A population-based validation of a clinical age-based prognostic tool to predict survival in melanoma patients (Preprint)

BACKGROUND Melanoma is the most serious form of skin cancer, and the treatment can be challenging if the disease progresses to the metastatic stage. Depth of invasion is a good prognostic factor for predicting outcome. However, no good outcome prediction system that combines the staging system with other chronic systemic diseases is available to date. We investigated melanoma-related data from a population-based database and developed an outcome prediction tool for melanoma patients via machine learning. OBJECTIVE Build up a prediction tool for melanoma patients METHODS The clinical data of patients with melanoma were extracted from Taiwan’s National Health Insurance Research Database between 2008 and 2015 and were analysed in this study. Clinical data including demographic, pathologic, staging, and treatment data from melanoma patients over 18 years old were abstracted and collected. Prognostic factors were analyzed. Logistic regression (LR), random forest (RF) modelling, and multivariate adaptive regression splines (MARS) were applied to calculate predicted overall survival (OS). A 5-fold cross-validation method was applied. Two age groups (≥64 years old as the older age group and <64 years old as the general population group) with different prognostic factors were identified, and prognostic models for survival outcomes were built. RESULTS A total of 3481 patients were enrolled in our study. The 1-, 3-, and 5-year overall survival rates were 92.2%, 80.1%, and 70.3%, respectively. The Cox proportional hazard model showed that older age, male sex, higher grade, higher clinical stage, larger tumour size, positive surgical margins, no surgical intervention, and a higher Charlson comorbidity index (CCI) were associated with higher hazard ratios. LR, RF, and MARS techniques were used to validate the overall survival without tracking time, the accuracy of the MARS model for the <64-year-old patients and ≥64-year-old patients was 90.4% and 80.7%, respectively, with 3-, and 5-year the accuracy of prediction models are 94% and 89.6%. CONCLUSIONS Machine learning techniques offer excellent survival prediction in melanoma patients. Age-based survival prediction models may be applied for better clinical decision making. CLINICALTRIAL N/A

Download Full-text

Development and External Validation of a Nomogram for Predicting Overall Survival in Stomach Cancer: A Population-Based Study

Journal of Healthcare Engineering ◽

10.1155/2021/8605869 ◽

2021 ◽

Vol 2021 ◽

pp. 1-13

Author(s):

Haonan Ji ◽

Huita Wu ◽

Yu Du ◽

Li Xiao ◽

Yiqin Zhang ◽

...

Keyword(s):

Overall Survival ◽

Prognostic Factors ◽

Stomach Cancer ◽

External Validation ◽

Model Development ◽

Training Group ◽

Population Based ◽

Survival Prediction ◽

Kolmogorov Smirnov ◽

Testing Group

Objective. The study was to develop and externally validate a prognostic nomogram to effectively predict the overall survival of patients with stomach cancer. Methods. Demographic and clinical variables of patients with stomach cancer in the Surveillance, Epidemiology, and End Results (SEER) database from 2007–2016 were retrospectively collected. Patients were then divided into the Training Group (n = 4,456) for model development and the Testing Group (n = 4,541) for external validation. Univariate and multivariate Cox regressions were used to explore prognostic factors. The concordance index (C-index) and the Kolmogorov–Smirnov (KS) value were used to measure the discrimination, and the calibration curve was used to assess the calibration of the nomogram. Results. Prognostic factors including age, race, marital status, TNM stage, surgery, chemotherapy, grade, and the number of regional nodes positive were used to construct a nomogram. The C-index was 0.790 and the KS value was 0.45 for the Training Group, and the C-index was 0.789 for the Testing Group, all suggesting the good performance of the nomogram. Conclusion. We have developed an effective nomogram with ten easily acquired prognostic factors. The nomogram could accurately predict the overall survival of patients with stomach cancer and performed well on external validation, which would help improve the individualized survival prediction and decision-making, thereby improving the outcome and survival of stomach cancer.

Download Full-text

Radiomics-Based Outcome Prediction for Pancreatic Cancer Following Stereotactic Body Radiotherapy

Cancers ◽

10.3390/cancers12041051 ◽

2020 ◽

Vol 12 (4) ◽

pp. 1051

Author(s):

Elsa Parr ◽

Qian Du ◽

Chi Zhang ◽

Chi Lin ◽

Ahsan Kamal ◽

...

