Silent Killer

Diagnosing the “Silent Killer”: AI Tackles Early Stage Ovarian Cancer.

Posted by

0


AI and ovarian cancer

A major bottleneck in early detection is the molecular heterogeneity between ovarian cancer (OC) patients, which limits the likelihood of identifying individual biomarkers that are shared among patients. In a new study “A personalized probabilistic approach to ovarian cancer diagnostics,” published in Gynecologic Oncology, researchers from Georgia Institute of Technology have addressed this challenge by applying machine learning (ML) on patient metabolic profiles to identify biomarker patterns for personalized OC diagnosis.

While early diagnosis is often crucial for successful cancer treatment, accurate diagnostics is especially challenging for diseases, such as OC, which progress rapidly yet display little clinical symptoms during the early stages of disease. While the average five-year survival rate for late-stage ovarian cancer patients with treatment is only 31%, that number rises to over 90% when the cancer is detected and treated early.

The Georgia Tech researchers developed ML-based classifiers that were able to distinguish cancer from control samples with 93% accuracy when tested over 564 patient samples from Georgia, North Carolina, Philadelphia, and Western Canada.

John McDonald, professor in the School of Biological Sciences at Georgia Tech and corresponding author of the study, told IPM, “the big buzz in therapeutics is targeting individual genes for personalized therapy. That can work if you have the same target in all of the patients with that disease, but that may not be the case. When we look at the success of targeted immune therapies in OC, it only works in about 5% of patients because the patients are so heterogeneous.”

While profiling individual patients addresses the challenge of patient heterogeneity, McDonald highlights that there’s a need to “know what you’re looking for.”

“You can do trial and error, but my feeling is that artificial intelligence (AI) is going to fill that gap by assigning a computer to look at the patterns,” McDonald continued.

Since only seven percent of the thousands of metabolites circulating the human blood have been characterized, pinpointing the specific molecular processes underlying an individual’s metabolic profile remains a challenge, thereby limiting a path for therapeutic development.

However, ML-based predictive models can use the large data set of uncharacterized metabolites that have been accurately identified by mass spectrometry to recognize metabolic patterns to assist in OC diagnostics.

“Historically, you don’t need to understand the cause and effect relationships to make predictions. For most of medical history, predictions were made based on correlations. We don’t need to know why these metabolites are changing,” said McDonald.

While McDonald acknowledges that a ML approach using multi-omic data would be ideal for learning patterns underlying disease, scalability and complexity are currently limiting factors.

The team used metabolic profiles as an alternative because they represent a biological “end point” that accounts for the combinatorial effects of molecular changes, including but not limited to, protein level, epigenetic control, diet and lifestyle, and more.

Based on the accuracy of their ML approach, the research team developed what they believe to be a clinically useful approach to OC diagnosis, where a patient’s individual metabolic profile is used to determine a probability of developing OC. For example, a patient whose metabolic profile scores within a low likelihood cancer range would be recommended for yearly monitoring. In contrast, a patient whose metabolic profile scores within a range where over 90% of patients have previously been diagnosed with OC would be recommended for immediate screening and treatment.

McDonald described that this probabilistic approach to diagnostics is more clinically informative than binary (yes/no) tests.

In terms of entering the clinic, McDonald said the diagnostic test has entered trials with various clinics in Georgia to prospectively evaluate the validity and utility of the test. In addition, a start-up company, named MyOncoDx, is being formed with the intent to market the technology after completion of requisite trials and FDA approval.

McDonald estimates that “it could be a year or so” before the test will be generally available.

Lung Cancer, ‘Silent Killer’, Still Curable If Detected Early

Posted by

0


Adenocarcinoma often begins along the outer parts of the lungs and is the most common type of cancer in people who have never smoked. (Shutterstock)

Adenocarcinoma often begins along the outer parts of the lungs and is the most common type of cancer in people who have never smoked. (Shutterstock)

Lung cancer is often called “the silent killer,” because it can go unnoticed until reaching advanced stages when death is inevitable.

According to National Cancer Institute, 65.8 percent of lung cancer cases were diagnosed at a late stage, surpassing other common cancers like colon cancer, breast cancer, and prostate cancer.

Epoch Times Photo
(Data Source: National Cancer Institute)

“Other cancers give you signs and symptoms,” Raja M. Flores, MD, thoracic surgeon, and Chief of the Division of Thoracic Surgery at Mount Sinai Hospital., told The Epoch Times.

