PPG-LM: A Photoplethysmography-Language Model with Multi-Level Clinical Alignment

Xiaoda Wang; Minxiao Wang; Maxwell A Xu; Patrick Langer; Kaiqiao Han; Defu Cao; Xiao Luo; Yuzhe Yang

cs.AISep 27, 2026

PPG-LM: A Photoplethysmography-Language Model with Multi-Level Clinical Alignment

Authors: Xiaoda Wang, Minxiao Wang, Maxwell A Xu, Patrick Langer, Kaiqiao Han, Defu Cao, Xiao Luo, Yuzhe Yang, +5 more

Organizations: Emory University · University of California, Los Angeles · Google · Stanford University · University of Southern California · University of Wisconsin–Madison

Abstract

Photoplethysmography (PPG) is widely recorded by clinical monitors and consumer wearables, providing a scalable source of continuous physiological information. These recordings offer an opportunity for physiological assessment at scale, but realizing this potential requires models to learn from both signal-derived physiological supervision and broader clinical context captured in electronic health records (EHRs). This involves aligning information spanning local observations, care events, and entire visits with PPG representations at corresponding temporal scales. However, existing PPG foundation models primarily rely on task-specific prediction heads, while the medical knowledge of large language models does not necessarily translate into waveform understanding. To bridge this gap, we introduce PPG-LM, the first PPG-language model family to learn physiological representations from both signal-derived supervision and broader clinical context captured in EHRs. To construct clinically grounded captions, we develop an automatic captioning pipeline that generates segment-, event-, and visit-level descriptions from signal measurements and structured EHR records. We then learn from these pairs through a two-stage framework that first establishes segment-language correspondence through contrastive learning and waveform-conditioned captioning, then extends alignment to events and visits through time-aware aggregation and temporal statement matching. Pretrained on approximately 73k hours of PPG, PPG-LM supports language-based recognition, cross-modal retrieval, and segment captioning. Experiments on MC-MED, MIMIC-III, and VitalDB show improved retrieval and caption factuality over language-model baselines and gains over PPG and time-series foundation models on multiple clinical prediction tasks.

Figures & tables

Figure 1: Motivation and overview of PPG-LM. PPG FMs learn waveform representations with limited integration of language and EHR context. General LLMs capture medical knowledge from text but require adaptation to encode raw PPG. PPG-LM bridges this gap by pairing PPG with captions derived from physiological measurements and structured EHRs. The radar plot highlights PPG-LM’s superior performance over baselines on selected segment-, event-, and visit-level tasks.

Study	Signal		Text Source	Text scope
Study	Raw	Context	Text Source	Segment	Event	Visit
SensorLM ( Zhang et al., 2026a )	✗	1 day	Sensor	✓	✗	✗
NormWear ( Luo et al., 2024 )	✓	6 s	Labels	✓	✗	✗
CSFM ( Gu et al., 2026 )	✓	10 s	Labels	✓	✗	✗
PulseLM ( Pham et al., 2026 )	✓	10 s	Labels	✓	✗	✗
CAP ( He et al., 2026 )	✓	5 min	EHR	✓	✗	✗

Table 1: Comparison of PPG–language studies.

Figure 2: Clinically Grounded Caption Generation: (1) Segment-level captions describe physiological features and signal quality within 30-second PPG windows. (2) Event-level captions provide medication context for fixed windows before and after administration. (3) Visit-level captions associate variable-length recordings with demographics, and medical history from clinical EHRs.

Figure 3: Two-stage multilevel alignment. (a) Stage 1 learns PPG and text encoders through contrastive segment–language alignment and PPG-conditioned caption generation. (b) Stage 2 extends the shared encoders to event- and visit-level alignment.

Model	MC-MED					MIMIC-III			VitalDB
Model	Rhythm $\uparrow$	Qual. $\uparrow$	Perf. $\uparrow$	Morph. $\uparrow$	RR $\uparrow$	Rhythm $\uparrow$	Qual. $\uparrow$	RR $\uparrow$	Rhythm $\uparrow$	Qual. $\uparrow$	RR $\uparrow$
GPT-5.6-luna	0.322	0.314	0.174	0.259	0.332	0.376	0.291	0.266	0.317	0.162	0.313
GPT-6-luna	0.319	0.361	0.193	0.263	0.259	0.357	0.315	0.253	0.326	0.175	0.307
GPT-6-sol	0.560	0.332	0.250	0.354	0.390	0.572	0.295	0.380	0.375	0.128	0.326
Opus 5.5	0.508	0.436	0.521	0.284	0.380	0.598	0.343	0.397	0.330	0.228	0.330
PulseLM	0.319	0.199	0.188	0.195	0.405	0.242	0.297	0.354	0.181	0.326	0.165

Table 2: Zero-shot physiological recognition. Macro-F1 (

\uparrow

) for rhythm, quality (Qual.), perfusion (Perf.), morphology (Morph.), and respiratory-rate class (RR). Bold marks the best in each column.

