Lab Edition API

#Lab version API

The laboratory version provides the core capabilities of ECGFounder, text generation to single lead, single lead to twelve leads, three leads to twelve leads, PPG signal generation to single lead, and single lead generation of cardiac ultrasound.

Notes

🔬 Welcome to the Lab API! All interfaces are currently in the public beta stage, and functions may be adjusted from time to time. To ensure normal access and data security, please enter the Scientific Research Cooperation Page and contact the staff to obtain the exclusive access key. 💡 Warm reminder: Please keep your key properly to avoid leakage or abuse.

Applicable scenarios

Medical research
ECG model verification

MCMA interface

POST /api/v1/experimental/mcma

Twelve-lead signals can be generated by inputting a single-lead signal.

Request parameters

Parameters	Type	Required	Description
ecgData	array	✅	ECG signal data array (ADC value)
ecgSamplerate	number	✅	Sampling rate, unit Hz (recommended 250-500)
original	boolean	❌	Whether to output the original waveform, default true

Request example

curl -X POST "https://api.heartvoice.com.cn/api/v1/experimental/mcma" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "ecgData": [512, 515, 520, 518, 525, ...],
    "ecgSampleRate": 500
  }'

Response example

{
  "errorCode": "0",
"msg": "success",
  "data": [
    [
      -0.0005600000149570405,
      0.05680999904870987,
      -0.002580000087618828,
      0.02824000082910061,
      ...
      ]
    ]
}

Visual display

import ecg_plot
ecg_plot.plot(gen_ecg12, sample_rate=fs, title='ECG 12')
ecg_plot.show()

Literature

@article{chen2024multi,
  title={Multi-channel masked autoencoder and comprehensive evaluations for reconstructing 12-lead ECG from arbitrary single-lead ECG},
  author={Chen, Jiarong and Wu, Wanqing and Liu, Tong and Hong, Shenda},
  journal={npj Cardiovascular Health},
  volume={1},
  number={1},
  pages={34},
  year={2024},
  publisher={Nature Publishing Group UK London}
}

Chen, J., Wu, W., Liu, T., & Hong, S. (2024). Multi-channel masked autoencoder and comprehensive evaluations for reconstructing 12-lead ECG from arbitrary single-lead ECG. npj Cardiovascular Health, 1(1), 34.

DiffuSETS interface

POST /api/v1/experimental/diffuSets

Twelve-lead signals can be generated by inputting a single-lead signal.

Request parameters

Parameters	Type	Required	Description
text	str	✅	Clinical diagnosis text, multiple diagnoses need to be separated by '\|'
age	int	✅	age
sex	str	✅	sex
hr	int	✅	heart rate
batch	int	❌	Select the number of ECGs to generate

Request example

curl -X POST "https://api.heartvoice.com.cn/api/v1/experimental/diffuSets" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": 'Sinus rhythm|Normal ECG.',  # Clinical text report, multi-reports should be split by '|'
    "age": 50,  # Age of patient
    "sex": 'M',
    "hr": 80,
    'batch': 1
  }'

Response example

{
  "errorCode": "0",
"msg": "success",
  "data": {
    "textImg": "[\"iVBORw0KGgoAAAANSUhI=...\"]"
  }
}

Visual display

import time
import requests
import json
import base64
import io
from PIL import Image

def base64_to_image(base64_str):
# Decode Base64 string
    image_data = base64.b64decode(base64_str)
# Use io.BytesIO to convert the decoded data into a file object
    image_file = io.BytesIO(image_data)
# Open the image using PIL
    image = Image.open(image_file)
    return image

ecg_img = base64_to_image(ecg_data)
ecg_img.show()  

Literature

@article{lai2025diffusets,
  title={DiffuSETS: 12-Lead ECG generation conditioned on clinical text reports and patient-specific information},
  author={Lai, Yongfan and Chen, Jiabo and Zhao, Qinghao and Zhang, Deyun and Wang, Yue and Geng, Shijia and Li, Hongyan and Hong, Shenda},
  journal={Patterns},
  year={2025},
  publisher={Elsevier}
}

Lai, Y., Chen, J., Zhao, Q., Zhang, D., Wang, Y., Geng, S., ... & Hong, S. (2025). DiffuSETS: 12-Lead ECG generation conditioned on clinical text reports and patient-specific information. Patterns.

