Prostate cancer treatment recommendation study based on machine learning and SHAP interpreter.

This study utilized data from 140,294 prostate cancer cases from the Surveillance, Epidemiology, and End Results (SEER) database. Here, 10 different machine learning algorithms were applied to develop treatment options for predicting patients with prostate cancer, differentiating between surgical and non-surgical treatments. The performances of the algorithms were measured using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, positive predictive value, negative predictive value. The Shapley Additive Explanations (SHAP) method was employed to investigate the key factors influencing the prediction process. Survival analysis methods were used to compare the survival rates of different treatment options. The CatBoost model yielded the best results (AUC = 0.939, sensitivity = 0.877, accuracy = 0.877). SHAP interpreters revealed that the T stage, cancer stage, age, cores positive percentage, prostate-specific antigen, and Gleason score were the most critical factors in predicting treatment options. The study found that surgery significantly improved survival rates, with patients undergoing surgery experiencing a 20.36% increase in 10-year survival rates compared with those receiving non-surgical treatments. Among surgical options, radical prostatectomy had the highest 10-year survival rate at 89.2%. This study successfully developed a predictive model to guide treatment decisions for prostate cancer. Moreover, the model enhanced the transparency of the decision-making process, providing clinicians with a reference for formulating personalized treatment plans.

Incidence Trends, Clinicopathologic Characteristics, and Overall Survival Prediction in Retinoblastoma Children: SEER Prognostic Nomogram Analysis.

BACKGROUND: Retinoblastoma is the most common intraocular malignant tumor occurring among children, with an incidence rate of 1/15 000. This study built a joinpoint regression model to assess the incidence trend of retinoblastoma from 2004 to 2015 and constructed a nomogram to predict the overall survival (OS) in children. MATERIALS AND METHODS: Patients less than 19 years diagnosed with retinoblastoma from 2004 to 2015 were selected from the SEER database. Joinpoint regression analysis (version 4.9.0.0) was performed to evaluate the trends in retinoblastoma incidence rates from 2004 to 2015. Cox Regression Analysis was applied to investigate prognostic risk factors that influence OS. RESULTS: Joinpoint regression revealed that retinoblastoma incidence exhibited no significant increase or decrease from 2004 to 2015. As per the multiple Cox regression, tumor size, laterality, and residence (rural-urban continuum code) were correlated with OS and were used to construct a nomogram. The nomogram exhibited a good C-index of 0.71 (95% CI, 0.63 to 0.79), and the calibration curve for survival probability demonstrated that the predictions corresponded well with actual observations. CONCLUSIONS AND RELEVANCE: A prognostic nomogram integrating the risk factors for retinoblastoma was constructed to provide comparatively accurate individual survival predictions. If validated, this type of assessment could be used to guide therapy in patients with retinoblastoma.

Trends in HR+ metastatic breast cancer survival before and after CDK4/6 inhibitor introduction in the United States: a SEER registry analysis of patients with HER2- and HER2+ metastatic breast cancer.

PURPOSE: Cyclin-dependent kinase 4/6 inhibitors (CDK4/6i) have improved patient survival in hormone receptor-positive/human epidermal growth factor receptor 2-negative (HR+/HER2-) metastatic breast cancer (mBC) in clinical trials and real-world studies. However, investigations of survival gains in broader HR+/HER2- mBC populations using epidemiological approaches are limited. METHODS: This retrospective study used SEER registry data to assess breast cancer-specific survival (BCSS) in patients diagnosed with HR+/HER2- de novo mBC from 2010 to 2019. Kaplan-Meier and Cox proportional hazards models were used to compare BCSS in patients diagnosed before (2010‒2013 with follow-up to 2014) and after (2015‒2018 with follow-up to 2019) the 2015 guideline recommendations for CDK4/6i use. A comparison was made to patients with HR+/HER2-positive (HER2+) de novo mBC, for which no major guideline changes occurred during 2015-2018. RESULTS: Data from 11,467 women with HR+/HER2- mBC and 3260 women with HR+/HER2+ mBC were included. After baseline characteristic adjustment, patients with HR+/HER2- mBC diagnosed post-2015 (n = 6163), had an approximately 10% reduction in risk of BC-specific death compared with patients diagnosed pre-2015 (n = 5304; HR = 0.895, p < 0.0001). Conversely, no significant change was observed in HR+/HER2+ BCSS post-2015 (n = 1798) versus pre-2015 (n = 1462). Similar results were found in patients aged ≥ 65 years. CONCLUSION: Using one of the largest US population-based longitudinal cancer databases, significant improvements in BCSS were noted in patients with HR+/HER2- mBC post-2015 versus pre-2015, potentially due to the introduction of CDK4/6i post-2015. No significant improvement in BCSS was observed in patients with HR+/HER2+ mBC post-2015 versus pre-2015, likely due to the availability of HER2-directed therapies in both time periods.

