PRESS-NEWS.org - Press Release Distribution
PRESS RELEASES DISTRIBUTION

New medical AI tool identifies more cases of long COVID from patient health records

Mass General Brigham researchers developed an AI algorithm to unveil the elusive traces of long COVID in patients’ health records using ‘precision phenotyping’

2024-11-08
(Press-News.org) KEY TAKEAWAYS

Researchers from Mass General Brigham are leveraging artificial intelligence to help identify the signs of long COVID, track how different symptoms manifest over time, and eliminate alternative explanations for patients’ symptoms. The new approach suggests that 22.8% of the population experience the symptoms of long COVID, a figure that may paint a more realistic picture of the pandemic’s long-term toll. Through analyzing a patient’s history over time, this new AI tool may offer a personalized approach to care and help reduce inequities and biases seen in current diagnostics for long COVID.  

Investigators at Mass General Brigham have developed an AI-based tool to sift through electronic health records to help clinicians identify cases of long COVID, an often mysterious condition that can encompass a litany of enduring symptoms, including fatigue, chronic cough, and brain fog after infection from SARS-CoV-2. The results, which are published in the journal Med, could identify more people who should be receiving care for this potentially debilitating condition. The number of cases they identified also suggests that the prevalence of long COVID could be greatly underrecognized.

“Our AI tool could turn a foggy diagnostic process into something sharp and focused, giving clinicians the power to make sense of a challenging condition,” said senior author Hossein Estiri, PhD, head of AI Research at the Center for AI and Biomedical Informatics of the Learning Healthcare System (CAIBILS) at Mass General Brigham and an associate professor of Medicine at Harvard Medical School. “With this work, we may finally be able to see long COVID for what it truly is—and more importantly, how to treat it.”

Long COVID, also known as Post-Acute Sequelae of SARS-CoV-2 infection (PASC), includes a wide range of symptoms. For the purposes of their study, Estiri and colleagues defined it as a diagnosis of exclusion that is also infection associated. That means the diagnosis could not be explained in the patient’s unique medical record and it also had to associate with a COVID infection. In addition, the diagnosis needed to have persisted for 2 months or longer in a 12-month follow up window.

The algorithm used in the AI tool was developed by drawing de-identified patient data from the clinical records of nearly 300,000 patients across 14 hospitals and 20 community health centers in the Mass General Brigham system. Rather than having to rely on a single diagnosis code, the AI utilizes a novel method developed by Estiri and colleagues called “precision phenotyping” that sifts through individual records to identify symptoms and conditions linked to COVID-19 and to track symptoms over time in order to differentiate them from other illnesses. For example, the algorithm can detect if shortness of breath may be the result of pre-existing conditions like heart failure or asthma rather than a long COVID. Only when every other possibility was exhausted would the tool flag the patient as having long COVID.

“Physicians are often faced with having to wade through a tangled web of symptoms and medical histories, unsure of which threads to pull, while balancing busy caseloads. Having a tool powered by AI that can methodically do it for them could be a game-changer,” said Alaleh Azhir, MD, the co-lead author who is an internal medicine resident at Brigham Women’s Hospital, a founding member of the Mass General Brigham healthcare system.

The patient-centered diagnoses provided by this new method may also help alleviate biases built into current diagnostics for long COVID, according to the researchers, who note that patients diagnosed with the official ICD-10 diagnostic code for long COVID trend towards those with easier access to healthcare. While other diagnostic studies have suggested that approximately 7% of the population suffers from long COVID, this new approach reveals a much higher estimate—22.8%. The authors stated that this figure aligns more closely with national trends and paints a more realistic picture of the pandemic’s long-term toll.

The researchers determined their tool was about 3 percent more accurate than what ICD-10 codes capture, while being less biased. Specifically, their study demonstrated that the individuals they identified as having long COVID mirror the broader demographic makeup of Massachusetts, unlike long COVID algorithms that rely on a single diagnostic code or individual clinical encounters, skewing results toward certain populations such as those with more access to care. “This broader scope ensures that marginalized communities, often sidelined in clinical studies, are no longer invisible,” said Estiri.