WearECG interface

POST /api/v1/experimental/lead3Lead12

Twelve-lead signals can be generated by inputting a single-lead signal.

Request parameters

Parameters	Type	Required	Description
ecgData	array	✅	ECG signal data array (ADC value)
ecgSampleRate	number	✅	Sampling rate, unit Hz (recommended 250-500)

Request example

curl -X POST "https://api.heartvoice.com.cn/api/v1/experimental/lead3Lead12" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "ecgData": [[512, 515, 520, 518, 525, ...],[512, 515, 520, 518, 525, ...],[512, 515, 520, 518, 525, ...]],
    "ecgSampleRate": 500
  }'

Response example

{
  "errorCode": "0",
"msg": "success",
  "data": [
    [
      -0.0025084596127271652,
      0.0118071788037084,
      0.014166647854523678,
      ...
      ]
    ]
}

Visual display

import ecg_plot
ecg_plot.plot(gen_ecg12, sample_rate=fs, title='ECG 12')
ecg_plot.show()

PPGFlowECG interface

POST /api/v1/experimental/ppgFlowEcg

Twelve-lead signals can be generated by inputting a single-lead signal.

Request parameters

Parameters	Type	Required	Description
ppgData	array	✅	PPG signal data array. Upload red light, green light or infrared light data
ppgSampleRate	number	✅	Sampling rate in Hz (recommended 250-500)

Request example

curl -X POST "https://api.heartvoice.com.cn/api/v1/experimental/ppgFlowEcg" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "ppgData": [512, 515, 520, 518, 525, ...],
    "ecgSampleRate": 500
  }'

Response example

{
  "errorCode": "0",
"msg": "success",
  "data": [
    [
      -0.0005600000149570405,
      0.05680999904870987,
      -0.002580000087618828,
      0.02824000082910061,
      ...
      ]
    ]
}

Visual display

Literature

@article{fang2025ppgflowecg,
  title={PPGFlowECG: Latent Rectified Flow with Cross-Modal Encoding for PPG-Guided ECG Generation and Cardiovascular Disease Detection},
  author={Fang, Xiaocheng and Jin, Jiarui and Wang, Haoyu and Liu, Che and Cai, Jieyi and Nie, Guangkun and Li, Jun and Li, Hongyan and Hong, Shenda},
  journal={arXiv preprint arXiv:2509.19774},
  year={2025}
}

Fang, X., Jin, J., Wang, H., Liu, C., Cai, J., Nie, G., ... & Hong, S. (2025). PPGFlowECG: Latent Rectified Flow with Cross-Modal Encoding for PPG-Guided ECG Generation and Cardiovascular Disease Detection. arXiv preprint arXiv:2509.19774.

ECHOPulse interface

POST /api/v1/experimental/ecgEcho

Twelve-lead signals can be generated by inputting a single-lead signal.

Request parameters

Parameters	Type	Required	Description
ecgData	array	✅	ECG signal data array (ADC value)
ecgSampleRate	number	✅	Sampling rate, unit Hz (recommended 250-500)

Request example

curl -X POST "https://api.heartvoice.com.cn/api/v1/experimental/ecgEcho" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "ecgData": [512, 515, 520, 518, 525, ...],
    "ecgSampleRate": 500
  }'

Response example

{
  "errorCode": "0",
"msg": "success",
  "data": {
    "ecgEcho": [
      [
        [
          [
            [
              0.0013988255523145199,
              0.004246973432600498,
              0.0010940954089164734,
              0.004930938594043255,
              -0.0024434151127934456,
              0.00477356743067503,
              ...
            ]
          ]
        ]
      ]
    ]
  }
}

