An Approach Designed to Help Physicians Make Decisions — ScienceDaily

Machine Learning

A new machine learning model that estimates optimal treatment timing for sepsis could pave the way for supporting tools that help physicians individualize treatment decisions at the patient’s bedside, researchers say. increase.

In a paper published today (April 6, 2023) nature machine intelligencescientists at Ohio State University describe a new model that uses artificial intelligence to address the complex problem of when to give antibiotics to patients with suspected sepsis.

Time is of the essence, as sepsis, the body’s overwhelming response to infection, can quickly lead to organ failure. Still, its symptoms — fever, low blood pressure, rapid heart rate, breathing problems — can look like many other conditions. Federal guidelines recommend broad-spectrum antibiotics as the first line of defense. Seeking immediate medical attention. This is a strategy that usually needs to be acted upon before obtaining cultures confirming bacterial infection from the lab.

This model was designed with these uncertainties and time pressures in mind.

The researchers tested the model’s performance using critical care patient information from US and European databases to determine outcomes for patients whose actual treatment matched the model’s recommended treatment schedule, and for patients whose actual treatment matched the model’s recommended treatment schedule. compared outcomes in patients who differed from those recommended by . For vital signs, test results and risk-related demographic data. Outcome measures were the patient’s survival rates after his 30 and 60 days of sepsis treatment.

“We’ve shown that when real treatments and artificial intelligence match, mortality can drop, and when they don’t match, mortality can be as high as 25%,” said senior author Ping Zhang, Ph.D. I’m here. He majored in Computer Science and Engineering and Biomedical Informatics at Ohio State University.

The model was trained and validated on a dataset obtained from a public database called MIMIC-III. The model was tested on various parts of MIMIC-III and a new external dataset from AmsterdamUMCdb. Key measurements in approximately 14,000 patients with sepsis included changes in patient vital signs and laboratory test results over time (which serve as indicators of disease severity and type of infection), and as infected patients. It included an innovative method devised to compare outcomes in patients who did not. Receive antibiotics at specific times.

“We want our modeling to predict whether antibiotic use is beneficial at a particular time. Yes or no. We applied the clinical trial concept: For every patient who took medication, we included clinically similar patients who were not taking antibiotics at that time.” Translational Data Analysis Institute. “Then we can predict counterfactual outcomes and train counterfactual treatment models to determine whether sepsis treatments work.”

Sepsis contributes to more than one-third of hospital deaths and is most frequently found in intensive care units and emergency departments. “We often make decisions there without a gold standard due to culture,” says the collaborators. – Author Katherine Buck, M.D., Assistant Professor of Emergency Medicine in the School of Medicine and Director of the Geriatric Emergency Department at Ohio State Wexner Medical Center. “Not all patients who meet criteria for sepsis have evidence of bacterial infection.”

Antibiotics carry risks. It can be toxic to the kidneys, cause allergic reactions, and cause C. difficile, an infection that causes severe diarrhea and inflammation of the colon.

“What this paper begins to say is that the information available to clinicians is changing in ways that suggest, sometimes at the forefront and sometimes not, that patients will benefit from antibiotics. “A decision support tool encourages us to ask ourselves if it matches what we already think, or what we’re missing.” We can tell clinicians whether or not, hopefully over time, signals will emerge from all the electronic health record data we have. It’s important to understand how to use it and get it to clinicians.”

These insights (and the availability of electronic health record data) are critical to feeding the model with the right kind of data and designing the model to take into account multiple considerations as the healthcare environment changes. Mr Zhang said.

“We modeled patient records like language,” he said. “And for machine learning, we always train our models batch-by-batch. You need a model to do, then the machine will always find better parameters to fit the model.”

A key metric used to guide how the model reaches its recommendations is the Sequential Organ Failure Assessment (SOFA) score. It is used to routinely assess how the organ systems of ICU patients are performing based on the results of six lab tests. Researchers ran a case study example to demonstrate what an interface developed for a clinical setting might look like, and the model recommended treatment timelines based on changes in personalized patient data. We showed how the SOFA score changes when adjusted.

“Our paper is the first to use AI to pursue antibiotic recommendations for sepsis and use real-world data to support clinical decision-making,” said Zhang. . “Studies like this require clinical validation. This is the first stage of retrospective data analysis, and the second stage will require human-AI collaboration for better patient care. ”

This work was supported by the National Science Foundation and the National Institutes of Health. Additional co-authors, both from Ohio, include lead author Ruoqi Liu, a PhD student in computer science and engineering, and Jeffrey Caterino, MD, professor and chairman of emergency medicine and director of emergency medical services. )was.

Source link

Leave a Reply

Your email address will not be published. Required fields are marked *