PAIRS preview
  Home Page | About Page | What's New Page | Contact Page | Photo Page  

PAIRS (Physician assistant Artificial Intelligence Reference System)

The code for AI engine has been written in C. The depth and stature of the PAIRS is similar to QMR whose AI system is based on Quickscore. Quickscore's AI is limited in scope compared to the PAIRS. PAIRS (Physician assistant Artificial Intelligence System) helps doctors diagnose difficult cases. It is currently (October 2003) being tested in clinical practice and its commercial launch is planned for January 2004.

PAIRS artificial intelligence system is based on variational methods developed by Jaakkola and Jordan. PAIRS works on a large database of over 30,000 disease-features and 620 internal medicine diseases. Each of the features given disease is quantified on the basis of its patho-physiology, disease incidence and possibility of it being caused by a disease not in the list. It includes a 7282-disease list, over 10,000-feature list and 415,000 feature-feature links. The clinical knowledge database has been built up from standard texts and peer-reviewed journals over the last eight years. One can access either disease-feature, feature-disease and feature-feature links or run a diagnosis from the front end.

A notable feature of the system is that it can provide a diagnosis for patient data including over 50 features. The accuracy of PAIRS is checked by patient data of each of 340 cases of Massachusetts General Hospital, which are published by New England Journal of Medicine. Some of these cases tested have a large number of features, which is a limiting factor for other AI systems based on Bayesian probabilistic belief networks. However, PAIRS can easily cope with such large patient data by partially doing an exact inference involving upper and lower bounds of quantifications of feature given disease. This process is known as variational transformation and involves finding conditional probabilities (exact and transformed) of features given disease. Only those (about 50% of positive findings) that have minimal difference between exact and transformed conditional probabilities are transformed and rest are treated exactly. The system calculates probabilities for each of diseases and gives a differential diagnosis, which eventually helps physician find an accurate diagnosis. A custom dictionary and a natural language processing (NLP) interface make entry of the patient data fully compatible with PAIRS database. This interface builds a word pool from translations and break-ups of Greek and Latin medical terms and finds their equivalent synonyms and antonyms before searching the database. Thus, based on the patient data a comprehensive case data is built on which the AI system works.

Disease List

Features List

Disease-feature Links

Feature-disease Links

Feature-feature Links

Diagnosis

AI run 1

AI run 2

AI run 3