Visual display

Save ECHO video frames

def save_video_and_plot_frames(video_tensor, save_dir='output'):
    os.makedirs(save_dir, exist_ok=True)
T = video_tensor.shape[2] # Time dimension
    fig, axes = plt.subplots(1, T, figsize=(T * 3, 3))

    for t in range(T):
# Take out the tth frame
        frame = video_tensor[0, :, t, :, :]  # [C, H, W]

# Convert to [H, W, C] numpy
        frame_np = frame.permute(1, 2, 0).cpu().numpy()

# Normalize to [0,1] to avoid imshow clipping
        frame_min, frame_max = frame_np.min(), frame_np.max()
        if frame_max > frame_min:
            frame_np = (frame_np - frame_min) / (frame_max - frame_min)
        else:
frame_np = np.zeros_like(frame_np) # Prevent division by zero

        ax = axes[t]
        ax.imshow(frame_np)
        ax.set_title(f'Frame {t}')
        ax.axis('off')

    for i in range(T, len(axes)):
        axes[i].axis('off')

    plt.tight_layout()
    plt.savefig(os.path.join(save_dir, 'echo_frames.png'))
    plt.show()
    plt.close()

    print(f"All frames plotted in {save_dir}")

Save the result as gif

def video_tensor_to_gif_with_ecg(video_tensor, ecg_data, output_path, title, duration=125, fps=8):
# Convert video content into numpy array
    video_np = np.array(video_tensor)
    video_np = np.squeeze(video_np, axis=0)
# Change dimension order (C, T, H, W) -> (T, H, W, C)
    video_np = np.transpose(video_np, (1, 2, 3, 0))

# EKG data preparation (reduced dimensions)
    ecg = np.array(ecg_data)
    ecg = ecg[0, 1, :]  # Assuming this is the correct dimension for EKG data

# Confirm frame number
    num_frames = 11
# EKG data is resampled based on frame number
    x_original = np.linspace(0, 1, len(ecg))
    x_resampled = np.linspace(0, 1, num_frames)
    ecg_resampled = np.interp(x_resampled, x_original, ecg)

# Set canvas
    fig, (ax1, ax2) = plt.subplots(2, 1, figsize=(8, 10), gridspec_kw={'height_ratios': [3, 1]})

# Set initialization image
    im = ax1.imshow(np.zeros((128, 128, 3)), animated=True)
    ax1.set_title(title)
    line, = ax2.plot([], [], 'r-')

    ax1.axis('off')
    ax2.set_xlim(0, num_frames)
    ax2.set_ylim(ecg_resampled.min(), ecg_resampled.max())
    ax2.set_xlabel('Frame')
    ax2.set_ylabel('EKG')
    ax2.set_title('Lead I EKG')

    def update(frame):
        im.set_array(video_np[frame])
        line.set_data(range(frame + 1), ecg_resampled[:frame + 1])
        return im, line

    num_frames = video_np.shape[0]
    anim = FuncAnimation(fig, update, frames=num_frames, interval=duration, blit=True)

    anim.save(output_path, writer='pillow', fps=fps)
    plt.close(fig)

    print(f"GIF saved to {output_path}")

Visual display

Generated ECHO frames (call save_video_and_plot_frames)

Convert to gif (call video_tensor_to_gif_with_ecg)

Literature

@article{li2024echopulse,
  title={Echopulse: Ecg controlled echocardio-grams video generation},
  author={Li, Yiwei and Kim, Sekeun and Wu, Zihao and Jiang, Hanqi and Pan, Yi and Jin, Pengfei and Song, Sifan and Shi, Yucheng and Liu, Tianming and Li, Quanzheng and others},
  journal={arXiv preprint arXiv:2410.03143},
  year={2024}
}

Li, Y., Kim, S., Wu, Z., Jiang, H., Pan, Y., Jin, P., ... & Li, X. (2024). Echopulse: Ecg controlled echocardio-grams video generation. arXiv preprint arXiv:2410.03143.

