Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Currently accepted at: JMIR Formative Research

Date Submitted: Nov 24, 2025
Open Peer Review Period: Nov 25, 2025 - Jan 20, 2026
Date Accepted: Aug 4, 2026
(closed for review but you can still tweet)

This paper has been accepted and is currently in production.

It will appear shortly on 10.2196/88404

The final accepted version (not copyedited yet) is in this tab.

Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.

Transforming Cancer Care Qualitative Data Analytics: Leveraging NLP to Uncover Insights from Big Qualitative Data

  • Jay Patel; 
  • Laura A Siminoff; 
  • Maria D Thomson

ABSTRACT

Background:

Qualitative research methods offer vital insights into how patients make treatment decisions, but these approaches are labor-intensive, limited by small samples, and difficult to scale. Natural Language Processing (NLP) provides a promising solution by automating the analysis of large volumes of unstructured clinical text, improving efficiency and enabling deeper understanding of complex interactions in cancer care.

Objective:

The objective of this study was to develop, test, and validate a Natural Language Processing (NLP) application capable of transforming large-scale qualitative clinical communication data into structured formats, thereby reducing the need for manual coding.

Methods:

Using 434 transcripts of physician–patient encounters collected from a prior study, we evaluated the feasibility of advanced NLP methods to analyze cancer care communication.

Results:

Transformer-based models demonstrated strong performance in extracting clinically relevant information, with RoBERTa achieving the highest F1 score (76%), outperforming both BERT (71%) and the rule-based SpaCy baseline (36%).

Conclusions:

These findings underscore the advantages of context-aware transformer architectures, which are better suited to capturing the complexity of medical dialogues than traditional rule-based approaches. Notably, while transformers provided the greatest accuracy, results also suggest the value of hybrid systems that integrate rule-based precision with the contextual depth of transformer models. Such approaches may be especially useful for capturing longer conversational sequences, such as emotional expressions, question–answer exchanges, and multi-topic utterances. Overall, this study demonstrates the potential of NLP to improve the efficiency and scalability of clinical communication analysis, expand institutional capacity to deliver standardized feedback, and enable large-scale, multi-site research on communication processes in cancer care. Clinical Trial: N/A


 Citation

Please cite as:

Patel J, Siminoff LA, Thomson MD

Transforming Cancer Care Qualitative Data Analytics: Leveraging NLP to Uncover Insights from Big Qualitative Data

JMIR Preprints. 24/11/2025:88404

DOI: 10.2196/preprints.88404

URL: https://preprints.jmir.org/preprint/88404

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.