This 90-minute webinar will help pathologists and lab executives understand artificial intelligence, its many available configurations, what’s on the horizon, and how your lab can profit from it. Special offers for teams! Because so many pathologists are working remotely, Dark Daily has arranged special group rates for pathology practices. Email info@darkreport.com or call Amanda Curtis at 512-264-7103 for additional information or to register your team.
Gottlieb will speak about the state of AI in healthcare at the event May 11-12
Medical technicians in clinical laboratories and pathology groups may worry that artificial intelligence (AI) will eventually put them out of their jobs.
However, that’s not likely to be the case, according to former Food and Drug Administration (FDA) Commissioner Scott Gottlieb. He was just announced as a top speaker at the Artificial Intelligence in Healthcare and Diagnostics (AIHD) Conference, which takes place May 10-11 in San Jose, Calif.
Instead, expect AI in healthcare to help labs better aggregate and analyze an ever-growing repository of clinical data.
“As we start to digitize more of this information, build out bigger repositories, and correlate more of this information with experimental evidence that’s also captured digitally, it’s going to become an immensely powerful tool,” Gottlieb said during a 2021 webinar hosted by Proscia, which develops pathology software embedded with AI.
Former FDA Commissioner Scott Gottlieb said AI in healthcare will “become an immensely powerful tool.” (Photo courtesy of: Worldwide Speakers Group)
“[AI is] going to be a predictive tool,” he continued. “So, now you start to think about digital data from traditional pathology, digital data from characterizing tumors to sequencing, alongside digital data capture through electronic health records. And you start to have a really powerful, robust set of information.”
Writing for MobiHealthNews last year, Liz Kwo, MD, also noted the potential of AI to deal with unstructured data—in other words, information that is not in a pre-set data model and thus difficult to analyze.
“In many cases, health data and medical records of patients are stored as complicated unstructured data, which makes it difficult to interpret and access,” wrote Kwo, who is Deputy Chief Clinical Officer at insurer Anthem and Faculty Lecturer at Harvard Medical School.
“AI can seek, collect, store, and standardize medical data regardless of the format, assisting repetitive tasks and supporting clinicians with fast, accurate, tailored treatment plans and medicine for their patients instead of being buried under the weight of searching, identifying, collecting and transcribing the solutions they need from piles of paper formatted EHRs,” she added.
AIHD conference to explore the state of artificial intelligence in healthcare
At AIHD, Gottlieb will take part in a fireside chat and also contribute to a panel discussion with other keynote speakers.
“There’s no better individual than Dr. Gottlieb to address AIHD participants about the state of artificial intelligence, where it’s going, how it’s regulatory oversight will unfold, and what’s likely to be the most surprising contribution of AI in patient care,” said Robert Michel, founder of AIHD, Executive Director of the Precision Medicine Institute, and Editor-in-Chief of clinical lab intelligence publication The Dark Report.
The event will bring together senior-level representatives from AI companies, hospitals, physician offices, and diagnostic providers.
Gottlieb promoted greater use of digital tools for clinicians
“I can envision a world where, one day, artificial intelligence can help detect and treat challenging health problems, for example by recognizing the signs of disease well in advance of what we can do today,” Gottlieb stated at the time. “These tools can provide more time for intervention, identifying effective therapies and ultimately saving lives.”
During and after his tenure at the FDA, he has been a prolific commentator about the SARS-CoV-2 pandemic and steps public health agencies have taken to curb COVID-19.
Gottlieb is currently a Senior Fellow at the American Enterprise Institute, a public policy think tank. He is also partner at venture capital firm New Enterprise Associates and serves on the boards of Pfizer and Illumina.
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.
Labcorp, the commercial laboratory giant headquartered in Burlington, N.C., has billions of diagnostic test results archived. It takes samplings of those results and runs them through a machine learning algorithm that compares the data against a condition of interest, such as chronic kidney disease (CKD). Machine learning is a subdiscipline of AI.