Identifying Optimal Candidates for Primary Tumor Resection Among Metastatic Pancreatic Cancer Patients: A Population-Based Predictive Model.

BACKGROUND: There is a controversy about whether surgery should proceed among metastatic pancreatic cancer (mPC) patients. A survival benefit was observed in mPC patients who underwent primary tumor resection; however, determining which patients would benefit from surgery is complex. For this purpose, we created a model to identify mPC patients who may benefit from primary tumor excision. METHODS: Patients with mPC were extracted from the Surveillance, Epidemiology, and End Results database, and separated into surgery and nonsurgery groups based on whether the primary tumor was resected. Propensity score matching (PSM) was applied to balance confounding factors between the two groups. A nomogram was developed using multivariable logistic regression to estimate surgical benefit. Our model is evaluated using multiple methods. RESULTS: About 662 of 14,183 mPC patients had primary tumor surgery. Kaplan-Meier analyses showed that the surgery group had a better prognosis. After PSM, a survival benefit was still observed in the surgery group. Among the surgery cohort, 202 patients survived longer than 4 months (surgery-beneficial group). The nomogram discriminated better in training and validation sets under the receiver operating characteristic (ROC) curve (AUC), and calibration curves were consistent. Decision curve analysis (DCA) revealed that it was clinically valuable. This model is better at identifying candidates for primary tumor excision. CONCLUSION: A helpful prediction model was developed and validated to identify ideal candidates who may benefit from primary tumor resection in mPC.

Post-mastectomy reirradiation for ipsilateral T3N0M0 breast tumor relapse: a population-based study.

INTRODUCTION: Post-mastectomy radiotherapy is commonly recommended for T3N0M0 breast cancer, particularly in the presence of adverse prognostic factors. However, for T3N0M0 ipsilateral recurrences following breast-conserving surgery and adjuvant radiotherapy, the situation is distinct. Recurrence alone signifies a negative prognostic factor. Moreover, tumor relapses within previously irradiated areas exhibit enhanced radioresistance, and reirradiation of the chest wall carries an escalated risk of radiation-induced toxicity. This study aimed to assess the impact of post-mastectomy reirradiation (PM-reRT) on patient outcomes in cases of ipsilateral T3N0M0 breast tumor recurrence, using data from the SEER database. MATERIALS AND METHODS: We identified all patients who underwent treatment for primary non-metastatic breast cancer with breast-conserving surgery followed by adjuvant radiotherapy in the SEER database; among them, those who later experienced a localized T3N0M0 breast tumor recurrence and underwent total mastectomy were included. The study's goal was to compare overall survival (OS) and cancer-specific survival (CSS) between patients who underwent only mastectomy versus those who had mastectomy followed by adjuvant PM-reRT for their ipsilateral T3N0M0 breast tumor relapse. RESULTS: From 2000 to 2020, the SEER database recorded 44 patients with an ipsilateral T3N0M0 breast tumor recurrence after initial conservative treatment, managed with total mastectomy. No statistically significant differences in OS or CSS were observed between patients undergoing mastectomy (MT) alone versus those receiving MT combined with PM-reRT (p = 0.68 and p = 0.86, respectively). Five-year OS rates for the MT and MT + PM-reRT cohorts were 49.5% [95% CI: 29.9-81.8] and 41.7% [10.0-100.0], respectively, while 5­year CSS rates were 51.6% [12.0-99.5] and 58.3% [15.2-100.0], respectively. CONCLUSION: For patients undergoing total mastectomy after an ipsilateral T3N0M0 breast tumor recurrence, subsequent to initial breast cancer treatment involving breast-conserving surgery and adjuvant radiotherapy, chest wall reirradiation does not enhance survival outcomes. As such, it should not be routinely performed.

Development and validation of a nomogram for predicting overall survival in patients with sinonasal mucosal melanoma.