Limitations of the study and AI tool include that health record data used in the algorithm to account for long COVID symptoms may be less complete than what is captured by physicians in post-visit clinical notes. Another limitation was the algorithm did not capture possible worsening of a prior condition, which may have been a long COVID symptom. For example, if a patient had COPD and prior episodes of it worsened before they developed COVID-19, the algorithm might have removed them even if their persisting symptoms were a long COVID indicator. Declines in the amount of COVID-19 testing in recent years also makes it difficult to identify when a patient may have first gotten COVID-19. The study was also limited to patients in Massachusetts.

Future studies may explore the algorithm in cohorts of patients with specific conditions, like COPD or diabetes. The researchers also plan to release this algorithm publicly on open access where physicians and healthcare systems globally can use it in their patient populations.

In addition to opening the door to better clinical care, this work may lay the foundation for future research into the genetic and biochemical factors behind long COVID’s various subtypes. “Questions about the true burden of long COVID—questions that have thus far remained elusive—now seem more within reach,” said Estiri.

 

Authorship: In addition to Estiri, Mass General Brigham authors include Alaleh Azhir, Jonas Hügel, Jiazi Tian, Jingya Cheng, Ingrid V. Bassett, Emily S. Lau, Yevgeniy R. Semenov, Virginia A. Triant, Zachary H. Strasser, Jeffrey G. Klann, and Shawn N. Murphy. Additional authors include, Douglas S. Bell, Elmer V. Bernstam, Maha R. Farhat, Darren W. Henderson, Michele Morris, and Shyam Visweswaran.

Disclosures: None.

Funding: Support from the National Institutes of Health, National Institute of Allergy and Infectious Diseases (NIAID) R01AI165535, National Heart, Lung, and Blood Institute (NHLBI) OT2HL161847, and National Center for Advancing Translational Sciences (NCATS) UL1 TR003167, UL1 TR001881, and U24TR004111. J.Hügel's work was partially funded by a fellowship within the IFI programme of the German Academic Exchange Service (DAAD) and by the Federal Ministry of Education and Research (BMBF) as well by the German Research Foundation (426671079).

Paper cited: Azhir A et al. “Precision Phenotyping for Curating Research Cohorts of Patients with Unexplained Post-Acute Sequelae of COVID-19” Med DOI: 10.1016/j.medj.2024.10.009

For More Information:

Study Finds Persistent Infection Could Explain Long COVID in Some People New Framework for Defining Long COVID Highlights 12 Signature Symptoms Artificial Intelligence Research News  

###

About Mass General Brigham

Mass General Brigham is an integrated academic health care system, uniting great minds to solve the hardest problems in medicine for our communities and the world. Mass General Brigham connects a full continuum of care across a system of academic medical centers, community and specialty hospitals, a health insurance plan, physician networks, community health centers, home care, and long-term care services. Mass General Brigham is a nonprofit organization committed to patient care, research, teaching, and service to the community. In addition, Mass General Brigham is one of the nation’s leading biomedical research organizations with several Harvard Medical School teaching hospitals. For more information, please visit massgeneralbrigham.org.

END



ELSE PRESS RELEASES FROM THIS DATE:

Heat waves and adverse health events among dually eligible individuals 65 years and older

2024-11-08
About The Study: In this time-series study, heat waves were associated with increased adverse health events among dually eligible individuals 65 years and older. Without adaptation strategies to address the health-related impacts of heat, dually eligible individuals are increasingly likely to face adverse outcomes.  Corresponding Author: To contact the corresponding author, Hyunjee Kim, PhD, email kihy@ohsu.edu. To access the embargoed study: Visit our For The Media website at this link https://media.jamanetwork.com/ (doi:10.1001/jamahealthforum.2024.3884) Editor’s Note: Please ...

