(Press-News.org) Researchers from Iceland trained a machine learning model with artificial intelligence to triage patients with respiratory symptoms before the patients visit a primary care clinic. To train the machine learning model, the researchers used only questions that a patient might be asked about before a clinic visit. Information was extracted from 1,500 clinical text notes that included a physician's interpretation of the patient's symptoms and signs, as well as reasons for clinical decisions made during the consultation, such as imaging referrals and prescriptions. Patients were categorized into one of five diagnostic categories based on information in clinical notes. Patients from all primary care clinics in the capital area of Iceland were included. The model scored each patient in two extrinsic datasets and divided patients into 10 risk groups. The researchers then analyzed selected outcomes in each group.
Patients in risk groups 1-5 were younger, had lower rates of lung inflammation, were less likely to be re-evaluated in primary and emergency care, were less likely to receive antibiotic prescriptions or chest X-ray referrals, as compared to higher risk groups 6-10. The lowest five groups contained no chest X-rays with signs of pneumonia or a pneumonia diagnosis by a physician. Researchers concluded that the model can reduce the number of chest X-ray referrals by eliminating them in risk groups 1-5.
What We Know: Respiratory symptoms are common reasons people visit primary care clinicians . However, many of their symptoms are self-resolving. Researchers argue that triaging patients before physician consultations may reduce unnecessary diagnostic testing; health care costs; and overprescription of antibiotics, which can lead to greater bacterial resistance.
What This Study Adds: Researchers found that a machine learning model can effectively categorize patients among 10 risk groups, allowing clinicians to communicate with lower-risk patients in ways that don’t add to their heavy work schedule and can allow for them to care for higher-risk patients and those with severe respiratory symptoms. The team asserts that the machine learning model could reduce costs for patients, the health care system, and society.
Triaging Patients With Artificial Intelligence for Respiratory Symptoms in Primary Care to Improve Patient Outcomes: A Retrospective Diagnostic Accuracy Study
Emil L. Sigurdsson, MD, PhD, et al
Primary Health Care of the Capital Area; Development Center for Primary Health Care in Iceland, and Department of Family Medicine, University of Iceland, Reykjavík, Iceland
Permanent link
END
Artificial intelligence can help categorize and triage primary care patients with respiratory symptoms
2023-05-23
ELSE PRESS RELEASES FROM THIS DATE:
Standardized measures are needed to quantify EHR workload outside time scheduled with patients
2023-05-23
Amid an uptick in publications looking to quantify the electronic health record (EHR) workload faced by clinicians, researchers propose three recommendations to ensure the accuracy and replicability of research in this space. Their recommendations include: 1) separating all time working in the EHR outside time scheduled with patients from time working in the EHR during time scheduled with patients, 2) including any time before or after scheduled appointments as “after-hours,” and 3) encouraging the EHR vendor and research communities to develop validated methods for measuring active EHR ...
Updated literature review reinforces link between care continuity, lower health care costs and more appropriate care usage
2023-05-23
In this systematic review, the authors summarized the wide range of peer-reviewed literature that links continuity of the doctor-patient relationship to health care costs and care utilization. This information is important to establish continuity measurement in value-based payment design.
The authors conducted a literature review of articles published between 2002 and 2022 about "continuity of care" and "continuity of patient care," as well as payor-relevant outcome categories, such as cost ...
Longtime University of Kentucky child neurologist receives Governor’s Service Award
2023-05-23
FRANKFORT, Ky. (May 19, 2023) — On Wednesday, May 17, Kentucky Gov. Andy Beshear and Cabinet for Health and Family Services (CHFS) Secretary Eric Friedlander recognized UK HealthCare’s Robert J. Baumann, M.D., with a Lifetime Achievement Award.
Baumann has worked in the field of child neurology in Kentucky for more than five decades. He was key in establishing the Office for Children with Special Health Care Needs (OCSHCN) network of regional medical clinics in Eastern ...
