The findings, published in npj Digital Medicine, suggest this technology could help surgeons refine their techniques and improve patient outcomes.

The AI system, called Frame-to-Outcome (F2O), analyzes video recorded during the nerve-sparing portion of robot-assisted prostate surgery, when surgeons work to preserve the nerves responsible for sexual function. Rather than relying on experts to manually evaluate each procedure, the system automatically identifies patterns in a surgeon’s movements—called “surgical gestures”—and uses them to predict patient recovery.

Prior studies of these surgical gestures demonstrated a strong relationship between the gestures performed by the surgeon—such as the sequence of instruments used or the speed of stretching nerves to move them aside—and the patient’s outcome. By analyzing the gestures used during surgery, the AI system made determinations about whether the patient will be more or less likely to have a good outcome. Until now, this type of analysis required labor-intensive review by trained human observers.

“Our goal isn’t simply to predict who will recover,” said Andrew Hung, MD, corresponding author of the study and professor of Urology at Cedars-Sinai. “We want to identify the surgical techniques with the best outcomes so surgeons can learn, refine and improve care for our future patients.”

Investigators found that F2O matched expert human reviewers in predicting patient outcomes while dramatically reducing the time required to analyze surgical performance. The technology could eventually provide surgeons with objective feedback on the techniques most closely associated with successful patient recovery.

To develop the system, researchers trained the AI system using videos annotated by human analysts from 294 surgeries from 23 surgeons across four international centers. Then they tested it on an additional 29 surgeries and found its predictions closely matched those of expert human reviewers.

“By identifying and interpreting the gestures that result in positive patient outcomes, we can offer surgeons insights that can help improve surgical performance and patient care,” Hung said.

The study was a collaboration between the Department of Urology, the Department of Computational Biomedicine and the Center for Artificial Intelligence Research and Education (CAIRE) at Cedars-Sinai.

“This work highlights what we can achieve when surgeons and computational biomedicine experts work together toward a shared clinical goal," said Jason Moore, PhD, chair of the Cedars-Sinai Department of Computational Biomedicine and director of CAIRE. "Bringing together these disciplines allowed the team to build something that is technically rigorous and genuinely meaningful for surgeons—and their patients."

Additional Cedars-Sinai authors include Xi Li, Nicholas Matsumoto, Jay Moran, Miguel E. Hernandez, Cherine Yang, Jeanine Kim, Jasmine Lin, Peter Wager, Ujjwal Pasupulety and Atharva Deo.

Other authors include Alvin C. Goh, Christian Wagner and Geoffrey A. Sonn.

Funding: Research reported in this publication was supported by the National Cancer Institute of the National Institutes of Health under Award Number R01CA273031. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health.

Cedars-Sinai Health Sciences University is advancing groundbreaking research and educating future leaders in medicine, biomedical sciences and allied health sciences. Learn more about the university.

“The annual AUA meeting is a pivotal event for urologists worldwide, providing a platform to discuss innovation and inspire future advancements,” said Hyung L. Kim, MD, professor of Urology and chair of the Department of Urology at Cedars-Sinai. “It is a great opportunity for our Cedars-Sinai team to collaborate with peers, sharing insights to advance research and elevate patient care across the field.” 

Cedars-Sinai Experts Available for Interviews

Michael Ahdoot, MD, assistant professor of Urology and director of the Minimally Invasive Urology Institute, will present research on the detection of bladder cancer using an advanced new urine test that measures multiple proteins and antibodies.

Timothy Daskivich, MD, associate professor of Urology and director of Urologic Oncology Research, can address the latest advances in prostate cancer treatment and patient care, including shared decision-making and life expectancy estimates in prostate cancer consultations.

Stephen Freedland, MD, professor of Urology and director of the Center for Integrated Research in Cancer and Lifestyle at Cedars-Sinai Cancer, is available to discuss the EMBARK Phase III international clinical trial, which tested a combination treatment option for men with recurrent prostate cancer. 

Andrew Hung, MD, professor of Urology and vice chair of Academic Development in the Department of Urology, can discuss artificial intelligence in surgical education and innovations in robotic surgery.

Aurash Naser-Tavakolian, MD, associate program director for the Urology Residency Training Program, can discuss treatment of male urinary incontinence and genitourinary reconstruction using minimally invasive surgical procedures.

