Journal of biomedical optics · 2026
Combining label-free Raman spectroscopy with machine learning to monitor COVID-19 disease from acute infection to recovery.
СтатьяНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Heidarifard Maryam, Leblond Frédéric, Dallaire Frédérick, Brunet-Ratnasingham Elsa, Ksantini Nassim, Mahfoud Myriam, Sheehy Guillaume, Soudeyns Hugo, Jouvet Philippe, Tse Sze Man, Quach Caroline, Kaufmann Daniel E, Ember Katherine, Dehaes Mathieu
Аннотация
SIGNIFICANCE: Monitoring COVID-19 disease from acute infection to recovery is critical to understand biochemical dysregulation and COVID-19 heterogeneity over time.
AIM: Our aim is to develop an approach combining label-free Raman spectroscopy and machine learning modeling to enable sensitive biomolecular detection of COVID-19 over time.
APPROACH: Hospitalized patients infected with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) were recruited and stratified based on respiratory support (critical and non-critical). Controls had a negative SARS-CoV-2 test. Blood was collected in the acute and recovery phases and was analyzed with Raman spectroscopy. Four machine learning models based on Raman spectra were developed to differentiate critical and non-critical patients in the acute and recovery phases from controls. For each group of patients, two additional models also classified the patient status (acute versus recovery) using cross-sectional and longitudinal analyses.
RESULTS: Raman peaks assigned to proteins, glucose, fatty acids, lactic acid, vitamin A, and lipids were identified in models. Overall, area under the receiver operating characteristic curve values were between 0.83 and 1.00 with sensitivities, specificities, and accuracies between 73% and 100%, 77% and 100%, and 78% and 100%, respectively.
CONCLUSIONS: These results highlight the capability of combined Raman spectroscopy and machine learning modeling to stratify patients at admission, monitor recovery after discharge, and support strategies to potentially reduce the risk of long-COVID.
AIM: Our aim is to develop an approach combining label-free Raman spectroscopy and machine learning modeling to enable sensitive biomolecular detection of COVID-19 over time.
APPROACH: Hospitalized patients infected with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) were recruited and stratified based on respiratory support (critical and non-critical). Controls had a negative SARS-CoV-2 test. Blood was collected in the acute and recovery phases and was analyzed with Raman spectroscopy. Four machine learning models based on Raman spectra were developed to differentiate critical and non-critical patients in the acute and recovery phases from controls. For each group of patients, two additional models also classified the patient status (acute versus recovery) using cross-sectional and longitudinal analyses.
RESULTS: Raman peaks assigned to proteins, glucose, fatty acids, lactic acid, vitamin A, and lipids were identified in models. Overall, area under the receiver operating characteristic curve values were between 0.83 and 1.00 with sensitivities, specificities, and accuracies between 73% and 100%, 77% and 100%, and 78% and 100%, respectively.
CONCLUSIONS: These results highlight the capability of combined Raman spectroscopy and machine learning modeling to stratify patients at admission, monitor recovery after discharge, and support strategies to potentially reduce the risk of long-COVID.