PLOS Digit Health July 2023 PMID 37490472

A retrospective cohort analysis leveraging augmented intelligence to characterize long COVID in the electronic health record: A precision medicine framework.

Zachary H Strasser, Arianna Dagliati, Zahra Shakeri Hossein Abad, Jeffrey G Klann, Kavishwar B Wagholikar, Rebecca Mesa, Shyam Visweswaran, Michele Morris, Yuan Luo, Darren W Henderson, Malarkodi Jebathilagam Samayamuthu, Gilbert S Omenn, Zongqi Xia, John H Holmes

Download social card

Mentions

Peak: 1 in Jul 2023

across 3 sources since Jul 2023

Extended reach

2,255

potential audience

Total likes

Video views

105

Mentions per month

Jul 2023 – Mar 2024

Where it's discussed

Blogs2 articles
X / Twitter1 posts
YouTube1 videos

AI synopsis

What people are saying

The discussions reflect a balanced appreciation of the research, with references to innovative use of machine learning to identify long COVID symptoms and statements like 'this could change how we diagnose PASC,' illustrating a forward-looking perspective. The tone mixes technical analysis with optimistic language, indicating active engagement and recognition of the study’s potential impact.

AgreementModerate agreement

Most discussions acknowledge the study’s value in addressing long COVID, with some explicitly supporting the use of augmented intelligence.

InterestModerate interest

Posts demonstrate an ongoing curiosity about the research, showing moderate enthusiasm and recognition of its relevance.

EngagementHigh engagement

Many contributors actively analyze the methods and implications, indicating a deep level of involvement.

ImpactModerate impact

The discussions suggest the study could influence future diagnostic approaches, but don't have widespread transformative influence yet.

Abstract in brief

Post-acute sequelae of COVID-19 (PASC) refers to ongoing physical and psychological symptoms that persist for months after an acute COVID-19 infection, necessitating better identification methods for affected patients.
A retrospective cohort study analyzed electronic health records (EHR) of over 30,000 hospitalized COVID-19 patients across three healthcare systems, employing machine learning techniques to enhance the identification of PASC symptoms like dyspnea, fatigue, or joint pain, beyond standard diagnosis codes.
The study concluded that significant percentages of hospitalized patients are likely to experience these symptoms three months post-infection, with predictive values for dyspnea, fatigue, and joint pain found to be 0.73, 0.74, and

Read the full abstract

All mentions

Using Augmented Intelligence to Characterize Long COVID in EHR Data

A retrospective cohort study analyzed electronic health records of over 30,000 hospitalized COVID-19 patients to identify post-acute sequelae like dyspnea, fatigue, and joint pain. Machine learning techniques improved…

Social RTCL TV · Mar 29, 2024 105 views

LongCovidPapers

@LongCovidPapers · X

A retrospective cohort analysis leveraging augmented intelligence to characterize long COVID in the electronic health record: A precision medicine framework #LongCovid #pwLC https://t.co/iedsO7Iw6s

Jul 25, 2023 · 2,150 followers View post →