Gratitude practice among health care workers shows positive effects on well-being, with limitations
2023-05-23
Researchers tested a digital version of a positive psychology intervention called “Three Good Things” (3GT) among health care workers to assess whether gratitude practice improved well-being. Two hundred and twenty-three participants—all of whom were based at a single, large academic medicine department—were randomized to an immediate intervention or delayed intervention control group. During the study, participants received text messages three times per week, prompting them to document three things for which they were grateful.
Participants completed surveys measuring levels of depression, positive affect, gratitude, and life satisfaction at the study’s ...
Allowing patients with disabilities to describe their own clinical experiences can improve doctor communications
2023-05-23
Researchers looking to better understand patient experiences are turning to patient-guided tours (PGT) of health facilities, an approach drawn from the experience-based design literature. However, little research has assessed how patients with disabilities perceive the approach. In this qualitative study, 18 patients were asked to walk through the clinic as they would on a typical visit while describing their experiences. Patients’ experiences and perceptions of the tours were audiotaped and transcribed. Additionally, investigators took field notes and completed thematic content analyses.
Their findings support the value ...
FDA clears bionic pancreas developed in BU Lab for people with type 1 diabetes
2023-05-23
A bionic pancreas—a wearable, pocket-sized, automated insulin delivery device—that was first developed in a Boston University lab has been cleared by the US Food and Drug Administration (FDA). The iLet Bionic Pancreas is now commercially available, bringing fresh hope to the almost two million Americans with type 1 diabetes.
The approval is a massive milestone in a two-decade—and deeply personal—journey. Invented 20 years ago in the lab of Ed Damiano, a BU College of Engineering professor of ...
A troubling reaction to school violence compounds the crisis
2023-05-23
Ann Arbor, May 23, 2023 – High school students who experience violence or bullying at school are more likely to bring weapons like a gun, knife, or club to school than those who have not experienced violence, according to a new study in the American Journal of Preventive Medicine, published by Elsevier. Because weapons increase the potential for injury and death when there is interpersonal conflict, developing a better understanding of the relationship between exposure to violence and weapon carrying is essential for developing effective public health interventions.
“With 93 school shootings in the US just the 2020-21 period alone, ...
José Andrés and the George Washington University’s groundbreaking new institute to lead the world in delivering food system solutions
2023-05-23
WASHINGTON, D.C. (May 23, 2023) – World-renowned chef, author, and humanitarian José Andrés and international research leader the George Washington University (GW) today announced their partnership to build a premier Global Food Institute at GW, an unprecedented and transformative collaboration in the heart of the nation’s capital with plans to be a world leader in food system solution delivery.
“Our global food system is experiencing a crisis, brought on by systemic inequities, rampant hunger and poverty, the climate crisis, and deteriorating public health and nutrition. But food has the power to solve problems: It can rebuild lives and communities, heal ...
COPDGene study follows emphysema patients over 10 years
2023-05-23
Researchers at National Jewish Health evaluating computerized tomography (CT) scans of emphysema progression in the COPDGene® study showed that, during a span of 10 years, participants with pre-existing emphysema who continued smoking had the largest decline in adjusted lung density (ALD). The lung density decline was notably worse in current smokers compared with former smokers. The study is significant because reliably measuring changes in emphysema over time has always been challenging, due in part to differences in CT equipment technology and imaging parameters across institutions. The study, which published ...
Trial aims to improve treatment for newborns with life-threatening sepsis
2023-05-23
An international clinical trial co-led by UCL (University College London) researchers will evaluate much-needed new antibiotic combinations for newborn babies with sepsis.
The trial, which has started in three public hospitals in South Africa and Kenya, will be expanded to other countries and regions in 2024, with a target of recruiting up to 3,000 newborns overall.
The NeoSep1 trial will evaluate new combinations of generic antibiotics and compare them to existing treatment regimens that are often used in newborn babies with suspected neonatal sepsis.
Chris Hani Baragwanath Academic Hospital in Johannesburg, Tygerberg ...