Keyword(s):

Pancreatic Cancer ◽

Overall Survival ◽

Stereotactic Body Radiotherapy ◽

Outcome Prediction ◽

Prediction Models ◽

Pancreatic Tumors ◽

Survival Prediction ◽

Clinical Prediction ◽

Clinical Prediction Models ◽

Clinical Model

(1) Background: Radiomics use high-throughput mining of medical imaging data to extract unique information and predict tumor behavior. Currently available clinical prediction models poorly predict treatment outcomes in pancreatic adenocarcinoma. Therefore, we used radiomic features of primary pancreatic tumors to develop outcome prediction models and compared them to traditional clinical models. (2) Methods: We extracted and analyzed radiomic data from pre-radiation contrast-enhanced CTs of 74 pancreatic cancer patients undergoing stereotactic body radiotherapy. A panel of over 800 radiomic features was screened to create overall survival and local-regional recurrence prediction models, which were compared to clinical prediction models and models combining radiomic and clinical information. (3) Results: A 6-feature radiomic signature was identified that achieved better overall survival prediction performance than the clinical model (mean concordance index: 0.66 vs. 0.54 on resampled cross-validation test sets), and the combined model improved the performance slightly further to 0.68. Similarly, a 7-feature radiomic signature better predicted recurrence than the clinical model (mean AUC of 0.78 vs. 0.66). (4) Conclusion: Overall survival and recurrence can be better predicted with models based on radiomic features than with those based on clinical features for pancreatic cancer.

Download Full-text

Association of chemotherapy with survival in stage II colon cancer patients who received radical surgery: a retrospective cohort study

BMC Cancer ◽

10.1186/s12885-021-08057-3 ◽

2021 ◽

Vol 21 (1) ◽

Author(s):

Zhihao Lv ◽

Yuqi Liang ◽

Huaxi Liu ◽

Delong Mo

Keyword(s):

Colon Cancer ◽

Overall Survival ◽

Cancer Patients ◽

Prediction Models ◽

Radical Surgery ◽

Survival Rates ◽

Stage Ii ◽

Survival Prediction ◽

Stage Ii Colon Cancer ◽

Overall Survival Rates

Abstract Background It remains controversial whether patients with Stage II colon cancer would benefit from chemotherapy after radical surgery. This study aims to assess the real effectiveness of chemotherapy in patients with stage II colon cancer undergoing radical surgery and to construct survival prediction models to predict the survival benefits of chemotherapy. Methods Data for stage II colon cancer patients with radical surgery were retrieved from the Surveillance, Epidemiology, and End Results (SEER) database. Propensity score matching (1:1) was performed according to receive or not receive chemotherapy. Competitive risk regression models were used to assess colon cancer cause-specific death (CSD) and non-colon cancer cause-specific death (NCSD). Survival prediction nomograms were constructed to predict overall survival (OS) and colon cancer cause-specific survival (CSS). The predictive abilities of the constructed models were evaluated by the concordance indexes (C-indexes) and calibration curves. Results A total of 25,110 patients were identified, 21.7% received chemotherapy, and 78.3% were without chemotherapy. A total of 10,916 patients were extracted after propensity score matching. The estimated 3-year overall survival rates of chemotherapy were 0.7% higher than non- chemotherapy. The estimated 5-year and 10-year overall survival rates of non-chemotherapy were 1.3 and 2.1% higher than chemotherapy, respectively. Survival prediction models showed good discrimination (the C-indexes between 0.582 and 0.757) and excellent calibration. Conclusions Chemotherapy improves the short-term (43 months) survival benefit of stage II colon cancer patients who received radical surgery. Survival prediction models can be used to predict OS and CSS of patients receiving chemotherapy as well as OS and CSS of patients not receiving chemotherapy and to make individualized treatment recommendations for stage II colon cancer patients who received radical surgery.

