Results explorer

Name: ChatPPG wearable AI results
Creator: ChatPPG
License: https://creativecommons.org/licenses/by/4.0/

One row per reported result from wearable PPG, ECG, motion and sleep papers. Filter by task, dataset, metric, sensor and year, or show only SOTA rows. Each value links to its source: a paper table or figure, or the leaderboard row it came from.

Last updated Oct 27, 2026

433
reported results
224
with a table or figure reference
92
papers and models
134
task × dataset × metric pairs
38
benchmarks with a SOTA star

SOTA only

433 results

Reported results with task, dataset, metric, value and source
			Metric		Comparability	Sensor / site		Source	Links
PaPaGei-P Baseline in PaPaGei: Open Foundation Models for Optical Physiological Signals	Sleep-disordered breathing	SDB (Garde et al.)	AUROC	0.54↑	subject-level train/val/testwithin-datasetlinear probe on frozen embeddings	PPG	2024	Tables 3 and 4 (as reported) (opens in a new tab)
Moment Baseline in PaPaGei: Open Foundation Models for Optical Physiological Signals	Sleep-disordered breathing	SDB (Garde et al.)	AUROC	0.45↑	subject-level train/val/testwithin-datasetlinear probe on frozen embeddings	PPG	2024	Tables 3 and 4 (as reported) (opens in a new tab)
REGLE Baseline in PaPaGei: Open Foundation Models for Optical Physiological Signals	Sleep-disordered breathing	SDB (Garde et al.)	AUROC	0.45↑	subject-level train/val/testwithin-datasetlinear probe on frozen embeddings	PPG	2024	Tables 3 and 4 (as reported) (opens in a new tab)
Stat. features + RF Baseline in PaPaGei: Open Foundation Models for Optical Physiological Signals	Sleep-disordered breathing	SDB (Garde et al.)	AUROC	0.32↑	subject-level train/val/testwithin-datasetlinear probe on frozen embeddings	PPG	—	Tables 3 and 4 (as reported) (opens in a new tab)
BLP (HRV-conditioned LLM personalization) In Beyond Latent Personalization: Integrating HRV-Conditioned Personalization via LLM for Interpretable Stress Detection	Stress / affect	TILES-2018	MCC	0.261↑	subject-independent 5-fold cross-validationwithin-datasetHRV features + LLM-generated physiological interpretation	PPG	2026	Table 4 (opens in a new tab)	Code (opens in a new tab)
Pulse-PPG In Pulse-PPG: An Open-Source Field-Trained PPG Foundation Model for Wearable Applications Across Lab and Field Settings	Stress / affect	WESAD	AUROC	0.9687↑	subject-wisewithin-datasetlinear probe on frozen embeddingsstress vs non-stress (2-class)	PPG · wrist	2025	Table 6 (opens in a new tab)	Code (opens in a new tab)Leaderboard
SimCLR Baseline in AnyPPG: An ECG-Guided PPG Foundation Model Trained on Over 100,000 Hours of Recordings for Holistic Health Profiling	Stress / affect	WESAD	AUROC	0.77↑	as defined per dataset in the paperwithin-datasetlinear probe on frozen embeddingsemotion recognition	PPG · wrist	2020	Table 4 (as reported) (opens in a new tab)
MOMENT Baseline in Pulse-PPG: An Open-Source Field-Trained PPG Foundation Model for Wearable Applications Across Lab and Field Settings	Stress / affect	WESAD	AUROC	0.9583↑	subject-wisewithin-datasetlinear probe on frozen embeddingsstress vs non-stress (2-class)	PPG · wrist	2024	Table 6 (as reported) (opens in a new tab)
Quality-aware PPG+ACC model In Quality-Aware Wrist Photoplethysmography for Subject Independent Stress-State Monitoring: ECG-Referenced Validation and Selective Prediction	Stress / affect	WESAD	AUROC	0.9560↑	leave-one-subject-outwithin-datasetclassical machine learning on wrist PPG + accelerometer	PPG, ACC	2026	Abstract (Results) (opens in a new tab)