BACKGROUND: Sinonasal mucosal melanoma (SNMM) is a relatively rare malignant tumour with a poor prognosis. This study was designed to identify prognostic factors and establish a nomogram model to predict the overall survival (OS) of patients with SNMM. METHODS: A total of 459 patients with SNMM were selected from the Surveillance, Epidemiology, and End Results (SEER) database as the training cohort. Univariate and multivariate Cox regression analyses were used to screen for independent factors associated with patient prognosis and develop the nomogram model. In addition, external validation was performed to evaluate the effectiveness of the nomogram with a cohort of 34 patients with SNMM from Peking Union Medical College Hospital. RESULTS: The median OS in the cohort from the SEER database was 28 months. The 1-year, 3-year and 5-year OS rates were 69.8%, 40.4%, and 30.0%, respectively. Multivariate Cox regression analysis indicated that age, T stage, N stage, surgery and radiotherapy were independent variables associated with OS. The areas under the receiver operating characteristic curves (AUCs) of the nomograms for predicting 1-, 3- and 5-year OS were 0.78, 0.71 and 0.71, respectively, in the training cohort. In the validation cohort, the area under the curve (AUC) of the nomogram for predicting 1-, 3- and 5-year OS were 0.90, 0.75 and 0.78, respectively. Patients were classified into low- and high-risk groups based on the total score of the nomogram. Patients in the low-risk group had a significantly better survival prognosis than patients in the high-risk group in both the training cohort (P < 0.0001) and the validation cohort (P = 0.0016). CONCLUSION: We established and validated a novel nomogram model to predict the OS of SNMM patients stratified by age, T stage, N stage, surgery and radiotherapy. This predictive tool is of potential importance in the realms of patient counselling and clinical decision-making.

Prognostic Impact of Neoadjuvant Chemotherapy in Localized or Locoregionally Advanced Gallbladder Cancer: A Population-Based and Propensity Score Matched SEER Analysis.

BACKGROUND: The effect of neoadjuvant chemotherapy (NACT) in gallbladder cancer (GBC) patients remains controversial. The aim of this study was to assess the impact of NACT on overall survival (OS) and cancer specific survival (CSS) in patients with localized or locoregionally advanced GBC, and to explore possible protective predictors for prognosis. METHODS: Data for patients with localized or locoregionally advanced GBC (i.e., categories cTx-cT4, cN0-2, and cM0) from 2004 to 2020 were collected from the Surveillance, Epidemiology, and End Results (SEER) database. Patients in the NACT and non-NACT groups were propensity score matched (PSM) 1:3, and the Kaplan-Meier method and log-rank test were performed to analyze the impact of NACT on OS and CSS. Univariable and multivariable Cox regression models were applied to identify the possible prognostic factors. Subgroup analysis was conducted to identify patients who would benefit from NACT. RESULTS: Of the 2676 cases included, 78 NACT and 234 non-NACT patients remained after PSM. In localized or locoregionally advanced GBC patients, the median OS of the NACT and non-NACT was 31 and 16 months (log-rank P < 0.01), and the median CSS of NACT and non-NACT was 32 and 17 months (log-rank P < 0.01), respectively. Longer median OS (31 vs 17 months, log-rank P < 0.01) and CSS (32 vs 20 months, log-rank P < 0.01) was associated with NACT compared with surgery alone. Multivariable Cox regression analysis showed that NACT, stage, and surgery type were prognostic factors for OS and CSS in GBC patients. Subgroup analysis revealed that the survival hazard ratios (HRs) of NACT vs non-NACT for localized or locoregionally advanced GBC patients were significant in most subgroups. CONCLUSIONS: NACT may provide therapeutic benefits for localized or locoregionally advanced GBC patients, especially for those with advanced stage, node-positive, poorly differentiated or undifferentiated disease. NACT combined with radical surgery was associated with a survival advantage. Therefore, NACT combined with surgery may provide a better treatment option for resectable GBC patients.

Establishment and Validation of Prognostic Nomograms for Patients with Metastatic Pulmonary Large Cell Neuroendocrine Carcinoma.

