Fabien Maldonado

Vanderbilt University
Country flagUnited States

Research Interests

ApplyKite TwinLearns as you apply

Make your next move.

Prepare your application

Review drafts before you send them.

Explore related searches

Articles (15)

Background CYFRA 21-1, a cytokeratin-19 fragment, is a validated serum biomarker for non-small cell lung cancer (NSCLC). However, most studies rely on single time-point measurements, limiting its specificity in differentiating malignancy from benign pulmonary conditions. Inspired by the clinical utility of serial PSA measurements in prostate cancer, we investigated whether longitudinal trends in CYFRA 21-1 could enhance diagnostic and monitoring capabilities in patients with pulmonary nodules Methods and Findings We analyzed 132 patients with pulmonary nodules, including 41 with lung cancer and 91 with benign diagnoses. CYFRA 21-1 levels were measured serially using electrochemiluminescence assays. Longitudinal trends were assessed using linear mixed-effects models to estimate biomarker trajectories. Subgroup analyses examined differences between benign, untreated cancer, and post-treatment cancer groups, as well as within-patient changes in a subset of 16 cancer patients with both pre- and post-surgical measurements. Log-transformed data were used for the analysis. At baseline, CYFRA 21-1 levels were significantly higher in malignant versus benign nodules. Over time, CYFRA trajectories diverged: benign cases showed slight increases, whereas cancer patients exhibited greater biomarker volatility. In treated cancer patients, trend of CYFRA levels on the natural log scale decline from –0.00137 pre-surgery to – 0.00263 to post-surgery, and both cancer groups showed significantly higher absolute slopes than the benign group (p < 0.05). While pre- vs post-treatment slope differences did not reach significance (p = 0.211), the general pattern indicated that CYFRA 21-1 is a dynamic marker responsive to tumor presence and removal. Conclusions CYFRA 21-1 exhibits substantial within-patient variability over time, with trajectories that reflect disease state and treatment. These findings suggest that longitudinal monitoring of CYFRA 21-1—analogous to PSA velocity in prostate cancer— may offer improved diagnostic and prognostic insight in the evaluation of pulmonary nodules. Further studies in larger cohorts are warranted to validate these findings and explore clinical implementation of CYFRA trajectory analysis.

Year:

2026

Background: This study used machine learning to develop a 3-year lung cancer risk prediction model with large real-world data in a mostly younger population. Methods: Over 4.7 million individuals, aged 45 to 65 years with no history of any cancer or lung cancer screening, diagnostic, or treatment procedures, with an outpatient visit in 2013 were identified in Optum's de-identified Electronic Health Record (EHR) dataset. A least absolute shrinkage and selection operator model was fit using all available data in the 365 days prior. Temporal validation was assessed with recent data. External validation was assessed with data from Mercy Health Systems EHR and Optum's de-identified Clinformatics Data Mart Database. Racial inequities in model discrimination were assessed with xAUCs. Results: The model AUC was 0.76. Top predictors included age, smoking, race, ethnicity, and diagnosis of chronic obstructive pulmonary disease. The model identified a high-risk group with lung cancer incidence 9 times the average cohort incidence, representing 10% of patients with lung cancer. Model performed well temporally and externally, while performance was reduced for Asians and Hispanics. Conclusions: A high-dimensional model trained using big data identified a subset of patients with high lung cancer risk. The model demonstrated transportability to EHR and claims data, while underscoring the need to assess racial disparities when using machine learning methods. Impact: This internally and externally validated real-world data-based lung cancer prediction model is available on an open-source platform for broad sharing and application. Model integration into an EHR system could minimize physician burden by automating identification of high-risk patients.

Year:

2025

Flow Chart of Cohort Attrition and Study Design. A, shows the cohort attrition after applying eligibility criteria and the distribution of samples used for training and test sets. B, shows the parameters used for model development and study design.