Chronos Baseline in Pulse-PPG: An Open-Source Field-Trained PPG Foundation Model for Wearable Applications Across Lab and Field Settings	Stress / affect	WESAD	AUROC	0.8878↑	subject-wisewithin-datasetlinear probe on frozen embeddingsstress vs non-stress (2-class)	PPG · wrist	2024	Table 6 (as reported) (opens in a new tab)
PaPaGei Baseline in Pulse-PPG: An Open-Source Field-Trained PPG Foundation Model for Wearable Applications Across Lab and Field Settings	Stress / affect	WESAD	AUROC	0.8043↑	subject-wisewithin-datasetlinear probe on frozen embeddingsstress vs non-stress (2-class)	PPG · wrist	2024	Table 6 (as reported) (opens in a new tab)	Code (opens in a new tab)
AnyPPG In AnyPPG: An ECG-Guided PPG Foundation Model Trained on Over 100,000 Hours of Recordings for Holistic Health Profiling	Stress / affect	WESAD	AUROC	0.76↑	as defined per dataset in the paperwithin-datasetlinear probe on frozen embeddingsemotion recognition	PPG · wrist	2025	Table 4 (opens in a new tab)	Code (opens in a new tab)
BYOL Baseline in AnyPPG: An ECG-Guided PPG Foundation Model Trained on Over 100,000 Hours of Recordings for Holistic Health Profiling	Stress / affect	WESAD	AUROC	0.74↑	as defined per dataset in the paperwithin-datasetlinear probe on frozen embeddingsemotion recognition	PPG · wrist	2020	Table 4 (as reported) (opens in a new tab)
Chronos-2 Baseline in AnyPPG: An ECG-Guided PPG Foundation Model Trained on Over 100,000 Hours of Recordings for Holistic Health Profiling	Stress / affect	WESAD	AUROC	0.74↑	as defined per dataset in the paperwithin-datasetlinear probe on frozen embeddingsemotion recognition	PPG · wrist	2025	Table 4 (as reported) (opens in a new tab)
PulsePPG Baseline in AnyPPG: An ECG-Guided PPG Foundation Model Trained on Over 100,000 Hours of Recordings for Holistic Health Profiling	Stress / affect	WESAD	AUROC	0.73↑	as defined per dataset in the paperwithin-datasetlinear probe on frozen embeddingsemotion recognition	PPG · wrist	2025	Table 4 (as reported) (opens in a new tab)	Code (opens in a new tab)
MOMENT Baseline in AnyPPG: An ECG-Guided PPG Foundation Model Trained on Over 100,000 Hours of Recordings for Holistic Health Profiling	Stress / affect	WESAD	AUROC	0.71↑	as defined per dataset in the paperwithin-datasetlinear probe on frozen embeddingsemotion recognition	PPG · wrist	2024	Table 4 (as reported) (opens in a new tab)
NormWear In NormWear: Toward Foundation Model for Multivariate Wearable Sensing of Physiological Signals	Stress / affect	WESAD	AUROC (%)	76.060%↑	held-out test setwithin-datasetlinear probe, full-shot	—	2024	Table 2 (opens in a new tab)	Hugging Face (opens in a new tab)
Cross-modal correlation fusion (ECG+PPG) In Cross-Modal Correlation Fusion for End-to-End ECG–PPG Stress Classification	Stress / affect	WESAD	AUROC (%)	97.29↑	subject-independent 5-fold cross-validationwithin-datasetdual ECG and PPG encoders with cross-modal fusion, end-to-end	ECG, PPG	2026	Abstract (Results) (opens in a new tab)
CLAP Baseline in NormWear: Toward Foundation Model for Multivariate Wearable Sensing of Physiological Signals	Stress / affect	WESAD	AUROC (%)	72.383%↑	held-out test setwithin-datasetlinear probe, full-shot	—	2023	Table 2 (as reported) (opens in a new tab)
Chronos Baseline in NormWear: Toward Foundation Model for Multivariate Wearable Sensing of Physiological Signals	Stress / affect	WESAD	AUROC (%)	71.489%↑	held-out test setwithin-datasetlinear probe, full-shot	—	2024	Table 2 (as reported) (opens in a new tab)
TF-C Baseline in NormWear: Toward Foundation Model for Multivariate Wearable Sensing of Physiological Signals	Stress / affect	WESAD	AUROC (%)	69.865%↑	held-out test setwithin-datasetlinear probe, full-shot	—	2022	Table 2 (as reported) (opens in a new tab)