ECGTwins interface

POST /api/v1/experimental/ecgTwins

Twelve-lead signals can be generated by inputting a single-lead signal.

Request parameters

Parameters	Type	Required	Description
reference_file	file	✅	Reference file, currently fixed Example file
text	str	✅	Clinical diagnosis text, multiple diagnoses need to be separated by '\|'
age	int	✅	age
sex	str	✅	sex
hr	int	✅	heart rate
batch	int	❌	Select the number of ECGs to generate

Request example

curl -X POST "https://api.heartvoice.com.cn/api/v1/experimental/diffuSets" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -F "file=@normal_1-66b62bfc8acabc11cf5cc34cafe860f4.pt"
  -d '{
    "text": 'Sinus rhythm|Normal ECG.',  # Clinical text report, multi-reports should be split by '|'
    "age": 50,  # Age of patient
    "sex": 'M',
    "hr": 80,
    'batch': 1
  }'

Response example

{
  "errorCode": "0",
"msg": "success",
  "data": {
    "ECGTwin_imgs": [
        [
          0.0013988255523145199,
          0.004246973432600498,
          0.0010940954089164734,
          0.004930938594043255,
          -0.0024434151127934456,
          0.00477356743067503,
          ...
        ]
    ]
  }
}

Visual display

import requests
import json
import base64
import io
from PIL import Image

def base64_to_image(base64_str):
# Decode Base64 string
    image_data = base64.b64decode(base64_str)
# Use io.BytesIO to convert the decoded data into a file object
    image_file = io.BytesIO(image_data)
# Open the image using PIL
    image = Image.open(image_file)
    return image

ecg_img = base64_to_image(ecg_data)
ecg_img.show()
    

Literature

@article{lai2025ecgtwin,
  title={ECGTwin: Personalized ECG Generation Using Controllable Diffusion Model},
  author={Lai, Yongfan and Liu, Bo and Guan, Xinyan and Zhao, Qinghao and Li, Hongyan and Hong, Shenda},
  journal={arXiv preprint arXiv:2508.02720},
  year={2025}
}

Lai, Y., Liu, B., Guan, X., Zhao, Q., Li, H., & Hong, S. (2025). ECGTwin: Personalized ECG Generation Using Controllable Diffusion Model. arXiv preprint arXiv:2508.02720.

ECGFounder interface

POST /api/v1/experimental/ecgFounder

Twelve-lead signals can be generated by inputting a single-lead signal.

Request parameters

Parameters	Type	Required	Description
ecgData	array	✅	ECG signal data array (ADC value)
ecgSampleRate	number	✅	Sampling rate, unit Hz (recommended 250-500)

Request example

curl -X POST "https://api.heartvoice.com.cn/api/v1/experimental/ecgFounder" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "ecgData": [512, 515, 520, 518, 525, ...],
    "ecgSampleRate": 500
  }'

Response example

{
  "errorCode": "0",
"msg": "success",
  "data": {
    "otherwise_normal_ecg": null,
    "rsr_OR_QR_PATTERN_IN_V1_SUGGESTS_RIGHT_VENTRICULAR_CONDUCTION_DELAY": null,
    "nonspecific_T_WAVE_ABNORMALITY_HAS_REPLACED_INVERTED_T_WAVES_IN": null,
    "inverted_T_WAVES_HAVE_REPLACED_NON_SPECIFIC_T_WAVE_ABNORMALITY_IN": null,
    "voltage_CRITERIA_FOR_LEFT_VENTRICULAR_HYPERTROPHY": null,
    "bifascicular_BLOCK": null,
    ...
  }
}

