This is the fifth in a series of blogs on the “AI is here.” podcasts. Each blog in the series will highlight the insights from a specific industry leader as they describe how their organization is deriving significant value from AI today.
In this edition of the “AI is here.” podcast, Dan Faggella, Founder and CEO, of market research and publishing company Emerj, speaks with Kostas Papagiannopoulos, Senior Surgeon Thoracic Surgery, at Leeds. Kostas talks with Dan about how AI has been important to his career by enabling him to connect with other leaders in the field and to establish a consensus on how to manage patients.
According to Papagiannopoulos, the critical outcome Leeds has achieved with AI was creating patient pathway management streams that enable patients to receive standardized care, which provides better patient outcomes and experiences. Additionally, these AI created patient streams had to be amenable to auditing to explain the reason why a particular treatment was recommended.
Papagiannopoulos discusses the key steps in creating the patient pathway, including:
Establishing the lab connection – A four to five year process that included collecting the data that would be used by the AI model.
Validating the data – This confirmed that their solution delivered the desired benefit. They looked at the disease, patient treatments, and ways to identify the disease earlier on.
Following up with Patients – The use of AI to follow up with patients remotely.
Kostas and Dan discuss two primary use cases:
- Using AI to direct patient pathways to treatment
- Being able to remotely follow up with patients
Critical to the first use case is the ability to set a standardized patient pathway journey, and if there is a deviation from the standard of care there is an alert to all involved to correct the pathway.
Papagiannopoulos identifies the ability to audit results as one of the most important components. This enables them to control performance through standardized pathway management, which is key to improving the management of patient health as well as the hospital itself.
As a healthcare provider, Papagiannopoulos utilizes KPIs that are patient centric. Ultimately it is about how many patients have a good outcome. Hospital management looks at financial KPIs such as overall costs and how many patients are treated.
The use of AI matched up his KPIs with management KPIs, resulting in a safe, cost effective business that delivers better patient outcomes. They were able to see more patients, and treat them better, so the providers at Leeds Hospital became both more effective and more productive.
The AI was trained on millions of data points including patient turnaround times, wait times, and the journey from pre-admission to treatment, to identify opportunities for increased efficiency. The data also evaluated, time of day and day of the week the patient was treated, and more. By collecting so much data they were able to create a statistical analysis that could guide them on how to improve patient treatment.
For patient follow up, tools, such as a saturation probe connected with wifi or bluetooth are used to collect accurate patient data, and if necessary, identify when something goes wrong and take action such as calling the patient into the hospital.
The key point is that where they once had to keep patients in the hospital, now they could be sent home and monitored. All of the patient information would be downloaded automatically and the AI is able to predict how quickly a patient can complete treatment so the provider can work on another patient. The result is that the provider can be more productive and still see where patients are deviating from what is expected.
While some of this can be handled with simple if-then rules, what really makes the AI so powerful is its ability to be predictive. AI assists Leeds Medical Professionals so that they can take action that can prevent people from getting diseases.
Under the traditional methodology, healthcare providers wait for people to come in when they have symptoms. AI lets them see which patients are likely to develop a condition, so they can be seen before symptoms are present, dramatically improving outcomes.
“If we want the best performance in terms of results for the patient, then we have to adopt AI”, said Papagiannopoulos.
AI is here. Discover how you can fundamentally transform what is possible for your organization with the power of AI in weeks, not years. Powered by the industry’s most powerful, full stack deep learning platform, SambaNova is the industry leader for GPT and large language models, delivering the highest accuracy and performance, while dramatically reducing the need for significant investment in infrastructure, personnel, and other resources.