News | Artificial Intelligence | September 26, 2019

AI Accurately Predicts Radiotherapy Side Effects for Head and Neck Cancer Patients

Machine learning model identified patients most likely to experience significant weight loss or need for a feeding tube

AI Accurately Predicts Radiotherapy Side Effects for Head and Neck Cancer Patients

September 26, 2019 — For the first time, a sophisticated computer model has been shown to accurately predict two of the most challenging side effects associated with radiation therapy for head and neck cancer. This precision oncology approach has the potential to better identify patients who might benefit from early interventions that may help to prevent significant weight loss after treatment or reduce the need for feeding tube placement. Findings were presented at the 61st Annual Meeting of the American Society for Radiation Oncology (ASTRO), Sept. 15-18, 2019, in Chicago.

“In the past, it has been hard to predict which patients might experience these side effects,” said Jay Reddy, M.D., Ph.D., an assistant professor of radiation oncology at The University of Texas MD Anderson Cancer Center and lead author on the study. “Now we have a reliable machine learning model, using a high volume of internal institutional data, that allows us to do so.”

Machine learning is a branch of artificial intelligence (AI) that uses statistical models to analyze large quantities of data, uncovering patterns that can predict outcomes with a high degree of accuracy. Used by the tech industry to allow speech and facial recognition, “spam” filtering and targeted advertising, machine learning has been an emerging topic of interest for medical researchers seeking to translate large amounts of data into knowledge that can support clinical decision making. 

Reddy and his team developed models to analyze large sets of data merged from three sources: electronic health records (Epic), an internal web-based charting tool (Brocade) and the record/verify system (Mosaiq). The data included more than 700 clinical and treatment variables for patients with head and neck cancer (75 percent male/25 percent female, with a median age of 62 years) who received more than 2,000 courses of radiation therapy (median dose 60 Gy) across five practice sites at MD Anderson from 2016 to 2018. 

Researchers used the models to predict three endpoints: significant weight loss, feeding tube placement and unplanned hospitalizations. Results from the best-performing model were then validated against 225 subsequent consecutive radiation therapy treatments. Models with a performance rate that met a pre-specified threshold of area under the curve (AUC) of 0.70 or higher were considered clinically valid. (An AUC score of 1.0 would mean the model’s predictions were 100 percent accurate, while a score of 0.0 would mean the predictions were never accurate.)

Approximately 53,000 people are diagnosed with head and neck (oral cavity or oropharyngeal) cancers each year in the United States. These cancers are more than twice as common in men as in women, and typically diagnosed later in life (with an average age of diagnosis of 62 years). Head and neck cancers, when diagnosed early, are typically treated with radiation therapy or surgery. Later-stage cancers are treated with a combination of radiation therapy and chemotherapy. A patient may also be treated first with surgery, followed by radiation therapy alone, or by a combination of radiation and chemotherapy.

Radiation therapy is effective at treating head and neck cancer by slowing or stopping the growth of new cancer cells. However, it may also damage oral tissue and upset the balance of bacteria in the mouth, causing adverse side effects such as a sore throat, mouth sores, loss of taste and dry mouth. When sore throats are severe, they can make it difficult for the patient to eat and may lead to weight loss or require the temporary insertion of a feeding tube. Nearly all patients with head and neck cancer experience some negative effects of treatment.

“Being able to identify which patients are at greatest risk would allow radiation oncologists to take steps to prevent or mitigate these possible side effects,” said Reddy. “If the patient has an intermediate risk, and they might get through treatment without needing a feeding tube, we could take precautions such as setting them up with a nutritionist and providing them with nutritional supplements. If we know their risk for feeding tube placement is extremely high – a better than 50 percent chance they would need one – we could place it ahead of time so they wouldn’t have to be admitted to the hospital after treatment. We’d know to keep a closer eye on that patient.”

The models predicted the likelihood of significant weight loss (AUC = 0.751) and need for feeding tube placement (AUC = 0.755) with a high degree of accuracy. 