Chinese and English

English label	Chinese translation
ABNORMAL ECG	Abnormal electrocardiogram
NORMAL SINUS RHYTHM	Normal sinus rhythm
NORMAL ECG	Normal electrocardiogram
SINUS RHYTHM	Sinus rhythm
SINUS BRADYCARDIA	Sinus bradycardia
ATRIAL FIBRILLATION	Atrial fibrillation
SINUS TACHYCARDIA	Sinus tachycardia
otherwise normal ecg	otherwise normal electrocardiogram
LEFT AXIS DEVIATION	Left axis offset
PREMATURE VENTRICULAR COMPLEXES	Premature ventricular contractions
BORDERLINE ECG	Borderline ECG
RIGHT BUNDLE BRANCH BLOCK	Right bundle branch block
SEPTAL INFARCT	Ventricular septal infarction
LEFT ATRIAL ENLARGEMENT	Left atrial enlargement
NONSPECIFIC T WAVE ABNORMALITY	Nonspecific T wave abnormality
LOW VOLTAGE QRS	Low voltage QRS complex
PREMATURE ATRIAL COMPLEXES	Premature atrial contractions
ANTERIOR INFARCT	Anterior wall infarction
INCOMPLETE RIGHT BUNDLE BRANCH BLOCK	INCOMPLETE RIGHT BUNDLE BRANCH BLOCK
PREMATURE SUPRAVENTRICULAR COMPLEXES	Premature superior ventricular contractions
LEFT BUNDLE BRANCH BLOCK	LEFT BUNDLE BRANCH BLOCK
NONSPECIFIC T WAVE ABNORMALITY NOW EVIDENT IN	Current non-specific T wave abnormality
NONSPECIFIC T WAVE ABNORMALITY NO LONGER EVIDENT IN	The nonspecific T wave abnormality has disappeared
T WAVE INVERSION NOW EVIDENT IN	T wave inversion is currently occurring
LATERAL INFARCT	Lateral infarction
NONSPECIFIC ST ABNORMALITY	Nonspecific ST segment abnormality
LEFT VENTRICULAR HYPERTROPHY	Left ventricular hypertrophy
T WAVE INVERSION NO LONGER EVIDENT IN	T WAVE INVERSION NO LONGER EVIDENT IN
WITH RAPID VENTRICULAR RESPONSE	WITH RAPID VENTRICULAR RESPONSE
QT HAS SHORTENED	QT interval shortened
QT HAS LENGTHENED	QT interval prolongation
FUSION COMPLEXES	Fusion Wave
ATRIAL FLUTTER	Atrial flutter
MARKED SINUS BRADYCARDIA	Marked sinus bradycardia
WITH SINUS ARRHYTHMIA	WITH SINUS ARRAYTHMIA
NONSPECIFIC ST AND T WAVE ABNORMALITY	Nonspecific ST-T wave abnormalities
LEFT ANTERIOR FASCICULAR BLOCK	LEFT ANTERIOR FASCICULAR BLOCK
RIGHT AXIS DEVIATION	Right axis offset
ECTOPIC ATRIAL RHYTHM	Ectopic Atrial Rhythm
UNDETERMINED RHYTHM	UNDETERMINED RHYTHM
ANTEROSEPTAL INFARCT	Anteroseptal infarction
RIGHTWARD AXIS	Right eccentric axis
ST NOW DEPRESSED IN	ST segment depression is currently occurring
WITH SHORT PR	With short PR interval
WITH MARKED SINUS ARRHYTHMIA	With significant sinus arrhythmia
ST NO LONGER DEPRESSED IN	ST segment depression has disappeared
INVERTED T WAVES HAVE REPLACED NONSPECIFIC T WAVE ABNORMALITY IN	T wave inversion replaces nonspecific T wave abnormalities
NON-SPECIFIC CHANGE IN ST SEGMENT IN	ST segment non-specific changes
NONSPECIFIC T WAVE ABNORMALITY HAS REPLACED INVERTED T WAVES IN	Nonspecific T wave abnormalities replacing inverted T waves
JUNCTIONAL RHYTHM	Junctional Rhythm
ELECTRONIC ATRIAL PACEMAKER	Electronic Atrial Pacemaker
ABERRANT CONDUCTION	Abnormal conduction
ELECTRONIC VENTRICULAR PACEMAKER	Electronic ventricular pacemaker
