Smart Blood Analytics

Smart Blood Analytics

CERTIFICATION Our Commitment to
Excellence and
Compliance

SBAS is committed to upholding the highest quality, safety, and reliability standards in every solution. By adhering to rigorous international regulations and meeting stringent certification requirements, the products ensure safety, accuracy, and trustworthiness. The certifications reflect dedication to providing physicians and individuals with the confidence they need to make accurate, informed decisions.

MDR Certification

MDR Certification

The products comply with the European Medical Device Regulation (MDR), ensuring the highest standards of safety, quality, and performance.

ISO 13485 Certification

ISO 13485 Certification

SBAS operates under the globally recognized ISO 13485 standard, reflecting commitment to quality management in the design and development of medical devices.

GDPR Complience

GDPR Complience

Data privacy is the company’s priority. SBAS solutions are fully compliant with GDPR regulations, ensuring the secure handling of all personal and medical data.

Global Market Approvals

SBAS devices are globally approved, meeting diverse regulatory standards to ensure safety, quality, and reliability for healthcare professionals worldwide.

SCIENCEThe foundation of Trust

SBAS has made ground-breaking discoveries, revealing that blood test results contain far more information than previously understood. Notably, SBAS has achieved a significant milestone as the first company in the world to develop machine-learning algorithms capable of predicting the most probable diseases or medical conditions based solely on a patient’s blood test results, biological sex and age.

The products are built on a foundation of peer-reviewed scientific articles that demonstrate their accuracy and reliability in clinical use. From differentiating between bacterial and viral infections to supporting the diagnosis of complex conditions, these studies underline the scientific validity of SBAS tools:

An application of machine learning to haematological diagnosis

  • High Predictive Accuracy: SBAS machine learning models achieve up to 88% accuracy in predicting the top five haematological diseases, matching the expertise of specialists.
  • Efficient and Practical: Using only 61 commonly measured blood parameters, the models maintain near-identical performance to those using a full dataset of 181 parameters.
  • Enhanced Clinical Support: These models outperform general practitioners, providing fast, reliable diagnostics and improving patient care through timely and accurate referrals.

Scientific Reports - Nature, 2018

Read Article

Diagnosing brain tumours by routine blood tests using machine learning

  • Precision in Tumor Detection: The machine learning model demonstrates 96% sensitivity and 74% specificity in detecting brain tumors using routine blood tests, offering performance comparable to imaging techniques.
  • Cost-Effective and Low-Risk: By leveraging standard blood test results, the model provides a low-risk and efficient method for early brain tumor detection, even in the initial stages of symptoms.
  • Advancing Neurological Diagnostics: This approach enables faster and more accurate diagnoses, minimizes unnecessary imaging, and introduces a new pathway for non-invasive diagnostics in neurology.

Scientific Reports - Nature, 2019

Read Article

COVID-19 diagnosis by routine blood tests using machine learning

  • High Performance: A machine learning model demonstrated 81.9% sensitivity and 97.9% specificity in distinguishing COVID-19 from other infectious diseases using routine blood test results.
  • Practical and Complementary: The model serves as an efficient and non-invasive tool for preliminary COVID-19 screening, complementing RT-PCR and chest CT scans, particularly in resource-limited settings.
  • Proactive Care: By analyzing subtle blood parameter patterns, the model supports early diagnosis and timely intervention for COVID-19, contributing significantly to improved patient care and pandemic management.

Scientific Reports - Nature, 2021

Read Article

Differentiating viral and bacterial infections: A machine learning model based on routine blood test values

  • Enhanced Diagnostic Accuracy: The machine learning model achieved 82.2% accuracy, 79.7% sensitivity, and 84.5% specificity, with an AUC of 0.905, outperforming CRP-based rules in distinguishing bacterial from viral infections.
  • Advancement in CRP Diagnostic Limitations: The model excels in the CRP range of 10–40 mg/L, a diagnostic "gray zone”.
  • Multifactorial Approach: By incorporating 16 routine blood parameters, CRP levels, age, and biological sex, the model leverages multiple variables for more precise diagnostics, highlighting the value of machine learning in complex medical decision-making.

Heliyon, 2024

Read Article
Smart Blood Analytics Swiss SA Höschgasse 25, CH-8008 ZÜRICH, Switzerland Contact Us
Products SBAS Software VIRUS vs BACTERIA mySmartBlood
About Company Info News & Insights
Legal Privacy Notice Cookies
© 2025 SMART BLOOD ANALYTICS SWISS SA. ALL RIGHTS RESERVED
This website uses cookies to provide online services. By continuing to use this website you agree to the use of some cookies.
More about cookie settings
I agree