Awards

Patrick Tamukong, MD, PhD, a urology resident in the Department of Urology at Cedars-Sinai, will receive the Humanism in Medicine Award for Residents and Fellows, presented by the Arnold P. Gold Foundation and the Urology Care Foundation. The award honors urology residents and fellows who exemplify humanism in their patient care and actively engage in humanitarian initiatives beyond their clinical responsibilities.

Scheduling Interviews

To schedule an interview with a Cedars-Sinai expert, contact Jillian Scholten at 949-244-2561 or jillian.scholten@cshs.org.

The research findings were published in the peer-reviewed journal JAMA Internal Medicine.

Prostate cancer is the second-most common cancer in the U.S., exceeded only by breast cancer. About one-eighth of U.S. men are diagnosed with prostate cancer at a median age of 67 according to the National Cancer Institute. Most patients have slow-growing, localized tumors, confined to the prostate gland, that are unlikely to threaten their lives. Instead of immediate treatment, these low-risk patients can be monitored through “active surveillance,” in which examinations and tests are performed on a regular schedule to make sure the disease is not progressing.

“Use of active surveillance has increased over the last 15 years for men with low-risk prostate cancer, and it is now the most common treatment for these men,” said Timothy Daskivich, MD, director of Urologic Oncology Research for the Cedars-Sinai Department of Urology and corresponding author of the new study. “This approach allows these patients to avoid the risks of urinary incontinence, erectile dysfunction and other potential side effects of surgery and radiation therapy.”

Conservative management, which includes active surveillance or watchful waiting, is also recommended for men with limited life expectancies who likely will not live long enough to benefit from aggressive local treatment, even for higher-risk cancers. However, for these men, the trend is going in the opposite direction, as measured by the investigators’ analysis of extensive data from the Veterans Affairs health system. They found that for men with limited life expectancies and intermediate- and high-risk cancers, conservative management was being employed less often and that more were receiving aggressive local treatment with surgery or radiation.

“We found this pattern surprising,” Daskivich said. “Prostate cancer patients with life expectancies of less than five or 10 years were being subjected to treatments that can take up to a decade to significantly improve their chances of surviving cancer, despite guidelines recommending against treatment.”

For their study, the investigators analyzed medical data on 243,928 men in the Veterans Affairs health system who were diagnosed with localized prostate cancer between 2000 and 2019.

Among patients with average life expectancies of less than 10 years, the proportion who underwent treatments such as surgery or radiation for low-risk prostate cancer rather than receiving active surveillance decreased from 37.4% to 14.7%; but treatment for intermediate-risk disease increased from 37.6% to 59.8%. Among patients with average life expectancies of less than five years, treatment for high-risk disease increased from 17.3% to 46.5%. Among men who were overtreated, roughly 80% were treated with radiation therapy.

Solving the issue of overtreatment in higher-risk prostate cancer patients with limited longevity requires a multifaceted approach involving better estimation, communication, and integration of life expectancy into decision-making, Daskivich said. He and his team have proposed a “trifecta” method for communicating cancer prognosis to the patient. This method involves the physician discussing the likelihood of dying from the cancer with treatment versus without treatment at the endpoint of the patient’s life expectancy. This approach personalizes the risk of the cancer that is relevant to each patient.

“Our goal is to encourage clinicians to make longevity part of the discussion about the best treatment options so that prostate cancer patients with limited life expectancies can make educated choices,” Daskivich said. “A patient may be given this data and choose to pursue surgery or radiation treatments regardless of a limited probability of benefit.  Another patient may take a different course.”

“Every individual is different, and statistical averages for lifespan, treatment effectiveness and cancer risk cannot predict outcomes with certainty,” Daskivich added. “But patients should be given the opportunity to make informed decisions with the best possible information.”

Hyung L. Kim, MD, chair of the Department of Urology at Cedars-Sinai, said the JAMA Internal Medicine study reflects a signature strength of Cedars-Sinai: the close cooperation among researchers and clinicians. “Many of our investigators are themselves clinicians, which ensures that their research addresses real-life problems in healthcare with an emphasis on finding solutions,” he said.

Other Cedars-Sinai authors include Michael Luu and John R. Heard. Other authors include I-Chun Thomas from Stanford University and senior author John T. Leppert from Stanford University in Stanford, California, and the VA Palo Alto Health Care System in Palo Alto, California.

