Study findings could lead to new clinical laboratory diagnostics that give pathologists a more detailed understanding about certain types of cancer
New studies proving artificial intelligence (AI) can be used effectively in clinical laboratory diagnostics and personalized healthcare continue to emerge. Scientists in the UK recently trained an AI model using machine learning and deep learning to enable earlier, more accurate detection of 13 different types of cancer.
DNA stores genetic information in sequences of four nucleotide bases: A (adenine), T (thymine), G (guanine) and C (cytosine). These bases can be modified through DNA methylation. There are millions of DNA methylation markers in every single cell, and they change in the early stages of cancer development.
One common characteristic of many cancers is an epigenetic phenomenon called aberrant DNA methylation. Modifications in DNA can influence gene expression and are observable in cancer cells. A methylation profile can differentiate tumor types and subtypes and changes in the process often come before malignancy appears. This renders methylation very useful in catching cancers while in the early stages.
However, deciphering slight changes in methylation patterns can be extremely difficult. According to the scientists, “identifying the specific DNA methylation signatures indicative of different cancer types is akin to searching for a needle in a haystack.”
Nevertheless, the researchers believe identifying these changes could become a useful biomarker for early detection of cancers, which is why they built their AI models.
“Computational methods such as this model, through better training on more varied data and rigorous testing in the clinic, will eventually provide AI models that can help doctors with early detection and screening of cancers,” said Shamith Samarajiwa, PhD (above), Senior Lecturer and Group Leader, Computational Biology and Genomic Data Science, Imperial College London, in a news release. “This will provide better patient outcomes.” With additional research, clinical laboratories and pathologists may soon have new cancer diagnostics based on these AI models. (Photo copyright: University of Cambridge.)
The researchers then used a combination of machine learning and deep learning techniques to train an AI algorithm to examine DNA methylation patterns of the collected data. The algorithm identified and differentiated specific cancer types, including breast, liver, lung and prostate, from non-cancerous tissue with a 98.2% accuracy rate. The team evaluated their AI model by comparing the results to independent research.
In their Biology Methods and Protocols paper, the authors noted that their model does require further training and testing and stressed that “the important aspect of this study was the use of an explainable and interpretable core AI model.” They also claim their model could help medical professionals understand “the underlying mechanisms that contribute to the development of cancer.”
Using AI to Lower Cancer Rates Worldwide
According to the Centers for Disease Control and Prevention (CDC), cancer ranks as the second leading cause of death in the United States with 608,371 deaths reported in 2022. The leading cause of death in the US is heart disease with 702,880 deaths reported in the same year.
Globally cancer diagnoses and death rates are even more alarming. World Health Organization (WHO) data shows an estimated 20 million new cancer cases worldwide in 2022, with 9.7 million persons perishing from various cancers that year.
The UK researchers are hopeful their new AI model will help lower those numbers. They state in their paper that “most cancers are treatable and curable if detected early enough.”
More research and studies are needed to confirm the results of this study, but it appears to be a very promising line of exploration and development of using AI to detect, identify, and diagnose cancer earlier. This type of probing could provide pathologists with improved tools for determining the presence of cancer and lead to better patient outcomes.
Proof-of-concept study ‘highlights that using AI to integrate different types of clinically informed data to predict disease outcomes is feasible’ researchers say
Artificial intelligence (AI) and machine learning are—in stepwise fashion—making progress in demonstrating value in the world of pathology diagnostics. But human anatomic pathologists are generally required for a prognosis. Now, in a proof-of-concept study, researchers at Brigham and Women’s Hospital in Boston have developed a method that uses AI models to integrate multiple types of data from disparate sources to accurately predict patient outcomes for 14 different types of cancer.
The process also uncovered “the predictive bases of features used to predict patient risk—a property that could be used to uncover new biomarkers,” according to Genetic Engineering and Biotechnology News (GEN).
Should these research findings become clinically viable, anatomic pathologists may gain powerful new AI tools specifically designed to help them predict what type of outcome a cancer patient can expect.
“Experts analyze many pieces of evidence to predict how well a patient may do. These early examinations become the basis of making decisions about enrolling in a clinical trial or specific treatment regimens,” said Faisal Mahmood, PhD (above) in a Brigham press release. “But that means that this multimodal prediction happens at the level of the expert. We’re trying to address the problem computationally,” he added. Should they be proven clinically-viable through additional studies, these findings could lead to useful tools that help anatomic pathologists and clinical laboratory scientists more accurately predict what type of outcomes cancer patient may experience. (Photo copyright: Harvard.)
AI-based Prognostics in Pathology and Clinical Laboratory Medicine
The team at Brigham constructed their AI model using The Cancer Genome Atlas (TCGA), a publicly available resource which contains data on many types of cancer. They then created a deep learning-based algorithm that examines information from different data sources.
Pathologists traditionally depend on several distinct sources of data, such as pathology images, genomic sequencing, and patient history to diagnose various cancers and help develop prognoses.
For their research, Mahmood and his colleagues trained and validated their AI algorithm on 6,592 H/E (hematoxylin and eosin) whole slide images (WSIs) from 5,720 cancer patients. Molecular profile features, which included mutation status, copy-number variation, and RNA sequencing expression, were also inputted into the model to measure and explain relative risk of cancer death.
The scientists “evaluated the model’s efficacy by feeding it data sets from 14 cancer types as well as patient histology and genomic data. Results demonstrated that the models yielded more accurate patient outcome predictions than those incorporating only single sources of information,” states a Brigham press release.
“This work sets the stage for larger healthcare AI studies that combine data from multiple sources,” said Faisal Mahmood, PhD, Associate Professor, Division of Computational Pathology, Brigham and Women’s Hospital; and Associate Member, Cancer Program, Broad Institute of MIT and Harvard, in the press release. “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.”
Future Prognostics Based on Multiple Data Sources
The Brigham researchers also generated a research tool they dubbed the Pathology-omics Research Platform for Integrative Survival Estimation (PORPOISE). This tool serves as an interactive platform that can yield prognostic markers detected by the algorithm for thousands of patients across various cancer types.
The researchers believe their algorithm reveals another role for AI technology in medical care, but that more research is needed before their model can be implemented clinically. Larger data sets will have to be examined and the researchers plan to use more types of patient information, such as radiology scans, family histories, and electronic medical records in future tests of their AI technology.
“Future work will focus on developing more focused prognostic models by curating larger multimodal datasets for individual disease models, adapting models to large independent multimodal test cohorts, and using multimodal deep learning for predicting response and resistance to treatment,” the Cancer Cell paper states.
“As research advances in sequencing technologies, such as single-cell RNA-seq, mass cytometry, and spatial transcriptomics, these technologies continue to mature and gain clinical penetrance, in combination with whole-slide imaging, and our approach to understanding molecular biology will become increasingly spatially resolved and multimodal,” the researchers concluded.
Anatomic pathologists may find the Brigham and Women’s Hospital research team’s findings intriguing. An AI tool that integrates data from disparate sources, analyzes that information, and provides useful insights, could one day help them provide more accurate cancer prognoses and improve the care of their patients.
