Artificial Intelligence Uses Patient Data to Anticipate Cancer Outcomes
A new study shows how artificial intelligence uses patient data to predict outcomes associated with 14 types of cancer.
Source: Getty Images
By - A study from the Mahmood Lab at Brigham and Women’s Hospital revealed how artificial intelligence (AI) uses factors such as patient history and gene pathology to identify and anticipate potential cancer outcomes.
Following the development of many novel AI technologies, researchers are attempting to determine how they can be used to advance healthcare. Recently, a group from the Mahmood Lab at Brigham and Women’s Hospital discovered that the implementation of an AI model can use data relating to genomic sequencing, pathology, and patient history to remain a step ahead of cancer activity.
During the process of creating and implementing AI models, Faisal Mahmood, PhD, an assistant professor in the Division of Computational Pathology at Brigham, and his research team consistently prioritized accuracy through the consistent use of various types of diagnostic information.
They also constructed the AI model with the assistance of The Cancer Genome Atlas (TCGA), which provided information on various types of cancer. They then created a multimodal deep learning-based algorithm.
After the application of the model, researchers determined that it had the ability to predict outcomes better than those that use single sources.
“Experts analyze many pieces of evidence to predict how well a patient may do,” Mahmood, who is also an associate member of the Cancer Program, said in a press release. “These early examinations become the basis of making decisions about enrolling in a clinical trial or specific treatment regimens. But that means that this multimodal prediction happens at the level of the expert. We’re trying to address the problem computationally.”
Furthermore, the use of certain data within AI can lead to accurate outcome predictions, researchers noted. However, to ensure accuracy, approval using large databases must occur.
“This work sets the stage for larger healthcare AI studies that combine data from multiple sources,” said Mahmood. “In a broader sense, our findings emphasize a need for building computational pathology prognostic models with much larger datasets and downstream clinical trials to establish utility.”
Various studies from the past have shared methods regarding the implementation of AI into predictive analytics.
In April 2022, researchers from Johns Hopkins University created an AI system that used patient data to predict cardiac arrests. This occurred following the collection of heart images and demographic information.
Another AI algorithm created by a Mayo Clinic research team in March 2022 used voice biomarkers to identify clogged arteries, leading to the diagnosis of heart conditions.