T WAVE INVERSION LESS EVIDENT IN	T wave inversion relief
ANTEROLATERAL INFARCT	Anterolateral infarction
WITH REPOLARIZATION ABNORMALITY	WITH REPOLARIZATION ABNORMALITY
RSR' OR QR PATTERN IN V1 SUGGESTS RIGHT VENTRICULAR CONDUCTION DELAY	RSR' or QR waveform in lead V1 suggests right ventricular conduction delay
T WAVE INVERSION MORE EVIDENT IN	T wave inversion more obvious
WIDE QRS RHYTHM	Wide QRS complex rhythm
WITH PREMATURE VENTRICULAR OR ABERRANTLY CONDUCTED COMPLEXES	With premature ventricular contractions or abnormal conduction complexes
RIGHT ATRIAL ENLARGEMENT	Right atrial enlargement
INFERIOR INFARCT	Inferior wall infarction
INCOMPLETE LEFT BUNDLE BRANCH BLOCK	INCOMPLETE LEFT BUNDLE BRANCH BLOCK
VOLTAGE CRITERIA FOR LEFT VENTRICULAR HYPERTROPHY	Voltage criteria for left ventricular hypertrophy
OR DIGITALIS EFFECT	OR DIGITALIS EFFECT
BIFASCICULAR BLOCK	Bifascicular block
ST NO LONGER ELEVATED IN	ST segment elevation has disappeared
WITH SLOW VENTRICULAR RESPONSE	WITH SLOW VENTRICULAR RESPONSE
ST ELEVATION NOW PRESENT IN	ST segment elevation is currently occurring
PREMATURE ECTOPIC COMPLEXES	Early ectopic complexes
LEFT POSTERIOR FASCICULAR BLOCK	LEFT POSTERIOR FASCICULAR BLOCK
T WAVE AMPLITUDE HAS DECREASED IN	T wave amplitude reduced
WITH A COMPETING JUNCTIONAL PACEMAKER	WITH COMPETING JUNCTIONAL PACEMAKER
RIGHT SUPERIOR AXIS DEVIATION	Upper right axis offset
BIATRIAL ENLARGEMENT	Biatrial enlargement
VENTRICULAR-PACED RHYTHM	Ventricular-paced rhythm
ATRIAL-PACED RHYTHM	Atrial-paced rhythm
T WAVE AMPLITUDE HAS INCREASED IN	T wave amplitude increased
WITH QRS WIDENING	With QRS complex widening
WITH 1ST DEGREE AV BLOCK	WITH 1ST DEGREE AV BLOCK
PROLONGED QT	QT interval prolongation
WITH PROLONGED AV CONDUCTION	WITH AV CONDUCTION DELAY
RIGHT VENTRICULAR HYPERTROPHY	Right ventricular hypertrophy
WITH QRS WIDENING AND REPOLARIZATION ABNORMALITY	With QRS complex widening and repolarization abnormalities
ATRIAL-SENSED VENTRICULAR-PACED RHYTHM	ATRIAL-SENSED VENTRICULAR-PACED RHYTHM
AV SEQUENTIAL OR DUAL CHAMBER ELECTRONIC PACEMAKER	AV SEQUENTIAL OR DUAL CHAMBER ELECTRONIC PACEMAKER
PULMONARY DISEASE PATTERN	Pulmonary electrocardiogram
ACUTE MI / STEMI	Acute myocardial infarction / ST-segment elevation myocardial infarction
INFERIOR-POSTERIOR INFARCT	Inferior posterior wall infarction
NONSPECIFIC INTRAVENTRICULAR CONDUCTION DELAY	Nonspecific intraventricular conduction delay
PREMATURE VENTRICULAR AND FUSION COMPLEXES	Premature ventricular contractions and fusion waves
IN A PATTERN OF BIGEMINY	Bigeminy pattern
AV DUAL-PACED RHYTHM	Dual-chamber pacing rhythm
SUPRAVENTRICULAR TACHYCARDIA	SUPRAVENTRICULAR TACHYCARDIA
VENTRICULAR-PACED COMPLEXES	Ventricular-paced complexes
WIDE QRS TACHYCARDIA	WIDE QRS TACHYCARDIA
RSR' PATTERN IN V1	V1 lead RSR' waveform
ST LESS DEPRESSED IN	ST segment depression reduced
VENTRICULAR TACHYCARDIA	Ventricular tachycardia
