Family History of Lung Cancer
Conditions
Keywords
Screening, CT Scan Images, Lung Cancer
Brief summary
This research is being done to determine if an image-based deep learning model (Sybil) can accurately predict the likelihood of future lung cancer based on chest computed tomography (CT) imaging from individuals with a family history of lung cancer.
Detailed description
This is a non-therapeutic study that will enroll individuals who have a family history of lung cancer. During the study, participants will provide questionnaire responses regarding their personal medical history, family lung cancer history, and exposures along with contributing images from at least one previously obtained CT chest scan. The images and data collected will be analyzed by an image-based deep learning model (Sybil). Sybil is a type of artificial intelligence model that has been shown to accurately predict individuals' future risk of lung cancer based solely on images from a CT Chest scan, but it is unknown if it works well in people with a family history of lung cancer. It is expected that 2,250 will take part in this research study.
Interventions
DIAGNOSTIC_TESTCT scan
Previously obtained computed tomography scan
OTHERSybil
Image-based deep learning model
Sponsors
Massachusetts General Hospital
Study design
Observational model
COHORT
Time perspective
RETROSPECTIVE
Eligibility
Sex/Gender
ALL
Age
18 Years to No maximum
Inclusion criteria
* ≥18 years of age * Positive family history of lung cancer (defined as): * Has ≥1 first-degree relative OR * Has ≥2 second-degree relatives with a diagnosis of non-small cell lung cancer or small cell lung cancer (NB: a first-degree relative = parent, sibling, or child, a second-degree relative = grandparent, blood-related aunt or uncle, grandchild, blood-related niece or nephew, half-sibling) * Willing to provide images from at least one previously obtained CT Chest scan, if available.
Exclusion criteria
\- None
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Sybil's performance in predicting future lung cancer diagnoses | From date of receival of retrospective CT scan for up to 2 years. | We will estimate future lung cancer diagnoses using the area under the receiver operating curve (AUROC). |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Distribution of Sybil lung cancer risk scores compared to participants in the NLST clinical trial | From receival of retrospective CT scan for up to 2 years. | We will compare the distribution of Sybil scores between participants in the LEGACY study and National Lung Screening Trial. |
| Incidence and prevalence of lung cancer in the study population | From receival of retrospective CT scan for up to 2 years. | We will estimate the incidence of lung cancer in the LEGACY population. |
| Incidence, prevalence, and characteristics of lung nodules in this population | From receival of retrospective CT scan for up to 2 years. | We will estimate the incidence, prevalence, and characteristics of lung nodules in the LEGACY population. |
Countries
United States
Contacts
CONTACTAllison Chang, MD
PRINCIPAL_INVESTIGATORAllison Chang, MD
Massachusetts General Hospital
Outcome results
None listed