Model	MC-MED					MIMIC-III			VitalDB
Model	HR $\downarrow$	RR $\downarrow$	SBP $\downarrow$	MAP $\downarrow$	Fact $\uparrow$	HR $\downarrow$	RR $\downarrow$	Fact $\uparrow$	HR $\downarrow$	RR $\downarrow$	Fact $\uparrow$
GPT-5.6-luna	10.06	3.95	21.73	15.12	0.499	9.42	5.15	0.456	8.49	2.99	0.486
GPT-6-luna	11.24	3.93	22.24	14.51	0.559	11.52	4.71	0.533	8.86	2.34	0.579
GPT-6-sol	4.58	3.85	21.56	14.48	0.659	5.21	5.10	0.660	5.51	2.26	0.619
Opus 5.5	4.67	3.32	19.80	14.26	0.696	4.37	3.99	0.647	4.88	2.44	0.642
PulseLM	29.20	4.21	20.44	15.47	0.356	29.44	4.59	0.440	37.12	7.03	0.481

Table 3: Zero-shot physiological estimation. Fact is the accuracy of stated facts across six shared attributes (

\uparrow

). Numerical columns report MAE (

\downarrow

): HR in bpm, RR in breaths/min, and SBP/MAP in mmHg. MAE uses valid numerical outputs; bold marks the best reported value in each column.

Model	MC-MED		MIMIC-III		VitalDB500
Model	S2T $\uparrow$	T2S $\uparrow$	S2T $\uparrow$	T2S $\uparrow$	S2T $\uparrow$	T2S $\uparrow$
GPT-5.6-luna	0.105	—	0.090	—	0.075	—
GPT-6-luna	0.110	—	0.085	—	0.085	—
GPT-6-sol	0.240	—	0.260	—	0.200	—
Opus 5.5	0.190	—	0.275	—	0.230	—
Qwen3-4B (SFT)	0.385	0.600	0.160	0.185	0.125	0.180

Table 4: Zero-shot cross-modal retrieval. R@1 with 100 candidates. Bold: best.

Model	MC-MED					VitalDB
Model	Rate ctrl. $\uparrow$	Vasopress. $\uparrow$	Vasodil. $\uparrow$	IV fluid $\uparrow$	Diuretic $\uparrow$	Opioid $\uparrow$	Sedative $\uparrow$	Vasopress. $\uparrow$	Vasodil. $\uparrow$
GPT-5.6-luna	0.674	0.707	0.553	0.587	0.499	0.567	0.641	0.578	0.614
GPT-6-luna	0.626	0.715	0.648	0.530	0.478	0.600	0.594	0.480	0.693
GPT-6-sol	0.651	0.699	0.648	0.536	0.467	0.663	0.679	0.480	0.585
Opus 5.5	0.595	0.707	0.636	0.633	0.460	0.722	0.766	0.571	0.634
PulseLM	0.591	0.589	0.458	0.493	0.553	0.591	0.613	0.602	0.480

Table 5: Zero-shot event-level physiological recognition. Class-versus-control AUROC (

\uparrow

) for the five highest-scoring MC-MED classes for PPG-LM and all available VitalDB classes. Bold marks the best score in each column.

Model	MC-MED				VitalDB
Model	CCB $\uparrow$	AntiHTN $\uparrow$	AntiPL $\uparrow$	AntiDM $\uparrow$	HTN $\uparrow$	DM $\uparrow$	Anemia $\uparrow$	eGFR $\uparrow$
GPT-5.6-luna	0.468	0.509	0.477	0.520	0.500	0.465	0.487	0.500
GPT-6-luna	0.497	0.484	0.421	0.464	0.475	0.507	0.495	0.498
GPT-6-sol	0.500	0.500	0.505	0.507	0.523	0.502	0.523	0.500
Opus 5.5	0.500	0.443	0.468	0.507	0.519	0.512	0.484	0.500
PulseLM	0.500	0.500	0.500	0.500	0.500	0.500	0.500	0.500

Table 6: Zero-shot visit-level recognition. Balanced accuracy (

\uparrow

) for home-medication use (MC-MED) and clinical status (VitalDB). PPG-LM uses eight-window fact embeddings with held-out threshold calibration. Bold marks the best score in each column.

