Nazgol Tavabi

Nazgol Tavabi

Auto-generated profile, based on publicly available information

Nazgol Tavabi

Boston Children Hospital (Harvard Medical School)

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 March 2024 in PLOS ONE
Verified
Journal Article
Open access
PDF file
NTNazgol Tavabi
Nazgol Tavabi
MSMallika Singh
Mallika Singh
JPJames Pruneski
James Pruneski
AKAta M Kiapour
Ata M Kiapour
Proper codification of medical diagnoses and procedures is essential for optimized health care management, quality improvement, research, and reimbursement tasks within large healthcare systems. Assignment of diagnostic or procedure codes is a tedious manual process, often prone to human error. Natural Language Processing (NLP) has been suggested to facilitate this manual codification process. Yet, little is known on best practices to utilize NLP for such applications. With Large Language Models (LLMs) becoming more ubiquitous in daily life, it is critical to remember, not every task requires that level of resource and effort. Here we comprehensively assessed the performance of common NLP techniques to predict current procedural terminology (CPT) from operative notes. CPT codes are commonly used to track surgical procedures and interventions and are the primary means for reimbursement. Our analysis of 100 most common musculoskeletal CPT codes suggest that traditional approaches can outperform more resource intensive approaches like BERT significantly (P-value = 4.4e-17) with average AUROC of 0.96 and accuracy of 0.97, in addition to providing interpretability which can be very helpful and even crucial in the clinical domain. We also proposed a complexity measure to quantify the complexity of a classification task and how this measure could influence the effect of dataset size on model’s performance. Finally, we provide preliminary evidence that NLP can help minimize the codification error, including mislabeling due to human error.

23 March 2024 in Artificial Intelligence in Medicine
Verified
Journal Article
Closed access
NTNazgol Tavabi
Nazgol Tavabi
JPJames Pruneski
James Pruneski
SGShahriar Golchin
Shahriar Golchin
MSMallika Singh
Mallika Singh
RSRyan Sanborn
Ryan Sanborn
AKAta Kiapour
Ata Kiapour

8 August 2023 in npj Digital Medicine
Verified
Journal Article
Open access
PDF file
NTNazgol Tavabi
Nazgol Tavabi
MRMarium Raza
Marium Raza
MSMallika Singh
Mallika Singh
SGShahriar Golchin
Shahriar Golchin
HSHarsev Singh
Harsev Singh
AKAta M. Kiapour
Ata M. Kiapour
The legalizations of medical and recreational cannabis have generated a great deal of interest in studying the health impacts of cannabis products. Despite increases in cannabis use, its documentation during clinical visits is not yet mainstream. This lack of information hampers efforts to study cannabis’s effects on health outcomes. A clear and in-depth understanding of current trends in cannabis use documentation is necessary to develop proper guidelines to screen and document cannabis use. Here we have developed and used a natural language processing pipeline to evaluate the trends and disparities in cannabis documentation. The pipeline includes a screening step to identify clinical notes with cannabis use documentation which is then fed into a BERT-based classifier to confirm positive use. This pipeline is applied to more than 23 million notes from a large cohort of 370,087 patients seen in a high-volume multi-site pediatric and young adult clinic over a period of 21 years. Our findings show a very low but growing rate of cannabis use documentation (<2%) in electronic health records with significant demographic and socioeconomic disparities in both documentation and positive use, which requires further attention.

10 October 2022 in medRxiv
Verified
Preprint
Open access
PDF file
NTNazgol Tavabi
Nazgol Tavabi
MSMallika Singh
Mallika Singh
JPJames Pruneski
James Pruneski
AKAta M. Kiapour
Ata M. Kiapour
Proper codification of medical diagnoses and procedures is essential for optimized health care management, quality improvement, research, and reimbursement tasks within large healthcare systems. Assignment of diagnostic or procedure codes is a tedious manual process, often prone to human error. Natural Language Processing (NLP) have been suggested to facilitate these manual codification process. Yet, little is known on best practices to utilize NLP for such applications. Here we comprehensively assessed the performance of common NLP techniques to predict current procedural terminology (CPT) from operative notes. CPT codes are commonly used to track surgical procedures and interventions and are the primary means for reimbursement. The direct links between operative notes and CPT codes makes them a perfect vehicle to test the feasibility and performance of NLP for clinical codification. Our analysis of 100 most common musculoskeletal CPT codes suggest that traditional approaches (i.e., TF-IDF) can outperform resource intensive approaches like BERT, in addition to providing interpretability which can be very helpful and even crucial in the clinical domain. We also proposed a complexity measure to quantify the complexity of a classification task and how this measure could influence the effect of dataset size on model’s performance. Finally, we provide preliminary evidence that NLP can help minimize the codification error, including mislabeling due to human error.

