- About CSAIL
- News + Events
- Alumni & Friends
Worried about losing your libido? New iPad app predicts sexual function following surgery
3 July 2014
For a guy, there’s perhaps no scarier surgery than a prostatectomy (most commonly undertaken for prostate cancer). Multiple studies have shown that many men who’ve had the procedure experience erectile dysfunction - but it’s traditionally difficult to determine which patients will be affected most deeply.
This month a researcher from MIT’s Computer Science and Artificial Intelligence Lab (CSAIL) developed an interactive tool - soon to be rolled out to a university clinic as an iPad app - that offers men personalized predictions about their recovery, including the time it will take to recover as well as how (and if) their sexual function will return to normal.
Lead researcher Cynthia Rudin, a principal investigator at CSAIL and an associate professor at the MIT Sloan School of Management, says that personalized predictions help patients better manage expectations about their recovery and the procedure’s long-term effects.
Using data from UCLA clinic patients who underwent prostatectomies, she and her colleagues developed a statistical model for recovery curves that they say can be used to model recovery curves from other surgeries and even other medical conditions, such as stroke.
Rudin's team, consisting of CSAIL PhD student Fulton Wang and Tyler McCormick and Dr. John Gore, both at the University of Washington, used data from about 300 patients both before radical prostatectomy surgery and during the four years immediately following surgery.
In the tool, a central predicted recovery curve shows the patient's average sexual function over time after the surgery. It also displays a range of lighter-colored curves illustrating the broader range of possible outcomes.
"We wanted to help patients who are considering this surgery to understand what they could expect," says Rudin. "We can't tell you exactly what your recovery will look like, but at least we can forecast a personalized recovery curve and show you an informed prediction of your possible outcomes.”
The model can be used in an interactive way. For example, patients could adjust their reported age or reported sexual function levels to see how their predicted recovery curves change.
Medical data was provided by Gore, an assistant professor of urology at the University of Washington. He plans to have an iPad app version of the tool approved and available for patient use within the clinic in a few months, says Rudin, with the potential for it being rolled out to other hospitals in the future.
Patients can greatly benefit by being able to leverage the vast amounts of medical data that are now being collected in order to make data-driven decisions, she says.
"Predictive medicine is getting to be a really big deal,” Rudin says. “Until now, when people had questions about possible treatment effects, their doctors might give them vague, textbook-type responses and they'd get a range of answers based on whom they ask. It's time for patients to be able to make decisions based on data. And this type of work helps the data speak."