Task	Foundation models						PPG-LM
Task	PaPaGei-S	PulsePPG	AnyPPG	SIGMA-PPG	MOMENT-L	Chronos-2	Stage 1	Stage 2
MC-MED (ED) — AUROC $\uparrow$
Sex	0.692 $\pm$ 0.006	0.719 $\pm$ 0.007	0.783 $\pm$ 0.008	0.712 $\pm$ 0.008	0.724 $\pm$ 0.005	0.739 $\pm$ 0.008	0.813 $\pm$ 0.006	0.856 $\pm$ 0.005
ED admission	0.673 $\pm$ 0.011	0.681 $\pm$ 0.009	0.750 $\pm$ 0.013	0.679 $\pm$ 0.011	0.700 $\pm$ 0.011	0.728 $\pm$ 0.013	0.765 $\pm$ 0.012	0.787 $\pm$ 0.010
Atrial fibrillation	0.742 $\pm$ 0.012	0.752 $\pm$ 0.013	0.845 $\pm$ 0.010	0.755 $\pm$ 0.013	0.768 $\pm$ 0.014	0.815 $\pm$ 0.012	0.857 $\pm$ 0.010	0.870 $\pm$ 0.011
MC-MED (ED) — $R^{2}\uparrow$

Table 7: Clinical prediction with linear probes. Three classification and three regression tasks per dataset (mean

\pm

SD). Bold: best mean;

\dagger

: window-level target.

Variant	Temporal acc. $\uparrow$	Event AUROC $\uparrow$	Segment R@1 $\uparrow$
w/o temporal loss	0.511	0.698	0.446
w/o signed offsets	0.923	0.617	0.445
w/o segment loss	0.922	0.697	0.202
w/o distillation	0.920	0.700	0.445
w/o seg. loss + distill.	0.919	0.699	0.015
PPG-LM	0.925	0.707	0.447

Table 8: Ablation studies.

Appendix figures & tables17 assets

Supplementary material from the paper’s appendix.

Appendix

Attribute	Evidence and description
Pulse rate	Median pulse-interval rate, expressed as a value and a category.
Rate trend	Instantaneous rate slope: falling, stable, or rising.
Rhythm	ECG R–R interval variability, expressed as a regularity category.
Perfusion	Pulsatile amplitude relative to baseline: weak, moderate, or strong.
Signal quality	NeuroKit2 quality score: clean, fair, or noisy but usable.
Augmentation	The pyPPG augmentation index: low, moderate, or high.

Appendix

Table 9: Segment-caption content. Perfusion and morphology are waveform surrogates rather than independent clinical diagnoses.

Component	Evidence and description
Demographics	Recorded age and sex.
Presentation	Arrival mode, Emergency Severity Index, and normalized chief complaints.
Triage measurements	Available heart rate, respiratory rate, oxygen saturation, blood pressure, and temperature.
Clinical history	Selected prior ICD-10 diagnoses, expressed as clinical descriptions.
Home medications	Recorded active home-medication classes.

Appendix

Table 10: Visit-caption content.

Component	Evidence and description
Event anchor	A recorded administration timestamp for an eligible medication class.
Pre-event context	The latest available PPG windows preceding the administration.
Post-event context	PPG windows sampled evenly across the period following administration.
Caption target	The medication class, with individual drug names, doses, and exact latencies omitted.
Control view	The same sampling rule around a within-visit anchor free of nearby eligible administrations.

Appendix

Table 11: Event-caption construction.

Operator	Evidence and description
Occurrence	Whether tachycardia or irregularity appears among known observations.
Proportion	The affected share of known windows, described as brief, part, or most.
Contiguous duration	Consecutive affected windows, grouped into short, intermediate, or long runs.
Rate ordering	Consecutive groups of observed rates, describing rising, falling, stable, rise-then-fall, or fall-then-rise patterns.

Appendix

Table 12: Temporal-caption content.

Split	Patients	Visits	30-second windows
Training	29,177	42,856	8,842,271
Validation	3,641	5,421	1,183,278
Test	3,612	5,196	1,099,395
Total	36,430	53,473	11,124,944

Appendix

Table 13: Processed MC-MED splits. Patients are disjoint across splits; window counts refer to the retained corpus.