Statistical Baseline in NormWear: Toward Foundation Model for Multivariate Wearable Sensing of Physiological Signals	Stress / affect	WESAD	AUROC (%)	66.213%↑	held-out test setwithin-datasetlinear probe, full-shot	—	—	Table 2 (as reported) (opens in a new tab)
Modality-specific baseline Baseline in NormWear: Toward Foundation Model for Multivariate Wearable Sensing of Physiological Signals	Stress / affect	WESAD	AUROC (%)	56.656%↑	held-out test setwithin-datasetlinear probe, full-shot	—	—	Table 2 (as reported) (opens in a new tab)
AnyPPG In PPG-Bench: A Unified Benchmark for PPG Foundation Models	Stress / affect	WESAD	Balanced accuracy	.543↑	subject-disjoint 5-fold CV, 5 seedswithin-datasetlinear probe on frozen embeddingsemotion classes	PPG · wrist	2026	Table 1 (opens in a new tab)	Code (opens in a new tab)
MOMENT Baseline in PPG-Bench: A Unified Benchmark for PPG Foundation Models	Stress / affect	WESAD	Balanced accuracy	.504↑	subject-disjoint 5-fold CV, 5 seedswithin-datasetlinear probe on frozen embeddingsemotion classes	PPG · wrist	2024	Table 1 (as reported) (opens in a new tab)
PulsePPG Baseline in PPG-Bench: A Unified Benchmark for PPG Foundation Models	Stress / affect	WESAD	Balanced accuracy	.474↑	subject-disjoint 5-fold CV, 5 seedswithin-datasetlinear probe on frozen embeddingsemotion classes	PPG · wrist	2025	Table 1 (as reported) (opens in a new tab)	Code (opens in a new tab)
SigmaPPG Baseline in PPG-Bench: A Unified Benchmark for PPG Foundation Models	Stress / affect	WESAD	Balanced accuracy	.456↑	subject-disjoint 5-fold CV, 5 seedswithin-datasetlinear probe on frozen embeddingsemotion classes	PPG · wrist	—	Table 1 (as reported) (opens in a new tab)
PaPaGei-S Baseline in PPG-Bench: A Unified Benchmark for PPG Foundation Models	Stress / affect	WESAD	Balanced accuracy	.396↑	subject-disjoint 5-fold CV, 5 seedswithin-datasetlinear probe on frozen embeddingsemotion classes	PPG · wrist	2024	Table 1 (as reported) (opens in a new tab)	Code (opens in a new tab)
AB-QGN (fused) In Trustworthy Stress Detection from Wearable Sensor Signals for Preventive Anxiety Monitoring: Subject-Independent Accuracy and Calibrated Confidence with the Autonomic-Branch Quantum-Graph Network	Stress / affect	WESAD	Macro F1 (%)	84.0↑	leave-one-subject-outwithin-datasetfused physiological model	PPG	2026	Abstract (Results) (opens in a new tab)
BLP (HRV-conditioned LLM personalization) In Beyond Latent Personalization: Integrating HRV-Conditioned Personalization via LLM for Interpretable Stress Detection	Stress / affect	WESAD	MCC	0.614↑	subject-independent 5-fold cross-validationwithin-datasetHRV features + LLM-generated physiological interpretationchest ECG-derived HRV	ECG	2026	Table 4 (opens in a new tab)	Code (opens in a new tab)
BLP Beyond Latent Personalization: Integrating HRV-Conditioned Personalization via LLM for Interpretable Stress Detection	Stress detection (acute / prolonged / affect)	TILES-2018	Accuracy	0.631↑	subject-disjointbinary daily stress (label construction per paper ref [7])	PPG, IMU, ECG	2026	Leaderboard row	Code (opens in a new tab)Leaderboard
A cross-subject stress recognition method integr A cross-subject stress recognition method integrating bidirectional cross-modal multi-path fusion and adaptive adversarial learning (WESAD; in Chinese)	Stress detection (acute / prolonged / affect)	WESAD	Accuracy	0.9158↑	subject-disjoint	PPG, ECG, IMU, TEMP, EDA, RESP · wrist, chest	2026	Leaderboard row	Leaderboard
BLP Beyond Latent Personalization: Integrating HRV-Conditioned Personalization via LLM for Interpretable Stress Detection	Stress detection (acute / prolonged / affect)	WESAD	Accuracy	0.823↑	subject-disjointbinary (baseline+amusement vs stress)	ECG · chest	2026	Leaderboard row	Code (opens in a new tab)Leaderboard

