Development of a nomogram for preoperative prediction of lymph node metastasis in non-small cell lung cancer: a SEER-based study

Risk profiles and a concise prediction model for lymph node metastasis in patients with lung adenocarcinoma

BACKGROUND

Lung cancer is the second most commonly diagnosed cancer and ranks the first in mortality. Pathological lymph node status(pN) of lung cancer affects the treatment strategy after surgery while systematic lymph node dissection(SLND) is always unsatisfied.

METHODS

We reviewed the clinicopathological features of 2,696 patients with LUAD and one single lesion ≤ 5 cm who underwent SLND in addition to lung resection at the Sun Yat-Sen University Cancer Center. The relationship between the pN status and all other clinicopathological features was assessed. All participants were stochastically divided into development and validation cohorts; the former was used to establish a logistic regression model based on selected factors from stepwise backward algorithm to predict pN status. C-statistics, accuracy, sensitivity, and specificity were calculated for both cohorts to test the model performance.

RESULTS

Nerve tract infiltration (NTI), visceral pleural infiltration (PI), lymphovascular infiltration (LVI), right upper lobe (RUL), low differentiated component, tumor size, micropapillary component, lepidic component, and micropapillary predominance were included in the final model. Model performance in the development and validation cohorts was as follows: 0.861 (95% CI: 0.842-0.883) and 0.840 (95% CI: 0.804-0.876) for the C-statistics and 0.803 (95% CI: 0.784-0.821) and 0.785 (95% CI: 0.755-0.814) for accuracy, and 0.754 (95% CI: 0.706-0.798) and 0.686 (95% CI: 0.607-0.757) for sensitivity and 0.814 (95% CI: 0.794-0.833) and 0.811 (95% CI: 0.778-0.841) for specificity, respectively.

CONCLUSION

Our study showed an easy and credible tool with good performance in predicting pN in patients with LUAD with a single tumor ≤ 5.0 cm without SLND and it is valuable to adjust the treatment strategy.

Using Natural Language Processing and Machine Learning to Preoperatively Predict Lymph Node Metastasis for Non-Small Cell Lung Cancer With Electronic Medical Records: Development and Validation Study

Background

Lymph node metastasis (LNM) is critical for treatment decision making of patients with resectable non–small cell lung cancer, but it is difficult to precisely diagnose preoperatively. Electronic medical records (EMRs) contain a large volume of valuable information about LNM, but some key information is recorded in free text, which hinders its secondary use.

Objective

This study aims to develop LNM prediction models based on EMRs using natural language processing (NLP) and machine learning algorithms.

Methods

We developed a multiturn question answering NLP model to extract features about the primary tumor and lymph nodes from computed tomography (CT) reports. We then combined these features with other structured clinical characteristics to develop LNM prediction models using machine learning algorithms. We conducted extensive experiments to explore the effectiveness of the predictive models and compared them with size criteria based on CT image findings (the maximum short axis diameter of lymph node >10 mm was regarded as a metastatic node) and clinician’s evaluation. Since the NLP model may extract features with mistakes, we also calculated the concordance correlation between the predicted probabilities of models using NLP-extracted features and gold standard features to explore the influence of NLP-driven automatic extraction.

Results

Experimental results show that the random forest models achieved the best performances with 0.792 area under the receiver operating characteristic curve (AUC) value and 0.456 average precision (AP) value for pN2 LNM prediction and 0.768 AUC value and 0.524 AP value for pN1&N2 LNM prediction. And all machine learning models outperformed the size criteria and clinician’s evaluation. The concordance correlation between the random forest models using NLP-extracted features and gold standard features is 0.950 and improved to 0.984 when the top 5 important NLP-extracted features were replaced with gold standard features.

Conclusions

The LNM models developed can achieve competitive performance using only limited EMR data such as CT reports and tumor markers in comparison with the clinician’s evaluation. The multiturn question answering NLP model can extract features effectively to support the development of LNM prediction models, which may facilitate the clinical application of predictive models.

Nomogram based on prognostic nutrition index and Chest CT imaging signs predicts lymph node metastasis in NSCLC patients

OBJECTIVE

To establish and validate a model capable of predicting lymph node metastasis (LNM) of non-small cell lung cancer (NSCLC) patients.

METHODS

Preoperative clinical and CT imaging data on patients with NSCLC undergoing surgery were retrospectively analyzed. A model was developed using a training cohort of 290 patients. The univariate analysis followed by dichotomous logistic regression was performed to estimate different risk factors of lymph node metastasis, and a nomogram was constructed. Using another testing cohort of 120 patients, the performance of the nomogram was validated using several evaluation methods and indices and evaluated including via the area under the curve (AUC), calibration curve, Hosmer-Lemeshow test and decision curve analysis (DCA).

RESULTS

CT-based imaging signs were important independent risk factors for lymph node metastasis in NSCLC patients. The possible risk factors also included four other independent risk factors through dichotomous logistic regression, i.e., age, SIRI, PNI and CEA, which were filtered and included in the nomogram. Nomogram yields AUC values of 0.828 [95% confidence interval (CI): 0.778-0.877] in the training cohort and 0.816 (95% CI: 0.737-0.895) in the validation cohort, respectively. The calibration curves showed high agreement in both the training and validation cohorts. At the threshold probability of 0-0.8, the nomogram increases the net outcomes compared to the treat-none and treat-all lines in the decision curve.

CONCLUSIONS

The nomogram based on the PNI and CT images signs holds promise as a novel and accurate tool for predicting the LNM in NSCLC patients and guiding intraoperative lymph node dissection.

Predict multicategory causes of death in lung cancer patients using clinicopathologic factors

BACKGROUND

Random forests (RF) is a widely used machine-learning algorithm, and outperforms many other machine learning algorithms in prediction-accuracy. But it is rarely used for predicting causes of death (COD) in cancer patients. On the other hand, multicategory COD are difficult to classify in lung cancer patients, largely because they have multiple labels (versus binary labels).

METHODS

We tuned RF algorithms to classify 5-category COD among the lung cancer patients in the surveillance, epidemiology and end results-18, whose lung cancers were diagnosed in 2004, for the completeness in their follow-up. The patients were randomly divided into training and validation sets (1:1 and 4:1 sample-splits). We compared the prediction accuracy of the tuned RF and multinomial logistic regression (MLR) models.

RESULTS

We included 42,257 qualified lung cancers in the database. The COD were lung cancer (72.41%), other causes or alive (14.43%), non-lung cancer (6.85%), cardiovascular disease (5.35%), and infection (0.96%). The tuned RF model with 300 iterations and 10 variables outperformed the MLR model (accuracy = 69.8% vs 64.6%, 1:1 sample-split), while 4:1 sample-split produced lower prediction-accuracy than 1:1 sample-split. The top-10 important factors in the RF model were sex, chemotherapy status, age (65+ vs < 65 years), radiotherapy status, nodal status, T category, histology type and laterality, all of which except T category and laterality were also important in MLR model.

CONCLUSION

We tuned RF models to predict 5-category CODs in lung cancer patients, and show RF outperforms MLR in prediction accuracy. We also identified the factors associated with these COD.