Task	Reference and clinical interpretation
Rhythm	Regular, slightly irregular, or markedly irregular according to synchronized ECG R–R interval CV ( $<0.05$ , $[0.05,0.12)$ , or $\geq 0.12$ ). Measures beat-timing regularity, without assigning a specific arrhythmia.
Quality (Qual.)	Clean, fair, or noisy according to the annotation quality score and usability gate. Describes waveform reliability and artifact burden.
Perfusion (Perf.)	Weak, moderate, or strong pulsatile amplitude relative to the signal baseline, using the waveform-derived AC/DC index. A peripheral perfusion surrogate, not a direct blood-flow measurement.
Morphology (Morph.)	Low, moderate, or high augmentation from the pyPPG augmentation index. Describes pulse-wave shape; it does not establish a vascular disease diagnosis.
HR class	Five pulse-rate bins: $<50$ , 50–59, 60–100, 101–120, and $>120$ bpm, spanning markedly slow to fast rates. These are benchmark annotation categories.
HR estimation	Heart rate in beats/min, evaluated against synchronized ECG. This independent reference differs from the PPG-derived pulse rate used to construct training captions.

Appendix

Table 14: Physiological task definitions. Tasks in Tables 2 and 3 , including the HR-class target used in few-shot evaluation. CV denotes coefficient of variation.

Task	Data	Recorded target and clinical meaning
Administration events: medication class versus control
Rate control	M	Administration of a rate-controlling medication, used to slow heart rate.
Vasopressor	M, V	Administration of an agent used to increase arterial blood pressure.
Vasodilator	M, V	Administration of a medication that dilates blood vessels.
IV fluid	M	Intravenous fluid administration, representing fluid delivery to the circulation.
Diuretic	M	Administration of medication that promotes renal salt and water excretion.

Appendix

Table 15: Medication and visit-fact definitions. Dataset abbreviations refer to the tasks displayed in Tables 5 and 6 .

Task	Data	Definition and clinical interpretation
Shared demographic target
Sex	M, I, V	Recorded patient sex.
MC-MED: ED disposition and prior clinical history
ED admission	M	Hospital admission following the ED encounter, versus no admission.
Atrial fibrillation	M	Prior atrial fibrillation: disorganized atrial electrical activity associated with an irregular rhythm. The label records history, not necessarily AF in the observed window.
Heart failure	M	Prior heart failure, a clinical syndrome involving impaired cardiac pumping and/or filling.

Appendix

Table 16: Clinical classification targets. These rows cover all 15 dataset–task pairs in Table 22 ; sex occurs in all three datasets. Positive disease labels refer to recorded conditions.

Task	Data	Measurement and clinical interpretation
Demographics and body size
Age	M, I, V	Patient age in years. MIMIC-III values above 120 are treated as missing because of de-identification shifts.
BMI	V	Body mass index: weight divided by squared height (kg/m 2 ), a measure of body size relative to height.
Kidney function, hematology, and blood chemistry
eGFR	M	Estimated glomerular filtration rate (mL/min/1.73 m 2 ), reflecting kidney filtration function. This target is continuous.
Hemoglobin (Hb)	M, I	Blood concentration of the oxygen-carrying protein in red blood cells.

Appendix

Table 17: Clinical regression targets. These rows cover all 17 dataset–task pairs in Table 22 . Shared measurements are defined once; sampling times and target levels are specified in the accompanying text.

[0pt][0pt] MC-MED (ED)
	Rule-based evaluation		LLM-judge evaluation
Model / caption source	Fact acc. $\uparrow$	Coverage $\uparrow$	Factuality $\uparrow$	Unsupported $\downarrow$
GPT-5.6-luna	0.499	0.99	2.63	6.54
PPG-LM : direct generation	0.923	1.00	3.64	2.94
PPG-LM : nearest-caption retrieval	0.877	1.00	3.83	1.51
[0pt][0pt] MIMIC-III (ICU)

Appendix

Table 19: Caption factuality by output method. Direct generation produces a new caption; nearest-caption retrieval selects an existing caption from the fixed bank. Fact accuracy covers six common fields; coverage includes all gradable fields. Judge factuality is on a 1–5 scale; unsupported claims are counted per caption. VitalDB uses the 40 Hz view. Bold marks the best value within each dataset.