PURPOSE: Metastatic pulmonary large cell neuroendocrine carcinoma (LCNEC) is an aggressive cancer with generally poor outcomes. Effective methods for predicting survival in patients with metastatic LCNEC are needed. This study aimed to identify independent survival predictors and develop nomograms for predicting survival in patients with metastatic LCNEC. PATIENTS AND METHODS: We conducted a retrospective analysis using the Surveillance, Epidemiology, and End Results (SEER) database, identifying patients with metastatic LCNEC diagnosed between 2010 and 2017. To find independent predictors of cancer-specific survival (CSS), we performed Cox regression analysis. A nomogram was developed to predict the 6-, 12-, and 18-month CSS rates of patients with metastatic LCNEC. The concordance index (C-index), area under the receiver operating characteristic (ROC) curves (AUC), and calibration curves were adopted with the aim of assessing whether the model can be discriminative and reliable. Decision curve analyses (DCAs) were used to assess the model's utility and benefits from a clinical perspective. RESULTS: This study enrolled a total of 616 patients, of whom 432 were allocated to the training cohort and 184 to the validation cohort. Age, T staging, N staging, metastatic sites, radiotherapy, and chemotherapy were identified as independent prognostic factors for patients with metastatic LCNEC based on multivariable Cox regression analysis results. The nomogram showed strong performance with C-index values of 0.733 and 0.728 for the training and validation cohorts, respectively. ROC curves indicated good predictive performance of the model, with AUC values of 0.796, 0.735, and 0.736 for predicting the 6-, 12-, and 18-month CSS rates of patients with metastatic LCNEC in the training cohort, and 0.795, 0.801, and 0.780 in the validation cohort, respectively. Calibration curves and DCAs confirmed the nomogram's reliability and clinical utility. CONCLUSION: The new nomogram was developed for predicting CSS in patients with metastatic LCNEC, providing personalized risk evaluation and aiding clinical decision-making.

Identifying the Best Candidate for Primary Tumor Resection in Patients With Advanced Osteosarcoma.

OBJECTIVES: Not all patients with stage III and IV osteosarcoma who undergo surgery to remove the primary tumor will benefit from surgery; therefore, we developed a nomogram model to test the hypothesis that only a subset of patients will benefit from surgery. METHODS: 412 patients were screened from the Surveillance, Epidemiology and End Results (SEER) database. Subsequently, 1:1 propensity score matching (PSM) was used to screen and balance confounders. We first made the hypothesis that patients who underwent the procedure would benefit more. A multivariate Cox model was used to explore the independent influencing factors of CSS in two groups (benefit group and non-benefit group) and constructed nomograms with predicted prognosis. Finally, receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA) were used to verify the performance of the nomogram. RESULTS: Of these patients, approximately 110 did not undergo primary tumour resection. After passing PSM, they were divided into a surgical group and a non-surgical group. Age, primary site and chemotherapy as calculated independent factors were used to construct a nomogra. The predicted nomogram showed good consistency in terms of the ROC curve and the calibration curve, and the DCA curve showed a certain clinical utility. Finally, dividing the surgical patients into surgical beneficiaries and surgical non-beneficiaries, a Kaplan-Meier analysis showed that the nomogram can identify patients with osteosarcoma who can benefit from surgery. CONCLUSION: A practical predictive model was established to determine whether patients with stage III or IV osteosarcoma would benefit from surgery.

Development and external validation of a nomogram predicting overall survival for Gastric adenocarcinoma patients with radical gastrectomy.

PURPOSE: The aim of this study was to develop and externally validate a nomogram to accurately predict the overall survival (OS) of patients with gastric adenocarcinoma who underwent radical gastrectomy. MATERIALS AND METHODS: A total of 3492 patients with gastric adenocarcinoma who underwent radical gastrectomy from 2012 to 2017 were included as the training cohort. Survival analysis was performed via Kaplan Meier method and log-rank test. Independent postoperative prognostic factors in patients with gastric adenocarcinoma were analyzed using univariate and multifactorial COX analysis methods. The prognosis nomogram was established in the training cohort and verified externally in the Surveillance, Epidemiology and End Results (SEER) database. RESULTS: According to the univariate and multifactorial COX analyses, metastatic lymph node ratio (MLNR) and five other independent prognostic factors (age at surgery, type of gastrectomy, tumor size, T stage, and pathological grade) were included in the prognostic nomogram. The nomogram had better prognostic predictive ability than the American Joint Committee on Cancer (AJCC) TNM staging in both the training (C-index: 0.736 VS. 0.668) and external validation cohort (C-index: 0.712 VS. 0.627). The calibration plots showed that the predicted survival rate was in good agreement with the actual survival rate. And the decision curve analysis (DCA) curves revealed that nomogram showed stronger ability in predicting 1-year, 3-year, and 5-year OS. CONCLUSION: This study estimated the excellent prognostic predictive power and clinical application potential of the MLNR-based nomogram, which may be used to facilitate postoperative clinical treatment decisions and potentially improve patient survival outcomes.