This work was supported in part by VA Merit Review (I01 HX0021261 to JL). The Department of Veterans Affairs Health Services Research and Development Service work was supported using resources and facilities at the VA Informatics and Computing Infrastructure (VINCI), VA HSR RES 13-457. The contents do not represent the views of the U.S. Department of Veterans Affairs or the U.S. Government.

Follow Cedars-Sinai Academic Medicine on LinkedIn for more on the latest basic science and clinical research from Cedars-Sinai.

“If these treatments are approved by the Food and Drug Administration, our results will be practice changing,” said Stephen Freedland, MD, associate director for Training and Education and the Warschaw, Robertson, Law Families Chair in Prostate Cancer at Cedars-Sinai, and lead author of the study. “In the study, both of these new options improved metastasis-free survival while preserving quality of life.”

Cancer of the prostate, a walnut-sized gland that helps make semen, will be diagnosed in 288,300 men in the U.S. in 2023, according to American Cancer Society estimates. For some, treatment may never be needed because they have a slow-growing form of the disease, but those with more aggressive prostate cancer are often first treated with surgery or radiation therapy.

“Unfortunately, in about a third of those patients, the cancer recurs within 10 years,” Freedland said.

Patients with aggressive recurrence are treated with androgen deprivation therapy (ADT), also known as hormone therapy, which reduces the patient’s production of the male sex hormone testosterone. Testosterone helps prostate cancer cells grow and spread, and the hormone therapy effectively reduces the growth-stimulating effects. But Freedland said ADT has two downsides: It doesn’t completely eliminate testosterone, and it can cause many side effects.

“When you go on ADT, the testosterone level in the blood is reduced, but not completely eliminated,” Freedland said. “And the concern is that the testosterone that remains may still be enough to stimulate tumor growth. Also, patients don’t love the idea of being on hormones.”

In this study of 1,068 prostate cancer patients from 244 sites in 17 countries, Freedland and fellow investigators tested two experimental interventions—one to address each of these issues.

In the randomized clinical trial, one-third of the patients received ADT plus a medication called enzalutamide, which blocks the effects of testosterone. Enzalutamide keeps any testosterone remaining in the blood from stimulating the growth of cancer cells.

Another third of the patients received enzalutamide alone. This option relied on the medication to block the effects of testosterone even though testosterone levels in the patients’ blood were not reduced.

“We wanted to see whether enzalutamide on its own was so effective that we didn’t need the ADT,” Freedland said.

The final group of patients received ADT alone, which is the current standard treatment.

Investigators found that the combination of ADT plus enzalutamide reduced the risk of metastasis or death by 58% over ADT alone. They found that enzalutamide alone reduced the risk of metastasis or death by 37% over ADT alone. Both treatments maintained quality of life relative to the ADT alone.

“While the combination therapy offers greater risk reduction, some men might prefer enzalutamide alone. It does a good job of preventing cancer spread or death, with different side effects that may be more acceptable for some men,” Freedland said.

The next step is for the makers of enzalutamide to apply for FDA approval, so the experimental therapy can come into wide use, Freedland said.

“Optimizing therapy for patients with aggressive recurrence after their prostate cancer is initially treated has been an unmet need,” said Dan Theodorescu, MD, PhD, director of Cedars-Sinai Cancer and the PHASE ONE Distinguished Chair. “The results of this trial point the way to two options which the study showed were more effective than current standard of care, giving these patients and their providers the opportunity to choose a potentially improved course of therapy that best meets their needs.”

Funding: The study was sponsored by Pfizer and Astellas Pharma, the co-developers of enzalutamide.

Read more on the Cedars-Sinai Blog: Radiation Therapy as Effective as Surgery for Prostate Cancer

Hung is highly skilled in robotics and advanced laparoscopic techniques to treat urologic cancers. He also is an internationally respected leader in the development of surgery simulation technology, as well as an innovator in developing automated performance metrics and machine learning algorithms to predict surgical outcomes.

“We extend a warm welcome to Dr. Hung, a leader in our field who has an excellent reputation as a surgeon and as a pioneering researcher in medical innovations,” said Hyung Kim, MD, chair of the Department of Urology at Cedars-Sinai and the Homer and Gloria Harvey Family Chair in Urologic Oncology in honor of Stuart Friedman, MD. “Dr. Hung’s leadership and expertise will continue to advance our next-generation clinical and research efforts to benefit urology patients.”    