Download Full-text

Demographic, Clinical, and Prognostic Factors of Ovarian Clear Cell Adenocarcinomas According to Endometriosis Status

International Journal of Gynecological Cancer ◽

10.1097/igc.0000000000001102 ◽

2017 ◽

Vol 27 (9) ◽

pp. 1804-1812 ◽

Cited By ~ 5

Author(s):

Tine H. Schnack ◽

Estrid Høgdall ◽

Lotte Nedergaard Thomsen ◽

Claus Høgdall

Keyword(s):

Overall Survival ◽

Prognostic Factors ◽

Cox Regression ◽

Clear Cell ◽

Statistical Tests ◽

Gynecological Cancer ◽

Population Based ◽

Clear Cell Adenocarcinoma ◽

Ovarian Endometriosis ◽

Increased Risk

ObjectivesWomen with endometriosis carry an increased risk for ovarian clear cell adenocarcinomas (CCCs). Clear cell adenocarcinoma may develop from endometriosis lesions. Few studies have compared clinical and prognostic factors and overall survival in patients diagnosed as having CCC according to endometriosis status.MethodsPopulation-based prospectively collected data on CCC with coexisting pelvic (including ovarian; n = 80) and ovarian (n = 46) endometriosis or without endometriosis (n = 95) were obtained through the Danish Gynecological Cancer Database. χ2 Test, independent-samples t test, logistic regression, Kaplan-Meier test, and Cox regression were used. Statistical tests were 2 sided. P values less than 0.05 were considered statistically significant.ResultsPatients with CCC and pelvic or ovarian endometriosis were significantly younger than CCC patients without endometriosis, and a higher proportion of them were nulliparous (28% and 31% vs 17% (P = 0.07 and P = 0.09). Accordingly, a significantly higher proportion of women without endometriosis had given birth to more than 1 child. Interestingly, a significantly higher proportion of patients with ovarian endometriosis had pure CCCs (97.8% vs 82.1%; P = 0.001) as compared with patients without endometriosis. Overall survival was poorer among CCC patients with concomitant ovarian endometriosis (hazard ratio, 2.56 [95% confidence interval, 1.29–5.02], in the multivariate analysis.ConclusionsAge at CCC diagnosis and parity as well as histology differ between CCC patients with and without concomitant endometriosis. Furthermore, CCC patients with concomitant ovarian endometriosis have a poorer prognosis compared with endometriosis-negative CCC patients. These differences warrant further research to determine whether CCCs with and without concomitant endometriosis develop through distinct pathogenic pathways.

Download Full-text

Survival prediction models since liver transplantation - comparisons between Cox models and machine learning techniques

10.21203/rs.3.rs-22670/v3 ◽

2020 ◽

Author(s):

Georgios Kantidakis ◽

Hein Putter ◽

Carlo Lancia ◽

Jacob de Boer ◽

Andries E Braat ◽

...

Keyword(s):

Machine Learning ◽

Neural Networks ◽

Liver Transplantation ◽

Prediction Models ◽

Machine Learning Techniques ◽

Brier Score ◽

Survival Prediction ◽

Cox Models ◽

Learning Techniques ◽

Random Survival Forest

Abstract Background: Predicting survival of recipients after liver transplantation is regarded as one of the most important challenges in contemporary medicine. Hence, improving on current prediction models is of great interest.Nowadays, there is a strong discussion in the medical field about machine learning (ML) and whether it has greater potential than traditional regression models when dealing with complex data. Criticism to ML is related to unsuitable performance measures and lack of interpretability which is important for clinicians.Methods: In this paper, ML techniques such as random forests and neural networks are applied to large data of 62294 patients from the United States with 97 predictors selected on clinical/statistical grounds, over more than 600, to predict survival from transplantation. Of particular interest is also the identification of potential risk factors. A comparison is performed between 3 different Cox models (with all variables, backward selection and LASSO) and 3 machine learning techniques: a random survival forest and 2 partial logistic artificial neural networks (PLANNs). For PLANNs, novel extensions to their original specification are tested. Emphasis is given on the advantages and pitfalls of each method and on the interpretability of the ML techniques.Results: Well-established predictive measures are employed from the survival field (C-index, Brier score and Integrated Brier Score) and the strongest prognostic factors are identified for each model. Clinical endpoint is overall graft-survival defined as the time between transplantation and the date of graft-failure or death. The random survival forest shows slightly better predictive performance than Cox models based on the C-index. Neural networks show better performance than both Cox models and random survival forest based on the Integrated Brier Score at 10 years.Conclusion: In this work, it is shown that machine learning techniques can be a useful tool for both prediction and interpretation in the survival context. From the ML techniques examined here, PLANN with 1 hidden layer predicts survival probabilities the most accurately, being as calibrated as the Cox model with all variables.