Construction and validation of a nomogram for cancer specific survival of postoperative pancreatic cancer based on the SEER and China database.

BACKGROUND: The recurrence rate and mortality rate among postoperative pancreatic cancer patients remain elevated. This study aims to develop and validate the cancer-specific survival period for individuals who have undergone pancreatic cancer surgery. METHODS: We extracted eligible data from the Surveillance, Epidemiology, and End Results database and randomly divided all patients into a training cohort and an internal validation cohort. External validation was performed using a separate Chinese cohort. The nomogram was developed using significant risk factors identified through univariate and multivariate Cox proportional hazards regression. The effectiveness of the nomogram was assessed using the area under the time-dependent curve, calibration plots, and decision curve analysis. Kaplan-Meier survival curves were utilized to visualize the risk stratification of nomogram and AJCC stage. RESULTS: Seven variables were identified through univariate and multivariate analysis to construct the nomogram. The consistency index of the nomogram for predicting overall survival was 0.683 (95% CI: 0.675-0.690), 0.689 (95% CI: 0.677-0.701), and 0.823 (95% CI: 0.786-0.860). The AUC values for the 1- and 2-year time-ROC curves were 0.751 and 0.721 for the training cohort, 0.731 and 0.7554 for the internal validation cohort, and 0.901 and 0.830 for the external validation cohorts, respectively. Calibration plots demonstrated favorable consistency between the predictions of the nomogram and actual observations. Moreover, the decision curve analysis indicated the clinical utility of the nomogram, and the risk stratification of the nomogram effectively identified high-risk patients. CONCLUSION: The nomogram guides clinicians in assessing the survival period of postoperative pancreatic cancer patients, identifying high-risk groups, and devising tailored follow-up strategies.

A novel log odds of positive lymph nodes-based nomogram for predicting overall survival in patients with colorectal signet ring cell carcinoma: a SEER population-based study.

PURPOSE: Considering the poor prognosis and high lymph node (LN) involvement rate of colorectal signet ring cell carcinoma (SRCC), this study aimed to construct a prognostic nomogram to predict overall survival (OS) with satisfactory accuracy and utility, based on LN status indicators with superior predictability. METHODS: Using the Surveillance, Epidemiology, and End Results (SEER) database, we obtained cases of colorectal SRCC patients and employed univariate and multivariate Cox analyses to determine independent prognostic factors. Kaplan-Meier curves were utilized to visualize survival differences among these factors. Receiver operating characteristic curves were generated to assess predictive performances of models incorporating various LN status indicators. A novel nomogram, containing optimal LN status indicators and other prognostic factors, was developed to predict OS, whose discriminatory ability and accuracy were evaluated using calibration curves and decision curve analysis. RESULTS: A total of 1663 SRCC patients were screened from SEER database. Older patients and those with grades III-IV, tumor sizes > 39 mm, T3/T4 stage, N1/N2 stage, M1 stage, and higher log odds of positive lymph nodes (LODDS) values exhibited poorer prognoses. Age, grade, tumor size, TNM stage, and LODDS were independent prognostic factors. The model containing N stage and LODDS outperformed the one relying solely on N stage as LN status indicator, resulting in a validated nomogram for accurately predicting OS in SRCC patients. CONCLUSION: The integration of LODDS, N stage, and other risk factors into a nomogram offered precise OS predictions, enhancing therapeutic decision-making and tailored follow-up management for colorectal SRCC patients.

Association of radioactive iodine treatment in differentiated thyroid cancer and cardiovascular death: a large population-based study.

PURPOSE: The risk of cardiovascular diseases' death (CVD) in patients with differentiated thyroid cancer (DTC) treated with radioactive iodine (RAI) after surgery has not been adequately studied. METHODS: Data of DTC patients who received RAI after surgery were retrieved from the Surveillance, Epidemiology, and End Result (SEER) database (2004-2015). Standardized mortality rate (SMR) analysis was used to evaluate the CVD risk in patients with RAI vs general population. A 1:1 propensity score matching (PSM) was applied to balance inter-group bias, and Pearson's correlation coefficient was used to detect collinearity between variables. The Cox proportional hazard model and multivariate competing risk model were utilized to evaluate the impact of RAI on CVD. At last, we curved forest plots to compare differences in factors significantly associated with CVD or cancer-related deaths. RESULTS: DTC patients with RAI treatment showed lower SMR for CVD than general population (RAI: SMR = 0.66, 95% CI 0.62-0.71, P < 0.05). After PSM, Cox proportional hazard regression demonstrated a decreased risk of CVD among patients with RAI compared to patients without (HR = 0.76, 95% CI 0.6-0.97, P = 0.029). However, in competing risk regression analysis, there was no significant difference (adjusted HR = 0.82, 95% CI 0.66-1.01, P = 0.11). The independent risk factors associated with CVD were different from those associated with cancer-related deaths. CONCLUSION: The CVD risk between DTC patients treated with RAI and those who did not was no statistical difference. Noteworthy, they had decreased CVD risk compared with the general population.

