Complexity analysis in Healthcare

The benefits of model-free quantitative complexity analysis are many and varied as the following illustrates beautifully – adapted from an article that appeared in November 2009:

OntoMed LLC has demonstrated its technology with physicians at the University of Michigan Health System. The company has begun clinical trials of its new patient-stability monitor in emergency room and intensive care unit settings.

If all goes well, the company plans to use data culled from the hospital system’s database to validate the technology.

OntoMed, in June, spun out of Ontonix, a developer of complexity-based risk-management software based in Italy for which Deshpande serves as managing partner and head of US business development. The company’s software, commercialised in 2005, has applications in fields like economics, finance, traffic management, defence and product development.

The new start-up licenses technology from the parent company to measure complexity in hospitalised patients. The technology is heavily based on mathematic concepts that draw from information and graph theory.

Its complexity-based stability monitoring system – or Cosmos – is a PC-based multi-channel device envisioned as a bedside monitor. It uses an algorithm to process in real time information available from a wide variety of monitors, reviewing various vital signs and allowing doctors to plug in laboratory or clinical history data.

“It serves as a pre-alarm,” Deshpande said. “If you treat one symptom, some other symptom might arise which you didn’t predict. Our system predicts that.”

Doctors sometimes complain that vital signs offer good but incomplete information on a patient’s overall stability, Deshpande said. OntoMed’s software can process up to 50 channels of data to help doctors better anticipate problems and improve patient outcomes.

“This is why the physicians also like it; they can plug in lab values, they can plug in any relative historical data and that will change the complexity,” he said

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s