Alison S. Rustagi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Alison S. Rustagi has a total of 42 co-authors. Here are the top co-authors by number of shared publications:
Salomeh Keyhani
Center for Data to Discovery and Delivery Innovation (3DI), San Francisco VA Health Care System, San Francisco, USA
7 shared publicationsAmy L. Byers
Center for Data to Discovery and Delivery Innovation (3DI), San Francisco VA Health Care System, San Francisco, USA
5 shared publicationsChristopher G. Slatore
Center to Improve Veteran Involvement in Care, VA Portland Health Care System, Portland, USA
5 shared publicationsBeth E. Cohen
Center for Data to Discovery and Delivery Innovation (3DI), San Francisco VA Health Care System, San Francisco, USA
3 shared publicationsFrancis J. Graham
Northern California Institute for Research and Education, San Francisco Veterans Affairs Health Care System
3 shared publicationsAbra M. Jeffers
Mongan Institute Health Policy Research Center, Massachusetts General Hospital, Boston, USA
2 shared publications
Latest Publications
- Open Access
Investigating AI’s potential in risk-stratifying lung cancer screenings for extending screening intervals and reducing workload: A retrospective analysis of a tertiary hospital cohort
Objective: We aimed to 1) evaluate whether AI algorithms could identify a very low-risk sub-population Lung-RADS 1/2 cases suitable for a safe switch to biennial screening, and 2) externally validate Sybil, an imaging-based deep learning lung cancer risk prediction tool. Materials and methods: We gathered all lung cancer screenings (LCSs) from a tertiary safety-net hospital (n=3120, up to September 2024), manually extracted relevant clinical data, and analyzed Sybil’s performance across various subgroups, with a specific focus on Lung-RADS 1 and 2 cases. We simulated LCS interval extension using Sybil and the Brock model risk scores calibrated on a subset of the National Lung Screening Trial (NLST). Confidence intervals were obtained through bootstrapping. Results: The median follow-up was 2.3 years (interquartile range 1.5–3.1), with a total 6-year cancer incidence rate of 2.3% (72/3120). Lung-RADS 1 and 2 cases comprised 90.5% of our scans. Sybil’s overall area under the curve (AUC) ranged from 0.819 to 0.912; while its 2-year AUC for Lung-RADS 1 and 2 cases was 0.746. In the screening interval extension simulation, calibrating for a 30% shift to biennial screening translated into 33.8% of negative screens in our data being safely extended using Sybil, with no delayed cancers. The Brock model demonstrated an AUC of 0.513 on our data, with a sensitivity of 18.2% using the 1.5% threshold. Conclusion: Sybil has the potential to safely extend LCS intervals for low-risk individuals, reducing radiology workload and opening spots for life-saving new screenings. Key points: We investigated whether AI risk stratification tools could identify the lowest-risk individuals undergoing lung cancer screening suitable for switching to a biennial screening schedule. In our simulations, Sybil reduced follow-up screening load by at least 30% through switching the lowest-risk Lung-RADS 1 and 2 cases to biennial screening without delayed cancer diagnoses. Very low-risk individuals, as predicted by AI algorithms, could potentially be placed on biennial screening schedules, reducing radiology department workload and freeing time for new patients.
