Arrow
use cases

AI-Powered Lung Cancer Prediction and Screening

Lung cancer screening based on various critical lung cancer risk factors, including age, smoking history, and family cancer history.

Problem

Lung cancer ranks among the deadliest cancers globally, often due to its late detection and links to risk factors like smoking and environmental carcinogens. Its aggressiveness and capacity to advance rapidly, frequently without clear symptoms, typically result in late-stage diagnoses when therapeutic interventions become limited and have diminished effectiveness—a fact underscored by a grim global five-year survival rate of 15% (2). With around 2.21 million new cases each year (1) and over 85% attributed to tobacco use (3), the impact of lung cancer is profound, not only on patient health but also on healthcare systems burdened with the high costs of treatment and ongoing care (4).

‍

Why it matters

  • Lung cancer is one of the deadliest cancers globally, often detected late due to its aggressive nature and symptomless progression.
  • It has a low global five-year survival rate of 15%, with around 2.21 million new cases each year and over 85% linked to tobacco use.
  • The high incidence and treatment costs of lung cancer place a significant burden on patient health and healthcare systems.

Solution

"LungScreen AI" uses artificial intelligence to analyze determining risk factors, thus helping to predict lung cancer and facilitating the possibility of timely interventions.

Discover more and interact with our AI!

Datasources

The model design is based on a combination of studies and clinical reports on risk factors and diagnosis of lung cancer, including a multi-cohort radiomics study found in PLOS Medicine (1), global data on the cancer from the World Health Organization (2), and knowledge on the interrelationship of tobacco and lung cancer from Cancer.org (3). These sources help define the scope and impact of the risk factors used in the AI model.

Citations

  1. "Deep learning for lung cancer prognostication: A retrospective multi-cohort radiomics study," PLOS Medicine. [Online]. Available: https://journals.plos.org/plosmedicine/article?id=10.1371/journal.pmed.1002711.
  2. World Health Organization, Cancer. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/cancer.
  3. "Tobacco smoking and lung cancer," Cancer.org. [Online]. Available: https://www.cancer.org/cancer/lung-cancer/causes-risks-prevention/tobacco-and-cancer.html.
  4. "Artificial intelligence in lung cancer pathology image analysis," Cancers, MDPI. [Online]. Available: https://www.mdpi.com/2072-6694/12/7/1677.

Problem

Lung cancer ranks among the deadliest cancers globally, often due to its late detection and links to risk factors like smoking and environmental carcinogens. Its aggressiveness and capacity to advance rapidly, frequently without clear symptoms, typically result in late-stage diagnoses when therapeutic interventions become limited and have diminished effectiveness—a fact underscored by a grim global five-year survival rate of 15% (2). With around 2.21 million new cases each year (1) and over 85% attributed to tobacco use (3), the impact of lung cancer is profound, not only on patient health but also on healthcare systems burdened with the high costs of treatment and ongoing care (4).

‍

Why it matters

  • Lung cancer is one of the deadliest cancers globally, often detected late due to its aggressive nature and symptomless progression.
  • It has a low global five-year survival rate of 15%, with around 2.21 million new cases each year and over 85% linked to tobacco use.
  • The high incidence and treatment costs of lung cancer place a significant burden on patient health and healthcare systems.

Solution

"LungScreen AI" uses artificial intelligence to analyze determining risk factors, thus helping to predict lung cancer and facilitating the possibility of timely interventions.


Impact


Data Sources

The model design is based on a combination of studies and clinical reports on risk factors and diagnosis of lung cancer, including a multi-cohort radiomics study found in PLOS Medicine (1), global data on the cancer from the World Health Organization (2), and knowledge on the interrelationship of tobacco and lung cancer from Cancer.org (3). These sources help define the scope and impact of the risk factors used in the AI model.


References

  1. "Deep learning for lung cancer prognostication: A retrospective multi-cohort radiomics study," PLOS Medicine. [Online]. Available: https://journals.plos.org/plosmedicine/article?id=10.1371/journal.pmed.1002711.
  2. World Health Organization, Cancer. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/cancer.
  3. "Tobacco smoking and lung cancer," Cancer.org. [Online]. Available: https://www.cancer.org/cancer/lung-cancer/causes-risks-prevention/tobacco-and-cancer.html.
  4. "Artificial intelligence in lung cancer pathology image analysis," Cancers, MDPI. [Online]. Available: https://www.mdpi.com/2072-6694/12/7/1677.

Book a Free Consultation

Trusted by the world's top healthcare institutions