EARLY REPOLARIZATION	EARLY REPOLARIZATION
ST MORE DEPRESSED IN	ST segment depression worsens
ANTEROLATERAL LEADS	Anterolateral leads
ELECTRONIC DEMAND PACING	Electronic demand pacing
RBBB AND LEFT ANTERIOR FASCICULAR BLOCK	Right bundle branch block with left anterior fascicular block
LATERAL INJURY PATTERN	Side wall injury pattern
BIVENTRICULAR PACEMAKER DETECTED	Biventricular pacemaker detected
SUSPECT UNSPECIFIED PACEMAKER FAILURE	Suspected unspecified pacemaker dysfunction
WOLFF-PARKINSON-WHITE	Pre-excitation syndrome (Wolff-Parkinson-White syndrome)
WITH VENTRICULAR ESCAPE COMPLEXES	WITH VENTRICULAR Escape Complexes
INFERIOR INJURY PATTERN	Inferior wall injury pattern
CONSIDER RIGHT VENTRICULAR INVOLVEMENT IN ACUTE INFERIOR INFARCT	Acute inferior wall myocardial infarction with possible right ventricular involvement
ST ELEVATION HAS REPLACED ST DEPRESSION IN	ST segment elevation replaces ST segment depression
NONSPECIFIC INTRAVENTRICULAR BLOCK	Nonspecific intraventricular block
MASKED BY FASCICULAR BLOCK	Masked by branch block
PEDIATRIC ECG ANALYSIS	Pediatric ECG Analysis
BLOCKED	BLOCKED
WITH UNDETERMINED RHYTHM IRREGULARITY	WITH UNDETERMINED RHYTHM IRREGULARITY
LEFTWARD AXIS	Left eccentric axis
WITH 2ND DEGREE SA BLOCK MOBITZ I	With second degree sinoatrial block Mobitz type I
ACUTE	Acute
ABNORMAL LEFT AXIS DEVIATION	Abnormal left axis deviation
WITH COMPLETE HEART BLOCK	WITH COMPLETE AV BLOCK
NO P-WAVES FOUND	No P-waves detected
ST LESS ELEVATED IN	ST segment elevation reduced
WITH RETROGRADE CONDUCTION	WITH RETROGRADE CONDUCTION
ST MORE ELEVATED IN	ST segment elevation worsens
JUNCTIONAL BRADYCARDIA	Junctional bradycardia
WITH VARIABLE AV BLOCK	WITH VARIABLE AV BLOCK
ANTERIOR INJURY PATTERN	Anterior wall injury pattern
WITH JUNCTIONAL ESCAPE COMPLEXES	WITH JUNCTIONAL Escape Complexes
ACUTE MI	Acute myocardial infarction
ACUTE PERICARDITIS	Acute pericarditis
POSTERIOR INFARCT	Posterior wall infarction
IDIOVENTRICULAR RHYTHM	Idiopathic ventricular rhythm
WITH 2ND DEGREE SA BLOCK MOBITZ II	WITH 2ND DEGREE SA BLOCK Mobitz type II
R IN AVL	AVL lead R wave
SINUS/ATRIAL CAPTURE	Sinus/Atrial Capture
AV DUAL-PACED COMPLEXES	Dual-chamber pacing complexes
INFEROLATERAL INJURY PATTERN	Inferolateral injury pattern
RBBB AND LEFT POSTERIOR FASCICULAR BLOCK	Right bundle branch block with left posterior fascicular block
ANTEROLATERAL INJURY PATTERN	Anterolateral injury pattern
ATRIAL-PACED COMPLEXES	Atrial-paced complexes
WITH SINUS PAUSE	WITH SINUS PAUSE
BIVENTRICULAR HYPERTROPHY	Biventricular hypertrophy
ABNORMAL RIGHT AXIS DEVIATION	Abnormal right axis deviation
SUPRAVENTRICULAR COMPLEXES	SUPRAVENTRICULAR COMPLEXES
WITH 2ND DEGREE AV BLOCK MOBITZ I	WITH 2nd degree atrioventricular block Mobitz type I
WITH 2:1 AV CONDUCTION	WITH 2:1 AV CONDUCTION
WITH AV DISSOCIATION	WITH AV DISSOCIATION
MULTIFOCAL ATRIAL TACHYCARDIA	MULTIFOCAL ATRIAL TACHYCARDIA

