Researchers create an artificial intelligence tool that accurately predicts outcomes for 14 types of cancer

0

[ad_1]

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 advancing, in stages, to demonstrate their value in the world of disease diagnosis. But human anatomical pathologists are usually required for 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 characteristics used to predict patient risk – a property that could be used to discover new biomarkers,” according to Genetic Engineering and Biotechnology News (GEN).

Should these research findings become clinically viable, pathologists could benefit from powerful new AI tools specifically designed to help them predict the type of outcome a cancer patient might expect.

The Brigham scientists published their findings in the journal cancer celltitled “Integrative histological-genomic analysis of cancer via multimodal deep learning”.

“Experts analyze many pieces of evidence to predict a patient’s condition. These early reviews become the basis for decision-making regarding enrollment in a clinical trial or specific treatment regimens,” said Faisal Mahmood, PhD (above) in a press release from Brigham. “But that means this multimodal prediction is happening at the expert level. We are trying to solve the problem by calculation,” he added. If proven clinically viable through additional studies, these findings could lead to useful tools that would help pathologists and clinical laboratory scientists more accurately predict the type of outcomes cancer patients might experience. . (Picture copyright: Harvard.)

AI-based prognosis in pathology and clinical laboratory medicine

Brigham’s team built their AI model using The Cancer Genome Atlas (TCGA), a publicly available resource that contains data on many types of cancer. They then created a deep learning-based algorithm that examines information from different data sources.

Pathologists have traditionally relied on several distinct data sources, such as pathology images, genomic sequencing, and patient history to diagnose various cancers and help make prognoses.

For their research, Mahmood and colleagues trained and validated their AI algorithm on 6,592 H/E (hematoxylin and eosin) (WSI) whole slide images of 5,720 cancer patients. Molecular profile characteristics, which included mutation status, copy number variation, and RNA sequencing expression, were also entered into the model to measure and explain the relative risk of cancer death.

The scientists “assessed the model’s effectiveness by feeding it datasets from 14 cancer types as well as patient histology and genomic data. The results demonstrated that the models gave more accurate predictions of patient outcomes than those that incorporated only single sources of information,” states a press release from Brigham.

“This work paves the way for larger studies of AI in healthcare that combine data from multiple sources,” said Faisal Mahmood, PhD, associate professor, Division of Computational Pathology, Brigham and Women’s Hospital ; and Associate Fellow, Cancer Program, Broad Institute of MIT and Harvard, in the press release. “In a broader sense, our findings underscore the need to build computational pathology prognosis models with much larger datasets and downstream clinical trials to establish utility.”

Future predictions 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 produce prognostic markers detected by the algorithm for thousands of patients in 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 datasets will need to be examined, and the researchers plan to use more types of patient information, such as X-ray scans, family history, and electronic medical records in future tests of their AI technology. .

“Future work will focus on developing more targeted prognostic models by curating larger multimodal datasets for individual disease models, fitting the models to large cohorts of independent multimodal testing, and using deep learning. multimodal to predict treatment response and resistance”, 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 slide imaging whole, and our approach to understanding molecular biology is becoming increasingly spatially resolved and multimodal,” the researchers concluded.

Pathologists may find the findings of the Brigham and Women’s Hospital research team intriguing. An AI tool that integrates data from disparate sources, analyzes that information, and provides actionable insights, could one day help them provide more accurate cancer prognoses and improve care for their patients.

J. P. Schlingman

Related information:

AI integrates multiple types of data to predict cancer outcomes

Integrative histological-genomic analysis of pan-cancer via multimodal deep learning

New AI technology integrates multiple types of data to predict cancer outcomes

Artificial intelligence in digital pathology developments turn to practical tools

Florida Hospital Uses Machine Learning Artificial Intelligence Platform to Reduce Clinical Variation in Its Healthcare, With Implications for Medical Laboratories

Artificial Intelligence and Computational Pathology

[ad_2]
Source link

Share.

Comments are closed.