While I am always reticent to promote anything that comes out of Stanford given my Cal Bear roots, a lawyer friend of mine, Stephen Thau, recently sent me an article from e!Science News that is definitely worth mentioning for the significance of the invention it describes and the fact that the inventors behind it are both women.
Entitled Researchers design more accurate method of determining premature infants’ risk of illness, the article describes how Stanford University researchers (one of whom happens to be Stephen’s wife) have developed a revolutionary, non-invasive way of quickly predicting the future health of premature infants. What is pretty cool about this, aside from the fact that it will lead to healthier babies (always a good thing), is that the system does not require any new test, device, chemical experiment, or other intervention to make a quantum leap forward in screening for potentially serious illnesses before they manifest obvious symptoms. Let me tell you, no mom wants to subject her kid to an unnecessary needle if at all possible. Thus, any leap forward in diagnostics that reduces the awful mommy guilt and baby screaming is a huge plus.
Instead, the test, called PhysiScore, relies on data which is collected and documented anyway from a number of already used monitoring, screening, diagnostic and reporting tools, integrates this data into a common set, applies software-based algorithms to this already collected data and predicts the baby’s likelihood of needing urgent medical intervention for a serious problem with an accuracy of between 91 and 98 percent. In the diagnostics world, those are pretty awesome statistics.
It is worth noting that the way this has been done for the last 50 or so years is with a methodology called the Apgar test, which is a far more subjective measure of newborn health performed manually/visually by a nurse two or three times after birth. The success of Apgar score predictions for the same conditions ranged from 69 to 74 percent. Notably, The PhysiScore proved particularly accurate in predicting the overall risk of life-threatening events in subgroups of infants who had intestinal infections and cardiopulmonary complications, even when these were not diagnosed until days or weeks later, according to the article. Moms everywhere are breathing a sigh of relief.
Among the reasons this is so cool is that it is a first-hand demonstration of why electronic medical records (EMRs) matter. As the article states:
…by taking into account gestational age and birth weight and using a stream of real-time data routinely collected in neonatal intensive care units – such as heart rate, respiratory rate and oxygen saturation – the Stanford researchers developed a probability scoring system for the health of prematurely born infants that outperformed not only the Apgar but three other systems that require invasive laboratory measurements.
Quoted in the article, Anna Penn, MD, PhD, wife of my friend Stephen, assistant professor of pediatrics at the School of Medicine and a neonatologist at Lucile Packard Children’s Hospital (where does she find the time to invent stuff?), “What the PhysiScore does is open a new frontier. The national push toward electronic medical records helped us create a tool to detect patterns not readily seen by the naked eye or by conventional monitoring. We’re now able to identify potential health problems before they become clinically obvious.”
In other words, they are using the power of computing to analyze multiple data inputs that a human mind could not do real time. Data goes into the EMR, actionable knowledge comes out. That is the whole raison d’etre behind the EMR cacophony and yet we hear so little about these tangible examples in practice. Instead the talk is all about who is going to fund it and whether doctors will accept it and is there going to be a big enough Geek Squad to install it and what is the least amount of regulatory compliance we can all get away with and still get that incentive money? But fundamentally, the purpose of the digitization of healthcare is to make it better and the PhysiScore is a perfect example of the reason we are even having this discussion.
Even better, the PhysiScore is accomplished with inexpensive software, a minor adjustment to the hardware to include this monitoring parameter and best of all, no new costly tests. The result is early identification or risky illnesses, prevention of potentially dire complications and thus elimination of a portion of the high costs of care associated with treating such conditions, which often occurs in specialized facilities and overall costs the U.S. $26 billion per year. Technology that improves quality of care and reduces cost of care—they are singing my song, albeit with a lullaby tempo.
There are still final touches to be placed on the PhysiScore system before it can enter widespread practice, including, no doubt, regulatory hurdles that will need to be overcome. However, it’s a great idea and one that can clearly be migrated to other parts of the hospital and other potentially at-risk populations.
According to PhysiScore co-inventor Daphne Koller, PhD, professor of computer science in the Stanford School of Engineering, “To achieve truly personalized medicine, we have to integrate an enormous amount of data: clinical symptoms, diagnostic test results, physiological data streams and, soon, genetic and genomic data. Computational methods derived from real patient records can deliver on the promise of personalized, evidence-based medicine.”
Amen sister. Now where is that pacifier? Mommy needs a cocktail.