“The models used in this study were consistently good at predicting those two outcomes,” said Reddy. “You could rerun those models with a new patient or series of patients and get a number saying this adverse effect is likely to happen or not to happen.”

For example, said Reddy, using their model, clinicians could potentially plug in information related to a specific patient – such as age, gender, type of cancer and other distinct variables – and the model might tell them, “Eighty percent of people like you with this clinical profile get through treatment without a feeding tube. It may not be perfect, but it’s better than having no understanding at all.”

The model fell short of predicting unplanned hospitalizations with sufficient clinical validity (AUC = 0.64). Redoing the analyses with more “training” data for unplanned hospitalizations could improve accuracy in predicting this side effect as well, said Reddy. “As we treat more and more patients, the sample size gets bigger, so every data point should get better. It’s possible we just didn’t have enough information accumulated for this aspect of the model.”

While the machine learning approach cannot isolate the single-most predictive factor or combination of factors that lead to negative side effects, it can provide patients and their clinicians with a better understanding of what to expect during the course of treatment, said Reddy. In addition to predicting the likelihood of side effects, machine learning models could potentially predict which treatment plans would be most effective for different types of patients and allow for more personalized approaches to radiation oncology, he explained.

“Machine learning can make doctors more efficient and treatment safer by reducing the risk of error,” said Reddy. “It has the potential for influencing all aspects of radiation oncology today – anything where a computer can look at data and recognize a pattern.”

For more information: www.astro.org

Additional coverage of ASTRO 2019

Related Content

 MaxQ AI
News | Artificial Intelligence | November 13, 2019
November 13, 2019 – MaxQ AI announced a new partnership agreement with...
Members of Congress from both sides of the aisle issued a series of oversight letters to the Centers for Medicare and Medicaid Services (CMS) in recent months to urge the Agency to adjust its proposed radiation oncology advanced alternative payment model (RO Model)

Image by whitfieldink from Pixabay

News | Radiation Oncology | November 13, 2019
November 13, 2019 — Members of Congress from both sides of the aisle issued a series of oversight letters to the...
An image on Brigham and Women's Hospital's 7T MRI system

An image on Brigham and Women's Hospital's 7T MRI system. Image courtesy of Brigham and Women's Hospital

News | Magnetic Resonance Imaging (MRI) | November 13, 2019
November 13, 2019 — Increased immune system activity along the surface of the brain, or meningeal inflammation, may b
 Paxera Ultima 360
News | Enterprise Imaging | November 12, 2019
November 12, 2019 — Medical Imaging developer PaxeraHealth will showcase the
 Lunit RSNA
News | Artificial Intelligence | November 12, 2019
November 12, 2019 — Lunit, a leading medical AI software company devoted to provi
 Laurel Bridge Machine Learning workflow
News | Artificial Intelligence | November 08, 2019
November 8, 2019 — Laurel Bridge Software announces the new Laurel Bridge
Image by Dr. Manuel González Reyes from Pixabay

Image by Dr. Manuel González Reyes from Pixabay 

News | SPECT Imaging | November 08, 2019
November 8, 2019 — Using ground-breaking technology, researchers at the...
This chest X-ray of a patient being treated for e-cigarette or vaping-associated lung injury shows lung opacities, densities and whitish cloud-like areas which are typically seen with unusual pneumonias, fluid in lungs or lung inflammation. Image courtesy of Intermountain Healthcare

This chest X-ray of a patient being treated for e-cigarette or vaping-associated lung injury shows lung opacities, densities and whitish cloud-like areas which are typically seen with unusual pneumonias, fluid in lungs or lung inflammation. Image courtesy of Intermountain Healthcare

News | Clinical Trials | November 08, 2019
November 8, 2019 — As the outbreak of lung injuries and deaths associated with e-cigarettes, or...
Unlike other technologies for imaging the placenta, pCASL MRI can distinguish maternal blood from fetal blood

Image courtesy of Pixabay

News | Clinical Trials | November 07, 2019
November 7, 2019 — A new imaging technique to track