Open AccessInvestigating AI’s potential in risk-stratifying lung cancer screenings for extending screening intervals and reducing workload: A retrospective analysis of a tertiary hospital cohort
Objective: We aimed to 1) evaluate whether AI algorithms could identify a very low-risk sub-population Lung-RADS 1/2 cases suitable for a safe switch to biennial screening, and 2) externally validate Sybil, an imaging-based deep learning lung cancer risk prediction tool. Materials and methods: We gathered all lung cancer screenings (LCSs) from a tertiary safety-net hospital (n=3120, up to September 2024), manually extracted relevant clinical data, and analyzed Sybil’s performance across various subgroups, with a specific focus on Lung-RADS 1 and 2 cases. We simulated LCS interval extension using Sybil and the Brock model risk scores calibrated on a subset of the National Lung Screening Trial (NLST). Confidence intervals were obtained through bootstrapping. Results: The median follow-up was 2.3 years (interquartile range 1.5–3.1), with a total 6-year cancer incidence rate of 2.3% (72/3120). Lung-RADS 1 and 2 cases comprised 90.5% of our scans. Sybil’s overall area under the curve (AUC) ranged from 0.819 to 0.912; while its 2-year AUC for Lung-RADS 1 and 2 cases was 0.746. In the screening interval extension simulation, calibrating for a 30% shift to biennial screening translated into 33.8% of negative screens in our data being safely extended using Sybil, with no delayed cancers. The Brock model demonstrated an AUC of 0.513 on our data, with a sensitivity of 18.2% using the 1.5% threshold. Conclusion: Sybil has the potential to safely extend LCS intervals for low-risk individuals, reducing radiology workload and opening spots for life-saving new screenings. Key points: We investigated whether AI risk stratification tools could identify the lowest-risk individuals undergoing lung cancer screening suitable for switching to a biennial screening schedule. In our simulations, Sybil reduced follow-up screening load by at least 30% through switching the lowest-risk Lung-RADS 1 and 2 cases to biennial screening without delayed cancer diagnoses. Very low-risk individuals, as predicted by AI algorithms, could potentially be placed on biennial screening schedules, reducing radiology department workload and freeing time for new patients.
- Open Access
- 1 April 2026
- Published by American Medical Association (AMA) in JAMA Network Open
- Vol. 9 (4) , e268622
Mortality and Generalizability of the National Lung Screening Trial
This cohort study evaluates all-cause mortality of National Lung Screening Trial participants compared with those of similar age and tobacco use in a national Veterans Health Administration cohort.
- 1 April 2026
- Published by American Medical Association (AMA) in JAMA Network Open
- Vol. 9 (4) , e268622
Open AccessMortality and Generalizability of the National Lung Screening Trial
This cohort study evaluates all-cause mortality of National Lung Screening Trial participants compared with those of similar age and tobacco use in a national Veterans Health Administration cohort.
- Open Access
- 4 September 2025
- Published by Springer Nature in Journal of General Internal Medicine
- Vol. 41 (4) , 1077-1086
Inhaled Cannabis, Asthma, and Chronic Obstructive Pulmonary Disease: A Population-Based Cross-Sectional Study of n = 379,049
Background: Cannabis may cause chronic pulmonary disease. Prior studies have been limited by low cannabis exposure, lack of data on tobacco cigarettes, and/or limited numbers of those without tobacco cigarette use. Objective: To examine whether inhaled cannabis associated with asthma and chronic obstructive pulmonary disease, independent of tobacco cigarettes. Design: Cross-sectional analysis of population-based, nationally representative survey data. Participants: Adults 18–74 years who participated in the 2016–2020 Behavioral Risk Factor Surveillance System surveys. Main Measures: The exposure was past-30-day cannabis use, from 0 (0/30 days) to 1 (30/30 days). Outcomes were self-reported diagnoses by a medical professional of asthma or chronic obstructive pulmonary disease. We used multivariable logistic regression to test whether inhaled cannabis was associated with odds of disease, adjusted for sociodemographics and tobacco cigarette use (current/former/never). Pre-specified analyses restricted to those with no lifetime tobacco cigarette use. Key Results: Among n = 379,049, n = 23,035 reported inhaled cannabis use. Inhaled cannabis was associated with asthma overall (adjusted odds ratio (aOR) 1.44, 95% CI 1.26–1.63 for daily use) and among n = 221,767 with no lifetime tobacco cigarette use (aOR 1.51 for daily use, 95% CI 1.18–1.93). Inhaled cannabis was associated with chronic obstructive pulmonary disease overall (aOR 1.27 for daily use, 95% CI 1.10–1.46), with a non-significant elevated odds of disease among those with no lifetime tobacco cigarette use (aOR 1.54 for daily use, 95% CI 0.92–2.57). Conclusions: Inhaled cannabis was associated with asthma and chronic obstructive pulmonary disease after adjusting for tobacco cigarette use. Among those with no lifetime tobacco cigarette use, the association with asthma persisted. Cannabis may be a potential modifiable risk factor for asthma and chronic obstructive pulmonary disease.
