Predicting the future to help patients today

It’s a dilemma faced hundreds of times a day, at hospitals across the country. A doctor is notified that a deceased donor kidney is being offered to their patient. But the organ may not be the best possible match. If the transplant team turns it down, however, in hope of a better match, how long will it be before another offer comes along? When waiting could mean more months, or even years, on dialysis, what is the right decision for the patient?

The process for matching donor kidneys to patients is complex. Factors like blood type, immune system compatibility, and how long patients have been waiting are all considered. Once the offer is made, though, a team of transplant professionals uses their years of experience and clinical expertise to determine whether to accept or reject that offer for their patient. Until now, they could evaluate the potential benefit of transplant for their patient against the characteristics of a specific offer. However, they would have no reliable way of estimating how long their patient might wait for another offer.

Now, those doctors and transplant teams have something new to aid their decision-making—the predictive analytics tool in DonorNet Mobile. Launched this year and available to all adult kidney programs nationally, the tool shows transplant teams both predicted time to next offer and predicted survival likelihood during that window of time, providing a never-before-seen look at the impact accepting or declining an organ offer could have on a patient.

Waiting for the right offer

“Sometimes you have a patient whom you really want to get a good kidney for, and an offer comes along, and you debate, ‘This isn’t perfect, but how much longer should I wait? Should we wait another month? Should we wait another two months?'” says Glyn Morgan, M.D., Chief of Transplant Surgery at Connecticut’s Hartford Hospital, which performs on average 70 deceased donor kidney transplants per year.

A variety of factors contribute to a patient’s ranking on the match run, including medical urgency, so many of Morgan’s less medically urgent patients, like thousands of others across the country waiting for the right match, may not receive an offer until an organ has been offered to hundreds of others. Says Morgan, “If a good organ is being offered, there’s a good chance it will be accepted before it reaches one of my patients.”

Morgan is now using the predictive analytics tool to see how long his patients may have to wait to receive another offer of similar quality. He can then determine if it makes sense to wait for another organ that could be a better match and provide a better outcome for his patient.

It’s a critical decision—waiting for a more compatible kidney for a patient could reduce the severity of rejection episodes that occur after transplant and ensure a kidney will function longer for a patient.

Unfortunately, not all patients are well enough to wait.

Getting patients off dialysis

Some transplant teams may determine that getting a kidney for an ailing patient sooner makes more sense than waiting for a higher quality kidney that may become available later.

“We’re at a point where we have to entertain every offer we possibly can to get our patients transplanted, just based on that wait time alone,” says Jacob Mansy, a physician assistant at Scripps Green Hospital in La Jolla, California. The situation he describes is familiar to transplant professionals working across southern California, where the number of patients in need of a kidney transplant is so large that estimated wait time can range between seven and 10 years, depending on blood type. Mansy is part of a team of transplant professionals who screen organ offers and decide whether to reject the offer or send it to a surgeon to review and potentially accept.

Mansy says he utilizes the “Time To Next Offer” function of the predictive analytics tool to estimate how long a patient could spend on dialysis waiting for another offer, if the current offer were to be rejected. “I’ve seen it be useful in making the decision on more marginal kidneys, especially for our older patients. If we can get them transplanted and save them six months, one year, two years, three years on dialysis, it’s a win.”

Making lifesaving decisions

Ultimately the predictive analytics tool, along with other components of UNet℠ technology, are designed to help transplant teams get their patients transplanted as quickly as possible. At Scripps Green Hospital, Mansy says the tool recently helped his team do just that.

Working with a patient with a high-risk medical history, Mansy’s team was offered an organ from an OPO on the other side of the country. The team hesitated to immediately take the offer, but the predictive analytics tool helped them decide to accept.

“There were several factors that led us to accept it, one of which was the predicted time to next offer for our patient. Based on what the predictive analytics tool was telling us, we saw we could get our patient transplanted and potentially save them six months or even a year plus on the waitlist.”