Lung cancer is different.

According to the American Lung Association (ALA), lung cancer is now the leading killer for both men and women in the U.S., and in 1987, it surpassed breast cancer to become the leading cause of cancer deaths in women.

Some Lung Cancer Patients Have Signs While Most Do Not

Many of the symptoms of lung cancer depend on location.

“When you have a tumor that’s closer to your trachea, you may cough up a little blood in early stage,” Flores said. “You may have a wheeze.”

However, the majority of lung cancers don’t occur centrally, near the trachea. Instead, they occur on the outer parts of the lung.

When it’s curable, you don’t know it’s there. Until it has spread.

That’s the biggest thing. “I think everybody tries to ask what signs should I look for—you’re not going to have signs,” said Flores. 

A 2020 Spainish study published in the European Society for Medical Oncology Open analyzed the symptoms of non-small cell lung cancer (NSCLC)—the most common type of lung cancer. The study involved nearly 10,000 patients. The result showed that at stage I, the most common symptom was coughing, however, only 1.8 percent of the patients showed this symptom. As the cancer progressed to stage IV, 17.9 percent of patients showed cough symptoms.

Epoch Times Photo
(Data Source: European Society for Medical Oncology Open)

The other main type of lung cancer is small cell lung cancer. There are treatments for both types that carry relatively high survival rates if the disease is caught early.

Small cell is usually treated with chemotherapy unless it’s in its very early stage, called a small nodule stage one, when it can be removed surgically.

“But they usually do chemotherapy in addition to that and they’ll get a brain scan to make sure there’s nothing that’s spread to the brain,” Flores said.

Non-small cell lung cancer can be split into two categories—adenocarcinoma and squamous cell carcinoma. They make up about 80 to 85 percent of lung cancers.

“These tend to grow and spread more slowly,” said Aimee Strong, DNP, Nurse Practitioner, University of Virginia Thoracic Surgery, Lung Cancer Screening Program

Adenocarcinoma often begins along the outer parts of the lungs and is the most common type of cancer in people who have never smoked. However, squamous cell cancer can begin near the middle of the lungs.  

Small cell lung cancer is almost always related to smoking. “It is fast growing and spreads quickly,”  said Strong.

Smoking Is Not the Only Risk Factor

The degree of risk depends from person to person, and it’s not only smoking but also secondhand smoke that increases the odds of developing lung cancer.

“Let’s say you grew up in a household where mom and dad were smoking like chimneys, especially back in the seventies, you’re at risk,” Flores said.

Flores has had patients who were DJs back when clubs were full of cigarette smoke, who eventually developed lung cancer.

This isn’t the only problem.

“People from 9/11 who were exposed to the asbestos in the pulverized dust down there [are also at risk],” he said. 

Besides, research published in European Respiratory Review, finds that there is a significant genetic component to lung cancer risk.

In China, lung cancer has been increasing over the past decades. 

“There are some people who believe there’s a genetic component to it, [and] that you see [it] in the Chinese population,” said Flores. At the same time, “when you go there you realize that pollution is out of control.”

He noted it’s hard to say whether genetic or environmental factors play a bigger role, but tends to think this is due to the environmental conditions in China.

“I do believe that if you develop cancer, you got it from some external insult that caused the mutation in your system, that’s given you this cancer,” said Flores. “I don’t think it’s just bad luck.”  

Early Detection Is ‘Very Curable’, Screening Is Essential

There are significantly more treatment options for lung cancer than were available even five years ago, and more sophisticated forms of radiation therapy to treat the disease. 

When caught early, especially with the low-dose CAT scan, lung cancers are “very curable,” said Flores. 

This even includes fast growing small cell lung cancers. 

The problem is not that we don’t have a cure. 

“We have a cure, 80 percent of the people with stage I will be cured,” Flores said. “The problem is that we don’t catch it early enough.”

He said the best solution is screening, and people who should be screened for lung cancer include:

  • Current and former smokers
  • People exposed to asbestos or radon gas
  • Those with a family history of lung cancer

People who are at risk can see a lung physician, whether it’s a surgeon, a pulmonologist, a radiologist, or an internal medicine doctor.

Flores observed that many at risk due to previous smoking, now have families.

“They have this guilt that they smoked and how can you fix that guilt?” Flores asked. “Get a screening CAT scan.”