Back

Sensor Geometry, Not Signal Processing, Limits Opportunistic Detection of Capillary-Refill-Like Signals by Rule-Based and Language-Model Methods in Archived ICU Waveforms

Landry, T. C.; Kim, Y.

2026-06-09 intensive care and critical care medicine
10.64898/2026.06.07.26355129 medRxiv
Show abstract

Background. Capillary refill time is a resuscitation target in septic shock,1-4 but bedside measurement is examiner-dependent. An ICU monitor co-records a photoplethysmogram on the pulse oximeter and intermittent noninvasive blood pressure cuff cycles; if the probe and the cuff share a limb, each cycle is an unplanned vascular occlusion test on the distal microvascular bed. Standard practice places the two on opposite limbs. Objective. To measure how often, in MIMIC-IV-WDB v0.1.0, charted cuff cycles show the photoplethysmographic morphology expected of a same-limb cuff and probe, and to characterize the candidate capillary refill-like signal when that morphology is present. Methods. MIMIC-IV-WDB v0.1.05 was linked to the MIMIC-IV clinical database.6 A pre-registered rule-based detector identified candidate occlusion-reperfusion signatures on the 1-Hz perfusion-index envelope around each charted cuff timestamp. The primary endpoint was the proportion of cuff cycles suitable for analysis that were detector-positive at a 15-second reperfusion threshold, with 95% confidence intervals estimated by resampling patients at a fixed seed. A secondary analysis used a locally hosted multimodal language model (a Gemma-3 derivative on a non-device server) to adjudicate the same signature on perfusion-index plots; no MIMIC-IV-WDB content left the workstation. Results. Of 9,224 charted cuff cycles, 8,909 had a usable pulse-oximeter waveform, and 268 cycles in 15 patients (4.30% of the 6,236 cuff cycles suitable for analysis, 95% CI 2.60 to 6.03) met the primary 15-second threshold. The language model adjudicated the same cycles and called 1,367 of the 8,909 cycles with a usable waveform (15.34%) signature-present, roughly five times the detectors count. Because no laterality ground truth exists, agreement with a single blinded reader served as the comparator rather than accuracy. The two methods were about equally concordant with the reader: precision was 0.25 (95% CI 0.14 to 0.39) for the detector and 0.24 (95% CI 0.10 to 0.35) for the language model, although reweighting to the full population of cycles with a usable waveform lowered the language model to 0.030 (95% CI 0.009 to 0.053). These estimates are reference-limited: a blinded re-read of a 150-card subsample showed only moderate intra-rater reliability (Cohen {kappa} 0.46 to 0.59) with systematic undercalling on the first pass, and rescoring against the corrected re-read roughly doubled precision for both methods. Conclusions. Opportunistic extraction of capillary refill-like signals from archived ICU pulse oximetry is limited in two distinct ways. First, sensor geometry limits how often the signal is recordable: cuff cycles rarely show the morphology expected of a same-limb cuff and probe pair, consistent with opposite-limb placement, so the bottleneck is geometry rather than signal processing. Second, the modest reliability of morphology adjudication limits how well any single flagged cycle can be confirmed: against a blinded reader the detector is a usable screen but a noisy confirmer, the reference is itself only moderately reliable, and the language model is no more concordant despite flagging many more cycles. The minority of cycles in which the morphology appears contain a candidate signal that may merit prospective study under controlled placement with laterality recorded.

Matching journals

The top 3 journals account for 50% of the predicted probability mass.

1
Critical Care Explorations
15 papers in training set
Top 0.1%
45.1%
2
PLOS ONE
4510 papers in training set
Top 33%
4.3%
3
Scientific Reports
3102 papers in training set
Top 27%
4.3%
50% of probability mass above
4
PLOS Digital Health
91 papers in training set
Top 0.6%
3.9%
5
BMJ Open
554 papers in training set
Top 6%
3.3%
6
Journal of General Internal Medicine
20 papers in training set
Top 0.3%
3.0%
7
eBioMedicine
130 papers in training set
Top 0.6%
2.6%
8
Critical Care
14 papers in training set
Top 0.2%
2.0%
9
Clinical Chemistry
22 papers in training set
Top 0.3%
1.8%
10
Wellcome Open Research
57 papers in training set
Top 1%
1.4%
11
JAMA Network Open
127 papers in training set
Top 3%
1.4%
12
Pediatric Research
18 papers in training set
Top 0.2%
1.4%
13
Frontiers in Medicine
113 papers in training set
Top 4%
1.4%
14
BMJ
49 papers in training set
Top 0.7%
1.3%
15
Physiological Measurement
12 papers in training set
Top 0.3%
1.3%
16
British Journal of Anaesthesia
14 papers in training set
Top 0.5%
1.3%
17
npj Digital Medicine
97 papers in training set
Top 3%
1.0%
18
Physiological Reports
35 papers in training set
Top 1.0%
0.8%
19
Annals of Clinical and Translational Neurology
29 papers in training set
Top 1%
0.8%
20
Computers in Biology and Medicine
120 papers in training set
Top 4%
0.8%
21
BMJ Open Respiratory Research
32 papers in training set
Top 0.6%
0.8%
22
European Heart Journal - Digital Health
15 papers in training set
Top 0.6%
0.8%
23
eLife
5422 papers in training set
Top 56%
0.8%
24
The American Journal of Cardiology
15 papers in training set
Top 1%
0.8%
25
Thorax
32 papers in training set
Top 0.8%
0.8%
26
Journal of the American Heart Association
119 papers in training set
Top 4%
0.8%
27
Circulation
66 papers in training set
Top 3%
0.7%
28
European Respiratory Journal
54 papers in training set
Top 2%
0.5%
29
Frontiers in Physiology
93 papers in training set
Top 7%
0.5%
30
JAMIA Open
37 papers in training set
Top 2%
0.5%