Treatment of secondary uterine malignancy following radiotherapy for cervical cancer: a study based on the SEER database.

BACKGROUND: Radiotherapy is one of the main treatments for cervical cancer. Long-term complications of radiation exposure include the emergence of secondary tumors. This is a retrospective study based on an American population. We discuss the optimal treatment modality for patients with radiation-induced secondary uterine malignancy based on the Surveillance, Epidemiology, and End Results database. METHODS: The study included patients with a definitive pathological diagnosis of cervical cancer who were diagnosed with a uterine malignant tumor ≥ 1 year later. Patients in whom cervical cancer was not the first tumor or patients with missing data were excluded. Univariate and multivariate analyses were performed using the COX regression model to screen independent prognostic factors affecting overall survival. Kaplan-Meier survival curves were analyzed using the R software package. RESULTS: We screened 142 patients with a secondary uterine malignancy after cervical cancer treatment, 115 patients with a secondary uterine malignancy after radiotherapy, and 27 patients with a secondary uterine malignancy who did not receive radiotherapy. The average latency period for developing a secondary tumor was 8 years, and 57.04% of the patients had a second tumor at ≥ 60 years of age. In patients with a secondary uterine malignancy after radiotherapy, surgery improved the prognosis [hazard ratio (HR), 0.374; 95% confidence interval (CI), 0.229-0.612], whereas radiotherapy and chemotherapy did not reduce the risk of death. In the subgroup analysis, the surgery plus chemotherapy group had a significantly better survival prognosis than the other groups (HR, 0.251; 95% CI, 0.122-0.515). CONCLUSIONS: The results suggest that the treatment modality in patients with secondary uterine malignancy after radiotherapy for cervical cancer has a significant impact on survival. The survival outcomes of patients receiving surgery combined with chemotherapy are superior to those of patients receiving other treatments.

Effect of different treatment modalities on the prognosis of stage IV epithelial ovarian cancer: analysis of the SEER database.

BACKGROUND: The prognosis of advanced ovarian cancer is often poor. Although there are several treatment options for stage IV epithelial ovarian cancer, it is not clear which treatment will benefit the patient's prognosis.We conducted an analysis using the SEER database to compare the impact of different treatment modalities on the prognosis of advanced ovarian cancer. METHODS: The present study conducts a retrospective analysis of relevant data from the SEER database pertaining to patients diagnosed with stage IV epithelial ovarian cancer between 2011 and 2020 (n = 5345). Statistical methods including Kaplan-Meier curves, log-rank tests, and Cox regression analysis are employed to ascertain the impact of different treatment regimens on the prognosis of patients with stage IV epithelial ovarian cancer. RESULTS: Among patients with stage IV epithelial ovarian cancer, age ≥ 60 and the presence of lung metastases or multiple metastases were identified as poor prognostic factors. Conversely, being Asian or Pacific Islander, married, and testing negative for CA125 were associated with favorable prognoses. In terms of the choice of treatment for patients, surgery plus chemotherapy was the best treatment modality, and timely surgery could significantly improve the prognosis of patients, but there was no difference between chemoradiotherapy alone and the surgery group among patients with lung metastases. CONCLUSION: The prognosis of patients with stage IV epithelial ovarian cancer is influenced by many factors. In terms of the choice of treatment, patients with surgery plus chemotherapy have the best prognosis. In cases where lung metastases are inoperable, a combination of radiotherapy and chemotherapy can be used. In other cases, radiotherapy does not improve outcomes in patients with stage IV epithelial ovarian cancer. This study provides a basis for the choice of treatment for patients with stage IV epithelial ovarian cancer.

Prognostic nomograms for breast cancer with lung metastasis: a SEER-based population study.

