Establishment of a Nomogram-Based Prognostic Model (LASSO-COX Regression) for Predicting Progression-Free Survival of Primary Non-Small Cell Lung Cancer Patients Treated with Adjuvant Chinese Herbal Medicines Therapy: A Retrospective Study of Case Series

Abstract

Nowadays, Jin-Fu-Kang oral liquid (JFK), one of Chinese herbal medicines (CHMs) preparations, has been widely used as an adjuvant therapy for primary non-small cell lung cancer (PNSCLC) patients with the syndrome of deficiency of both Qi and Yin (Qi–Yin deficiency pattern) based on Traditional Chinese Medicine (TCM) theory. However, we found insufficient evidence of how long-term CHM treatment influence PNSCLC patients’ progression-free survival (PFS). Thus, using electronic medical records, we established a nomograph-based prognostic model for predicting PNSCLC patients’ PFS involved with JFK supplementary formulas (JFK-SFs) over 6 months, in order to preliminarily investigate potential predictors highly related to adjuvant CHMs therapies in theoretical epidemiology. In our retrospective study, a series of 197 PNSCLC cases from Long Hua Hospital were enrolled by non-probability sampling and divided into 2 datasets at the ratio of 5:4 by Kennard–Stone algorithm, as a result of 109 in training dataset and 88 in validation dataset. Besides, TNM stage, operation history, sIL-2R, and CA724 were considered as 4 highly correlated predictors for modeling based on LASSO-Cox regression. Additionally, we respectively used training dataset and validation dataset for establishment including internal validation and external validation, and the prediction performance of model was measured by concordance index (C-index), integrated discrimination improvement, and net reclassification indices (NRI). Moreover, we found that the model containing clinical characteristics and bio-features presented the best performance by pairwise comparison. Next, the result of sensitivity analysis proved its stability. Then, for preliminarily examination of its discriminative power, all eligible cases were divided into high-risk or low-risk progression by the cut-off value of 57, in the light of predicted nomogram scores. Ultimately, a completed TRIPOD checklist was used for self-assessment of normativity and integrity in modeling. In conclusion, our model might offer crude probability of uncertainly individualized PFS with long-term CHMs therapy in the real-world setting, which could discern the individuals implicated with worse prognosis from the better ones. Nevertheless, our findings were prone to unmeasured bias caused by confounding factors, owing to retrospective cases series.

A Nomogram Model for Predicting the Polyphenol Content of Pu-Erh Tea

“…The study determined and analyzed tea polyphenol contents of teas from various altitudes, soil compositions, and other different conditions in Yuecheng base. The prediction system for tea polyphenol content was constructed with the assistance of the three factors, altitude, organic matter, and P as selected with the LASSO regression model [24]. The evaluation of stability indicated that the AUC values of the training and…”

Nomogram-based prognostic tool for stage IIIB/IV non-small cell lung cancer patients undergoing traditional Chinese medicine treatment

“…Luo et al created a nomogram to predict progression-free survival (PFS) in patients undergoing adjuvant TCM treatment for NSCLC. Their study, however, did not focus on patients with advanced-stage disease nor on overall survival (OS) [ 13 ]. The present study, therefore, aimed to evaluate the prognostic factors affecting OS in patients with NSCLC treated with TCM, and to establish a nomogram for accurate prognostication, providing evidence for the use of TCM in NSCLC treatment.…”

Construction and validation of a nomogram for predicting the prognosis of patients with lymph node-positive invasive micropapillary carcinoma of the breast: based on SEER database and external validation cohort

“…and the inclusion of variables that are not significantly related to the outcome contributed little to the improvement of the model. Compared with the traditional multivariable regression, LASSO regression is considered as a better method to select variables since it can minimize overfitting and reduce the complexity of the model by using a loss function or penalty term that is added to the objective function (21)(22)(23). In addition, we have developed a network calculator based on the nomogram.…”