{rfName}
Ev

License and Use

Icono OpenAccess

Altmetrics

Impact on the Sustainable Development Goals (SDGs)

Analysis of institutional authors

Pagan, JosueAuthorAyala, Jose LAuthor

Share

December 10, 2024
Publications
>
Article

Evaluating AI Methods for Pulse Oximetry: Performance, Clinical Accuracy, and Comprehensive Bias Analysis

Publicated to: Bioengineering (Basel). 11 (11): 1061- - 2024-11-01 11(11), DOI: 10.3390/bioengineering11111061

Authors:

Cabanas, AM; Sáez, N; Collao-Caiconte, PO; Martín-Escudero, P; Pagán, J; Jiménez-Herranz, E; Ayala, JL
[+]

Affiliations

Univ Complutense Madrid, Dept Comp Architecture & Automat, Madrid 28040, Spain - Author
Univ Complutense Madrid, Fac Med, Profess Med Sch Phys Educ & Sport, Madrid 28040, Spain - Author
Univ Politecn Madrid, Ctr Computat Simulat, Campus Montegancedo, Boadilla Del Monte 28660, Spain - Author
Univ Politecn Madrid, Elect Engn Dept, Madrid 28040, Spain - Author
Univ Tarapaca, Dept Fis, FACI, Arica 1000000, Chile - Author
Univ Tarapaca, Direcc Gest Digital & Transparencia, Arica 1000000, Chile - Author
See more

Abstract

Blood oxygen saturation (SpO(2)) is vital for patient monitoring, particularly in clinical settings. Traditional SpO(2 )estimation methods have limitations, which can be addressed by analyzing photoplethysmography (PPG) signals with artificial intelligence (AI) techniques. This systematic review, following PRISMA guidelines, analyzed 183 unique references from WOS, PubMed, and Scopus, with 26 studies meeting the inclusion criteria. The review examined AI models, key features, oximeters used, datasets, tested saturation intervals, and performance metrics while also assessing bias through the QUADAS-2 criteria. Linear regression models and deep neural networks (DNNs) emerged as the leading AI methodologies, utilizing features such as statistical metrics, signal-to-noise ratios, and intricate waveform morphology to enhance accuracy. Gaussian Process models, in particular, exhibited superior performance, achieving Mean Absolute Error (MAE) values as low as 0.57% and Root Mean Square Error (RMSE) as low as 0.69%. The bias analysis highlighted the need for better patient selection, reliable reference standards, and comprehensive SpO(2 )intervals to improve model generalizability. A persistent challenge is the reliance on non-invasive methods over the more accurate arterial blood gas analysis and the limited datasets representing diverse physiological conditions. Future research must focus on improving reference standards, test protocols, and addressing ethical considerations in clinical trials. Integrating AI with traditional physiological models can further enhance SpO(2 )estimation accuracy and robustness, offering significant advancements in patient care.
[+]

Keywords

Artificial intelligenceBias assessmenBias assessmentMachine learningOximetryPrecision medicinePredictive modelingSpo 2Spo(2)Spo2Zero hunger

Quality index

Bibliometric impact. Analysis of the contribution and dissemination channel

The work has been published in the journal Bioengineering (Basel) due to its progression and the good impact it has achieved in recent years, according to the agency WoS (JCR), it has become a reference in its field. In the year of publication of the work, 2024 there are still no calculated indicators, but in 2023, it was in position 51/124, thus managing to position itself as a Q2 (Segundo Cuartil), in the category Engineering, Biomedical. Notably, the journal is positioned en el Cuartil Q2 para la agencia Scopus (SJR) en la categoría Bioengineering.

Independientemente del impacto esperado determinado por el canal de difusión, es importante destacar el impacto real observado de la propia aportación.

Según las diferentes agencias de indexación, el número de citas acumuladas por esta publicación hasta la fecha 2026-04-25:

  • WoS: 4
  • Scopus: 5
[+]

Impact and social visibility

From the perspective of influence or social adoption, and based on metrics associated with mentions and interactions provided by agencies specializing in calculating the so-called "Alternative or Social Metrics," we can highlight as of 2026-04-25:

  • The use, from an academic perspective evidenced by the Altmetric agency indicator referring to aggregations made by the personal bibliographic manager Mendeley, gives us a total of: 57.
  • The use of this contribution in bookmarks, code forks, additions to favorite lists for recurrent reading, as well as general views, indicates that someone is using the publication as a basis for their current work. This may be a notable indicator of future more formal and academic citations. This claim is supported by the result of the "Capture" indicator, which yields a total of: 51 (PlumX).

With a more dissemination-oriented intent and targeting more general audiences, we can observe other more global scores such as:

  • The Total Score from Altmetric: 1.
  • The number of mentions on the social network X (formerly Twitter): 2 (Altmetric).

It is essential to present evidence supporting full alignment with institutional principles and guidelines on Open Science and the Conservation and Dissemination of Intellectual Heritage. A clear example of this is:

  • The work has been submitted to a journal whose editorial policy allows open Open Access publication.
  • Assignment of a Handle/URN as an identifier within the deposit in the Institutional Repository: https://oa.upm.es/88994/

As a result of the publication of the work in the institutional repository, statistical usage data has been obtained that reflects its impact. In terms of dissemination, we can state that, as of

  • Views: 150
  • Downloads: 287
Continuing with the social impact of the work, it is important to emphasize that, due to its content, it can be assigned to the area of interest of ODS 2 - End hunger, achieve food security and improved nutrition and promote sustainable agriculture, with a probability of 50% according to the mBERT algorithm developed by Aurora University.
[+]

Leadership analysis of institutional authors

This work has been carried out with international collaboration, specifically with researchers from: Chile.

There is a significant leadership presence as some of the institution’s authors appear as the first or last signer, detailed as follows: Last Author (AYALA RODRIGO, JOSE LUIS).

[+]

Project objectives

Esta aportación persigue los siguientes objetivos: analizar métodos de inteligencia artificial aplicados a la estimación de la saturación de oxígeno en sangre (SpO2) mediante señales fotopletismográficas; evaluar el desempeño y la precisión clínica de modelos como regresión lineal, redes neuronales profundas y procesos gaussianos; determinar las características clave, intervalos de saturación y métricas de rendimiento utilizadas en estudios seleccionados; caracterizar sesgos presentes en la selección de pacientes y estándares de referencia mediante criterios QUADAS-2; identificar limitaciones en la generalizabilidad de los modelos debido a la dependencia de métodos no invasivos y conjuntos de datos limitados; y proponer mejoras en estándares de referencia, protocolos de prueba y consideraciones éticas para futuras investigaciones.
[+]

Most relevant results

La aportación presenta una revisión sistemática sobre métodos de inteligencia artificial (IA) aplicados a la oximetría de pulso, evaluando desempeño, precisión clínica y sesgos. Los resultados más relevantes incluyen: (1) la identificación de 26 estudios que cumplen criterios de inclusión, analizando modelos de regresión lineal y redes neuronales profundas como principales metodologías; (2) el uso de características como métricas estadísticas, relaciones señal-ruido y morfología de la señal para mejorar la precisión; (3) el modelo de Procesos Gaussianos alcanzó un error absoluto medio (MAE) de 0,57% y un error cuadrático medio (RMSE) de 0,69%; (4) el análisis de sesgos evidenció la necesidad de mejorar la selección de pacientes, estándares de referencia y rangos de saturación SpO2 para aumentar la generalizabilidad.
[+]

Awards linked to the item

This research was funded by ANID grant number Project SA22I0178 and Project SA77210039. The APC was funded by ANID grant number Project SA22I0178.
[+]