Key Takeaways 

• A cancer survival calculator prototype developed with machine learning showed that for each of three cancer types tested, more factors than cancer stage significantly influenced patients’ survival. 
• Preliminary research on the calculator found high accuracy of this individualized survival estimator. 

BOSTON (October 20, 2023): Researchers have developed an artificial intelligence (AI)–based tool for estimating a newly diagnosed cancer patient’s chances for surviving long term, according to a study presented at the American College of Surgeons (ACS) Clinical Congress 2023. 

Currently, estimating survival rates for patients with cancer primarily depends on their cancer stage, said lead study author Lauren Janczewski, MD, a clinical scholar with ACS Cancer Programs and a general surgical resident at Northwestern University McGaw Medical Center, Chicago.  

“There is a multitude of other factors that may influence a patient’s survival beyond just their staging criteria,” Dr. Janczewski said. “We sought to develop this Cancer Survival Calculator to provide a more personalized estimate of what patients can expect regarding their cancer prognosis.” 

Using a type of AI known as machine learning, the multicenter research team created a prototype tool called the Cancer Survival Calculator and tested it on a nationwide cancer dataset. Initial tests estimated five-year survival for patients with cancers of the breast, thyroid, and pancreas. 

Study details 

According to Dr. Janczewski, this study aimed to identify the patient, tumor, and treatment characteristics that most greatly influence patient survival for each cancer type. 

After cancer experts recommended characteristics to study, the researchers collected relevant information from patients diagnosed in 2015 and 2017 with breast, thyroid, and pancreatic cancers. The patients’ records were part of the National Cancer Database (NCDB), which contains records of 72 percent of newly diagnosed cancer cases in the United States.* 

Three-fourths of the collected data were used to train the machine learning algorithms to recognize patterns between characteristics at diagnosis and patients’ survival at five years, and then to rank the factors with the greatest influence on survival. With the remaining data, the researchers used statistical methods to test the prototype’s accuracy in estimating survival. 

Key findings 

The team included data from 259,485 breast cancer patients, 76,624 thyroid cancer patients, and 84,514 pancreatic cancer patients. The researchers found multiple characteristics specific to patients, tumors, and treatments for all three cancer sites significantly influenced survival.  

The top four factors influencing whether patients were alive five years after diagnosis were as follows, by cancer site: 

• Breast cancer: (1) whether the patient had cancer surgery, (2) the patient’s age at diagnosis, (3) tumor size, and (4) time from diagnosis to treatment. 
• Thyroid cancer: (1) age at diagnosis, (2) tumor size, (3) time to treatment, and (4) lymph node involvement. 
• Pancreatic cancer: (1) cancer surgery; (2) histology, or microscopic analysis of the cancer, (3) tumor size, and (4) age at diagnosis. 

Also found to be important for survival from breast cancer were hormone receptor status, which is part of breast cancer staging, and the presence of Ki-67, a biomarker in breast cancer. 

Although some of the predictive factors, such as tumor size, are part of cancer staging, Dr. Janczewski said their results showed that many more factors influence survival for cancer patients beyond their disease stage. 

Furthermore, their validation testing showed that the calculator was “highly accurate” for all three cancer sites at estimating cancer survival rates – within nine to 10 months of actual survival, Dr. Janczewski reported. 

Advantages of the new calculator 

The Cancer Survival Calculator differs in several ways from cancer survival estimators already in use, according to Dr. Janczewski: 

1. The novel calculator includes specific tumor biomarkers and treatment variables that are known to affect a patient’s estimated prognosis, which Dr. Janczewski said many prior survival calculators lack.  
2. The dataset used to develop the new calculator, the NCDB, is more comprehensive than other calculators’ datasets, according to Dr. Janczewski.
3. The Cancer Survival Calculator uses new data modeling, such as machine learning, which speeds up processing. The models’ risk predictions also demonstrated improved accuracy compared with predictions generated by older calculators, she said.  

Future steps 

The next steps that Dr. Janczewski identified are to finalize a user interface that will allow the use of the Cancer Survival Calculator in clinical practice, followed by pilot testing the calculator at selected cancer centers.  

Eventually, the researchers hope to broaden the calculator by adding all other cancer sites included in the NCDB. Initially, the calculator included breast, thyroid, and pancreatic cancers because these cancers have diverse patient populations and differing frequencies and average survival rates, she said. 

The research team plans to make the finalized informational tool available to healthcare practitioners. 

Study coauthors are Joseph Cotler, PhD; Bryan Palis, MA; Tanya Hoskin, MA; Courtney Day, MS; Ryan Merkow, MD, MS, FACS; Heidi Nelson, MD, FACS; Tracy Wang, MD, FACS; and Judy Boughey, MBBCh, FACS. Mayo Clinic and the Medical College of Wisconsin were study centers with Northwestern University. 

The study authors have no disclosures. 

Citation: Janczewski L, et al. Development of a National Cancer Survival Calculator Prototype Using Machine Learning, Scientific Forum, American College of Surgeons (ACS) Clinical Congress 2023. 

___________________ 

*The NCDB is a joint program of the ACS Commission on Cancer and the American Cancer Society. The database collects more than 1.5 million new cancer cases each year. 

# # # 

About the American College of Surgeons 

The American College of Surgeons is a scientific and educational organization of surgeons that was founded in 1913 to raise the standards of surgical practice and improve the quality of care for all surgical patients. The College is dedicated to the ethical and competent practice of surgery. Its achievements have significantly influenced the course of scientific surgery in America and have established it as an important advocate for all surgical patients. The College has approximately 90,000 members and is the largest organization of surgeons in the world. “FACS” designates that a surgeon is a Fellow of the American College of Surgeons.

