Thomas A Lasko

Associate Professor

Vanderbilt University Medical Center
Country flagUnited States
ApplyKite TwinLearns as you apply

Make your next move.

Prepare your application

Review drafts before you send them.

Explore related searches

Articles (3)

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 The widespread adoption of electronic health records (EHRs) has resulted in the generation of large volumes of clinical notes. Learning algorithms and large language models (LLMs) train from these resources but are susceptible to noise—irrelevant or non-informative data from them. This sensitivity can lead to significant challenges, including performance degradation and the generation of inaccurate predictions or “hallucinations.” This study addresses a critical challenge in clinical informatics: efficiently filtering millions of documents for relevance before advanced language model processing, particularly in resource-constrained environments. We present a novel framework for determining document relevance in clinical settings, utilizing a chronic obstructive pulmonary disease (COPD) dataset. Methods We developed a novel framework using weak supervision and domain-expert heuristics to generate “silver standard” labels for training data and expert annotated labels (gold stand),creating two datasets to optimize the model during the development phase and subsequent testing phase. Various text representation techniques, including Bag-of-Words, TF-IDF, lightweight document embeddings, compression-based features, and UMLS concept extraction, were evaluated. These representations were used to train Random Forest, XGBoost, and K-Nearest Neighbors classifiers. Models were optimized on a small expert-annotated dataset and evaluated on a held-out test set. Results The combination of lightweight document embedding with a Random Forest classifier demonstrated the best performance, achieving a precision of 0.75, recall of 0.89, and F1-score of 0.81 (95% CI: 0.76-0.87) for identifying relevant COPD documents. This significantly outperformed baseline heuristics (precision: 0.70, recall: 0.38, F1-score: 0.50, 95% CI: 0.43-0.56) and other tested methods. Conclusion Our study presents a novel framework for identifying COPD-relevant clinical documents using lightweight embedding and machine learning. This approach effectively filters pertinent documents, enhancing information retrieval precision. The framework’s scalability and minimal annotation needs make it promising for diverse healthcare applications, potentially optimizing clinical outcomes through efficient document selection for data-driven decision support systems.

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

Collaborators (8)

Sharon Davis

Assistant Professor

Vanderbilt University Medical Center

UNITED STATES
View details

Bennett Landman

Professor

Vanderbilt University

UNITED STATES
View details

Bradley Richmond

Assistant Professor

Vanderbilt University Medical Center

UNITED STATES
View details

Fabien Maldonado

Vanderbilt University

UNITED STATES
View details

Mohammed Al-Garadi

Research Assistant Professor

Vanderbilt University Medical Center

UNITED STATES
View details

Michael Matheny

Associate Professor

Vanderbilt University Medical Center

UNITED STATES
View details

Eric L. Grogan

Vanderbilt University Medical Center

UNITED STATES
View details

Laura Paulin

Assistant Professor of Epidemiology

Dartmouth College Geisel School of Medicine

UNITED STATES
View details