Based on patterns it identifies, the machine learning algorithm can predict future test results for CKD based on patients’ testing histories, explained Stan Letovsky, PhD, Vice President for AI, Data Sciences, and Bioinformatics at Labcorp. Labcorp has found the accuracy of those predictions to be better than 90%, he added.
Labcorp also has created an AI-powered dashboard that—once layered over an electronic health record (EHR) system—allows physicians to configure views of an individual patient’s existing health data and add a predictive view based on the machine learning results.
For anatomic pathologists, this type of setup can quickly bring a trove of data into their hands, allowing them to be more efficient with patient diagnoses. The long-term implications of using this technology are significant for pathology groups’ bottom line.
Stan Letovsky, PhD (above), Vice President for AI, Data Sciences, and Bioinformatics at Labcorp, discussed AI developments in digital pathology during his keynote address at the 2022 Executive War College in New Orleans. “The best thing as a community that we can do for patients and their physicians with AI is to identify care gaps early on,” he said, adding, “If pathologists want to grow and improve their revenue, they have to be more productive.” (Photo copyright: Dark Intelligence Group).
Mayo Clinic Plans to Digitize 25 Million Glass Slides
In other AI developments, Mayo Clinic in Rochester, Minn., has started a project to digitally scan 25 million tissue samples on glass slides—some more than 100 years old. As part of the initiative, Mayo wants to digitize five million of those slides within three years and put them on the cloud, said pathologist and physician scientist Jason Hipp, MD, PhD, Chair of Computational Pathology and AI at Mayo Clinic.
“We want to be a hub within Mayo Clinic for digital pathology,” Hipp told Executive War College attendees during his keynote address.
Hipp views his team as the bridge between pathologists and the data science engineers who develop AI algorithms. Both sides must collaborate to move AI forward, he commented, yet most clinical laboratories and pathology groups have not yet developed those relationships.
“We want to embed both sides,” Hipp added. “We need the data scientists working with the pathologists side by side. That practical part is missing today.”
The future medical laboratory at Mayo Clinic will feature an intersection of pathology, computer technology, and patient data. Cloud storage is a big part of that vision.
“AI requires storage and lots of data to be practical,” Hipp said.
At hospitals where results of molecular COVID-19 testing can take up to several days to return, this new method for identifying potentially infected patients could improve triage
Frustrated by shortages of essential COVID-19 tests and supplies—as well by lengthy coronavirus test turn-around times—researchers at Weill Cornell Medicine have created an Artificial Intelligence (AI) algorithm that can use routine clinical laboratory test data to determine if a patient is infected with SARS-CoV-2, the coronavirus that causes the COVID-19 disease.
This is an important development because the turn-around-time (TAT) for common lab tests is generally much shorter than COVID-19 molecular diagnostics—such as real-time reverse transcription polymerase chain reaction (RT-PCR), currently the most popular coronavirus test—and certainly serological (antibody) diagnostics, which require an infection incubation time of as much as 10-14 days before testing.
Some RT-PCR diagnostic tests for COVID-19, which detect viral RNA on nasopharyngeal swab specimens, can take up to several days to return depending on the test and on the lab’s location. But routine medical laboratory tests generally return much sooner, often within minutes or hours, making this a potential game-changer for triaging infected patients.
Machine Learning Brings AI to COVID-19 Diagnostics
Advances in the use of AI in healthcare have led to the development of machine-learning algorithms that are being utilized as diagnostic tools for anatomic pathology, radiology, and for specific complex diseases, such as cancer. The Weill Cornell scientists wanted to see if alternative lab test results could be used by an algorithmic model to identify people infected with the SARS-CoV-2 coronavirus.
