Secondary Care

Data and analytics supporting the stranded patients challenge

HTN met with Orlando Agrippa, CEO and Richard Parker, COO of Draper & Dash to understand how their technology, the use of data and analytics on historic and live data is now being used by some trusts to identify, understand and review trends and issues that lead to patients becoming stranded in their care pathway.

Richard Parker, COO, Draper & Dash said “Stranded patients are patients that have been in hospital for more than a week, super stranded patients have been in hospital for more than three weeks. Here at Draper & Dash we are pretty clear that nobody should be in hospital for more than three weeks. Working with our hospitals we have developed a module that enables teams to better understand the pathway for stranded patients. Of course, it means they can track them, but it also means you can dig into what is happening to those patients and look for patterns earlier on in the pathway.”

“Our modules allow teams to look where stranded patients are coming from, in which specialty they belong to and the care environment perhaps leading them to become stranded patients. From this information teams can hopefully then intervene and prevent patients from becoming super stranded.”

Orlando Agrippa, CEO, Draper & Dash said “It’s important healthcare professionals and managers have quick, actionable insight by highlighting these types of patients by specialty and wards. And within one-click the patient detail can be reviewed. Ultimately providing insight to help patient flow and information and to provide alerts before patients become stranded.”

The technology is backed by a unique machine learning algorithm, it explores the relationships with data to predict hotspots and aims to determine certain contributing factors.

Orlando said “For those patients currently in the hospital but not yet stranded, the dashboard utilises our unique machine learning algorithms to determine how many patients are predicted to be stranded with a likelihood score provided to prioritise early intervention for at risk patients. Moreover, this predicted gure is then used against performance management benchmarks to future plan for the impact on performance.”

The technology is being used to help hospitals identify quickly those patients that may become stranded. There are lots of variables and data sets feeding the technology, to highlight the top 20 most important variables that drive a patient being predicted as stranded. It provides granularity into factors by specialty, ward and consultant, enabling users to review where the issues are occurring most often to promote wider process change across the organisation.


Real-time view of ED

The company is also supporting Royal Free Hospital NHS Foundation Trust’s Emergency Department. It utilises vast volumes of data to provide a real-time view of ED performance. The ED application supports operational managers providing more control over the flow of patients, both in and out. Real-time analytics now alert the ED team to a higher than expected demand so that a potential breach of the 4-hour standard can be countered, with immediate action. The solution further includes projections and forecasting, providing the Trust with greater insight into the busiest periods in the ED.

Insight into Cancer Wait Times data

Salford Royal NHS Foundation Trust benefits from real time insight into their Cancer Wait Times data, to reduce waiting times for Cancer patients. When the merger between Salford Royal and the Pennine Care NHS Foundation Trust took place, a key obstacle for The Northern Care Alliance, was the data integration that came with the merger. With two entirely different schemas to amalgamate, the solution allowed the Trust to unite data from both sites and offer a single source of truth for both BI teams. At the click of a button, the Trust now have the capacity to improve patient flow, and ultimately achieve significant efficiency savings across both sites.

Predictive Readmissions insight

The company is utilising advanced data science and machine learning technology to help predict whether a patient will be readmitted and to identify patterns and the likelihood of readmittance.

Orlando said “With the issue of readmissions AI offers some what a simple set of assistance to clinicians, operations teams and leadership. With hospitals having some of the richest patient data, leveraging advanced algorithms to better predict some of the variables already known to a healthcare practitioner is now more than ever available as part of patient flow and management. AI offers limitless possibilities in helping teams to better know which patients are at a greater risk of being recalled or readmitted to hospitals by better understanding the variables driving the discharge process.”

“In my opinion, nothing trumps the clinical experience and prompt intervention for patients that are provided by a clinician’s years of experience in assessing patient’s fitness however harnessing data through the use of AI offers a great companion for seasoned veterans and recent graduates in healthcare to have more insights into the patient journey.”

Richard commented “The tool helps trusts manage and plan for those patients who are likely to be readmitted. This supports early intervention and the planning process. It takes hundreds of data sets to provide a risk analysis view and a view of tracking performance across specialty over time.”