Catastrophic health expenditures for in-state and out-of-state abortion care

2024-11-08
About The Study: In this cross-sectional study of U.S. patients seeking abortion, many individuals and their households were estimated to incur catastrophic health expenditures, particularly those traveling from out of state. The financial and psychological burdens of abortion seeking have likely worsened after the Dobbs decision, as more people need to cross state lines to reach abortion care. The findings suggest expansion of insurance coverage to ensure equitable access to abortion care, irrespective of people’s state of residence, ...

State divorce laws, reproductive care policies, and pregnancy-associated homicide rates

2024-11-08
About The Study: In this cross-sectional study of pregnancy-associated homicide rates, barriers to divorce were associated with higher homicide rates and access to reproductive health care was associated with lower homicide rates. This study highlights the association between state legislation and pregnancy-associated homicide in the U.S., which is important information for policymakers.  Corresponding Author: To contact the corresponding author, Kaitlin M. Boyle, PhD, email kb49@mailbox.sc.edu. To access the embargoed study: Visit our For The Media website at this link https://media.jamanetwork.com/ (doi:10.1001/jamanetworkopen.2024.44199) Editor’s ...

Emerging roles of high-mobility group box-1 in liver disease

Emerging roles of high-mobility group box-1 in liver disease
2024-11-08
Liver diseases, both acute and chronic, continue to pose significant clinical challenges due to high morbidity and mortality rates. Acute liver injury (ALI) caused by acetaminophen (APAP) overdose, hepatic ischemia-reperfusion injury (HIRI), and chronic conditions like nonalcoholic fatty liver disease (NAFLD) and alcohol-associated liver disease (ALD) are influenced by HMGB1-mediated pathways. HMGB1 is released from injured or necrotic liver cells and triggers inflammatory responses. Its circulating levels have been associated with disease severity in liver conditions, marking ...

Exploring the systematic anticancer mechanism in selected medicinal plants

2024-11-08
Cancer remains one of the leading global causes of mortality, with an estimated increase in cases due to lifestyle, environmental, and genetic factors. Despite advancements in treatment, cancer's complexity and the side effects of conventional therapies necessitate alternative approaches. Medicinal plants, long valued for their therapeutic properties, have shown promise in cancer treatment, attributed to their natural phytoconstituents. This review focuses on the anticancer mechanisms of specific medicinal plants and discusses their potential for future therapeutic development. Anticancer Mechanisms of Selected Medicinal Plants Medicinal plants exert anticancer ...

University of Cincinnati researchers pen editorial analyzing present, future of emergency consent in stroke trials

University of Cincinnati researchers pen editorial analyzing present, future of emergency consent in stroke trials
2024-11-08
The University of Cincinnati’s Yasmin Aziz, MD, and Joseph Broderick, MD, coauthored an editorial published Nov. 7 in the journal Neurology analyzing the current use and potential future of alternatives to traditional informed consent in acute stroke trials.    Patient informed consent is a crucial part of ethical clinical trial design and implementation, but time is of the essence for stroke trials. Approximately 2 million neurons die each minute they are deprived of oxygen, and patients are also sometimes incapacitated and therefore unable to consent ...

Scarlet Macaw parents ‘play favorites,’ purposefully neglect younger chicks

2024-11-08
Scarlet macaws are a symbol of fidelity and virtue to many people because they are thought to mate for life — but it turns out that they also “play favorites” when feeding their young, making them excellent mates, but neglectful parents. Fortunately, Texas A&M scientists have developed a way to ensure the birds’ bad parenting results in fewer chick deaths.   Researchers at the College of Veterinary Medicine and Biomedical Sciences have discovered that scarlet macaws purposefully neglect feeding the youngest chicks ...

One gene provides diagnoses for 30 patients whose condition was unexplained for years

2024-11-08
An international team of researchers has provided a genetic diagnosis for 30 individuals whose condition was undiagnosed for years despite extensive clinical or genetic testing. The study, conducted by researchers at Baylor College of Medicine, National University of Singapore and collaborating institutions worldwide, appeared in Genetics in Medicine, the official journal of the American College of Medical Genetics and Genomics. “The story of our findings began with one patient I saw in the clinic presenting an uncommon combination of problems,” said first and co-corresponding ...