“When patients come to the [emergency department] and the doctor orders several panels of routine lab [tests] and also the [SARS-CoV-2] RT-PCR test, generally the routine test results come back in a couple of hours,” Sarina Yang, MD, PhD (above), one of the authors of the study, told Modern Healthcare. “So, we thought it could be useful to use the routine labs to predict whether the RT-PCR results would be positive or negative to improve the triage process.” Yang is an assistant professor in the Department of Pathology and Laboratory Medicine, and Assistant Director of the central laboratory and Director of the toxicology laboratory at Weill Cornell Medicine. (Photo copyright: Weill Cornell Medicine.)
To perform the research, the team incorporated patients’ age, sex, and race, into a machine learning model that was based on results from 27 routine lab tests chosen from a total of 685 different tests ordered for the patients. The study included 3,356 patients who were tested for SARS-CoV-2 at New York-Presbyterian Hospital/Weill Cornell Medical Center between March 11 and April 29 of this year. The patients ranged in ages from 18 to 101 with the mean age being 56.4 years. Of those patients, 1,402 were RT-PCR positive and the remaining 1,954 were RT-PCR negative.
Using a machine-learning technique known as a gradient-boosting decision tree, the algorithm identified SARS-CoV-2 infections with 76% sensitivity and 81% specificity. When looking at only emergency department (ED) patients, the model performed even better with 80% sensitivity and 83% specificity. ED patients comprised just over half (54%) of the patients used for the study.
Weill Cornell Medicine Algorithm Could Lower False Negative Test Results
The algorithm also correctly identified patients who originally tested negative for COVID-19, but who tested positive for the coronavirus upon retesting within two days. According to the researchers, these results indicated their model could potentially decrease the amount of incorrect test results.
“We are thinking that those potentially false negative patients may demonstrate a different routine lab test profile that might be more similar to those that test positive,” Fei Wang, PhD, Assistant Professor of Healthcare Policy and Research at Weill Cornell Medicine and the study’s senior author, told Modern Healthcare. “So, it offers us a chance to capture those patients who are false negatives.”
The researchers validated their model by comparing the results with patients seen at New York Presbyterian Hospital/Lower Manhattan Hospital during the same time period. Among those patients, 496 were RT-PCR positive and 968 were negative and the algorithmic model performed with 74% specificity and 76% sensitivity.
preliminarily identify high-risk SARS-CoV-2 infected patients before RT-PCR results are available,
risk stratify patients in the ED,
select patients who need relatively urgent retesting if initial RT-PCR results are negative,
help isolate infected patients earlier, and
assist in the identification of SARS-CoV-2 infected patients in areas where RT-PCR testing is unavailable due to financial or supply constraints.
Early Results of Study Promising, But More Research is Needed
Wang noted that more research is needed on the algorithm and that he and his colleagues are currently working on ways to improve the model. They are hoping to test it with different conditions and geographies.
“Our model in the paper was built on data from when New York was at its COVID peak,” he told Modern Healthcare. “At that time, we were not doing wide PCR testing, and the patients who were getting tested were pretty sick.”
At the time of the study, the positivity rate for COVID-19 at New York-Presbyterian Hospital was in the 40% to 50% range. That was substantially higher than the current positivity rate, which is in the 2% to 3% range, Modern Healthcare reported.
“This model we built in a population in New York in a certain time period, so we can’t guarantee that it will work well universally,” Wang told Modern Healthcare.
It’s exciting to think that advances in software algorithms may one day make it possible to combine routine clinical laboratory testing and create diagnostics that identify diseases in ways the individual tests were not originally designed to do.
This study is an example that researchers in AI and informatics are working to bring new tools and diagnostic capabilities to clinical laboratories. Also, this is a demonstration of how a patient’s results from multiple other types of lab tests can by analyzed using AI and similar analytical algorithms to diagnose a health condition unrelated to the original reasons for performing those tests.
If this can be demonstrated with other diseases and health conditions, it would open up one more way that pathologists and clinical laboratory scientists can contribute to more accurate diagnoses and improved selection of the most appropriate therapies for individual patients.