Download Full-text

A Novel Nomogram for Predicting Cancer-Specific Survival in Patients With Spinal Chordoma: A Population-Based Analysis

Technology in Cancer Research & Treatment ◽

10.1177/15330338211036533 ◽

2021 ◽

Vol 20 ◽

pp. 153303382110365

Author(s):

Zhangheng Huang ◽

Zhiyi Fan ◽

Chengliang Zhao ◽

He Sun

Keyword(s):

Prognostic Factors ◽

Area Under The Curve ◽

Risk Groups ◽

Population Based ◽

Disease Stage ◽

Survival Prediction ◽

Cancer Specific Survival ◽

Spinal Chordoma ◽

Prediction Of Prognosis ◽

High Degree

Background: Chordoma is a rare malignant bone tumor, and the survival prediction for patients with chordoma is difficult. The objective of this study was to construct and validate a nomogram for predicting cancer-specific survival (CSS) in patients with spinal chordoma. Methods: A total of 316 patients with spinal chordoma were identified from the SEER database between 1998 and 2015. The independent prognostic factors for patients with spinal chordoma were determined by univariate and multivariate Cox analyses. The prognostic nomogram was established for patients with spinal chordoma based on independent prognostic factors. Furthermore, we performed internal and external validations for this nomogram. Results: Primary site, disease stage, histological type, surgery, and age were identified as independent prognostic factors for patients with spinal chordoma. A nomogram for predicting CSS in patients with spinal chordoma was constructed based on the above 5 variables. In the training cohort, the area under the curve for predicting 1-, 3-, and 5-year CSS were 0.821, 0.856, and 0.920, respectively. The corresponding area under the curve in the validation cohort were 0.728, 0.804, and 0.839, respectively. The calibration curves of the nomogram showed a high degree of agreement between the predicted and the actual results, and the decision curve analysis further demonstrated the satisfactory clinical utility of the nomogram. Conclusions: The prognostic nomogram provides a considerably more accurate prediction of prognosis for patients with spinal chordoma. Clinicians can use it to categorize patients into different risk groups and make personalized treatment methods.

Download Full-text

An Application of Machine Learning to Etiological Diagnosis of Secondary Hypertension: Retrospective Study Using Electronic Medical Records (Preprint)

10.2196/preprints.19739 ◽

2020 ◽

Author(s):

Xiaolin Diao ◽

Yanni Huo ◽

Zhanzheng Yan ◽

Haibin Wang ◽

Jing Yuan ◽

...

Keyword(s):

