Graduate Student Leverages AI to Transform Lung Disease Management

Artificial intelligence (AI) is paving new pathways in the management of lung diseases, allowing for more personalized treatment options. Yixiu (Helen) He, a master’s student at Western University, is at the forefront of this innovation, working within the Advanced Pulmonary Imaging (API) Lab at the Robarts Research Institute. Her research focuses on applying machine learning techniques to enhance patient care for those suffering from chronic lung conditions.

Helen, who is pursuing a specialization in machine learning in the health and biomedical sciences, engages directly with patients during their testing processes. This hands-on experience was initially unexpected for her. “I’d thought only medical students could work with patients, but here I’m getting an interdisciplinary experience that combines actual patient visits, along with data analysis and engineering principles to improve health care,” she said.

Under the guidance of lab director and medical biophysics professor Grace Parraga, Helen is acquiring the technical skills necessary to implement AI in addressing health challenges. Parraga’s team is dedicated to developing innovative non-invasive imaging methods that can identify lung damage often overlooked by traditional clinical assessments. Their research aims to predict worsening conditions and customize treatments for chronic lung disease, particularly focusing on asthma.

Asthma, characterized by inflamed and narrowed airways, poses significant challenges in treatment. Detecting the disease in patients exhibiting severe symptoms but having normal clinical test results can be particularly difficult. “When patients are still breathless, it’s challenging to ascertain who is responding to treatment, and when to try something different,” Parraga explained.

Helen’s work in the API Lab is crucial in overcoming this hurdle. She is creating analytical tools that help researchers better comprehend how patients with severe asthma react to various therapies. By collecting data from lung function tests, she integrates this information with MRI, CT, and X-ray scans to identify subtle variations in gas distribution in the lungs, referred to as ‘texture features.’

To streamline this process, a statistical method known as Boruta analysis is employed to pinpoint the most relevant features for disease detection. This is where AI significantly accelerates research, enabling models to evaluate thousands of pixel-by-pixel comparisons simultaneously, uncovering patterns that would take humans considerably longer to identify. “It’s amazing to see how much we can learn in such a short period of time with machine learning,” Helen noted.

Machine learning models utilize extensive datasets to recognize patterns and make predictions based on new, unseen data. As these models evolve, they enhance their accuracy without needing explicit programming for every possible scenario. Helen finds this predictive capability particularly exciting, believing it allows for substantial advancements in health care.

Her scholarship journey is supported by the Vector Institute, which awarded her a Vector Scholarship in Artificial Intelligence (VSAI). This Canadian research organization is committed to fostering AI innovation and economic growth. The Vector Institute provides scholarships to exceptional students entering AI-related master’s programs at universities in Ontario, aiming to bolster Canada’s leadership in this field.

Parraga emphasizes the value Helen brings to the team with her engineering expertise, which is instrumental in developing tools for tailored asthma therapies. “This work will improve overall patient outcomes and save time and money,” she said.

Helen is not only motivated by the potential of AI to enhance patient care but also by the rapid acquisition of knowledge that comes from interdisciplinary collaboration in the API Lab. Despite her initial lack of coding experience, she quickly learned the programming language Python using AI tools, allowing her to tackle more complex tasks. “It really shortens the learning curve. With AI, you can be the connector – the person who learns different aspects to support interdisciplinary work,” she explained.

As an international student from Chongqing, China, Helen appreciates the financial backing and networking opportunities provided by the Vector scholarship. “Vector helps me make connections with industry partners, entrepreneurs and educators. I’ve come to know the Canadian environment, so I can go even further in imaging. I feel this is a really important area for study,” she stated.

The significance of this research is underscored by Parraga, who highlights Canada’s leadership in medical imaging and pulmonary functional imaging research. “Western-trained imaging scientists have now established new approaches and strong teams who are positioning novel lung imaging markers and technologies to improve the health of patients worldwide,” she said. With researchers like Helen at the helm, the future of lung disease management looks promising as AI continues to unlock new possibilities.