How analytics and machine learning can aid organ transplant decisions – Dimitris Bertsimas and Nikolaos Trichakis

MIT Sloan Prof. Dimitris Bertsimas

MIT Sloan Asst. Prof. Nikolaos (Nikos) Trichakis

From Health Data Management

magine this scenario: A patient named John has waited 5.5 years for a much-needed kidney transplant. One day, he learns that a deceased donor kidney is available and that he is the 153rd patient to whom this kidney was offered.

Clearly, this is not a “high-quality” organ if it was declined by 152 patients or the clinicians treating them. But because John has been waiting a long time for a new kidney, should he accept or decline the kidney? And can analytics and machine learning help make that decision easier?

Currently, that decision is usually made by John’s doctor based on a variety of factors, such as John’s current overall health status on dialysis and a gut instinct about whether (and when) John will get a better offer for a healthier kidney.

If John is young and relatively healthy, the risk of prematurely accepting a lower-quality kidney is future organ failure and more surgeries. If John’s health status is critical and he rejects the kidney, he could be underestimating how long it will take until a higher-quality organ is available. The decision could be a matter of life or death.

John’s dilemma isn’t unique in the world of kidney transplantation, where current demand outpaces supply. Since 2002, the number of candidates on the waiting list has nearly doubled, from slightly more than 50,000 to more than 96,000 in 2013. During the same time, live donation rates have decreased. Complicating this problem of supply and demand is an unacceptably high deceased donor organ discard rate, as much as 50 percent in some instances.

Read More »

The myth that mental illness causes mass shootings – Tage Rai

MIT Sloan Research Associate and Lecturer, Tage Rai

From Behavioral Science

“A sick, demented man.” That was Donald Trump’s assessment of Stephen Paddock, who shot nearly 600 people, leaving 58 dead, during a concert in Las Vegas on Sunday. Echoing Trump’s rhetoric, House Speaker Paul Ryan said that “one of the things we’ve learned from these shootings is often underneath this is a diagnosis of mental illness.” Most Americans agree that there is a strong link between mental illness and mass shooting, and shifting the national conversation to mental health reform carries the advantage of avoiding the more politically divisive gun-control debate. But what if Stephen Paddock had no diagnosable mental illness? And what if his mental state was the rule, not the exception?

In the aftermath of a mass shooting, we naturally seek to understand the killer’s motives. Our first instinct is to assume that the killer must be mentally deranged somehow. He must be a sadist who takes pleasure in the suffering of innocents, or a psychopath who feels no empathy for his victims, or a schizophrenic haunted by paranoid delusions. How else could someone commit such an awful atrocity? Yet, there is no evidence that Stephen Paddock was any of those things. He had no history of mental illness. He had no criminal record. He was a successful businessman. Relatives and people who know him are in disbelief. Paddock’s father was a notorious bank robber, but the two men never met, and if Paddock inherited violent tendencies from his father genetically, they never manifested until now. Read More »

Why home care costs too much – Paul Osterman

MIT Sloan Prof. Paul Osterman

MIT Sloan Prof. Paul Osterman

From the Wall Street Journal

As baby boomers age into long-term care facilities, Medicaid costs will go through the roof. Americans already spend – counting both public and private money – more than $310 billion a year on long-term support services, excluding medical care, for the elderly and the disabled. Medicaid accounts for about 50% of that, according to a 2015 report from the Kaiser Commission on Medicaid and the Uninsured. Other public programs cover an additional 20%.

Yet in another decade or so these figures may look small. In 2015 around 14 million Americans needed long-term care. That number is expected to hit 22 million by 2030. There’s an urgent need to find ways of providing good long-term care at a lower cost. One fix would be to deregulate important aspects of home care.

There are two million home health aides in the U.S. They spend more time with the elderly and disabled than anyone else, and their skills are essential to their clients’ quality of life. Yet these aides are poorly trained, and their national median wage is only a smidgen more than $10 an hour.

The reason? State regulations – in particular, Nurse Practice Acts – require registered nurses to perform even routine home-care tasks like administering eyedrops. That duty might not require a nursing degree, but defenders of the current system say aides lack the proper training. “What if they put in the cat’s eyedrops instead?’ a healthcare consultant asked me. In another conversation, the CEO of a managed-care insurance company wrote off home-care aides as “minimum wage people.”

Read More »

MBA diary: tackling the diabetes epidemic – Stefany Shaheen

Stefany Shaheen, EMBA ’18

From The Economist

My entrepreneurial journey began on a chilly January morning in 2008, not long after my daughter, Elle, was diagnosed with type-1 diabetes. She and I were in the kitchen of our New Hampshire home getting ready for breakfast. Elle, who was eight at the time and the eldest of four children, reached into the cupboard and picked out a box of Cheerios and a bowl. I handed her a measuring cup, calculator and notepad.

The realities of living with type-1 diabetes—a chronic, autoimmune disease that destroys the body’s ability to make insulin—were just starting to sink in. Fixing a bowl of cereal was no longer a simple process; it was maths problem. Together, we needed to figure out the amount of carbohydrates in the cereal and milk and then determine how much insulin Elle would need to inject to turn that food into fuel. We also needed to keep track of the food she was eating along with her physical activity and blood sugar levels to avoid dangerous high and low blood sugars. Having blood sugar that is either too high or too low can cause serious complications and could lead to death.

Elle and I got to work but she soon became frustrated. She threw the cereal box across the room; Cheerios flew everywhere. “Why does this have to be so hard?” she asked me through muffled tears.

Read More »

As You Were Saying … MGH needs checkup for possible ER bottlenecks — Steven J. Spear

MIT Sloan Senior Lecturer Steven Spear

MIT Sloan Senior Lecturer Steven Spear

From The Boston Herald

Five years after a $500 million expansion, Massachusetts General Hospital’s emergency department is again overburdened, in the words of hospital President Peter Slavin with “delays, dissatisfaction, and sometimes even concerns about quality and safety.”

Before the public, payers, policymakers and donors get on the hook — again — for more staff and more extraordinarily expensive capital expenditures, let’s ask these questions first.

• What’s the mix and volume of patients presenting at the emergency department?

• What portion of discharges occur on time, and of the rest, how long are they delayed?

• From when a patient first presents in the ED, what’s the lag until that patient is examined and treatment begins, the time from “door to doc?”

As to the first question, there are certainly patients with conditions that truly are life- or limb-threatening and arise unexpectedly. Think stroke, heart attack, or aneurysm.

Read More »