The AI tool that could save the NHS 300m a year by cutting missed appointments

"An AI-powered appointments system developed by UK health-tech company DrDoctor could save the NHS up to £300 million a year by dramatically reducing missed hospital appointments, one of the health service's most persistent and costly problems. Missed outpatient appointments cost the NHS close to £1 billion annually, tying up staff time, wasting clinical capacity and lengthening waiting lists. DrDoctor believes its new AI platform, Smart Centre, can cut non-attendance rates by around 30% by predicting which patients are most likely not to turn up and adjusting clinic capacity in advance."

"The company was founded in 2012 by Tom Whicher after he observed repeated appointment failures while waiting in outpatient departments - patients arriving on the wrong day, at the wrong time, or clutching outdated letters. "Until recently, we were solving parts of the problem with things like reminder texts," Whicher said. "But we reached a point where we hit a ceiling. AI has unlocked something that would have been unimaginable five years ago.""

"To build the model, DrDoctor trained its system on an anonymised dataset of four billion rows of NHS data, covering 55 million patients and 160 million appointments. A team of ten engineers spent months cleaning and validating the data before the model was deployed. Development took around two years and was supported by a £1 million award from the Department of Health and Social Care, which is repaid via revenue-sharing, with participating NHS organisations receiving discounted access."

Missed outpatient appointments cost the NHS close to £1 billion each year, wasting staff time, clinical capacity and lengthening waiting lists. Smart Centre, launched in 2024, uses machine learning to assess the likelihood of a patient attending by analysing age, deprivation indices, past attendance behaviour, demographics, and appointment time and day. The model was trained on an anonymised dataset of four billion rows covering 55 million patients and 160 million appointments after months of data cleaning and validation by a ten-engineer team. Development took about two years and received a £1 million Department of Health and Social Care award repaid via revenue-sharing. Early deployments increased treated patient numbers significantly.

Read at Business Matters