Evaluating blood oxygen saturation measurements by popular fitness trackers in postoperative patients: A prospective clinical trial

Abstract

Blood oxygen saturation is an important clinical parameter, especially in postoperative hospitalized patients, monitored in clinical practice by arterial blood gas (ABG) and/or pulse oximetry that both are not suitable for a long-term continuous monitoring of patients during the entire hospital stay, or beyond. Technological advances developed recently for consumer-grade fitness trackers could-at least in theory-help to fill in this gap, but benchmarks on the applicability and accuracy of these technologies in hospitalized patients are currently lacking. We therefore conducted at the postanaesthesia care unit under controlled settings a prospective clinical trial with 201 patients, comparing in total >1,000 oxygen blood saturation measurements by fitness trackers of three brands with the ABG gold standard and with pulse oximetry. Our results suggest that, despite of an overall still tolerable measuring accuracy, comparatively high dropout rates severely limit the possibilities of employing fitness trackers, particularly during the immediate postoperative period of hospitalized patients.

Keywords: Bioelectronics; Clinical measurement in health technology; Health sciences.

Graphical abstract

Figure 1

Study flow chart Top : (I) During screening of 288 patients, 87 of these met exclusion criteria. (II) Informed consent was obtained by 201 patients, of whom 112 patients could be included in the measurements. Bottom : For the SaO₂ benchmark (left ), 347 valid measurements (IIIa) were obtained, which after outlier removal led to 343 measurement pairs to be considered in our statistical analysis (IVa). Regarding the SpO₂ benchmark, 706 valid measurements (IIIb) yielded 694 pairs to be evaluated. Of note, data acquisition in (IIIa, IVa) and (IIIb, IVb) are based on the same patient cohort recruited in (I, II).

Figure 2

Bland-Altman plots comparing SaO₂ measurements by ABG to the SpO₂ readings of each of the investigated devices, including TPO Following the visualization proposed by Bland and Altman, scatterplots showing the real errors of the measurements (y axis: SpO₂ measurements minus SaO₂ reference) stratified by the mean of each measurement pair (x axis). Dashed horizontal lines mark the bias (B), i.e., the arithmetic average of all real errors with the limits of agreement (LoA) as determined by an offset of ±2 times the standard deviation (SD). Error bars show the 95% confidence interval (CI) for the bias and both LoA. For the ease of comparison, data points are color-coded, specifically for each of the devices: TPO = orange (top-left); Apple = red (top-right); Garmin = blue (bottom-left); Withings = green (bottom-right).

Figure 3

Linear correlation assessment of the blood oxygen saturation measurements comparing the investigated devices to ABG Scatterplots localize each of the paired measurements (x,y) by the SaO₂ reference value obtained by ABG (x) and the corresponding SpO₂ measurement of the benchmarked device (y). The black solid line depicts the linear regression model, with the 95% confidence interval shaded in gray. Color codes for the devices: TPO = orange (top-left); Apple = red (top-right); Garmin = blue (bottom-left); Withings = green (bottom-right).

Figure 4

Agreement of SpO₂ measurements between fitness trackers and TPO Bland-Altman diagrams (upper ) and scatterplots (lower ) assess the agreement between the SpO₂ readings obtained by fitness trackers to the SpO₂ reference values defined by TPO measurements. Due to the discrete nature of the SpO₂ measurements, multiple data points coinciding at the same coordinates are visualized by circles with varying diameters. The black solid line depicts the linear regression model, with the 95% confidence interval shaded in gray. Color codes for the fitness trackers: Apple = red (left); Garmin = blue (center); Withings = green (right).

Figure 5

Analysis of potential confounders Patients were segregated in different cohorts according to their attributes classified by variables of different nature (x axis), to assess potential influences on the fitness trackers readings (y axis). In all diagrams, the colors identify the device: TPO = orange; Apple = red; Garmin = blue; Withings = green. (A) the real errors are stratified by perfusion index. (B and C) characteristics of the ABG analysis. (D and E) boxplot visualisations of the absolute errors binned by categorical classifications of the patient attributes. (F) barplots contrasting the dropout rate in non-vs. shivering patients after surgery. ∗∗p < 0.01; ∗∗∗p < 0.001 (Fisher’s Exact Test).