Current practice and emerging endoscopic technology in the diagnosis of colorectal cancer

2024-11-08
The evolution of gastrointestinal (GI) endoscopy has transformed CRC diagnostics since its early 20th-century origins. Initial rigid endoscopes provided limited visualization, were highly uncomfortable for patients, and only partially visualized the colon. With the introduction of fiber-optic technology in the 1950s, endoscopy began transmitting real-time images, greatly enhancing diagnostic applications for GI conditions. Today, CRC remains a primary target for endoscopic screening due to its high prevalence as the second leading cause of cancer ...

Decoding 17-beta-hydroxysteroid dehydrogenase 13: A multifaceted perspective on its role in hepatic steatosis and associated disorders

Decoding 17-beta-hydroxysteroid dehydrogenase 13: A multifaceted perspective on its role in hepatic steatosis and associated disorders
2024-11-08
Chronic liver disease (CLD) is a growing global health challenge, accounting for millions of deaths each year. Its major contributors include metabolic dysfunction-associated steatohepatitis (MASH), alcoholic liver disease (ALD), and hepatitis C virus infection. These conditions are closely tied to hepatic steatosis, a condition characterized by the abnormal accumulation of fat in the liver. Recent genome-wide association studies have identified the 17-beta-hydroxysteroid dehydrogenase 13 (HSD17B13) gene and its loss-of-function variant ...

LAST 30 PRESS RELEASES:

Grant to support new research to address alcohol-related partner violence among sexual minorities

Biodiversity change amidst disappearing human traditions

New approaches to synthesize compounds for pharmaceutical research

Cohesion through resilient democratic communities

UC Santa Cruz chemists discover new process to make biodiesel production easier, less energy intensive

MD Anderson launches Institute for Cell Therapy Discovery & Innovation to deliver transformational new therapies

New quantum encoding methods slash circuit complexity in machine learning

New research promises an unprecedented look at how psychosocial stress affects military service members’ heart health

Faster measurement of response to antibiotic treatment in sepsis patients using Dimeric HNL

Cleveland Clinic announces updated findings in preventive breast cancer vaccine study

Intergenerational effects of adversity on mind-body health: Pathways through the gut-brain axis

Watch this elephant turn a hose into a sophisticated showering tool

Chimpanzees perform better on challenging computer tasks when they have an audience

New medical AI tool identifies more cases of long COVID from patient health records

Heat waves and adverse health events among dually eligible individuals 65 years and older

Catastrophic health expenditures for in-state and out-of-state abortion care

State divorce laws, reproductive care policies, and pregnancy-associated homicide rates

Emerging roles of high-mobility group box-1 in liver disease

Exploring the systematic anticancer mechanism in selected medicinal plants

University of Cincinnati researchers pen editorial analyzing present, future of emergency consent in stroke trials

Scarlet Macaw parents ‘play favorites,’ purposefully neglect younger chicks

One gene provides diagnoses for 30 patients whose condition was unexplained for years

Current practice and emerging endoscopic technology in the diagnosis of colorectal cancer

Decoding 17-beta-hydroxysteroid dehydrogenase 13: A multifaceted perspective on its role in hepatic steatosis and associated disorders

Key pathway leading to neurodegeneration in early stages of ALS identified

Ferroptosis in regulating treatment tolerance of digestive system tumors

A promising future in pancreatic incidentaloma detection

Stabilizing lithium-ion batteries: The vanadium touch

Innovative approaches to the surgical challenges in the management of gastroschisis

Mouse models for the study of liver fibrosis regression in vivo and ex vivo

[Press-News.org] New medical AI tool identifies more cases of long COVID from patient health records
Mass General Brigham researchers developed an AI algorithm to unveil the elusive traces of long COVID in patients’ health records using ‘precision phenotyping’