All Publications


  • Development of a Natural Language Processing Algorithm to Aid Creation of a Surgical Spine Database. The spine journal : official journal of the North American Spine Society Wong, H. J., Song, M., Miller, S. L., Damle, E. B., Muniz, R., Mehta, S., McFarlane, K., Berg, A., Li, Y. D., Koltsov, J. C., Xiong, G. X. 2026

    Abstract

    Manual effort required for feature extraction from operative reports can be time-intensive, inaccurate, and costly.Develop a natural language processing (NLP) algorithm for surgical spine database creation and validate performance against human reviewers with varying clinical experience.Retrospective study at a tertiary academic institution from 2008-2024.Operative spinal cases on adult patients from 22,951 spinal operative reports.Primary outcome was accuracy in operated spinal level classification. Secondary outcomes include clinical diagnoses, operative procedures, and additional surgical detail classification.A rule-based NLP algorithm was developed and validated on a random sample of 100 operative reports. Performance of the NLP algorithm and human reviewers was assessed against a reference standard. An a priori acceptability threshold was set at 0.90 for agreement, kappa, and F1. Time required for chart review/processing were also assessed for the NLP algorithm and human reviewers.The NLP algorithm matched the reference standard on operated spinal levels (Percent Agreement=93%; Kappa=0.98; F1=0.98), which outperformed human reviewers in clinical training. Performance on procedural and diagnostic feature extraction did not meet the accepted threshold but largely outperformed human validators in clinical training. NLP algorithm computation time averaged speed of 1,039 reports per minute, compared to the fastest median time of 1 minute per operative report for human chart reviewers.The NLP algorithm can accurately and reliably extract operated spinal levels from high volumes of operative reports. However, classification of diagnosis, operative procedures, and additional surgical procedures were not sufficient for practical implementation.

    View details for DOI 10.1016/j.spinee.2026.10.012

    View details for PubMedID 42893773

  • Targeting cellular senescence in progenitor cells as a strategy to enhance bone regeneration by cell therapies: a systematic review of pre-clinical investigations. Stem cell research & therapy Morita, M., Damle, E. B., Shinohara, I., Murayama, M., Susuki, Y., Gao, Q., Ma, C., Chow, S. K., Goodman, S. B. 2025; 16 (1): 669

    Abstract

    With the global population aging, optimizing bone regeneration is becoming increasingly important for enhancing the quality of life among elderly individuals. Progenitor cell-based therapies, such as mesenchymal stromal cells and induced pluripotent stem cells for bone regeneration have shown challenges due to cellular senescence and the control of the differentiation processes remain significant hurdles. In particular, elevated expression of senescence markers may play a pivotal role in limiting bone regeneration. This systematic review examines how these senescence markers influence the efficacy of progenitor cell therapies and whether targeting them could improve outcomes.We conducted a systematic literature review following the PRISMA guidelines, using the PubMed, Web of Science, Embase and Scopus with the algorithm of "bone regeneration AND senescence AND marker". Data synthesis focused on human cell sources and specifically examined senescence markers related to bone regeneration.Studies using human cells were discussed in 101 papers. Based on our inclusion and exclusion criteria, 13 papers remained for our review on senescence markers in human cells within the context of bone regeneration and senescence, with and without interventional strategies. More than half of the cell sources in current aging-related studies are derived from bone marrow. Markers of aging relevant to bone regeneration include changes in cell size and morphology, increased levels of β-galactosidase (β-Gal) and Reactive Oxygen Species (ROS), and the presence of a senescence-associated secretory phenotype (SASP). Additionally, distinct senescence markers such as p16Ink4a, p21, and p53, and mitochondrial dysfunction were associated with reduced osteogenic potential and impaired regenerative capacity.Bone marrow is the most common source of cells for studies of senescence. Cellular senescence characterized by elevated expression of specific markers was consistently shown to be negatively associated with osteogenic capacity and regenerative outcomes. The most common strategies to rejuvenate senescent cells include targeting of senescence markers and oxidative stress. Among these, modulation of p53, p21, and p16 signaling pathways has been highlighted as a potential therapeutic approach for mitigating cell senescence in bone-related conditions.

    View details for DOI 10.1186/s13287-025-04767-8

    View details for PubMedID 41316412

    View details for PubMedCentralID 11010966