Literature

@article{li2025electrocardiogram,
  title={An Electrocardiogram Foundation Model Built on over 10 Million Recordings},
  author={Li, Jun and Aguirre, Aaron D and Junior, Valdery Moura and Jin, Jiarui and Liu, Che and Zhong, Lanhai and Sun, Chenxi and Clifford, Gari and Brandon Westover, M and Hong, Shenda},
  journal={NEJM AI},
  volume={2},
  number={7},
  pages={AIoa2401033},
  year={2025},
  publisher={Massachusetts Medical Society}
}

Li, J., Aguirre, A., Moura, J., Liu, C., Zhong, L., Sun, C., ... & Hong, S. (2024). An electrocardiogram foundation model built on over 10 million recordings with external evaluation across multiple domains. arXiv preprint arXiv:2410.04133.

MCMA interface​

POST /api/v1/experimental/mcma​

Request parameters​

Request example​

Response example​

Visual display​

Literature​

DiffuSETS interface​

POST /api/v1/experimental/diffuSets​

Request parameters​

Request example​

Response example​

Visual display​

Literature​

WearECG interface​

POST /api/v1/experimental/lead3Lead12​

Request parameters​

Request example​

Response example​

Visual display​

PPGFlowECG interface​

POST /api/v1/experimental/ppgFlowEcg​

Request parameters​

Request example​

Response example​

Visual display​

Literature​

ECHOPulse interface​

POST /api/v1/experimental/ecgEcho​

Request parameters​

Request example​

Response example​

Visual display​

Save ECHO video frames​

Save the result as gif​

Visual display​

Literature​

ECGTwins interface​

POST /api/v1/experimental/ecgTwins​

Request parameters​

Request example​

Response example​

Visual display​

Literature​

ECGFounder interface​

POST /api/v1/experimental/ecgFounder​

Request parameters​

Request example​

Response example​

Chinese and English​

Literature​

MCMA interface

POST /api/v1/experimental/mcma

Request parameters

Request example

Response example

Visual display

Literature

DiffuSETS interface

POST /api/v1/experimental/diffuSets

Request parameters

Request example

Response example

Visual display

Literature

WearECG interface

POST /api/v1/experimental/lead3Lead12

Request parameters

Request example

Response example

Visual display

PPGFlowECG interface

POST /api/v1/experimental/ppgFlowEcg

Request parameters

Request example

Response example

Visual display

Literature

ECHOPulse interface

POST /api/v1/experimental/ecgEcho

Request parameters

Request example

Response example

Visual display

Save ECHO video frames

Save the result as gif

Visual display

Literature

ECGTwins interface

POST /api/v1/experimental/ecgTwins

Request parameters

Request example

Response example

Visual display

Literature

ECGFounder interface

POST /api/v1/experimental/ecgFounder

Request parameters

Request example

Response example

Chinese and English

Literature