Year:

2025

Background: Indeterminate pulmonary nodules (IPN) are a diagnostic challenge in regions where pulmonary fungal disease and smoking prevalence are high. We aimed to determine the impact of a combined fungal and imaging biomarker approach compared with a validated prediction model (Mayo) to rule out benign disease and diagnose lung cancer. Methods: Adults ages 40 to 90 years with 6–30 mm IPNs were included from four sites. Serum samples were tested for histoplasmosis IgG and IgM antibodies by enzyme immunoassay and a CT-based risk score was estimated from a validated radiomic model. Multivariable logistic regression models including Mayo score, radiomics score, and IgG and IgM histoplasmosis antibody levels were estimated. The areas under the ROC curves (AUC) of the models were compared among themselves and to Mayo. Bias-corrected clinical net reclassification index (cNRI) was estimated to assess clinical reclassification using a combined biomarker model. Results: We included 327 patients; 157 from histoplasmosis-endemic regions. The combined biomarker model including radiomics, histoplasmosis serology, and Mayo score demonstrated improved diagnostic accuracy when endemic histoplasmosis was accounted for [AUC, 0.84; 95% confidence interval (CI), 0.79–0.88; P Conclusions: Fungal and imaging biomarkers may improve diagnostic accuracy and meaningfully reclassify IPNs. The endemic prevalence of histoplasmosis and cancer impact model performance when using disease related biomarkers. Impact: Integrating a combined biomarker approach into the diagnostic algorithm of IPNs could decrease time to diagnosis.

Year:

2025

ROC and Calibration Plots for Temporal Validation. A, shows the area under the receiver operating characteristics curve for the main model indexed in 2013 and when it was applied to cohorts indexed in 2014, 2015, 2016, and 2017 as part of temporal validation in the Optum EHR dataset. B, shows calibration of the main model and the calibration for model applied to cohorts indexed in 2014, 2015, 2016, and 2017 in the Optum EHR dataset.

Year:

2025

Introduction: The diagnostic yield of lung biopsy modalities is often compared using data from single-arm studies. These comparisons are biased due to differences in study populations, institutional practices, and diagnostic yield definitions. While individual patient data may be useful to account for some of these co-variables, individual patient data may only be available for one study. What is the difference in the primary outcome between two single-arm studies that utilized different bronchoscopy technologies? Methods: A matching-adjusted indirect comparison analysis was performed comparing individual patient data from a retrospective multicenter cohort of consecutive RAB procedures to aggregate patient data in a prospective, multicenter clinical study of ENB procedures. The diagnostic yield was first calculated with the definition used in the comparator study, determined at 12 months after initial biopsy, with lost to follow-up excluded from the denominator (method 1), and second with a strict definition, determined at the time of bronchoscopy and nonspecific benign findings excluded (method 2). Results: Using method 1, the weighted diagnostic yield for RAB (87.1%) was significantly higher than for ENB (72.9%) (p < 0.001). Using method 2, the weighted diagnostic yield for RAB (64.9%) was also significantly higher than for ENB (50.6%) (p = 0.001). Conclusions: An optimization-based weighting approach for indirect comparisons between single-arm studies confirmed a significantly higher diagnostic yield for RAB compared to ENB. When using method 2, it was demonstrated that various factors significantly influence the diagnostic yield of RAB, highlighting the need for balancing to mitigate confounding effects, and ideally, randomized controlled trials.

Year:

2025

Background Robotic assisted bronchoscopy (RAB) and electromagnetic navigational bronchoscopy (ENB) are two approaches to biopsy peripheral pulmonary lesions (PPLs). A recently completed cluster randomized controlled trial, RELIANT ( NCT05705544 ), showed no difference in diagnostic yield between these two modalities. The ENB platform used in RELIANT included integrated digital tomosynthesis, allowing for real-time assessment of PPL location for more precise targeting at the time of biopsy. RAB has since been integrated with cone beam computed tomography (CBCT) to accomplish the same intraprocedural correction. It is unclear if the diagnostic yield of RAB with integrated CBCT (RAB-CBCT) is superior to ENB with integrated digital tomosynthesis (ENB-DT). Methods R obotic versus E lectromagnetic Bronchoscopy for Pulmonary L es I on A ssessme NT using integrated intraprocedural imaging (RELIANT 2) is an investigator-initiated, multicenter, open label, superiority, cluster randomized trial. At each participating institution, procedural rooms are randomly assigned to either RAB-CBCT or ENB-DT, with each procedure room-day considered a cluster. All adult patients undergoing navigational bronchoscopy for evaluation of PPL(s) are eligible. Allocation is concealed from schedulers, proceduralists, and patients until the morning of procedure when each room is randomized to a platform. The primary endpoint is the diagnostic yield, defined as the proportion of cases yielding a specific benign or malignant diagnosis per current ATS/ACCP definition. Secondary and safety endpoints include procedure duration and procedural complications. Enrollment began on November 11, 2024 and is expected to enroll approximately 440 patients in 220 clusters. Discussion RELIANT 2 is an ongoing cluster randomized trial comparing the diagnostic yield of RAB-CBCT to that of ENB-DT in patients undergoing bronchoscopy to biopsy PPLs. This trial will help address some of the limitations of the recently published RELIANT trial. Trial Registration The trial was registered in ClinicalTrials.gov ( NCT06654271 ) on October 21, 2024, prior to patient enrollment.

