≡ Menu

Using decision management to make e-prescribing useful


Bill over at the Wireless MD had a couple of interesting posts on e-prescribing today – Senatorial bi-partisan support for e-prescribing and Caveats for e-prescribing. The use of technology to improve healthcare is an endlessly fascinating discussion and the use of information systems to handle prescriptions (e-prescribing) is one of the most debated.
There is growing support for e-prescribing in government and the first of Bill’s posts was discussing some of the bipartisan support for incentive programs and I was about to blog about the importance of automated decisioning in this context when I saw his second approach in which he repeated some concerns about e-prescribing. In particular he said:

Many patients have prescriptions written by a multitude of practitioners, which are then often filled at a number of different pharmacies

Now this is true but what worries me is that it is used as an excuse to say that nothing can be done until bi-directional data sharing is enabled between all doctors and all pharmacies. Of course this may never happen yet we must make progress. Decision management can be applied to the e-prescribing process either at the doctor or at the pharmacy to add value. It can do several things.

  • Check for drug interactions (rules-based analysis of all the prescriptions known at the point/time of checking)
  • Check doses and instructions against patient data (weight, age, sex etc), applying the rules specific to the drug
  • Identify potentially fraudulent identities using rules and analytics like neural nets to find unusual patterns
  • Recommend follow-up activities using rules about drug procedures and predictive models for things like likelihood of following a protocol.

Many patients, in fact I think most, have a pharmacy they use for the vast majority (if not all) of their prescriptions. This means that the pharmacy is a perfect point of control. Just because it will not work in 100% of cases is no excuse to do nothing. Similarly, many doctors or medical groups handle a significant percentage of the prescriptions for a particular individual and there is no reason they could not also participate in this. Would a highly collaborate, open yet secure data exchange help, sure. Are we going to hold our breath and do nothing until one comes along, I sure hope not.

Bill made a couple of other points on which I wanted to comment. He pointed out that there are problems “definitively identifying patients” because people borrow ID cards and so on and quoted someone as saying that biometric identification was required. Again, this would be great, but in the meantime there are some pretty sophisticated analytics out there that can give you a good sense of whether someone really is who they say they are and a decision management approach would allow these to be applied as a prescription was filled.

Finally he said that

[the] ultimate goal in the use of digital technology to improve health care is collaboration

I don’t think so. The ultimate goal in the use of technology to improve health care is to save lives; help people live longer, healthier lives; and do so more cost effectively. Collaboration might help us get there, it should not be the objective.