Two researchers at Indiana University believe they have created a computer program that can better and more cheaply diagnose medical problems. From Indiana University:
Using an artificial intelligence framework combining Markov Decision Processes and Dynamic Decision Networks, IU School of Informatics and Computing researchers Casey Bennett and Kris Hauser show how simulation modeling that understands and predicts the outcomes of treatment could reduce health care costs by over 50 percent while also improving patient outcomes by nearly 50 percent. [...]
Using 500 randomly selected patients from that group for simulations, the two compared actual doctor performance and patient outcomes against sequential decision-making models, all using real patient data. They found great disparity in the cost per unit of outcome change when the artificial intelligence model’s cost of $189 was compared to the treatment-as-usual cost of $497.
“This was at the same time that the AI approach obtained a 30 to 35 percent increase in patient outcomes,” Bennett said. “And we determined that tweaking certain model parameters could enhance the outcome advantage to about 50 percent more improvement at about half the cost.”
Whether a practical application will emerge from this particular effort is yet to be seen, but this general concept is the future. Many groups are looking at how to use computer modeling to diagnose patients and the research is very promising
This development is worth highlighting because so much of the debate in Washington is currently dominated by CBO projections that are likely horribly wrong. The CBO assumes government health care spending will grow faster than the rest economy forever, and by 2085 nearly 20 percent of the GDP will be spent on Medicare and Medicaid.
Up until recently most of the efficiency gains from computers and mechanization has come from replacing people doing simple repetitive tasks. But with computer processing growing so quickly, that is changing. We could soon see computers causing the same rapid efficiency improvement in medicine we have seen in many other fields. Just because the digital revolution has not dramatically changed medicine yet, doesn’t mean that it won’t eventually.
Basically all of our long term deficit discussions are based on the assumption of continued health care growth. If a few technologies that are already in development live up to their promise, our long term deficit would basically be eliminated. It is possible Washington is currently obsessed with a problem that may not even really exist.
Predicting the future is very hard.