PaPaGei-P

Baseline in PaPaGei: Open Foundation Models for Optical Physiological Signals

0.54↑

Sleep-disordered breathing · SDB (Garde et al.) · AUROC

subject-level train/val/testwithin-datasetlinear probe on frozen embeddings

Tables 3 and 4 (as reported)

2024

Moment

Baseline in PaPaGei: Open Foundation Models for Optical Physiological Signals

0.45↑

Sleep-disordered breathing · SDB (Garde et al.) · AUROC

subject-level train/val/testwithin-datasetlinear probe on frozen embeddings

Tables 3 and 4 (as reported)

2024

REGLE

Baseline in PaPaGei: Open Foundation Models for Optical Physiological Signals

0.45↑

Sleep-disordered breathing · SDB (Garde et al.) · AUROC

subject-level train/val/testwithin-datasetlinear probe on frozen embeddings

Tables 3 and 4 (as reported)

2024

Stat. features + RF

Baseline in PaPaGei: Open Foundation Models for Optical Physiological Signals

0.32↑

Sleep-disordered breathing · SDB (Garde et al.) · AUROC

subject-level train/val/testwithin-datasetlinear probe on frozen embeddings

Tables 3 and 4 (as reported)

BLP (HRV-conditioned LLM personalization)

In Beyond Latent Personalization: Integrating HRV-Conditioned Personalization via LLM for Interpretable Stress Detection

0.261↑

Stress / affect · TILES-2018 · MCC

subject-independent 5-fold cross-validationwithin-datasetHRV features + LLM-generated physiological interpretation

Table 4

2026

Pulse-PPG

In Pulse-PPG: An Open-Source Field-Trained PPG Foundation Model for Wearable Applications Across Lab and Field Settings

0.9687↑

Stress / affect · WESAD · AUROC

subject-wisewithin-datasetlinear probe on frozen embeddingsstress vs non-stress (2-class)

Table 6

2025

SimCLR

Baseline in AnyPPG: An ECG-Guided PPG Foundation Model Trained on Over 100,000 Hours of Recordings for Holistic Health Profiling

0.77↑

Stress / affect · WESAD · AUROC

as defined per dataset in the paperwithin-datasetlinear probe on frozen embeddingsemotion recognition

Table 4 (as reported)

2020

MOMENT

Baseline in Pulse-PPG: An Open-Source Field-Trained PPG Foundation Model for Wearable Applications Across Lab and Field Settings

0.9583↑

Stress / affect · WESAD · AUROC

subject-wisewithin-datasetlinear probe on frozen embeddingsstress vs non-stress (2-class)

Table 6 (as reported)

2024

Quality-aware PPG+ACC model

In Quality-Aware Wrist Photoplethysmography for Subject Independent Stress-State Monitoring: ECG-Referenced Validation and Selective Prediction

0.9560↑

Stress / affect · WESAD · AUROC

leave-one-subject-outwithin-datasetclassical machine learning on wrist PPG + accelerometer

Abstract (Results)

2026

Chronos

Baseline in Pulse-PPG: An Open-Source Field-Trained PPG Foundation Model for Wearable Applications Across Lab and Field Settings

0.8878↑

Stress / affect · WESAD · AUROC

subject-wisewithin-datasetlinear probe on frozen embeddingsstress vs non-stress (2-class)

Table 6 (as reported)

2024

PaPaGei

Baseline in Pulse-PPG: An Open-Source Field-Trained PPG Foundation Model for Wearable Applications Across Lab and Field Settings

0.8043↑

Stress / affect · WESAD · AUROC

subject-wisewithin-datasetlinear probe on frozen embeddingsstress vs non-stress (2-class)

Table 6 (as reported)

2024

AnyPPG

In AnyPPG: An ECG-Guided PPG Foundation Model Trained on Over 100,000 Hours of Recordings for Holistic Health Profiling

0.76↑

Stress / affect · WESAD · AUROC

as defined per dataset in the paperwithin-datasetlinear probe on frozen embeddingsemotion recognition

Table 4

2025

BYOL

Baseline in AnyPPG: An ECG-Guided PPG Foundation Model Trained on Over 100,000 Hours of Recordings for Holistic Health Profiling

0.74↑

Stress / affect · WESAD · AUROC

as defined per dataset in the paperwithin-datasetlinear probe on frozen embeddingsemotion recognition

