Shining Light on Dark Skin: Pulse Oximetry Correction Models

• Tipo: Artigo em Livro de Atas de Conferência Internacional
• Data: 2023

Autores

Matos, J (Autor) Outra; Struja, T (Autor) Outra; Gallifant, J (Autor) Outra; Charpignon, ML (Autor) Outra; Jaime S Cardoso (Autor) FEUP; Celi, LA (Autor) Outra

Ata de Conferência Internacional

Título: 2023 IEEE 7TH PORTUGUESE MEETING ON BIOENGINEERING, ENBENG

Páginas: 211-214

IEEE 7th Portuguese Meeting on Bioengineering (ENBENG)

Porto, PORTUGAL, JUN 22-23, 2023

Indexação

ISI Web of Knowledge - 4 Citações

Scopus - 5 Citações

Outras Informações

ID Authenticus: P-00Y-V3Q

DOI: 10.1109/enbeng58165.2023.10175316

Abstract (EN): Pulse oximeters are medical devices used to assess peripheral arterial oxygen saturation (SpO(2)) noninvasively. In contrast, the gold standard requires arterial blood to be drawn to measure the arterial oxygen saturation (SaO(2)). Devices currently on the market measure SpO(2) with lower accuracy in populations with darker skin tones. Pulse oximetry inaccuracies can yield episodes of hidden hypoxemia (HH), with SpO(2) >= 88%, but SaO(2) < 88%. HH can result in less treatment and increased mortality. Despite being flawed, pulse oximeters remain ubiquitously used; debiasing models could alleviate the downstream repercussions of HH. To our knowledge, this is the first study to propose such models. Experiments were conducted using the MIMIC-IV dataset. The cohort includes patients admitted to the Intensive Care Unit with paired (SaO(2), SpO(2)) measurements captured within 10min of each other. We built a XGBoost regression predicting SaO(2) from SpO(2), patient demographics, physiological data, and treatment information. We used an asymmetric mean squared error as the loss function to minimize falsely elevated predicted values. The model achieved R-2 = 67.6% among Black patients; frequency of HH episodes was partially mitigated. Respiratory function was most predictive of SaO(2); race-ethnicity was not a top predictor. This singlecenter study shows that SpO(2) corrections can be achieved with Machine Learning. In future, model validation will be performed on additional patient cohorts featuring diverse settings.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 4