- 4 September 2025
- Published by Springer Nature in Journal of General Internal Medicine
- Vol. 41 (4) , 1077-1086
Open AccessInhaled Cannabis, Asthma, and Chronic Obstructive Pulmonary Disease: A Population-Based Cross-Sectional Study of n = 379,049
Background: Cannabis may cause chronic pulmonary disease. Prior studies have been limited by low cannabis exposure, lack of data on tobacco cigarettes, and/or limited numbers of those without tobacco cigarette use. Objective: To examine whether inhaled cannabis associated with asthma and chronic obstructive pulmonary disease, independent of tobacco cigarettes. Design: Cross-sectional analysis of population-based, nationally representative survey data. Participants: Adults 18–74 years who participated in the 2016–2020 Behavioral Risk Factor Surveillance System surveys. Main Measures: The exposure was past-30-day cannabis use, from 0 (0/30 days) to 1 (30/30 days). Outcomes were self-reported diagnoses by a medical professional of asthma or chronic obstructive pulmonary disease. We used multivariable logistic regression to test whether inhaled cannabis was associated with odds of disease, adjusted for sociodemographics and tobacco cigarette use (current/former/never). Pre-specified analyses restricted to those with no lifetime tobacco cigarette use. Key Results: Among n = 379,049, n = 23,035 reported inhaled cannabis use. Inhaled cannabis was associated with asthma overall (adjusted odds ratio (aOR) 1.44, 95% CI 1.26–1.63 for daily use) and among n = 221,767 with no lifetime tobacco cigarette use (aOR 1.51 for daily use, 95% CI 1.18–1.93). Inhaled cannabis was associated with chronic obstructive pulmonary disease overall (aOR 1.27 for daily use, 95% CI 1.10–1.46), with a non-significant elevated odds of disease among those with no lifetime tobacco cigarette use (aOR 1.54 for daily use, 95% CI 0.92–2.57). Conclusions: Inhaled cannabis was associated with asthma and chronic obstructive pulmonary disease after adjusting for tobacco cigarette use. Among those with no lifetime tobacco cigarette use, the association with asthma persisted. Cannabis may be a potential modifiable risk factor for asthma and chronic obstructive pulmonary disease.
- Open Access
- 28 May 2025
- Published by Elsevier in American Journal of Preventive Medicine
- Vol. 69 (2) , 107736
Time to Benefit for Lung Cancer Screening: A Systematic Review and Survival Meta-Analysis
- 28 May 2025
- Published by Elsevier in American Journal of Preventive Medicine
- Vol. 69 (2) , 107736
Open AccessTime to Benefit for Lung Cancer Screening: A Systematic Review and Survival Meta-Analysis
- Open Access
- 25 February 2025
- Published by Springer Nature in Journal of General Internal Medicine
- Vol. 40 (6) , 1306-1314
A Novel Automated Algorithm to Identify Lung Cancer Screening from Free Text of Radiology Orders
Background: Lung cancer screening (LCS) is recommended for asymptomatic patients. Administrative codes for LCS may capture tests prompted by signs/symptoms. Objective: To validate an automated algorithm that identifies LCS among asymptomatic patients. Design: In this cross-sectional study, an algorithm was iteratively developed to identify outpatient low-dose chest CT scans via Current Procedural Terminology (CPT) codes, search free text of radiology orders for screening terms and signs/symptoms (e.g., cough), and classify scans as screening or not. Participants: National population-based sample of 4503 adults ages 65–80 in Veterans Health Affairs primary care, with detailed smoking history to identify LCS-eligible individuals (30 + pack-years, current tobacco use, or quit < 15 years prior). Main Measures: Algorithm specificity, sensitivity, positive predictive value (PPV), and negative predictive value (NPV) relative to manual chart review (gold standard) on 100% of screening scans and > 10% random sample of non-screening scans. Key Results: Chart review was conducted on n = 335 scans. The final algorithm could not classify 22% of scans, of which 73% were non-screening; these were excluded from primary analyses. Among 842 LCS-eligible individuals, the algorithm demonstrated 97% sensitivity (95%CI 91–99%) and 79% specificity (58–93%). Only 69% (61–77%) of scans classified as LCS via administrative codes were truly screening, compared to 95% of those classified as screening via the algorithm (p < 0.001). Algorithm performance was similar regardless of LCS eligibility, with 90% PPV (84–94%) and 93% NPV (86–97%) in the overall population regardless of tobacco cigarette history. Conclusions: An automated algorithm can accurately identify screening versus diagnostic chest imaging, a necessary step to unbiased analyses of LCS in non-randomized settings. Studies should assess the accuracy of administrative codes for LCS in other health systems.
