Category Ranking

98%

Total Visits

921

Avg Visit Duration

2 minutes

Citations

20

Article Abstract

Background: Natural language processing (NLP) is thought to be a promising solution to extract and store concepts from free text in a structured manner for data mining purposes. This is also true for radiology reports, which still consist mostly of free text. Accurate and complete reports are very important for clinical decision support, for instance, in oncological staging. As such, NLP can be a tool to structure the content of the radiology report, thereby increasing the report's value.

Objective: This study describes the implementation and validation of an N-stage classifier for pulmonary oncology. It is based on free-text radiological chest computed tomography reports according to the tumor, node, and metastasis (TNM) classification, which has been added to the already existing T-stage classifier to create a combined TN-stage classifier.

Methods: SpaCy, PyContextNLP, and regular expressions were used for proper information extraction, after additional rules were set to accurately extract N-stage.

Results: The overall TN-stage classifier accuracy scores were 0.84 and 0.85, respectively, for the training (N=95) and validation (N=97) sets. This is comparable to the outcomes of the T-stage classifier (0.87-0.92).

Conclusions: This study shows that NLP has potential in classifying pulmonary oncology from free-text radiological reports according to the TNM classification system as both the T- and N-stages can be extracted with high accuracy.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10131747PMC
http://dx.doi.org/10.2196/38125DOI Listing

Publication Analysis

Top Keywords

pulmonary oncology
12
natural language
8
language processing
8
tumor node
8
node metastasis
8
radiology reports
8
free text
8
free-text radiological
8
tnm classification
8
t-stage classifier
8

Similar Publications

Background: Active vitamin D metabolites, including 25-hydroxyvitamin D (25D) and 1,25-dihydroxyvitamin D (1,25D), have potent immunomodulatory effects that attenuate acute kidney injury (AKI) in animal models.

Methods: We conducted a phase 2, randomized, double-blind, multiple-dose, 3-arm clinical trial comparing oral calcifediol (25D), calcitriol (1,25D), and placebo among 150 critically ill adult patients at high-risk of moderate-to-severe AKI. The primary endpoint was a hierarchical composite of death, kidney replacement therapy (KRT), and kidney injury (baseline-adjusted mean change in serum creatinine), each assessed within 7 days following enrollment using a rank-based procedure.

View Article and Find Full Text PDF

Importance: Patients with advanced cancer frequently receive broad-spectrum antibiotics, but changing use patterns across the end-of-life trajectory remain poorly understood.

Objective: To describe the patterns of broad-spectrum antibiotic use across defined end-of-life intervals in patients with advanced cancer.

Design, Setting, And Participants: This nationwide, population-based, retrospective cohort study used data from the South Korean National Health Insurance Service database to examine broad-spectrum antibiotic use among patients with advanced cancer who died between July 1, 2002, and December 31, 2021.

View Article and Find Full Text PDF

Purpose: Frailty measures are critical for predicting outcomes in metastatic spine disease (MSD) patients. This study aimed to evaluate frailty measures throughout the disease process.

Methods: This retrospective analysis measured frailty in MSD patients at multiple time points using a modified Metastatic Spinal Tumor Frailty Index (MSTFI).

View Article and Find Full Text PDF

Saturation of respiratory strain during robotic hysterectomy in obese women with endometrial cancer.

J Robot Surg

September 2025

Division of Gynecologic Oncology, Department of Obstetrics and Gynecology, UT Health San Antonio, 7703 Floyd Curl Drive, 7836, San Antonio, TX, 78229-3900, USA.

To evaluate intraoperative ventilatory mechanics during robotic-assisted hysterectomy in obese women with endometrial cancer and introduce the concept of a physiologic "ceiling effect" in respiratory strain. We conducted a retrospective cohort study of 89 women with biopsy-confirmed endometrial cancer who underwent robotic-assisted total hysterectomy between 2011 and 2015. Intraoperative ventilatory parameters, including plateau airway pressure and static lung compliance, were recorded at five-minute intervals.

View Article and Find Full Text PDF

Purpose: The German sector-based healthcare system poses a major challenge to continuous patient monitoring and long-term follow-up, both essential for generating high-quality, longitudinal real-world data. The national Network for Genomic Medicine (nNGM) bridges the inpatient and outpatient care sectors to provide comprehensive molecular diagnostics and personalized treatment for non-small cell lung cancer (NSCLC) patients in Germany. Building on the established nNGM infrastructure, the DigiNet study aims to evaluate the impact of digitally integrated, personalized care on overall survival (OS) and the optimization of treatment pathways, compared to routine care.

View Article and Find Full Text PDF