Table 4 (as reported)

2020

Chronos-2

Baseline in AnyPPG: An ECG-Guided PPG Foundation Model Trained on Over 100,000 Hours of Recordings for Holistic Health Profiling

0.74↑

Stress / affect · WESAD · AUROC

as defined per dataset in the paperwithin-datasetlinear probe on frozen embeddingsemotion recognition

Table 4 (as reported)

2025

PulsePPG

Baseline in AnyPPG: An ECG-Guided PPG Foundation Model Trained on Over 100,000 Hours of Recordings for Holistic Health Profiling

0.73↑

Stress / affect · WESAD · AUROC

as defined per dataset in the paperwithin-datasetlinear probe on frozen embeddingsemotion recognition

Table 4 (as reported)

2025

MOMENT

Baseline in AnyPPG: An ECG-Guided PPG Foundation Model Trained on Over 100,000 Hours of Recordings for Holistic Health Profiling

0.71↑

Stress / affect · WESAD · AUROC

as defined per dataset in the paperwithin-datasetlinear probe on frozen embeddingsemotion recognition

Table 4 (as reported)

2024

NormWear

In NormWear: Toward Foundation Model for Multivariate Wearable Sensing of Physiological Signals

76.060%↑

Stress / affect · WESAD · AUROC (%)

held-out test setwithin-datasetlinear probe, full-shot

Table 2

2024

Cross-modal correlation fusion (ECG+PPG)

In Cross-Modal Correlation Fusion for End-to-End ECG–PPG Stress Classification

97.29↑

Stress / affect · WESAD · AUROC (%)

subject-independent 5-fold cross-validationwithin-datasetdual ECG and PPG encoders with cross-modal fusion, end-to-end

Abstract (Results)

2026

CLAP

Baseline in NormWear: Toward Foundation Model for Multivariate Wearable Sensing of Physiological Signals

72.383%↑

Stress / affect · WESAD · AUROC (%)

held-out test setwithin-datasetlinear probe, full-shot

Table 2 (as reported)

2023

Chronos

Baseline in NormWear: Toward Foundation Model for Multivariate Wearable Sensing of Physiological Signals

71.489%↑

Stress / affect · WESAD · AUROC (%)

held-out test setwithin-datasetlinear probe, full-shot

Table 2 (as reported)

2024

TF-C

Baseline in NormWear: Toward Foundation Model for Multivariate Wearable Sensing of Physiological Signals

69.865%↑

Stress / affect · WESAD · AUROC (%)

held-out test setwithin-datasetlinear probe, full-shot

Table 2 (as reported)

2022

Statistical

Baseline in NormWear: Toward Foundation Model for Multivariate Wearable Sensing of Physiological Signals

66.213%↑

Stress / affect · WESAD · AUROC (%)

held-out test setwithin-datasetlinear probe, full-shot

Table 2 (as reported)

Modality-specific baseline

Baseline in NormWear: Toward Foundation Model for Multivariate Wearable Sensing of Physiological Signals

56.656%↑

Stress / affect · WESAD · AUROC (%)

held-out test setwithin-datasetlinear probe, full-shot

Table 2 (as reported)

AnyPPG

In PPG-Bench: A Unified Benchmark for PPG Foundation Models

.543↑

Stress / affect · WESAD · Balanced accuracy

subject-disjoint 5-fold CV, 5 seedswithin-datasetlinear probe on frozen embeddingsemotion classes

Table 1

2026

MOMENT

Baseline in PPG-Bench: A Unified Benchmark for PPG Foundation Models

.504↑

Stress / affect · WESAD · Balanced accuracy

subject-disjoint 5-fold CV, 5 seedswithin-datasetlinear probe on frozen embeddingsemotion classes

Table 1 (as reported)

2024

PulsePPG

Baseline in PPG-Bench: A Unified Benchmark for PPG Foundation Models

.474↑

Stress / affect · WESAD · Balanced accuracy

subject-disjoint 5-fold CV, 5 seedswithin-datasetlinear probe on frozen embeddingsemotion classes

Table 1 (as reported)

2025

SigmaPPG

Baseline in PPG-Bench: A Unified Benchmark for PPG Foundation Models

.456↑

Stress / affect · WESAD · Balanced accuracy

subject-disjoint 5-fold CV, 5 seedswithin-datasetlinear probe on frozen embeddingsemotion classes