Machine Learning ◽

Aortic Stenosis ◽

Electronic Medical Records ◽

Medical Records ◽

Thyroid Dysfunction ◽

Outcome Prediction ◽

Prediction Models ◽

Secondary Hypertension ◽

Validation Dataset ◽

Composite Outcome

BACKGROUND Secondary hypertension is a kind of hypertension with definite etiology and may be cured. Patients with suspected secondary hypertension can benefit from detection and treatment in time and, conversely, will have higher risk of morbidity and mortality than patients with primary hypertension. OBJECTIVE The aim of this study was to develop and validate machine learning (ML) prediction models of common etiologies in patients with suspected secondary hypertension. METHODS The analyzed dataset was retrospectively extracted from electronic medical records (EMRs) of patients discharged from Fuwai hospital between January 1, 2016 and June 30, 2019. A total of 7532 unique patients were included and divided into two datasets by time: 6302 patients in 2016-2018 as training dataset for model building and 1230 patients in 2019 as validation dataset for further evaluation. Extreme Gradient Boosting (XGBoost) was adopted to develop five prediction models of four etiologies of secondary hypertension and occurrence of any of them, including renovascular hypertension (RVH), primary aldosteronism (PA), thyroid dysfunction and aortic stenosis. Both univariate logistic analysis and Gini impure method were used for feature selection, while grid search and 10-fold cross-validation were used to select the optimal hyperparameters for each model. RESULTS Validation of the composite outcome prediction model showed good performance with an area under the receiver-operating characteristic curve (AUC) of 0.924 in the validation dataset, while the four prediction models of RVH, PA, thyroid dysfunction and aortic stenosis achieved AUC of 0.938, 0.965, 0.959, 0.946, respectively, in the validation dataset. 79 clinical indicators were identified in all and finally used in our prediction models. The result of subgroup analysis on the composite outcome prediction model demonstrated high discrimination with AUCs all higher than 0.890 among all age groups of adults. CONCLUSIONS The ML prediction models in this study showed good performance in detecting four etiologies of patients with suspected secondary hypertension, thus they may potentially facilitate clinical diagnosis decision making of secondary hypertension in an intelligent way. CLINICALTRIAL

Download Full-text

Breast Subtypes and Prognosis of Breast Cancer Patients With Initial Bone Metastasis: A Population-Based Study

Frontiers in Oncology ◽

10.3389/fonc.2020.580112 ◽

2020 ◽

Vol 10 ◽

Author(s):

Deyue Liu ◽

Jiayi Wu ◽

Caijin Lin ◽

Lisa Andriani ◽

Shuning Ding ◽

...

Keyword(s):

Breast Cancer ◽

Overall Survival ◽

Prognostic Factors ◽

Metastatic Breast Cancer ◽

Bone Metastasis ◽

Cancer Patients ◽

Metastatic Breast ◽

Risk Groups ◽

Population Based ◽

Breast Cancer Patients

BackgroundMetastatic breast cancer (MBC) is a highly heterogeneous disease and bone is one of the most common metastatic sites. This retrospective study was conducted to investigate the clinical features, prognostic factors and benefits of surgery of breast cancer patients with initial bone metastases.MethodsFrom 2010 to 2015, 6,860 breast cancer patients diagnosed with initial bone metastasis were analyzed from Surveillance, Epidemiology, and End Results (SEER) database. Univariate and Multivariable analysis were used to identify prognostic factors. A nomogram was performed based on the factors selected from cox regression result. Survival curves were plotted according to different subtypes, metastatic burdens and risk groups differentiated by nomogram.ResultsHormone receptor (HR) positive/human epidermal growth factor receptor 2 (HER2) positive patients showed the best outcome compared to other subtypes. Patients of younger age (<60 years old), white race, lower grade, lower T stage (<=T2), not combining visceral metastasis tended to have better outcome. About 37% (2,249) patients received surgery of primary tumor. Patients of all subtypes could benefit from surgery. Patients of bone-only metastases (BOM), bone and liver metastases, bone and lung metastases also showed superior survival time if surgery was performed. However, patients of bone and brain metastasis could not benefit from surgery (p = 0.05). The C-index of nomogram was 0.66. Cutoff values of nomogram point were identified as 87 and 157 points, which divided all patients into low-, intermediate- and high-risk groups. Patients of all groups showed better overall survival when receiving surgery.ConclusionOur study has provided population-based prognostic analysis in patients with initial bone metastatic breast cancer and constructed a predicting nomogram with good accuracy. The finding of potential benefit of surgery to overall survival will cast some lights on the treatment tactics of this group of patients.

Download Full-text

Nomogram for predicting the overall survival and cancer-specific survival of patients with extremity liposarcoma: a population-based study

BMC Cancer ◽

10.1186/s12885-020-07396-x ◽

2020 ◽

Vol 20 (1) ◽

Cited By ~ 1

Author(s):

Lin Ye ◽

Chuan Hu ◽

Cailin Wang ◽

Weiyang Yu ◽

Feijun Liu ◽

...

