Artificial intelligence (AI) in the healthcare industry is still emerging, and yet has already received much attention in recent years. It has the potential to optimize various processes, collect multitudes of data to create valuable analytical insights and help healthcare providers in providing efficient care delivery and operations. AI can curate and analyze large amounts of information, from traditional clinical and claims data, to unstructured medical notes.
AI can transform healthcare administration and operations including the ways in identifying fraud and waste. It can also empower consumers by providing them with personalized engagement and recommendations.
Most importantly, AI can also help in reducing the total cost of healthcare. The US spends about 18% of the GDP on healthcare, twice as much as other high-income countries. By integrating medical, pharmacy and behavioral interventions, AI has the potential to significantly reduce the cost of healthcare in America.
What are some of the optimization issues that can be addressed by AI?
Healthcare Revenue Cycle Management
Revenue cycle management (RCM) refers to the use of medical billing software by healthcare facilities to track each step in patient care from registration and appointment to final payment of a balance.
Managing the revenue cycle is highly complex and is very difficult to scale, especially for large organizations. Joe Polaris, Senior Vice President of product and technology at R1 RCM, a revenue cycle management vendor, explained, “It’s a very transaction-oriented business in that every patient who has a need for medical care is going to have a significant number of transactions from the point of scheduling all the way through the multitude of steps to create a clean claim, submit it, and get paid.”
Without the right technology, it might be difficult to achieve scale, unless a company hires really smart people who will be willing to work harder and become smarter. An alternative, more cost-efficient way, according to Polaris, is with the use of AI.
AI is pretty uniquely good at evaluating those variables and coming up with an ever-improving success rate
“Whether it’s matching a patient with the right provider, estimating out-of-pocket costs, or coding the claim, those are things that have long lists of variables associated with them, and AI is pretty uniquely good at evaluating those variables and coming up with an ever-improving success rate of getting to the right outcome against any of those process steps,” he said.
Learn how Perceiver AI can optimize your processes, saving you time and money. Learn more!
Since the revenue cycle contains an abundance of tagged data, AI can codify these data points to indicate certain events, like why a claim was denied or attributes of a patient’s diagnosis. AI can also use algorithms to find patterns and plan future actions to produce positive outcomes.
Improving predictions of surgical procedures durations with AI/ML
Popular AI techniques today such as machine learning (ML) and deep learning can look at a dataset and learn from it. They can also make new predictions by discovering data patterns that people might miss.
A recent study by British AI company Deepmind identified aspects of electronic health records that can predict a patient’s likelihood of developing acute kidney injury (AKI) up to 48 hours before it would otherwise be diagnosed. AKI is a condition where a patient’s kidney suddenly stops working properly and affects over 100,000 people in the UK every year. Deepmind worked alongside experts from the US Department of Veterans Affairs, in studying how AI can help give doctors a headstart when treating this condition.
The model they proposed correctly predicted 9 out of 10 patients whose condition deteriorated severely
The model they proposed correctly predicted 9 out of 10 patients whose condition deteriorated severely. This helped them receive the required dialysis faster. This only gives us a glimpse of the future for earlier preventative treatment and potentially avoid invasive procedures like kidney dialysis.
Another company, Optum, the health services arm of American insurance company UnitedHealth Group, also used AI in collecting data to predict whether a patient is likely to develop atrial fibrillation, a heart condition that can lead to strokes and is common among people with irregular heartbeat.
Using a training set of health insurance claims and clinical data, the company was able to create an AI model that was able to detect 70% of the patients who were diagnosed with atrial fibrillation.
“This could be a new way of abstracting data and presenting it back to the doctor,” according to Dr. Arthur Forni, an infectious disease doctor at Westchester, New York-based WestMed who’s working with Optum with the trial.
Reducing delays in admission to the post anesthesia care unit (PACU)
Patient scheduling system is another area where AI can help in optimizing healthcare processes. Using doctors’ notes or other structured clinical data about the patient, ML programs and AI can be useful in determining the type of appointment to schedule. AI can also resolve other optimization issues and help maximize patient volume, minimize delay and overbooking.
For example, the Massachusetts General Hospital was able to reduce overcrowding in patient beds by using AI to assign schedule blocks in the operating room.
AI is also now being used in anesthesiology and in the intensive care units. Vital signs such as blood pressure, heart rate or oxygen saturation, and also include respiratory and laboratory parameters are all being monitored by anesthesiologists. They also need to know certain details about the patient such as diagnostic imaging, medication administration, dosages, and volumes. All of this data can be structured and interpreted by AI and predict certain outcomes.
According to Prof. Bettina Jungwirth, Director of the Department of Anesthesiology and Intensive Care Medicine at the University Hospital of Ulm, Germany,
“The goal of AI in anesthesiology and critical care medicine is to use big data to sustainably improve patient outcomes via personalized perioperative treatment. This necessitates individualized risk prediction, which has already been addressed in several studies. The objective is to effectively predict postoperative nausea and vomiting or patient deterioration in the recovery room, or to identify patients at risk for postoperative delirium.”
Learn how Perceiver AI can optimize processes to improve patient outcomes. Learn more!
It may seem risky to invest in new solutions, especially when budgets are strained. However, investing in AI and other smart technologies can prove to be a better option in addressing financial challenges and maintaining solvency.
The current health care payment process in the US is unsustainable. Almost $200B in administrative waste is generated annually and is harder to reduce by health care payers and providers on their own. Some of the contributors to this waste are lack of price transparency and inaccurate or missing documentation and coding.
In a survey published at Revcyleintelligence.com, 84% of hospital leaders say that clinical documentation and coding are their top areas of vulnerability for lost or decreased revenue. In the same survey, 68% of hospital leaders said they are not technologically equipped enough to manage Diagnosis Related Group coding.
AI analytics have the potential to be proactive and offer the information needed and make appropriate recommendations for coding and documentation. For example, the program may, in real time, show a pop-up screen when an order isn’t coded correctly. This then leads to more accurate claims, resulting in fewer denials and faster reimbursement for services.
Another cause for annual waste is lack of price transparency. Patients who feel that they are not receiving enough price transparency when it comes to health care services, tend to switch providers. According to the Becker’s Hospital CFO Report, patients who receive an unexpected bill are more likely to ditch their current provider for a new one, and can cost the average hospital up to $100 million each year.
With AI technologies, patients can now anticipate their financial obligations pre-service. Data such as policies, benefits and costs, can be aggregated and interpreted by AI. This does not only relieve the hospital of the burden of manually sorting out complex information, but also increases the accuracy of the cost estimate for the patient.
Learn how Perceiver AI can reduce waste, saving money and build better outcomes. Learn more!
There are more optimization problems in the healthcare industry that can be resolved by AI. They do not just make healthcare workers more efficient in delivering services, they also improve the patient’s entire hospital experience.
Perceiver AI is currently accepting applications for new clients for a limited time.
Learn how Perceiver AI can optimize healthcare processes, saving time and money and improving patient outcomes. Get in touch today!