Researchers are developing an automated tool to identify respiratory discomfort when ventilated patients are unable to communicate.
RT’s Three Key Takeaways:
- Federal Research Grant: The National Institutes of Health awarded $3.5 million to fund a five-year study evaluating the physiological markers of shortness of breath.
- Predictive Algorithm: Investigators are designing a machine-learning model that uses biomarker data to detect respiratory distress more accurately than observational estimates.
- Critical Care Focus: The study will evaluate individuals with chronic obstructive pulmonary disease and intensive care unit patients receiving mechanical ventilation who cannot verbally communicate.
Erica Heinrich, an assistant professor of biomedical sciences at the University of California, Riverside School of Medicine, has received a $3.5 million grant from the National Institutes of Health (NIH) National Heart, Lung, and Blood Institute (NHLBI) to study dyspnea, according to a university news release.
The five-year initiative focuses on identifying physiological signals linked with dyspnea, creating methods to recognize patient distress, and improving bedside healthcare delivery for patients with COPD and those receiving mechanical ventilation in the intensive care unit (ICU).
Respiratory distress can frequently go unnoticed in clinical environments, and disconnects can occur between a patient’s actual experience and a clinician’s assessment. Unaddressed respiratory discomfort can lead to elevated anxiety, fear, long-term psychological trauma, and adverse clinical outcomes, researchers say.
“The research could ultimately provide physicians with a new tool to recognize and monitor respiratory distress in patients who may be unable to communicate it themselves and help guide interventions to improve their comfort and outcomes,” said Heinrich, assistant professor of biomedical sciences at the UC Riverside School of Medicine.
Two-Phase Investigation and Machine-Learning Development
According to project details, the investigation consists of two primary aims. The first aim involves laboratory experiments designed to induce breathlessness across varied cohorts to capture biomarker data. Heinrich and her team plan to utilize those data points to train a machine-learning algorithm capable of predicting respiratory comfort levels, which Heinrich noted can detect dyspnea more accurately than visual clinical observation.
While the predictive model has demonstrated success in individuals with healthy lungs, the second aim expands testing to patients diagnosed with COPD, who present with altered respiratory mechanics and neural breathing adaptations. In this phase, researchers will track multiple biomarkers while inducing shortness of breath using exercise and airflow resistance.
The study will also include an ICU cohort based at Jacobs Medical Center at UC San Diego.
“The clinical population is particularly important because ICU patients can have severe lung pathology, while also receiving medications that can alter how the brain processes signals and how the patient perceives dyspnea,” said Heinrich, assistant professor of biomedical sciences at the UC Riverside School of Medicine, in a news release. “Patients may be receiving pain medications, sedation, or neuromuscular blockade that leaves them unable to move or communicate. However, paralytic drugs do not prevent dyspnea but mask a patient’s distress. Determining whether respiratory discomfort can still be accurately predicted under those circumstances is critical because these are among the patients who could ultimately benefit most from the technology.”
Informing Mechanical Ventilation and Outpatient Care
According to the release, patients undergoing mechanical ventilation frequently experience acute breathlessness, which elevates anxiety levels and can hinder ventilator weaning timelines.
For individuals living with COPD outside inpatient settings, continuous tracking could supply objective metrics to inform outpatient therapeutic management, according to the researchers.
“For these patients, quality of life is closely connected to the severity and frequency of their dyspnea,” said Heinrich, assistant professor of biomedical sciences at the UC Riverside School of Medicine, in a news release. “A way to continuously monitor and quantify that experience could give physicians additional information to guide treatment. It could also give patients a stronger voice by providing objective data about the severity of the distress they experience.”
The project includes collaboration with Shujie Ma, a professor of statistics at UC Riverside with expertise in machine learning and real-time clinical biomarker analysis, and Mona Eskandari, an assistant professor of mechanical engineering at UC Riverside who specializes in lung-tissue mechanics. Eskandari will direct experiments comparing the algorithm’s performance against standard clinician observations.
According to Heinrich, the proposed algorithm is designed to supplement, rather than replace, clinical judgment by providing actionable data directly through bedside patient monitors.
