AI Predicts Pancreatic Cancer Three Years before Diagnosis from Patients’ Medical Records

Screening for common cancers like breast, cervix, and prostate cancer relies on relatively simple and highly effective techniques, such as mammograms, Pap smears, and blood tests. These methods have revolutionized outcomes for these diseases by enabling early detection and intervention during the most treatable stages. However, pancreatic cancer screening is more challenging and costly. Physicians primarily consider family history and genetic mutations, which are important risk indicators but often overlook many patients. There is a need for a method that can expedite the diagnosis of pancreatic cancer, which is frequently found in advanced stages when treatment is less effective and outcomes are poor. Now, an artificial intelligence (AI) tool can successfully identify individuals at the highest risk for pancreatic cancer up to three years before diagnosis using only patients' medical records.

The findings of the new research led by investigators at Harvard Medical School (Boston, MA, USA; www.hms.harvard.edu) and the University of Copenhagen (Copenhagen, Denmark; www.ku.dk) suggest that AI-based population screening could be valuable for detecting those at increased risk for pancreatic cancer. Applied at scale, the AI tool could accelerate detection, lead to earlier treatment, and improve outcomes and extend patients' life spans. In the study, the AI algorithm was trained on two separate datasets totaling nine million patient records from Denmark and the U.S. The researchers "asked" the AI model to look for telltale signs based on the data contained in the records. Based on combinations of disease codes and their timing, the model was able to predict which patients are likely to develop pancreatic cancer in the future. Interestingly, many of the symptoms and disease codes were not directly related to or originating from the pancreas.

The researchers tested different versions of the AI models for their ability to detect people at elevated risk for disease development within different time scales — 6 months, one year, two years, and three years. Overall, each version of the AI algorithm was substantially more accurate at predicting who would develop pancreatic cancer than current population-wide estimates of disease incidence. The researchers believe the model is at least as accurate in predicting disease occurrence as current genetic sequencing tests, which are usually only available for a small subset of patients in datasets.

A significant advantage of the AI tool is that it can be used on any patient with available health records and medical history, not just those with known family history or genetic predisposition for the disease. This is particularly important because many high-risk patients may not be aware of their genetic predisposition or family history. Without symptoms and a clear indication of high risk for pancreatic cancer, clinicians may be hesitant to recommend more sophisticated and expensive testing, such as CT scans, MRI, or endoscopic ultrasound. When these tests are used and suspicious lesions discovered, the patient must undergo a procedure to obtain a biopsy. An AI tool that identifies those at the highest risk for pancreatic cancer would ensure that clinicians test the right population while sparing others unnecessary testing and additional procedures, according to the researchers.

“One of the most important decisions clinicians face day to day is who is at high risk for a disease, and who would benefit from further testing, which can also mean more invasive and more expensive procedures that carry their own risks,” said study co-senior investigator Chris Sander, faculty member in the Department of Systems Biology in the Blavatnik Institute at HMS. “An AI tool that can zero in on those at highest risk for pancreatic cancer who stand to benefit most from further tests could go a long way toward improving clinical decision-making.”

“Many types of cancer, especially those hard to identify and treat early, exert a disproportionate toll on patients, families and the healthcare system as a whole,” said study co-senior investigator Søren Brunak, professor of disease systems biology and director of research at the Novo Nordisk Foundation Center for Protein Research at the University of Copenhagen. “AI-based screening is an opportunity to alter the trajectory of pancreatic cancer, an aggressive disease that is notoriously hard to diagnose early and treat promptly when the chances for success are highest.”

Related Links:
Harvard Medical School 
University of Copenhagen 

Visit expo >

New

Gold Member

X-Ray QA Meter

T3 AD Pro

Gold Member

Real-Time Diagnostics Onscreen Viewer

GEMweb Live

New

X-ray Diagnostic System

FDX Visionary-A

New

Vertebral Body Replacement System

Hydrolift