Keyword(s):

Overall Survival ◽

Prognostic Factors ◽

Area Under The Curve ◽

Risk Groups ◽

Population Based ◽

Cancer Specific Survival ◽

Kaplan Meier ◽

Extremity Soft Tissue Sarcoma ◽

Individual Survival ◽

Size Grade

Abstract Background Extremity liposarcoma represents 25% of extremity soft tissue sarcoma and has a better prognosis than liposarcoma occurring in other anatomic sites. The purpose of this study was to develop two nomograms for predicting the overall survival (OS) and cancer-specific survival (CSS) of patients with extremity liposarcoma. Methods A total of 2170 patients diagnosed with primary extremity liposarcoma between 2004 and 2015 were extracted from the Surveillance, Epidemiology, and End Results (SEER) database. Univariate and multivariate Cox analyses were performed to explore the independent prognostic factors and establish two nomograms. The area under the curve (AUC), C-index, calibration curve, decision curve analysis (DCA), Kaplan-Meier analysis, and subgroup analyses were used to evaluate the nomograms. Results Six variables were identified as independent prognostic factors for both OS and CSS. In the training cohort, the AUCs of the OS nomogram were 0.842, 0.841, and 0.823 for predicting 3-, 5-, and 8-year OS, respectively, while the AUCs of the CSS nomogram were 0.889, 0.884, and 0.859 for predicting 3-, 5-, and 8-year CSS, respectively. Calibration plots and DCA revealed that the nomogram had a satisfactory ability to predict OS and CSS. The above results were also observed in the validation cohort. In addition, the C-indices of both nomograms were significantly higher than those of all independent prognostic factors in both the training and validation cohorts. Stratification of the patients into high- and low-risk groups highlighted the differences in prognosis between the two groups in the training and validation cohorts. Conclusion Age, sex, tumor size, grade, M stage, and surgery status were confirmed as independent prognostic variables for both OS and CSS in extremity liposarcoma patients. Two nomograms based on the above variables were established to provide more accurate individual survival predictions for extremity liposarcoma patients and to help physicians make appropriate clinical decisions.

Download Full-text

Time Trends and Prognostic Factors for Overall Survival in Myxoid Liposarcomas: A Population-Based Study

Sarcoma ◽

10.1155/2020/2437850 ◽

2020 ◽

Vol 2020 ◽

pp. 1-8

Author(s):

Jules Lansu ◽

Winan J. Van Houdt ◽

Michael Schaapveld ◽

Iris Walraven ◽

Michiel A. J. Van de Sande ◽

...

Keyword(s):

Overall Survival ◽

Prognostic Factors ◽

The Netherlands ◽

Metastatic Disease ◽

Lower Limb ◽

Tumor Size ◽

Tumor Location ◽

Population Based ◽

Population Based Study ◽

Over Time

Background. The purpose of this study was to evaluate the overall survival (OS) and associated characteristics for patients with Myxoid Liposarcoma (MLS) over time in The Netherlands. Methods. A population-based study was performed of patients with primary localized (n = 851) and metastatic (n = 50) MLS diagnosed in The Netherlands between 1989 and 2016, based on data from the National Cancer Registry. Results. The median age of the MLS patients was 49 years, and approximately two-thirds was located in the lower limb. An association was revealed between age and the risk of having a Round Cell (RC) tumor. OS rates for primary localized MLS were 93%, 83%, 78%, and 66% after 1, 3, 5, and 10 years, respectively. The median OS for patients with metastatic disease at diagnosis was 10 months. Increasing age (Hazard Ratio (HR) 1.05, p=0.00), a tumor size >5 cm (HR 2.18; p=0.00), and tumor location (trunk HR 1.29; p=0.09, upper limb HR 0.83; p=0.55, and “other” locations HR 2.73; p=0.00, as compared to lower limb) were independent prognostic factors for OS. The percentage of patients treated with radiotherapy (RT) increased over time, and preoperative RT gradually replaced postoperative RT. In contrast to patients with localized disease, significant improvement of OS was observed in patients with metastatic disease over time. Conclusions. In this large nationwide cohort, tumor size and tumor location were independent prognostic factors for OS. Furthermore, a higher probability of an RC tumor with increasing age was suggested. An increased use of RT over the years did not translate into improved OS for localized MLS.

Download Full-text