Detecting spiritual pain in electronic medical records using large language models.
4 affiliations
- 1Department of Palliative Nursing, Health Sciences, Tohoku University Graduate School of Medicine, Sendai, Miyagi, Japan. [email protected].
- 2Department of Palliative Nursing, Health Sciences, Tohoku University Graduate School of Medicine, Sendai, Miyagi, Japan.
- 3Medical Information Technology Center, Tohoku University Hospital, Sendai, Miyagi, Japan.
- 4Department of Medical Informatics, Tohoku University Graduate School of Medicine, Sendai, Miyagi, Japan.
Abstract
Purpose
Spiritual pain is one dimension of total pain in terminally ill patients with cancer. Reducing the burden of assessing spiritual pain in electronic medical records is essential for improving the quality of spiritual care. Large language models may offer a solution. This study explored whether large language models can be used to develop an automatic system for accurately identifying spiritual pain in patients with terminal cancer.Methods
We used unstructured nursing records from patients with cancer who died in an inpatient palliative care unit at a university hospital in Japan between July and December 2024. A total of 500 records generated within 3 weeks before patients' death were randomly selected for analysis. Records were labeled for the presence of spiritual pain. Gemini-2.5-flash and Microsoft Copilot, accessible within the Tohoku University network environment, were utilized. Prompts included definitions of spiritual pain and example sentences.Results
The analyzed records were derived from 109 patients with cancer (57 (52.3%) male; mean age, 70.9 years). Manual review identified spiritual pain in 56 records (11.2%). Sensitivity for Gemini and Copilot was 1.00; specificity was 0.75 and 0.61; positive predictive value was 0.34 and 0.25; and negative predictive value was 1.00 and 1.00, respectively. Error analysis of false positives indicated that the models frequently misclassified decreased physical functions and delirium as spiritual pain.Conclusion
This study demonstrates that large language models can identify spiritual pain with performance comparable to, or exceeding, that of previous studies utilizing classical natural language processing methods.
Related
- Survival outcomes of spleen-strengthening and dampness-eliminating traditional Chinese medicine granules combined with lenvatinib for unresectable hepatocellular carcinoma: a large-sample retrospective study based on electronic medical records
- Language model-assisted label refinement for accurate sepsis detection from electronic health records
- Multi-label auxiliary decision-making model for pharmacotherapy of ischemic stroke based on BR-SA-LightGBM using real-world electronic medical records
- Determinants of healthcare providers’ satisfaction with electronic medical records system in the Ashanti region of Ghana: A multicenter cross-sectional survey
- Evaluate epidemiologic burden, treatment patterns and treatment outcomes of advanced prostate cancer in Hong Kong using territory-wide electronic medical records
BibTeX
@article{masukawa2026detecting,
title = {{Detecting spiritual pain in electronic medical records using large language models.}},
author = {Kento Masukawa and Momoe Meguro and Erika Aihara and Miku Ishida and Uta Kondo and Ryusuke Inoue and Masaharu Nakayama and Mitsunori Miyashita},
journal = {Supportive care in cancer : official journal of the Multinational Association of Supportive Care in Cancer},
year = {2026},
month = oct,
doi = {10.1007/s00520-026-11416-0},
url = {https://europepmc.org/article/MED/42955097},
note = {CC BY},
}
RIS
TY - JOUR
TI - Detecting spiritual pain in electronic medical records using large language models.
AU - Kento Masukawa
AU - Momoe Meguro
AU - Erika Aihara
AU - Miku Ishida
AU - Uta Kondo
AU - Ryusuke Inoue
AU - Masaharu Nakayama
AU - Mitsunori Miyashita
PY - 2026
DA - 2026/10/29
JO - Supportive care in cancer : official journal of the Multinational Association of Supportive Care in Cancer
DO - 10.1007/s00520-026-11416-0
UR - https://europepmc.org/article/MED/42955097
AB - Purpose Spiritual pain is one dimension of total pain in terminally ill patients with cancer. Reducing the burden of assessing spiritual pain in electronic medical records is essential for improving the quality of spiritual care. Large language models may offer a solution. This study explored whether large language models can be used to develop an automatic system for accurately identifying spiritual pain in patients with terminal cancer.Methods We used unstructured nursing records from patients with cancer who died in an inpatient palliative care unit at a university hospital in Japan between July and December 2024. A total of 500 records generated within 3 weeks before patients' death were randomly selected for analysis. Records were labeled for the presence of spiritual pain. Gemini-2.5-flash and Microsoft Copilot, accessible within the Tohoku University network environment, were utilized. Prompts included definitions of spiritual pain and example sentences.Results The analyzed records were derived from 109 patients with cancer (57 (52.3%) male; mean age, 70.9 years). Manual review identified spiritual pain in 56 records (11.2%). Sensitivity for Gemini and Copilot was 1.00; specificity was 0.75 and 0.61; positive predictive value was 0.34 and 0.25; and negative predictive value was 1.00 and 1.00, respectively. Error analysis of false positives indicated that the models frequently misclassified decreased physical functions and delirium as spiritual pain.Conclusion This study demonstrates that large language models can identify spiritual pain with performance comparable to, or exceeding, that of previous studies utilizing classical natural language processing methods.
SN - 0941-4355
SN - 1433-7339
ER -