Two years ago, the Saudi Arabian National Guard’s Riyadh-based hospital, King Abdulaziz Medical City, became the first hospital in the world to reach Stage 7 in four different HIMSS models . (It recently became a pioneer with some impressive work to reach Stage 6 on a different model.) Its use of advanced health information and technology has paid dividends for the health system’s 1.3 million patients.
Since then, the 3,720-bed MNGHA has continued its efforts to transform digital health across a variety of specific use cases, including one that seems simple but has long puzzled providers. Services worldwide exasperated: no-shows at outpatient facilities.
They are disruptive, add unnecessary costs to care delivery, and they can have a real impact on care management and patient outcomes.
However, Huda Al Ghamdi, director of data management and business intelligence at MNGHA, said the National Guard Health Department has been able to achieve some notable benefits in reducing absenteeism by How to apply artificial intelligence to your analytics. Patients are more likely to miss appointments at the emergency department.
Health systems are using machine learning to take data from electronic health records – patient summaries, clinical information, appointment histories – and then process and train that data for AI models can alert physicians in the EHR – helping them send necessary reminders to patients and even schedule appointments within their own workflow.
MNGHA includes more than 30 hospitals, specialty hospitals and primary care centers across Saudi Arabia, with all facilities linked to a unified EHR system called BESTCare.
That gives “the advantage of having huge amounts of data,” Al Ghamdi explains. “Advanced analytics, prediction, and machine learning.”
Innovative approaches to analytics have helped health systems in many areas, she said, but no-shows are a particular area of concern.
“The reason this issue has to be specifically addressed is because the outpatient facility is considered the largest channel through which MNGHA is providing medical services to patients,” she said. “Unlike inpatients or emergency rooms, outpatients are considered the largest because we’re talking about about 20,000 visits per day.” [on] medium.”
That adds up to five to six million visits per year.
“So when there is an issue like no-shows, it certainly affects the care providers, it affects the resources, it affects the patients themselves,” Al Ghamdi said.
She noted that the fact that MNGHA is a public hospital means it is sometimes difficult to measure costs when patients do not come in, but there are still costs, “and we should be aware of that and start thinking about save”. .”
Luckily, MNGHA has “a huge amount of data that we can start to analyze and study and try to find the factors that influence this,” Al Ghamdi said. “We have a unified electronic medical record system that has different modules for registration, hospitalization and outpatient treatment.
“When it comes to the datasets that we are using in this project, it is mainly demographic information, very simple information, mainly gender, age, in addition to information related to government clinic, because there is a difference in no-shows from one clinic to another,” she explains. “And the third part of the data set is the patient’s own history. Some patients, we found that they had a high rate of missed appointments and were like other patients. So kind of the history That gives us insight.” about those types of patients.”
Importantly, for this project, “we’re not dealing with any kind of clinical data,” she added, because that would require clinicians with expertise to decide what kind of factors What clinical conditions may influence absenteeism?
But using a basic data set of patient information allowed for the creation of several initial models, which were then validated to ensure which model was the best and most accurate.
“The project started two years ago. It took many phases to make sure we were ready to go.” [incorporate the model] in the electronic medical record system,” Al Ghamdi said. “So in the first year the model was created, and I would say we are in the model validation phase, the model validation phase To receive this, it takes about 4 to 6 months.
“Part of that validation was done in data science and then we rolled it out to a small group of clinicians and nursing and patient services staff,” she added. “And that phase takes about another six months. At that point, it’s been a year of us validating and ensuring that the model is reliable and that we can actually rely on the results from that model.”
Once the data science experts were satisfied with the algorithm, MNGHA took the step of incorporating the model into its EHR system and integrating it into the clinical workflow.
“Clinicians can see that patients scheduled for that day are likely to not show up for their appointments. And by flagging this type of thing in the medical records system, the clinician can send additional reminders.” remind or, for example, ask the patient service to make some kind of call to remind the patient,” Al Ghamdi said.
Ultimately, the plan is to roll out this model across all MNGHA facilities, in all regions.
For health systems looking to try something similar for their organizations, Al Ghamdi offers some advice.
“Even if they start with a small data set, it’s better to do this type of implementation, even in a small amount of data or a small list of parameters, because we know for sure that the data That data is telling us a lot about our patients, and there’s a kind of hidden pattern that we can uncover using machine learning and artificial intelligence techniques.
“Taking the next steps to process the data and gain knowledge from that data is very important,” she said. “It’s a very simple model that can be created. But it has a huge impact on the organization.”
Read a more in-depth case study on MNGHA’s use of machine learning for predictive analytics here.
Mike Miliard is the executive editor of Healthcare IT News
Email the writer: [email protected]
Healthcare IT News is a HIMSS publication.
