instance disease risk assessment for over a thousand health conditions.
In a groundbreaking development, a new artificial intelligence (AI) tool named Delphi-2M has been created by a German-Danish research group. This innovative AI tool is designed to estimate the risk of over 1,000 diseases for individuals, offering a powerful lens into how diseases unfold and potentially supporting earlier, more tailored interventions.
Delphi-2M learns from the order of medical events and the time between them to forecast disease risk. It uses anonymized patient record data to make predictions about future health, taking into account factors such as age, sex, lifestyle (including obesity, smoking, and alcohol consumption), and past disease history.
The AI tool has proven to be more effective at predicting conditions with clear and consistent progression patterns, such as certain types of cancer, heart attacks, and septicaemia. However, it is less reliable for conditions that may be variable, like mental health problems or pregnancy-related complications.
The model was custom-built and trained on anonymized patient data from 400,000 people from the UK Biobank, and its predictions were successfully tested using data from 1.9 million patients in the Danish National Patient Registry. Delphi-2M's predictions are comparable in accuracy to existing single-disease models.
The future vision is for clinicians to use this AI tool to provide personalized disease risk information and advice to patients. Moritz Gerstung, head of the division of AI in oncology at the German Cancer Research Centre, believes Delphi-2M marks the beginning of a new way to understand human health and disease progression.
Generative models like Delphi-2M could one day help personalize care and anticipate healthcare needs at scale. Moreover, Delphi-2M's generative nature could help public health leaders plan better and allocate resources where they are needed. The team behind the research hopes the AI tool will be in the hands of doctors in five to 10 years.
In conclusion, Delphi-2M is a significant step forward in the field of AI and healthcare. Its ability to predict the rates of over 1,000 diseases for individuals, taking into account their past disease history, could revolutionize the way we approach disease prevention, diagnosis, and treatment.
Read also:
- Abu Dhabi initiative for comprehensive genetic screening, aiming to diagnose over 800 conditions and enhance the health of future generations in the UAE.
- Elderly shingles: Recognizing symptoms, potential problems, and available treatments
- Exploring the Reasons, Purposes, and Enigmas of Hiccups: Delving into Their Origins, Roles, and Unsolved Aspects
- Various forms of cataracts include nuclear, pediatric, traumatic, and additional types
