AI-Driven and Automated Systems for Continuous Oxygen Saturation Monitoring in Long-Term Oxygen Therapy: Systematic Review

PRISMA 2020 / PRISMA-S review of 2000 to Jan 2025 literature (PubMed, IEEE Xplore, Springer, ACM, MDPI). Of 928 records, 61 full texts were assessed and 8 studies included: 5 AI-based, 3 automated non-AI oxygen delivery. Risk of bias was assessed with adapted ROBINS-I and synthesis was narrative (no meta-analysis).

• Form factor: finger

Background

Long-term oxygen therapy (LTOT) improves outcomes in selected patients with severe chronic hypoxemia, but conventional LTOT uses fixed oxygen flow prescriptions that may not reflect changing needs during activity, sleep, or exacerbations. AI and automated oxygen systems may support continuous peripheral capillary oxygen saturation (SpO 2 ) monitoring, signal-quality assessment, and adaptive oxygen titration. Evidence comparing AI-driven and non-AI automated approaches across performance, clinical readiness, LTOT applicability, and equity remains limited.

Objective

This systematic review synthesized peer-reviewed evidence on AI-driven and automated systems for continuous SpO 2 monitoring or oxygen titration relevant to adult LTOT, focusing on accuracy, motion robustness, clinical performance, demographic equity, and readiness for home or ambulatory deployment.

Methods

This review followed PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) 2020 and PRISMA-S (Preferred Reporting Items for Systematic Reviews and Meta-Analyses–Search). PubMed, IEEE Xplore, Springer Link, ACM Digital Library, and supplementary MDPI publisher-level searches were searched for English-language peer-reviewed studies published during 2000 to January 2025. Eligible studies evaluated AI-driven or automated systems for continuous SpO 2 monitoring or oxygen titration in adult LTOT-relevant populations and addressed motion artifact, low-perfusion signal management, skin tone bias, or prolonged signal stability. Two reviewers independently screened and extracted data; disagreements were resolved with a third reviewer. Risk of bias was assessed using an adapted Risk of Bias in Non-randomized Studies of Interventions (ROBINS-I) framework. Heterogeneous designs and outcomes precluded meta-analysis, so findings were synthesized narratively following Popay et al.

Results

Of 928 records (926 from databases or platforms and 2 from manual reference screening), 912 remained after deduplication, 61 full texts were assessed, and 8 studies were included. Five studies evaluated AI-based systems and 3 evaluated automated non-AI oxygen delivery. AI models reported SpO 2 estimation mean absolute error as low as 0.57% and root mean square error as low as 0.69%, but most were simulated, retrospective, or non–chronic obstructive pulmonary disease (COPD) specific. Only Cabanas et al reported skin tone–stratified bias analysis. Automated systems showed stronger clinical deployment evidence: O 2 matic maintained the target SpO 2 85.1% of the time versus 46.6% with manual titration, while Cirio and Nava reported mean SpO 2 of 95% versus 93% manually. Risk of bias was moderate to serious, mainly due to participant selection, limited demographic reporting, and algorithmic transparency.

Conclusions

AI-driven and automated LTOT-relevant systems address complementary gaps. AI approaches show promise for signal interpretation and personalized prediction, whereas rule-based automated systems have stronger near-term clinical evidence for oxygen titration. Evidence is limited by small study numbers, heterogeneous outcomes, limited COPD or home LTOT validation, and sparse equity reporting. Future work should prioritize longitudinal validation in diverse LTOT populations, prespecified equity outcomes, failure-mode reporting, and hybrid architectures combining AI signal intelligence with safety-critical automated control.

Verbatim from the publisher's DOI record (opens in a new tab) · Abstract as deposited by the publisher with Crossref; © the authors/publisher

No results from this paper on ChatPPG leaderboards yet. Browse the leaderboards.

Wavelengths

red, IR