Prior to joining Cedars-Sinai, Hung was tenured associate professor of Urology and director of the AI Center in Urology at the University of Southern California (USC), where he was instrumental in incorporating artificial intelligence into robotic surgery. 

He has received multiple grants from the National Institutes of Health, and his work, comprising more than 200 papers, has been published in top peer-reviewed journals such as Nature Medicine, Nature Biomedical Engineering, Nature Communications Medicine, JAMA Surgery and the Journal of Urology.

Hung was the first consulting editor on AI for the British Journal of Urology International. He currently serves on the American Urological Association’s Research Grants and Investigator Support Committee and New Technologies Committee.

Hung earned his bachelor of science degree in molecular, cellular and developmental biology from Yale University and his medical degree from Weill Cornell Medical College at Cornell University. He completed his urology residency and robotics fellowship in the Department of Urology at USC.  

“It is an exciting time in urological technology and treatment innovation,” Hung said. “I’m honored to be among the team of world-class Cedars-Sinai surgeons and researchers who are bringing the latest discoveries to patients.”

Cedars-Sinai once again has been recognized by U.S. News & World Report, this year as the #5 program in the U.S. for Urology. Cedars-Sinai is also #1 for Urology in California and Los Angeles (highest U.S. News ranking in the state and region).

Read more on the Cedars-Sinai Blog: Who Should Get a Prostate Cancer Screening and When?

Kim will head the nationally recognized department with his unwavering commitment to clinical excellence, cutting-edge research, and medical education.

"Dr. Kim's expertise as a urologic oncologist, surgeon, and NIH-funded researcher will undoubtedly continue to drive the success of the Department of Urology," said Cristina Ferrone, MD, chair of the Department of Surgery at Cedars-Sinai. "He is equally dedicated to his patients and his colleagues, which continuously fosters his innovation and collaboration.”

Kim recently sat down with the Cedars-Sinai Newsroom and shared his vision for patients and staff, highlighting the important roles education and research play in ensuring the department's success.

Newsroom: What types of patients seek care from a urologist?

Kim: Urology covers diseases of the genitourinary system.

At Cedars-Sinai we have physicians who subspecialize within all the super-subspecialty areas of urology. For example, we have pediatric urologists, urologists who specialize in kidney stones, urologic oncologists who specialize in cancers of the urinary system, urologists who work with reconstruction and urinary incontinence, urologists who specialize in infertility and sexual dysfunction, and we have a transgender medicine program within urology that offers surgical services for adults who wish to transition from male to female or female to male.

Newsroom: What is your specialty?

Kim: I am a urologic oncologist. I take care of cancers of the bladder, kidney, and prostate. I run clinical trials and a molecular biology lab, focused on tumor immunology where we are looking for drugs and therapies that help stimulate the immune response against cancer.

When I first started out, there were only two treatments for advanced kidney cancers, and they were not very effective. Most patients quickly passed away and I felt like there was room for discovery and improvement in care.

Since then, so much has changed, surgeries have improved and there are now over a dozen new therapies for kidney cancer, many that are highly effective. All of us do a small part in making these discoveries, but it has been very satisfying to see the advances in the field that I've devoted my career to.

Newsroom: How has urologic surgery evolved over time?

Kim: When I was training as a resident, we made big incisions to take out cancer, and while we continue to take out cancers with surgery, we're now doing it in less invasive ways. We're now performing operations robotically, resulting in smaller incisions, less pain, and a faster recovery.

In addition to robotic surgery, we have platforms that allow us to do the operation completely noninvasively. That means, in some cases, energy is transmitted through tissue and focused on cancerous areas to ablate the tissue without actually having to cut it out.

Newsroom: As the inaugural chair, what is your vision for the department?

Kim: We have the highest urology volume of all the hospitals in L.A. County, and the goal is to continue to provide the great care we've been providing to our patients while continuing to grow our research enterprise.

We have research excellence and training, which is an important part of our department because if you have excellent doctors who are doing cutting-edge research, you want to then use that platform to train future doctors who are going to go out and have an impact on patient care elsewhere in the country.

Newsroom:  How does education and research contribute to the success of the department?