14 August 2025 in Journal of Bone and Joint Surgery
Verified
Journal Article
Closed access
ENEduardo N. Novais
Eduardo N. Novais
MMMohammadreza Movahhedi
Mohammadreza Movahhedi
PPPratik Pradhan
Pratik Pradhan
NTNazgol Tavabi
Nazgol Tavabi
MSMallika Singh
Mallika Singh
AKAta M. Kiapour
Ata M. Kiapour
Background: The precise pathological mechanisms through which obesity increases the risk of slipped capital femoral epiphysis (SCFE) remain unclear. We aimed to investigate the impact of childhood obesity on the morphology of the capital femoral epiphysis in children and adolescents without hip disorders. Methods: We performed a retrospective cross-sectional study that included 4,888 children and adolescents 7 to 19 years of age who underwent a hip or pelvic computed tomography (CT) scan, most for abdominal pain, between 2004 and 2022. Automated 3D-CT analysis assessed epiphyseal tubercle height, superior and anterior peripheral cupping, and epiphyseal tilt. Generalized additive models (GAMs) were used to examine the associations between epiphyseal morphology and age, stratified by obesity status, while adjusting for sex. Results: We observed distinct age-related trajectories of femoral-head morphology related to obesity. Subjects with obesity demonstrated a larger femoral-head diameter from ages 7 to 15 years (obese versus normal-weight differences: 0.3 to 2.3 mm), smaller epiphyseal tubercle height after 9 years of age (normal-weight versus obese differences: 0.4% to 1.3%), and a more posteriorly tilted epiphysis, as assessed by a smaller axial tilt angle (normal-weight versus obese differences: 4° to 1°) from ages 7 to 15 years. In subjects with obesity, the superior epiphyseal cupping was larger before 11 years of age (obese versus normal-weight differences: 1.6% to 0.4%), but after 13 years of age, the superior epiphyseal cupping was smaller (normal-weight versus obese differences: 0.2% to 2%). Conclusions: Children with obesity demonstrated a smaller epiphyseal tubercle height, greater posterior epiphyseal tilt, and reduced superior cupping compared with children of normal weight. These anatomical differences may contribute to the increased risk of SCFE in patients with obesity and offer potential imaging markers for earlier identification and risk-stratification. Level of Evidence: Prognostic Level III. See Instructions for Authors for a complete description of levels of evidence.

26 December 2022 in medRxiv
Verified
Preprint
Open access
PDF file
NTNazgol Tavabi
Nazgol Tavabi
JPJames Pruneski
James Pruneski
SGShahriar Golchin
Shahriar Golchin
MSMallika Singh
Mallika Singh
RSRyan M. Sanborn
Ryan M. Sanborn
AKAta Kiapour
Ata Kiapour
Building clinical registries is an important step in improving the quality and safety of patient care. With the growing size of medical records, manual abstraction becomes more and more infeasible and impractical. On the other hand, Natural Language Processing Techniques have shown promising results in extracting valuable information from unstructured clinical notes. However, the structure and nature of clinical notes are very different from regular text that state-of-the-art NLP models are trained and tested on and they have their own set of challenges. In this study, we propose SE-K, an efficient and interpretable classification approach for extracting information from clinical notes, and show that it outperforms current state-of-the-art models in text classification. We use this approach to generate a 20-year comprehensive registry of anterior cruciate ligament reconstruction operations, one of the most common orthopedics operations among children and young adults. This registry can help us better understand the outcomes of this surgery and identify potential areas for improvement which can ultimately lead to better treatment outcomes.