Observational cohort study involving individuals of both sexes with a history of smoking, residing in municipalities in the state of Bahia and attended by the mobile unit, with the aim of evaluating the integration of artificial intelligence (AI) in the detection of pulmonary nodules and the prediction of ASCT in high-risk individuals undergoing CT screening.

The main objective of the study is compare the performance of a Sybil AI tool with the LungRADS classifications assigned by radiologists for the risk stratification of pulmonary nodules. Furthermore, it aims to assess the correlation between the AI-predicted STAS and histopathological confirmation, alongside imaging and AI results. The hypothesis is that the Sybil AI model will demonstrate comparable predictive accuracy and that the features predicted by the AI will correlate with the presence of STAS.

Inclusion Criteria:

• Individuals of both sexes, smokers or former smokers for a maximum of 15 years;

  • Smoking history of 20 pack-years or more;
  • Between 50 and 80 years old;
  • Provision of Free and Informed Consent in writing, signed and dated.

Exclusion Criteria:

• Individuals who are unable to undergo a CT scan;

  • Individuals who cannot tolerate lying on their back for more than 10 minutes continuously;
  • Individuals who present with symptoms highly suggestive of lung cancer (hemoptysis, chest pain, altered cough pattern, unintentional weight loss greater than 10 kg);
  • Diagnosis of severe heart disease while using multiple medications;
  • Diagnosis of severe lung disease, using multiple medications and/or requiring home oxygen therapy;
  • History of radiation therapy to the chest area;
  • Individuals undergoing cancer evaluation or treatment;
  • Individuals exhibiting signs of respiratory distress (nasal flaring, suprasternal retraction, use of accessory muscles, cyanosis);
  • Pregnancy.

The study population includes individuals at high risk for lung cancer enrolled in the ProPulmão screening program. A convenience sample of 1,500 high-risk individuals will be included.

Qualified researchers can request access to anonymized individual patient-level data from AstraZeneca group of companies sponsored clinical trials via the request portal Vivli.org. All requests will be evaluated as per the AZ disclosure commitment: https://astrazenecagrouptrials.pharmacm.com/ST/Submission/Disclosure.

"Yes", indicates that AZ are accepting requests for IPD, but this does not mean all requests will be approved.

AstraZeneca will meet or exceed data availability as per the commitments made to the EFPIA/PhRMA Data-Sharing Principles. For details of our timelines, please refer to our disclosure commitment at https://astrazenecagrouptrials.pharmacm.com/ST/Submission/Disclosure.

When a request has been approved AstraZeneca will provide access to the anonymized individual patient-level data via secure research environment Vivli.org. A Signed Data Usage Agreement (non-negotiable contract for data accessors) must be in place before accessing requested information.