- 25 February 2025
- Published by Springer Nature in Journal of General Internal Medicine
- Vol. 40 (6) , 1306-1314
Open AccessA Novel Automated Algorithm to Identify Lung Cancer Screening from Free Text of Radiology Orders
Background: Lung cancer screening (LCS) is recommended for asymptomatic patients. Administrative codes for LCS may capture tests prompted by signs/symptoms. Objective: To validate an automated algorithm that identifies LCS among asymptomatic patients. Design: In this cross-sectional study, an algorithm was iteratively developed to identify outpatient low-dose chest CT scans via Current Procedural Terminology (CPT) codes, search free text of radiology orders for screening terms and signs/symptoms (e.g., cough), and classify scans as screening or not. Participants: National population-based sample of 4503 adults ages 65–80 in Veterans Health Affairs primary care, with detailed smoking history to identify LCS-eligible individuals (30 + pack-years, current tobacco use, or quit < 15 years prior). Main Measures: Algorithm specificity, sensitivity, positive predictive value (PPV), and negative predictive value (NPV) relative to manual chart review (gold standard) on 100% of screening scans and > 10% random sample of non-screening scans. Key Results: Chart review was conducted on n = 335 scans. The final algorithm could not classify 22% of scans, of which 73% were non-screening; these were excluded from primary analyses. Among 842 LCS-eligible individuals, the algorithm demonstrated 97% sensitivity (95%CI 91–99%) and 79% specificity (58–93%). Only 69% (61–77%) of scans classified as LCS via administrative codes were truly screening, compared to 95% of those classified as screening via the algorithm (p < 0.001). Algorithm performance was similar regardless of LCS eligibility, with 90% PPV (84–94%) and 93% NPV (86–97%) in the overall population regardless of tobacco cigarette history. Conclusions: An automated algorithm can accurately identify screening versus diagnostic chest imaging, a necessary step to unbiased analyses of LCS in non-randomized settings. Studies should assess the accuracy of administrative codes for LCS in other health systems.
- 7 March 2023
- Published by American College of Physicians in Annals of Internal Medicine
- Vol. 176 (4) , 568-+
Self-Rated Health and Ability to Climb Stairs: A Pragmatic Health Assessment Before Lung Cancer Screening
- 7 March 2023
- Published by American College of Physicians in Annals of Internal Medicine
- Vol. 176 (4) , 568-+
Self-Rated Health and Ability to Climb Stairs: A Pragmatic Health Assessment Before Lung Cancer Screening
- Open Access
- 9 February 2023
- Published by Elsevier in AJPM Focus
- Vol. 2 (2) , 100084
Lung Cancer Screening Among U.S. Military Veterans by Health Status and Race and Ethnicity, 2017–2020: A Cross-Sectional Population-Based Study
- 9 February 2023
- Published by Elsevier in AJPM Focus
- Vol. 2 (2) , 100084
Open AccessLung Cancer Screening Among U.S. Military Veterans by Health Status and Race and Ethnicity, 2017–2020: A Cross-Sectional Population-Based Study
- Open Access
- 1 March 2022
- Published by American Medical Association (AMA) in JAMA Network Open
- Vol. 5 (3) , e225318
Likelihood of Lung Cancer Screening by Poor Health Status and Race and Ethnicity in US Adults, 2017 to 2020
Lung cancer is the leading cause of cancer deaths in the US.1 From 2013 to 2021, the US Preventive Services Task Force recommended lung cancer screening (LCS) via low-dose computed tomography for adults aged 55 to 80 years with a greater than or equal to 30 pack-year history who are current smokers or quit within 15 years.2 The US Preventive Services Task Force additionally highlights the need to screen only those willing and able to undergo lung surgery,2,3 and all national guidelines recommend against screening those with poor baseline health status, whether quantified as less than 10 years’ life expectancy (American College of Chest Physicians),4 “life limiting comorbid conditions” (American Cancer Society),5 or “as long as patient functional status and comorbidity allow consideration for curative intent therapy” (National Comprehensive Cancer Network).6 Although national guidelines are consistent in recommending that baseline health should be considered prior to screening, how to define poor health is unclear, and the American Thoracic Society recognizes that there is an urgent need for more research in this area.7
