AI-powered skin spectral imaging enables instant sepsis diagnosis and outcome prediction in critically ill patients
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917008178675712 |
|---|---|
| author | Seidlitz, Silvia Hölzl, Katharina von Garrel, Ayca Sellner, Jan Katzenschlager, Stephan Hölle, Tobias Fischer, Dania von der Forst, Maik Schmitt, Felix C. F. Studier-Fischer, Alexander Weigand, Markus A. Maier-Hein, Lena Dietrich, Maximilian |
| author_facet | Seidlitz, Silvia Hölzl, Katharina von Garrel, Ayca Sellner, Jan Katzenschlager, Stephan Hölle, Tobias Fischer, Dania von der Forst, Maik Schmitt, Felix C. F. Studier-Fischer, Alexander Weigand, Markus A. Maier-Hein, Lena Dietrich, Maximilian |
| contents | With sepsis remaining a leading cause of mortality, early identification of patients with sepsis and those at high risk of death is a challenge of high socioeconomic importance. Given the potential of hyperspectral imaging (HSI) to monitor microcirculatory alterations, we propose a deep learning approach to automated sepsis diagnosis and mortality prediction using a single HSI cube acquired within seconds. In a prospective observational study, we collected HSI data from the palms and fingers of more than 480 intensive care unit patients. Neural networks applied to HSI measurements predicted sepsis and mortality with areas under the receiver operating characteristic curve (AUROCs) of 0.80 and 0.72, respectively. Performance improved substantially with additional clinical data, reaching AUROCs of 0.94 for sepsis and 0.83 for mortality. We conclude that deep learning-based HSI analysis enables rapid and noninvasive prediction of sepsis and mortality, with a potential clinical value for enhancing diagnosis and treatment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_09873 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AI-powered skin spectral imaging enables instant sepsis diagnosis and outcome prediction in critically ill patients Seidlitz, Silvia Hölzl, Katharina von Garrel, Ayca Sellner, Jan Katzenschlager, Stephan Hölle, Tobias Fischer, Dania von der Forst, Maik Schmitt, Felix C. F. Studier-Fischer, Alexander Weigand, Markus A. Maier-Hein, Lena Dietrich, Maximilian Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Image and Video Processing With sepsis remaining a leading cause of mortality, early identification of patients with sepsis and those at high risk of death is a challenge of high socioeconomic importance. Given the potential of hyperspectral imaging (HSI) to monitor microcirculatory alterations, we propose a deep learning approach to automated sepsis diagnosis and mortality prediction using a single HSI cube acquired within seconds. In a prospective observational study, we collected HSI data from the palms and fingers of more than 480 intensive care unit patients. Neural networks applied to HSI measurements predicted sepsis and mortality with areas under the receiver operating characteristic curve (AUROCs) of 0.80 and 0.72, respectively. Performance improved substantially with additional clinical data, reaching AUROCs of 0.94 for sepsis and 0.83 for mortality. We conclude that deep learning-based HSI analysis enables rapid and noninvasive prediction of sepsis and mortality, with a potential clinical value for enhancing diagnosis and treatment. |
| title | AI-powered skin spectral imaging enables instant sepsis diagnosis and outcome prediction in critically ill patients |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2408.09873 |