(a) Triage-context recognition
Model	ESI $\uparrow$	Arrival $\uparrow$	HR $\uparrow$	SpO 2 $\uparrow$	RR $\uparrow$	Temp. $\uparrow$	BP $\uparrow$	CC $\uparrow$
GPT-5.6-luna	0.501	0.445	0.463	0.497	0.506	0.500	0.269	0.134
GPT-6-luna	0.500	0.498	0.486	0.500	0.500	0.500	0.238	0.128
GPT-6-sol	0.536	0.509	0.736	0.499	0.506	0.512	0.265	0.126
Opus 5.5	0.501	0.504	0.528	0.500	0.500	0.500	0.259	0.100
PulseLM	0.483	0.500	0.656	0.499	0.500	0.498	0.250	0.113

Appendix

Table 21: Additional visit-level clinical-fact recognition. Balanced accuracy (

\uparrow

) for (a) triage context and (b) medical history on 400 MC-MED visits using eight windows each. PPG-LM read-outs use thresholds calibrated on held-out MC-MED validation visits. Bold marks column maxima.

	Foundation models						PPG-LM
Task	PaPaGei-S	PulsePPG	AnyPPG	SIGMA-PPG	MOMENT-L	Chronos-2	Stage 1	Stage 2
MC-MED (ED) — AUROC $\uparrow$
Sex	0.692 $\pm$ 0.006	0.719 $\pm$ 0.007	0.783 $\pm$ 0.008	0.712 $\pm$ 0.008	0.724 $\pm$ 0.005	0.739 $\pm$ 0.008	0.813 $\pm$ 0.006	0.856 $\pm$ 0.005
ED admission	0.673 $\pm$ 0.011	0.681 $\pm$ 0.009	0.750 $\pm$ 0.013	0.679 $\pm$ 0.011	0.700 $\pm$ 0.011	0.728 $\pm$ 0.013	0.765 $\pm$ 0.012	0.787 $\pm$ 0.010
Atrial fibrillation	0.742 $\pm$ 0.012	0.752 $\pm$ 0.013	0.845 $\pm$ 0.010	0.755 $\pm$ 0.013	0.768 $\pm$ 0.014	0.815 $\pm$ 0.012	0.857 $\pm$ 0.010	0.870 $\pm$ 0.011
Heart failure	0.708 $\pm$ 0.018	0.723 $\pm$ 0.015	0.825 $\pm$ 0.013	0.711 $\pm$ 0.017	0.731 $\pm$ 0.015	0.781 $\pm$ 0.012	0.836 $\pm$ 0.010	0.860 $\pm$ 0.009

Appendix

Table 22: Full clinical prediction results. Test AUROC and

R^{2}

(mean

\pm

SD;

\uparrow

) for all 32 tasks. All models use the same four windows for visit-level targets. Bold: best mean;

\dagger

: window-level target.

Task	$k=5$	$k=10$	$k=20$	$k=50$
[0pt][0pt] MC-MED (ED) — Macro-F1 $\uparrow$
Rhythm	0.488 $\pm$ 0.051	0.537 $\pm$ 0.019	0.567 $\pm$ 0.037	0.597 $\pm$ 0.022
HR class	0.755 $\pm$ 0.023	0.831 $\pm$ 0.025	0.898 $\pm$ 0.018	0.921 $\pm$ 0.003
Sex	0.568 $\pm$ 0.042	0.645 $\pm$ 0.054	0.696 $\pm$ 0.041	0.710 $\pm$ 0.026
ED admission	0.563 $\pm$ 0.014	0.558 $\pm$ 0.026	0.583 $\pm$ 0.018	0.617 $\pm$ 0.008
[0pt][0pt] MIMIC-III (ICU) — Macro-F1 $\uparrow$

Appendix

Table 23: Few-shot adaptation of PPG-LM . Macro-F1 (mean

\pm

SD;

\uparrow

) over five support draws. VitalDB uses the 40 Hz waveform view.

k

: examples per class. Bold: best mean per row.

[0pt][0pt] Stage 1
Variant	Rhythm $\uparrow$	Quality $\uparrow$	R@1 $\uparrow$
CLIP	0.650	0.505	0.790
SigLIP	0.620	0.400	0.815
CoCa	0.640	0.614	0.783
[0pt][0pt] Stage 2
CLIP	0.534	0.580	0.797

Appendix

Table 24: Objective ablations on MC-MED. Rhythm/quality: macro-F1; retrieval: signal-to-text R@1 with 2,000 candidates. Stage-2 CLIP/CoCa report per-metric bests across configurations.