BACKGROUND: Lung metastasis is a significant adverse predictor of prognosis in patients with breast cancer. Accurate estimation for the prognosis of patients with lung metastasis and population-based validation for the models are lacking. In the present study, we aimed to establish the nomogram to identify prognostic factors correlated with lung metastases and evaluate individualized survival in patients with lung metastasis based on SEER (Surveillance, Epidemiology, and End Results) database. METHODS: We selected 1197 patients diagnosed with breast cancer with lung metastasis (BCLM) from the SEER database and randomly assigned them to the training group (n = 837) and the testing group (n = 360). Based on univariate and multivariate Cox regression analysis, we evaluated the effects of multiple variables on survival in the training group and constructed a nomogram to predict the 1-, 2-, and 3-year survival probability of patients. The nomogram were verified internally and externally by Concordance index (C-index), Net Reclassification (NRI), Integrated Discrimination Improvement (IDI), Decision Curve Analysis (DCA), and calibration plots. RESULTS: According to the results of multi-factor Cox regression analysis, age, histopathology, grade, marital status, bone metastasis, brain metastasis, liver metastasis, human epidermal growth factor receptor 2 (HER2), estrogen receptor (ER), progesterone receptor (PR), surgery, neoadjuvant therapy and chemotherapy were considered as independent prognostic factors for patients with BCLM. The C-index in the training group was 0.719 and the testing group was 0.695, respectively. The AUC values of the 1-, 2-, and 3-year prognostic nomogram in the training group were 0.798, 0.790 and 0.793, and the corresponding AUC values in the testing group were 0.765, 0.761 and 0.722. The calculation results of IDI and NRI were shown. The nomograms significantly improved the risk reclassification for 1-, 2-, and 3-year overall mortality prediction compared with the AJCC 7th staging system. According to the calibration plot, nomograms showed good consistency between predicted and actual overall survival (OS) values for the patients with BCLM. DCA showed that nomograms had better net benefits at different threshold probabilities at different time points compared with the AJCC 7th staging system. CONCLUSIONS: Nomograms that predicted 1-, 2-, and 3-year OS for patients with BCLM were successfully constructed and validated to help physicians in evaluating the high risk of mortality in breast cancer patients.

Development and validation of prognostic models for small cell lung cancer patients with liver metastasis: a SEER population-based study.

BACKGROUND: This study was to establish and validate prediction models to predict the cancer-specific survival (CSS) and overall survival (OS) of small-cell lung cancer (SCLC) patients with liver metastasis. METHODS: In the retrospective cohort study, SCLC patients with liver metastasis between 2010 and 2015 were retrospectively retrieved from the Surveillance, Epidemiology, and End Results (SEER) database. Patients were randomly divided into the training group and testing group (3: 1 ratio). The Cox proportional hazards model was used to determine the predictive factors for CSS and OS in SCLC with liver metastasis. The prediction models were conducted based on the predictive factors. The performances of the prediction models were evaluated by concordance indexes (C-index), and calibration plots. The clinical value of the models was evaluated by decision curve analysis (DCA). RESULTS: In total, 8,587 patients were included, with 154 patients experiencing CSS and 154 patients experiencing OS. The median follow-up was 3 months. Age, gender, marital status, N stage, lung metastases, multiple metastases surgery of metastatic site, chemotherapy, and radiotherapy were independent predictive factors for the CSS and OS of SCLC patients with liver metastasis. The prediction models presented good performances of CSS and OS among patients with liver metastasis, with the C-index for CSS being 0.724, whereas the C-index for OS was 0.732, in the training set. The calibration curve showed a high degree of consistency between the actual and predicted CSS and OS. DCA suggested that the prediction models provided greater net clinical benefit to these patients. CONCLUSION: Our prediction models showed good predictive performance for the CSS and OS among SCLC patients with liver metastasis. Our developed nomograms may help clinicians predict CSS and OS in SCLC patients with liver metastasis.

The survival prediction of advanced colorectal cancer received neoadjuvant therapy-a study of SEER database.

