Scholarlink

Purpose <p>The nursing science precision health (NSPH) model considers identifying the biological basis of symptoms in order to develop precise intervention strategies that ultimately improve the overall health of the symptomatic individual. This study sought to construct a nomogram for predicting cancer-related cognitive impairment (CRCI) in patients with lung cancer within the context of the NSPH model.</p> Methods <p>A cohort of 252 patients with lung cancer was prospectively collected and randomly divided into training and validation cohorts in a 7:3 ratio. The least absolute shrinkage and selection operator (LASSO) regression method optimized variable selection, followed by multivariate logistic regression to develop a model, which subsequently formed the basis for the nomogram. The nomogram’s discrimination and calibration were evaluated using a calibration plot, the Hosmer–Lemeshow test, and the receiver operating characteristic curve (ROC). Decision curve analysis (DCA) quantified the net benefits of the nomogram across various threshold probabilities.</p> Results <p>Five pivotal variables were incorporated into the nomogram: age (≥ 65&#xa0;years), treatment, education level, albumin, and platelet-to-lymphocyte ratio (PLR). The area under the ROC curve (0.970 for the training cohort and 0.973 for the validation cohort) demonstrated the nomogram’s excellent discriminative ability. Calibration curves closely aligning with ideal curves indicated accurate predictive capability. Moreover, the nomogram exhibited a positive net benefit for predicted probability thresholds ranging from 1 to 98% in DCA.</p> Conclusion <p>Key risk factors, including advanced age (≥ 65&#xa0;years), low education level, combined chemotherapy, low albumin, and high PLR, were significantly associated with higher CRCI incidence. This nomogram model has good performance and can help identify CRCI with high accuracy in lung cancer patients.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A nomogram for predicting cancer-related cognitive impairment in lung cancer patients from a nursing science precision health model perspective

  • 期刊论文

  • 发表日期：

    2025年3月25日

查看全文
  • Lei Ye,
  • Xiaoyu Xu,
  • Lijuan Liu,
  • Fangmei Chen,
  • Guanghui Xia

摘要

Purpose

The nursing science precision health (NSPH) model considers identifying the biological basis of symptoms in order to develop precise intervention strategies that ultimately improve the overall health of the symptomatic individual. This study sought to construct a nomogram for predicting cancer-related cognitive impairment (CRCI) in patients with lung cancer within the context of the NSPH model.

Methods

A cohort of 252 patients with lung cancer was prospectively collected and randomly divided into training and validation cohorts in a 7:3 ratio. The least absolute shrinkage and selection operator (LASSO) regression method optimized variable selection, followed by multivariate logistic regression to develop a model, which subsequently formed the basis for the nomogram. The nomogram’s discrimination and calibration were evaluated using a calibration plot, the Hosmer–Lemeshow test, and the receiver operating characteristic curve (ROC). Decision curve analysis (DCA) quantified the net benefits of the nomogram across various threshold probabilities.

Results

Five pivotal variables were incorporated into the nomogram: age (≥ 65 years), treatment, education level, albumin, and platelet-to-lymphocyte ratio (PLR). The area under the ROC curve (0.970 for the training cohort and 0.973 for the validation cohort) demonstrated the nomogram’s excellent discriminative ability. Calibration curves closely aligning with ideal curves indicated accurate predictive capability. Moreover, the nomogram exhibited a positive net benefit for predicted probability thresholds ranging from 1 to 98% in DCA.

Conclusion

Key risk factors, including advanced age (≥ 65 years), low education level, combined chemotherapy, low albumin, and high PLR, were significantly associated with higher CRCI incidence. This nomogram model has good performance and can help identify CRCI with high accuracy in lung cancer patients.