Was there a particular hospital department where your model identified a hidden bottleneck that nobody had spotted? And if so, what did the data reveal?

Yes, that is a really good question.

So we had an exciting project in respiratory where we were thinking or we had to balance out new patients and follow-up patients.

So if you accept new patients in your system, then obviously that has an effect on the follow-up patients.

So, for example, if you have one respiratory patient that you admit, then that means they have several follow-up appointments down the line every three months, six months or every year depending on the condition.

But when we were talking to our clinician and showing the mathematical model and behind the analysis, Then we found, or that explained actually their current situation, that they had accepted too many new patients that created that bottleneck for the follow-up patients.

So that doctor, unfortunately, was in that hamster wheel that they had that long new patient list and were always... or lots of times accepting these new patients.

So looking at recovering missed appointments, how does predictive modelling, or indeed can predictive modelling, identify which patients are likely to did not attend? And what can a hospital actually do with that prediction before the appointment slot is wasted?