Kim: When I arrived at Cedars-Sinai 13 years ago, a residency program did not exist. We knew we wanted to attract other clinicians who felt that it was an important part of their mission to train and educate future doctors. So, if you want to attract those people, you have to have a training program in place, so we applied for a residency program, and we've now had a residency program for 10 years.

When you have a doctor who is always thinking about where the frontier of knowledge is, and they’re always thinking about how to do things even better than what is already being done, I think you're going to have a more thoughtful doctor. You're going to have a doctor who's providing you with not just the standard treatments, but maybe even experimental treatments as part of a trial, and you may have access to future therapies, and in return, you could be helping develop the future standard of care.

I think having a team of researchers in your program makes for better care for everybody.

Read more on the Cedars-Sinai Blog: What You Need to Know About Kidney Stones

Older women are among the most susceptible to developing UTIs, an infection of the bladder and urethra that causes urinary urgency and pain. UTIs also can cause delirium in older people, resulting in a sharp decline in mental abilities that triggers disoriented thinking.

“Up to one-third of elderly patients hospitalized with UTIs can experience some degree of confusion and reduced awareness of their surroundings,” said Shouri Lahiri, MD, director of the Neurosciences Critical Care Unit and Neurocritical Care Research at Cedars-Sinai and senior author of the study. “Delirium affects millions of patients a year in the U.S., contributing to longer hospital stays, long-term cognitive problems and increased mortality. Delirium can be a tipping point from which patients never fully recover. This is well established. What is less well established is why this is happening.”

To better understand the specific biological mechanisms behind UTI-associated delirium, Lahiri and colleagues observed laboratory mice with and without UTIs in specially designed mazes. In an arena where the animals could move about freely, uninfected mice spent more time in the center of the chamber. Those with UTIs huddled in the periphery, suggesting they had higher levels of anxiety, a common symptom of delirium.

In a Y-shaped maze with three arms to explore, uninfected mice tended to explore all three arms, while mice with UTIs kept returning to the same one, suggesting a lapse in short-term memory, another feature of delirium.

The investigators also observed structural changes in the brains of mice with UTIs.

In a previous study led by Lahiri, published in February in the American Journal of Respiratory Cell and Molecular Biology, investigators found a connection between ventilator-induced lung injury and delirium. Lahiri and colleagues theorized that in both cases this was because of the reaction of IL-6, which helps regulate immune response, to the lung injury or the UTI.

“Occasionally, when the response of IL-6 is excessive, our research indicates that there can be brain injury,” Lahiri said. “IL-6 induces changes within the neurons that our studies connected with delirium-like behavior. This is the first time this type of structural and functional change has been demonstrated. We’ve now shown two distinct models of this connection, one non-infectious and one infectious.”

In the current study, when investigators treated some of the infected mice with antibodies that blocked the effects of IL-6, the delirium-like behavior of those animals resolved. “Treatment with anti-IL-6 antibody in the UTI group normalized all the brain changes, both structural and functional,” Lahiri said. “A wealth of studies have shown a link between IL-6 and delirium, but only this study and our previous study have shown that IL-6 may play a direct pathological role in delirium.”

If symptoms are treated early, he added, full recovery is possible, and the next step is to design clinical trials with anti-IL-6 antibodies as a treatment for patients with UTI-induced delirium.

“Dr. Lahiri and his team have built a research framework with implications far beyond this study,” said Nancy Sicotte, MD, chair of the Department of Neurology who holds the Women’s Guild Distinguished Chair in Neurology at Cedars-Sinai. “Building on these efforts could improve outcomes for many of our patients.”

Lahiri believes the model he and co-investigators created could be used to study delirium in other conditions associated with increased incidence of UTI. These include those with pre-existing neurologic disorders like Alzheimer’s disease, Parkinson’s disease, stroke and multiple sclerosis where delirium can be hard to distinguish from the underlying disease but is important to treat.

“A huge population stands to benefit from these investigations,” he said. “We’re looking to apply this model to these other systemic disease conditions and states where the brain dysfunction caused is potentially reversible.”

Funding: This study was supported by National Institutes of Health/National Institute on Aging Grant R03AG064106, the American Academy of Neurology Institute and the F. Widjaja Foundation.

Read more on the Cedars-Sinai Blog: Alzheimer’s and Dementia FAQs