Key Takeaways 

• Trauma centers with the highest pediatric readiness scores (93 or greater) on a national assessment have much lower death rates than centers scoring lower. 

• All trauma centers should address gaps in pediatric emergency care — most importantly, the lack of having a pediatric-specific quality improvement plan. 

BOSTON (October 20, 2023): Children initially treated at trauma centers with the highest level of preparedness to care for children, called pediatric readiness, are significantly less likely to die than those initially treated at trauma facilities with lower pediatric readiness levels, new research shows. The findings are being presented at the American College of Surgeons (ACS) Clinical Congress 2023. 

“What happens in that first hour after injury really impacts whether you survive, so rapid access to trauma center care for kids is important,” said principal investigator Aaron Jensen, MD, FACS, trauma medical director at the University of California, San Francisco (UCSF) Benioff Children’s Hospital Oakland.  

“But most children in the United States receive initial trauma care at non-pediatric centers because they are more readily available,” Dr. Jensen said. 

Trauma centers that specialize in treating children have the comprehensive infrastructure and resources needed to care for injured children, Dr. Jensen said. Emergency departments (EDs) in centers without comprehensive pediatric capabilities must be ready to resuscitate and stabilize severely injured children and quickly transfer them to pediatric trauma centers, he noted.  

Study details 

In this study, the investigators aimed to identify a minimum threshold of pediatric readiness among trauma centers that represents the lowest chance of patient death. To do so, they used data from the 2021 national assessment administered by the National Pediatric Readiness Project (NPRP).*  

The NPRP works to ensure that all EDs in the U.S. are prepared to provide high-quality emergency care for children. It uses a voluntary survey for EDs to self-assess pediatric readiness across six domains: administration and care coordination, personnel, quality improvement, patient safety, policies and procedures, and equipment and supplies. Survey responses are used to create a weighted pediatric readiness score that ranges from zero to 100. 

The new study included 790 U.S. trauma centers, 630 of which completed the NPRP’s 2021 national assessment, contributed data to the ACS National Trauma Data Bank^® (NTDB), and treated at least some children from newborns through age 15 years. Most centers were not pediatric trauma centers, Dr. Jensen said. 

The research team used ACS Pediatric Trauma Quality Improvement Program risk-adjusted models to estimate the adjusted odds of dying in each trauma center. Center-level adjusted mortality estimates were then compared across quartiles of ED pediatric readiness at the initial treating trauma center. 

Centers that reported pediatric readiness in the top 25th percentile (a score of 93 or higher) had the lowest adjusted odds of death, the investigators reported. This high-readiness quartile had 17 to 27 percent lower adjusted odds of death than any other quartile. 

Gaps in care 

Among the lower-scoring quartiles, Dr. Jensen said, “the most common deficiencies are lack of a pediatric emergency care coordinator, pediatric-specific quality improvement plan, and pediatric disaster preparedness plan.” 

The researchers found that having a pediatric-specific quality improvement plan was independently associated with significantly lower odds of death.  

Dr. Jensen stressed that the goal of pediatric readiness is not to transform every ED into a pediatric trauma center providing the full spectrum of emergency care for children. Rather, the goal is to help EDs optimize the initial care for pediatric trauma patients. Ways that EDs can improve their pediatric readiness are easy and usually inexpensive, he stated. 

“Access for kids to high-quality pediatric trauma care is an achievable goal and has a real impact on kids,” Dr. Jensen said. 

NPRP pediatric readiness scores are not publicly available. However, according to Dr. Jensen, almost every ACS-verified Level I pediatric trauma center in the study had pediatric readiness scores in the top quartile. ACS-verified trauma centers are searchable on the ACS website. 

Caroline Melhado, MD, a study coauthor and UCSF general surgery resident, presented this research at the conference. 

Other study coauthors: Katherine Remick, MD; Amy Miskovic, MS; Bhavin Patel, MPH; Hilary Hewes, MD; Avery B. Nathens, MD, PhD, FACS; Craig Newgard, MD, MPH; Brian Yorkgitis, DO, FACS; and Michael Dingeldein, MD, FACS. 

The study authors have no disclosures. 

Funding: This research was supported by the Health Resources and Services Administration (HRSA, #U07MC37471­01­00) of the U.S. Department of Health and Human Services (HHS) as part of the Emergency Medical Services for Children Innovation and Improvement Center. The contents are those of the authors and do not necessarily represent the official views of, nor an endorsement, by HRSA, HHS, or the U.S. government. 

This research has been accepted for publication in Annals of Surgery. 

Citation: Melhado C, et al. The Association Between Pediatric Readiness Scores and Mortality for Injured Children Treated at US Trauma Centers, Scientific Forum, American College of Surgeons (ACS) Clinical Congress 2023. 

________________________ 

* The NPRP is led by the U.S. government’s Emergency Medical Services for Children Program in partnership with the American Academy of Pediatrics, American College of Emergency Physicians, and Emergency Nurses Association. 

# # # 

About the American College of Surgeons 

The American College of Surgeons is a scientific and educational organization of surgeons that was founded in 1913 to raise the standards of surgical practice and improve the quality of care for all surgical patients. The College is dedicated to the ethical and competent practice of surgery. Its achievements have significantly influenced the course of scientific surgery in America and have established it as an important advocate for all surgical patients. The College has approximately 90,000 members and is the largest organization of surgeons in the world. “FACS” designates that a surgeon is a Fellow of the American College of Surgeons.