Table 1 (as reported)

PaPaGei-S

Baseline in PPG-Bench: A Unified Benchmark for PPG Foundation Models

.396↑

Stress / affect · WESAD · Balanced accuracy

subject-disjoint 5-fold CV, 5 seedswithin-datasetlinear probe on frozen embeddingsemotion classes

Table 1 (as reported)

2024

AB-QGN (fused)

In Trustworthy Stress Detection from Wearable Sensor Signals for Preventive Anxiety Monitoring: Subject-Independent Accuracy and Calibrated Confidence with the Autonomic-Branch Quantum-Graph Network

84.0↑

Stress / affect · WESAD · Macro F1 (%)

leave-one-subject-outwithin-datasetfused physiological model

Abstract (Results)

2026

BLP (HRV-conditioned LLM personalization)

In Beyond Latent Personalization: Integrating HRV-Conditioned Personalization via LLM for Interpretable Stress Detection

0.614↑

Stress / affect · WESAD · MCC

subject-independent 5-fold cross-validationwithin-datasetHRV features + LLM-generated physiological interpretationchest ECG-derived HRV

Table 4

2026

BLP

Beyond Latent Personalization: Integrating HRV-Conditioned Personalization via LLM for Interpretable Stress Detection

0.631↑

Stress detection (acute / prolonged / affect) · TILES-2018 · Accuracy

subject-disjointbinary daily stress (label construction per paper ref [7])

Leaderboard row

2026

A cross-subject stress recognition method integr

A cross-subject stress recognition method integrating bidirectional cross-modal multi-path fusion and adaptive adversarial learning (WESAD; in Chinese)

0.9158↑

Stress detection (acute / prolonged / affect) · WESAD · Accuracy

subject-disjoint

Leaderboard row

2026

BLP

Beyond Latent Personalization: Integrating HRV-Conditioned Personalization via LLM for Interpretable Stress Detection

0.823↑

Stress detection (acute / prolonged / affect) · WESAD · Accuracy

subject-disjointbinary (baseline+amusement vs stress)

Leaderboard row

2026

Showing 401–433 of 433 results

Recent changes

Oct 27, 2026
New entry: A cross-subject stress recognition method…, 0.9158
Stress detection (acute / prolonged / affect): WESAD: accuracy
Oct 27, 2026
New entry: SPAFT, 5.066
Heart rate estimation: PPG-DaLiA: MAE (BPM)
Oct 27, 2026
New entry: SPAFT, 8.345
Cuffless blood pressure estimation: uci-bp: MAE (mmHg)
Oct 25, 2026
Leaderboard added with 1 result
Cuffless blood pressure estimation: neo-bp: MAE (mmHg)
Oct 23, 2026
New entry: PC-AVCT wearable-state model, 7.697
Cuffless blood pressure estimation: aurora-bp: MAE (mmHg)
Oct 23, 2026
New entry: PPG-FusionNet, 7.46
Cuffless blood pressure estimation: pulsedb-calbased: MAE (mmHg)

From the hub's dated sync history: new results as they are added, and SOTA stars as they are awarded or move.

How SOTA is decided

marks the best value for one task, dataset and metric, using the metric's direction (higher or lower is better).
Results are compared only under the same evaluation protocol: split type, within- or cross-dataset testing, filtering, inputs and label set. Different protocols stay separate and are never ranked together.
Only results with a table, figure or section reference compete, and a star needs at least two competing methods. Ties go to the earlier publication.
Stars are recomputed whenever the research hub syncs, and every change is logged.

Downloads of every result (JSON and CSV) are free for members. Sign in to download.

Results as reported by the authors; not independently reproduced. Leaderboard rows without a structured protocol are listed but don't receive stars. See also the leaderboards.

Cite or reuse this

CC BY 4.0ChatPPG compiled this data. You can copy, adapt and republish it, including in articles, slides, papers and AI tools, as long as you credit ChatPPG and link to this page. Please also cite the original studies for any number you use.

Attribution

Source: ChatPPG, Wearable AI results explorer, https://chatppg.com/research/results (CC BY 4.0)

HTML link

Source: <a href="https://chatppg.com/research/results">ChatPPG, Wearable AI results explorer</a> (<a href="https://creativecommons.org/licenses/by/4.0/" rel="license">CC BY 4.0</a>)