PURPOSE: The aim of study was to screen factors associated with the overall survival of colorectal cancer patients with lymph nodes metastasis who received neoadjuvant therapy and construct a nomogram model. METHODS: All enrolled subjects of the SEER database were randomly assigned to the training and testing group in a ratio of 3:2. The patients of Tangdu Hospital were seemed as validation group. Univariate cox regression analysis, lasso regression and random forest survival were used to screen variables related to the survival of advanced CRC patients received neoadjuvant therapy in the training group. Area under curves were adopted to evaluate the 1,3,5-year prediction value of the optimal model in three cohorts. Calibration curves were drawn to observe the prediction accuracy of the nomogram model. Decision curve analysis was used to assess the potential clinical value of the nomogram model. RESULTS: A total of 1833 subjects were enrolled in this study. After random allocation, 1055 cases of the SEER database served as the training group, 704 cases as the testing group and 74 patients from our center as the external validation group. Variables were screened by univariate cox regression used to construct a nomogram survival prediction model, including M, age, chemotherapy, CEA, perineural invasion, tumor size, LODDS, liver metastasis and radiation. The AUCs of the model for predicting 1-year OS in the training group, testing and validation group were 0.765 (0.703,0.827), 0.772 (0.697,0.847) and 0.742 (0.601,0.883), predicting 3-year OS were 0.761 (0.725,0.780), 0.742 (0.699,0.785), 0.733 (0.560,0.905) and 5-year OS were 0.742 (0.711,0.773), 0.746 (0.709,0.783), 0.838 (0.670,0.980), respectively. The calibration curves showed the difference between prediction probability of the model and the actual survival was not significant in three cohorts and the decision curve analysis revealed the practice clinical application value. And the prediction value of model was better for young CRC than older CRC patients. CONCLUSION: A nomogram model including LODDS for the prognosis of advanced CRC received neoadjuvant therapy was constructed and verified based on the SEER database and single center practice. The accuracy and potential clinical application value of the model performed well, and the model had better predictive value for EOCRC than LOCRC.

Pelvic organ-preserving radical cystectomy versus standard radical cystectomy in female patients diagnosed with bladder cancer.

BACKGROUND: Pelvic organ-preserving radical cystectomy (POPRC) has been reported to result in a better postoperative quality of life in female with bladder cancer compared to standard radical cystectomy (SRC). However, its oncological outcomes remain a concern. PATIENTS AND METHODS: Female patients with bladder cancer who underwent POPRC or SRC were identified from the Surveillance, Epidemiology, and End Results (SEER) database. Logistic regression was used to identify predictors of POPRC usage. To avoid the potential impact of baseline differences between groups on survival, a 1:2 propensity score matching (PSM) was implemented. After that, Kaplan-Meier curves and Log-rank tests were used to determine the significance of overall survival (OS) differences between patients in the SRC group and POPRC group. Finally, subgroup analysis based on predetermined indicators was performed. RESULTS: A total of 2193 patients were included with a median follow-up of 53 months, of whom 233 (10.6%) received POPRC and 1960 (89.4%) received SRC. No definitive predictors of POPRC were identified. Before PSM, POPRC resulted in comparable OS to SRC (HR = 1.09, p = 0.309), while after PSM, POPRC was associated with significantly worse OS (HR = 1.23, p = 0.038). In subgroup analyses, POPRC led to non-inferior OS (HR = 1.18, 95%CI 0.71-1.95, p = 0.531) in patients with non-muscle invasive bladder cancer (NMIBC) and T2 patients (HR = 1.07, p = 0.669), but significantly worse OS in T3 patients (HR = 1.41, p = 0.02). CONCLUSION: Currently, patients undergoing POPRC have not undergone strict screening, and candidates for POPRC should have more stringent criteria in the future to achieve satisfactory oncological outcomes. However, flaws in the study make more evidence needed to support our findings.

A novel nomogram based on the number of positive lymph nodes can predict the overall survival of patients with pancreatic head cancer after radical surgery.

BACKGROUND: This study aimed to construct a novel nomogram based on the number of positive lymph nodes to predict the overall survival of patients with pancreatic head cancer after radical surgery. MATERIALS AND METHODS: 2271 and 973 patients in the SEER Database were included in the development set and validation set, respectively. The primary clinical endpoint was OS (overall survival). Univariate and multivariate Cox regression analyses were used to screen independent risk factors of OS, and then independent risk factors were used to construct a novel nomogram. The C-index, calibration curves, and decision analysis curves were used to evaluate the predictive power of the nomogram in the development and validation sets. RESULTS: After multivariate Cox regression analysis, the independent risk factors for OS included age, tumor extent, chemotherapy, tumor size, LN (lymph nodes) examined, and LN positive. A nomogram was constructed by using independent risk factors for OS. The C-index of the nomogram for OS was 0.652 [(95% confidence interval (CI): 0.639-0.666)] and 0.661 (95%CI: 0.641-0.680) in the development and validation sets, respectively. The calibration curves and decision analysis curves proved that the nomogram had good predictive ability. CONCLUSIONS: The nomogram based on the number of positive LN can effectively predict the overall survival of patients with pancreatic head cancer after surgery.