- 1 March 2022
- Published by American Medical Association (AMA) in JAMA Network Open
- Vol. 5 (3) , e225318
Open AccessLikelihood of Lung Cancer Screening by Poor Health Status and Race and Ethnicity in US Adults, 2017 to 2020
Lung cancer is the leading cause of cancer deaths in the US.1 From 2013 to 2021, the US Preventive Services Task Force recommended lung cancer screening (LCS) via low-dose computed tomography for adults aged 55 to 80 years with a greater than or equal to 30 pack-year history who are current smokers or quit within 15 years.2 The US Preventive Services Task Force additionally highlights the need to screen only those willing and able to undergo lung surgery,2,3 and all national guidelines recommend against screening those with poor baseline health status, whether quantified as less than 10 years’ life expectancy (American College of Chest Physicians),4 “life limiting comorbid conditions” (American Cancer Society),5 or “as long as patient functional status and comorbidity allow consideration for curative intent therapy” (National Comprehensive Cancer Network).6 Although national guidelines are consistent in recommending that baseline health should be considered prior to screening, how to define poor health is unclear, and the American Thoracic Society recognizes that there is an urgent need for more research in this area.7
- Open Access
- 4 February 2021
- Published by Oxford University Press (OUP) in JNCI Cancer Spectrum
- Vol. 5 (2) , pkaa124
Association of Daily Alcohol Intake, Volumetric Breast Density, and Breast Cancer Risk
High alcohol intake and breast density increase breast cancer (BC) risk, but their interrelationship is unknown. We examined whether volumetric density modifies and/or mediates the alcohol-BC association. BC cases (n = 2233) diagnosed from 2006 to 2013 in the San Francisco Bay area had screening mammograms 6 or more months before diagnosis; controls (n = 4562) were matched on age, mammogram date, race or ethnicity, facility, and mammography machine. Logistic regression was used to estimate alcohol-BC associations adjusted for age, body mass index, and menopause; interaction terms assessed modification. Percent mediation was quantified as the ratio of log (odds ratios [ORs]) from models with and without density measures. Alcohol consumption was associated with increased BC risk (2-sided Ptrend = .004), as were volumetric percent density (OR = 1.45 per SD, 95% confidence interval [CI] = 1.36 to 1.56) and dense volume (OR = 1.30, 95% CI = 1.24 to 1.37). Breast density did not modify the alcohol-BC association (2-sided P > .10 for all). Dense volume mediated 25.0% (95% CI = 5.5% to 44.4%) of the alcohol-BC association (2-sided P = .01), suggesting alcohol may partially increase BC risk by increasing fibroglandular tissue.
- 4 February 2021
- Published by Oxford University Press (OUP) in JNCI Cancer Spectrum
- Vol. 5 (2) , pkaa124
Open AccessAssociation of Daily Alcohol Intake, Volumetric Breast Density, and Breast Cancer Risk
High alcohol intake and breast density increase breast cancer (BC) risk, but their interrelationship is unknown. We examined whether volumetric density modifies and/or mediates the alcohol-BC association. BC cases (n = 2233) diagnosed from 2006 to 2013 in the San Francisco Bay area had screening mammograms 6 or more months before diagnosis; controls (n = 4562) were matched on age, mammogram date, race or ethnicity, facility, and mammography machine. Logistic regression was used to estimate alcohol-BC associations adjusted for age, body mass index, and menopause; interaction terms assessed modification. Percent mediation was quantified as the ratio of log (odds ratios [ORs]) from models with and without density measures. Alcohol consumption was associated with increased BC risk (2-sided Ptrend = .004), as were volumetric percent density (OR = 1.45 per SD, 95% confidence interval [CI] = 1.36 to 1.56) and dense volume (OR = 1.30, 95% CI = 1.24 to 1.37). Breast density did not modify the alcohol-BC association (2-sided P > .10 for all). Dense volume mediated 25.0% (95% CI = 5.5% to 44.4%) of the alcohol-BC association (2-sided P = .01), suggesting alcohol may partially increase BC risk by increasing fibroglandular tissue.