	MC-MED			MIMIC-III			VitalDB
Prompt bank	Rhythm	HR class	Quality	Rhythm	HR class	Quality	Rhythm	HR class	Quality
Template	0.651	0.355	0.673	0.670	0.337	0.786	0.389	0.327	0.583
Combined	0.629	0.393	0.592	0.642	0.350	0.677	0.384	0.282	0.515

Appendix

Table 25: Prompt sensitivity of PPG-LM . Template uses caption-style class descriptions; Combined adds reworded variants. Macro-F1 (

\uparrow

); bold marks the best score per column.

Target	Template
Segment rate	The pulse rate is about {val} beats per minute, {level}.
Segment rhythm	The cardiac rhythm is {level}.
Segment quality	The PPG trace is {level}.
Poor-quality segment	This segment’s pulse waveform is too noisy to characterize reliably.
Medication event	During this period the patient was given {desc}.
Control interval	This period of monitoring contains no medication administration.

Appendix

Table 26: Representative training templates. Strings are reproduced verbatim; braced fields are filled from measurements or records.

Concept	Prompt
Pulse rate
Marked bradycardia	The measured pulse rate is markedly bradycardic.
Bradycardia	The measured pulse rate is bradycardic.
Normal rate	The measured pulse rate is within the normal range.
Mild tachycardia	The measured pulse rate is mildly tachycardic.
Tachycardia	The measured pulse rate is tachycardic.

Appendix

Table 27: Representative zero-shot prompts. Verbatim examples from the segment template bank and the visit and event class descriptions, grouped by task.

Explore similar work

CAP: Towards PPG Universal Representation Learning with Patient-level Supervision
Jun 13, 2026Chenyang He, Xinyi Shao, Shun Huang +4Remote Photoplethysmography Medical World Model
Nanjing University of Aeronautics and Astronautics Nanjing, Jiangsu, China · Peking University Beijing, Beijing, China · Independent Researcher +1
A robust PPG foundation model using multimodal physiological supervision
Jun 5, 2026Eloy Geenjaar, Vince Calhoun, Scott Daly +4Remote Photoplethysmography Heart Rate
Department of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, USA · Tri-Institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS), Georgia State University, Georgia Institute of Technology, Emory University, Atlanta, USA · Dolby Laboratories, San Francisco, USA
PG-LRF: Physiology-Guided Latent Rectified Flow for Electro-Hemodynamic PPG-to-ECG Generation
May 9, 2026Xiaoda Wang, Minxiao Wang, Kaiqiao Han +10Cardiac Physiological Data
Department of Computer Science, Emory University · Department of Computer Science, University of California, Los Angeles · Nell Hodgson Woodruff School of Nursing, Emory University +2

Jun 13, 2026, eess.SPJ/K move · Enter open · S save

CAP: Towards PPG Universal Representation Learning with Patient-level Supervision

Chenyang He, Xinyi Shao, Shun Huang, Bosong Huang+3

Nanjing University of Aeronautics and Astronautics Nanjing, Jiangsu, China · Peking University Beijing, Beijing, China · Independent Researcher+1

Remote Photoplethysmography Medical World Model Patients Electronic Health Records Representation Learning Pretraining

Open paper AskPDF arXiv

Photoplethysmography (PPG) plays a central role in wearable health monitoring and clinical decision support. Yet existing approaches to universal PPG representation learning largely focus on signal-level objectives and often overlook patient-level health context, which limits generalization to complex clinical tasks and heterogeneous cohorts. To address this gap, we construct a large-scale paired PPG-EHR multimodal dataset by distilling fragmented medical histories and clinical records into cohesive, patient-level electronic health records (EHR). Building on this resource, we propose Clinical Anchored Pretraining for PPG (CAP). During pretraining, CAP performs cross-modal contrastive alignment that anchors PPG representations to patient-level clinical semantics, guiding the encoder beyond waveform fitting toward modeling consistency in a patient's overall physiological state. During downstream adaptation, the pretrained PPG encoder provides clinically grounded representations that strengthen inductive bias and improve robustness and transferability. Experiments demonstrate that CAP consistently outperforms strong baselines on four diverse downstream tasks. CAP achieves a particularly large gain on respiratory rate prediction (up to +87.6% relative improvement over the state-of-the-art baseline) and delivers an average relative +26.7% across all tasks. We further enhance the interpretability of our approach through comprehensive analyses, including ablations and multiple complementary visualizations of the learned representations. The code for our experiments is available at: https://github.com/gody123gody/CAP .

Abstract

Explore similar work

CAP: Towards PPG Universal Representation Learning with Patient-level Supervision

A robust PPG foundation model using multimodal physiological supervision

PG-LRF: Physiology-Guided Latent Rectified Flow for Electro-Hemodynamic PPG-to-ECG Generation