Year:

2025

Background: The heterogeneous biology of cancer subtypes, especially in lung cancer, poses significant challenges for biomarker development. Standard model building techniques often fall short in accurately incorporating various histologic subtypes because of their diverse biological characteristics. This study explores a nested biomarker model to address this issue, aiming to improve lung cancer early detection. Methods: The study included 337 patients from two clinical sites. Blood biomarkers were analyzed and various statistical methods employed to develop a nested model. This model was designed to account for the biological heterogeneity across histologic subtypes, compared against traditional logistic regression models. Results: The patient cohort included a range of malignant and benign nodules and included different cancer subtypes reflecting lung cancer heterogeneity. The nested model had comparable performance overall with the Mayo Clinic model and a standard logistic regression model with an AUC of 77.6 (95% confidence interval, 72.2–83.0) in training and 77.3 (95% confidence interval, 65.8–88.9) in testing. The nested subtype versus benign model had the best performance in the training set overall and had a particular advantage for small cell subtype prediction. Conclusions: This study highlights the challenges cancer heterogeneity present for biomarker development and the potential for nested biomarker models to improve early cancer detection. Validation of this approach in larger cohorts is essential to prove its predictive benefit in biologically diverse cancers. Impact: This work addresses the challenge of biological heterogeneity in biomarker development. A nested modeling approach may assist in developing more effective multicancer early detection strategies.

Year:

2025

The performance of eight different statistical models for lung cancer prediction depended heavily on the clinical setting they were applied in, and models generalized poorly on sites outside of their training distributions.

Year:

2025

Population health benefits of a blood-based test in lung cancer screening. A, Care pathway reflecting the recommended standard of care for lung cancer screening with LDCT that is received by 6%–10% of eligible individuals annually, as well as potential pathway employing initial blood-based test and follow-on events. B, The predicted number of cancers detected by screening scenario: LDCT alone (“base case”); LDCT + low test uptake; LDCT + high test uptake. C, Predicted cancers diagnosed at stage I versus Stage IV by screening scenario: LDCT alone (“base case”); LDCT + low test uptake; LDCT + high test uptake. D, Predicted decrease in lung cancer deaths represented by screening scenario: LDCT alone (“base case”); LDCT + low test uptake; LDCT + high test uptake. E, Simulated comparison of the predicted number needed to scan with LDCT to detect one lung cancer: LDCT alone (“base case”); LDCT + low test uptake; LDCT + high test uptake. Population-level modeling demonstrates significant health benefits when a blood-based test is available as an alternative for lung cancer screening.

Year:

2024

Year:

2024

Year:

2024

Year:

2024

Year:

2024

Year:

2022

Collaborators (15)

Michael Kammer

Research Assistant Professor

Vanderbilt University Medical Center

UNITED STATES
View details

Thomas A Lasko

Associate Professor

Vanderbilt University Medical Center

UNITED STATES
View details

Ali Zaidi

Associate Professor of Surgery / Medical Director Research

-

UNITED STATES
View details

Victor E. Velculescu

Assistant/Associate/Professor of Oncology and Pathology

Johns Hopkins University School of Medicine

UNITED STATES
View details

Bennett Landman

Professor

Vanderbilt University

UNITED STATES
View details

Nichole Tanner

Professor of Medicine

Medical University of South Carolina

UNITED STATES
View details

Samira Shojaee

Associate Professor

Vanderbilt University Medical Center

UNITED STATES
View details

Heidi Chen

Research Associate Professor

-

UNITED STATES
View details

Anil Vachani

Associate Professor, Clinician-Educator

University of Pennsylvania

UNITED STATES
View details

Manmeet Singh Ahluwalia

Professor of Translational Medicine

Florida International University Herbert Wertheim College of Medicine

UNITED STATES
View details

Rafael Paez

Assistant Professor

Vanderbilt University Medical Center

UNITED STATES
View details

Nicholas Dracopoli

Chief Scientific Officer

-

UNITED STATES
View details

Eric L. Grogan

Vanderbilt University Medical Center

UNITED STATES
View details

Kwok-Kin Wong

NYU Langone Medical Center

UNITED STATES
View details

Robert B Scharpf

Associate Professor

Johns Hopkins University School of Medicine

UNITED STATES
View details