Ambulatory monitoring and diagnostics
Cardiologs AI
The future of cardiac diagnostics lies within AI-assisted analysis
Demonstrated dose reduction in clinical studies
1st
AI solution for ECG analysis
Cardiologs was the first AI solution approved by the FDA for ECG analysis in 2017.
2M+
Patients diagnosed every year
Our AI is used on 5 continents, helping diagnose cardiac patients all over the world.
20+
Peer-reviewed scientific publications and abstracts
The AI algorithms used in our products have been clinically validated and we continue to innovate.
42%
Reduction in Holter analysis time [2,3]
Based on a clinical study that compared Cardiologs AI solution with a traditional solution [3].
Features
Philips Cardiologs AI
Based on deep learning technology and built upon 200M+ recordings [4], Philips Cardiologs AI analyzes ECG waveforms as a whole, mimicking the way the human brain works. This enables our algorithms to handle complex ECG patterns better than traditional algorithms that rely on a limited number of predefined rules. Want to learn more?
Our Holter algorithm detects more than 20 types of events
- Pause - Atrioventricular Block (second-degree, third-degree, advanced high-grade AV block) - Atrial Fibrillation or Atrial Flutter - Ventricular Tachycardia- Premature Supraventricular Complexes (PSVCs), PSVC Couplets - Premature Ventricular Complexes (PVCs) - Ventricular Couplets, Ventricular Bigeminy, Ventricular Trigeminy - Sinus Rhythm, Bradycardia, Tachycardia
Including the main arrhythmias:
10 times reduction in AF false positives in Holter
Validation of our AI algorithm. Using the MIT-BIH public database, our Cardiologs AI algorithm was compared to the results of a reference RR interval-based method [5]. Our AI algorithm has been shown to improve the specificity of atrial fibrillation detection while maintaining comparable sensitivity, reducing the false positives rate from 17.2% to 1.5%.
Higher sensitivity for VT detection in Holter
We conducted a multicenter study comparing the performance of the Cardiologs AI-based algorithm to a traditional algorithm. It demonstrated a 29% increase in sensitivity for VT detection (97% vs 68%, p<0.001) [6]. CTA: Read the publication.
Reduction of inconclusive results by 95% in smartwatch ECGs
We compared the performance of our Cardiologs AI in smartwatch ECG to the results of the embedded algorithm. Results showed a reduction of inconclusive diagnoses from 19 of 100 recordings to only one with Cardiologs AI. This could reduce the time doctors spend reviewing smartwatch data, reducing the risk of diagnostic delays [1,7].
Prediction of AF from a sinus ECG
First results suggest that Cardiologs deep learning model using a 24-hour Holter recording can be used to identify patients at risk of developing paroxysmal AF [1,8]. CTA: Read the publication.
Cardiologs AI is available on
-
Fusion and navigation
Make confident decisions even in challenging diagnostic cases with Philips image fusion and needle navigation capabilities. Streamlined workflow allows clinicians to achieve fast and effective fusion of CT/MR/PET with live ultrasound while needle navigation aids in guiding biopsy of small and difficult-to-access lesions.
NOCTN150
Our medical-grade AI is available in Cardiologs Holter
The Cardiologs Holter platform uses deep neural network and cloud technology to help you analyze continuous ambulatory ECGs more efficiently.
Documentation
- Brochure
-
- White paper
-
Footnotes
[1] The Cardiologs algorithms for analyzing smartwatch data and ECG biomarkers are being investigated. They are not available for sale. [2] The Cardiologs Holter Platform is a medical device intended for use by qualified healthcare professionals for the assessment of arrhythmias using ECG data. It is CE marked and cleared by the FDA under 510(k). [3] Fiorina, L., Marijon, E., Maupain, C., et al. AI-based strategy enables faster Holter ECG analysis with equivalent clinical accuracy compared to a classical strategy. EP Europace. 2020;22(suppl 1), euaa162.374. DOI: 10.1093/europace/euaa162.374. [4] Philips Cardiologs database - October 2023. [5] Li, J., Rapin, J., Rosier, A., Smith, S.W., Fleureau, Y., Taboulet, P. Deep neural networks improve atrial fibrillation detection in Holter: first results. European Journal of Preventive Cardiology. 2016;23(2suppl):41–55. DOI: 10.1177/2047487316668070. [6] Fiorina, L., Maupain, C., Gardella, C., et al. Evaluation of an Ambulatory ECG Analysis Platform Using Deep Neural Networks in Routine Clinical Practice. Journal of the American Heart Association. 2022;11(18):e026196. DOI: 10.1161/JAHA.122.026196. [7] Fiorina, L., Chemaly, P., Cellier, J., et al. Artificial intelligence–based electrocardiogram analysis improves atrial arrhythmia detection from a smartwatch electrocardiogram. European Heart Journal - Digital Health. 2024;00:1-7. DOI: 10.1093/ehjdh/ztae047. [8] Singh, J.P., Fontanarava, J., de Massé, G., et al. Short-term prediction of atrial fibrillation from ambulatory monitoring ECG using a deep neural network. European Heart Journal - Digital Health. 2022;3(2):208–217. DOI: 10.1093/ehjdh/ztac014ztac014.
Disclaimer
Results are specific to the institution where they were obtained and may not reflect the results achievable at other institutions. Results in other cases may vary.
