Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Jun;42(11-12):1008-1020.
doi: 10.1089/neu.2024.0301. Epub 2025 Apr 9.

Linking Symptom Inventories Using Semantic Textual Similarity

Eamonn Kennedy  1   2   3 Shashank Vadlamani  1   3 Hannah M Lindsey  1   2 Kelly S Peterson  3   4 Kristen Dams O'Connor  5   6 Ronak Agarwal  1 Houshang H Amiri  7   8 Raeda K Andersen  9   10 Talin Babikian  11   12 David A Baron  13 Erin D Bigler  1   14   15 Karen Caeyenberghs  16 Lisa Delano-Wood  17   18 Seth G Disner  19   20 Ekaterina Dobryakova  21   22 Blessen C Eapen  23   24 Rachel M Edelstein  25 Carrie Esopenko  5 Helen M Genova  26 Elbert Geuze  27 Naomi J Goodrich-Hunsaker  1 Jordan Grafman  28   29 Asta K Håberg  30   31 Cooper B Hodges  32 Kristen R Hoskinson  33   34 Elizabeth S Hovenden  1 Andrei Irimia  35   36   37 Neda Jahanshad  38 Ruchira M Jha  39 Finian Keleher  1 Kimbra Kenney  40   41 Inga K Koerte  42   43 Spencer W Liebel  1 Abigail Livny  44   45 Marianne Løvstad  46   47 Sarah L Martindale  48   49 Jeffrey E Max  50 Andrew R Mayer  51 Timothy B Meier  52 Deleene S Menefee  53   54 Abdalla Z Mohamed  55 Stefania Mondello  56 Martin M Monti  57   58 Rajendra A Morey  59   60 Virginia Newcombe  61 Mary R Newsome  1   2 Alexander Olsen  62   63   64 Nicholas J Pastorek  53   65 Mary Jo Pugh  66   67 Adeel Razi  68   69   70 Jacob E Resch  71 Jared A Rowland  48   72   73 Kelly Russell  74   75 Nicholas P Ryan  16   76 Randall S Scheibel  53   65 Adam T Schmidt  77   78 Gershon Spitz  79   80 Jaclyn A Stephens  81   82 Assaf Tal  83 Leah D Talbert  32 Maria Carmela Tartaglia  84   85 Brian A Taylor  86 Sophia I Thomopoulos  38 Maya Troyanskaya  53   65 Eve M Valera  87   88 Harm Jan van der Horn  51 John D Van Horn  89 Ragini Verma  90   91 Benjamin S C Wade  92 Willian C Walker  93   94 Ashley L Ware  95   96 J Kent Werner Jr  40 Keith Owen Yeates  97 Ross D Zafonte  98   99 Michael M Zeineh  100 Brandon Zielinski  1   101   102 Paul M Thompson  38   103 Frank G Hillary  104   105 David F Tate  1   2 Elisabeth A Wilde  1   2 Emily L Dennis  1   2
Affiliations

Linking Symptom Inventories Using Semantic Textual Similarity

Eamonn Kennedy et al. J Neurotrauma. 2025 Jun.

Abstract

An extensive library of symptom inventories has been developed over time to measure clinical symptoms of traumatic brain injury (TBI), but this variety has led to several long-standing issues. Most notably, results drawn from different settings and studies are not comparable. This creates a fundamental problem in TBI diagnostics and outcome prediction, namely that it is not possible to equate results drawn from distinct tools and symptom inventories. Here, we present an approach using semantic textual similarity (STS) to link symptoms and scores across previously incongruous symptom inventories by ranking item text similarities according to their conceptual likeness. We tested the ability of four pretrained deep learning models to screen thousands of symptom description pairs for related content-a challenging task typically requiring expert panels. Models were tasked to predict symptom severity across four different inventories for 6,607 participants drawn from 16 international data sources. The STS approach achieved 74.8% accuracy across five tasks, outperforming other models tested. Correlation and factor analysis found the properties of the scales were broadly preserved under conversion. This work suggests that incorporating contextual, semantic information can assist expert decision-making processes, yielding broad gains for the harmonization of TBI assessment.

Keywords: artificial intelligence; harmonization; semantic textual similarity; symptom inventories; traumatic brain injury.

PubMed Disclaimer

References

    1. Wallace W, Chan C, Chidambaram S, et al. The diagnostic and triage accuracy of digital and online symptom checker tools: A systematic review. NPJ Digit Med 2022;5(1):118; doi: 10.1038/s41746-022-00667-w - DOI - PMC - PubMed
    1. King NS, Crawford S, Wenden FJ, et al. The Rivermead Post-Concussion Symptoms Questionnaire: A measure of symptoms commonly experienced after head injury and its reliability. J Neurol 1995;242(9):587–592; doi: 10.1007/BF00868811 - DOI - PubMed
    1. Potter S, Leigh E, Wade D, et al. The Rivermead Post-Concussion Symptoms Questionnaire: A confirmatory factor analysis. J Neurol 2006;253(12):1603–1614; doi: 10.1007/s00415-006-0275-z - DOI - PubMed
    1. Cicerone KD, Kalmar K. Persistent postconcussion syndrome: The structure of subjective complaints after mild traumatic brain injury. J Head Trauma Rehabil 1995;10(3):1–17; doi: 10.1097/00001199-199510030-00002 - DOI
    1. Derogatis LR. Brief Symptom Inventory 18. n.d. Available from: https://www.researchgate.net/profile/Rachel-Bachner-Melman/post/Can_the_... [Last accessed: July 27, 2023].

LinkOut - more resources