Predictive model for the 5-year survival status of osteosarcoma patients based on the SEER database and XGBoost algorithm

Identification of relevant features using SEQENS to improve supervised machine learning models predicting AML treatment outcome

BACKGROUND AND OBJECTIVE

This study has two main objectives. First, to evaluate a feature selection methodology based on SEQENS, an algorithm for identifying relevant variables. Second, to validate machine learning models that predict the risk of complications in patients with acute myeloid leukemia (AML) using data available at diagnosis. Predictions are made at three time points: 90 days, six months, and one year post-diagnosis. These objectives represent fundamental steps toward the development of a tool to assist clinicians in therapeutic decision-making and provide insights into the risk factors associated with AML complications.

METHODS

A dataset of 568 patients, including demographic, clinical, genetic (VAF), and cytogenetic information, was created by combining data from Hospital 12 de Octubre (Madrid, Spain) and Instituto de Investigación Sanitaria La Fe (Valencia, Spain). Feature selection based on an enhanced version of SEQENS was conducted for each time point, followed by the comparison of four classifiers (XGBoost, Multi-Layer Perceptron, Logistic Regression and Decision Tree) to assess the impact of feature selection on model performance.

RESULTS

SEQENS identified different relevant features for each prediction horizon, with Age, TP53, - 7/7Q, and EZH2 consistently relevant across all time points. The models were evaluated using 5-fold cross-validation, XGBoost achieve the highest average ROC-AUC scores of 0.81, 0.84, and 0.82 for 90-day, 6-month, and 1-year predictions, respectively. Generally, performance remained stable or improved after applying SEQENS-based feature selection. Evaluation on an external test set of 54 patients yielded ROC-AUC scores of 0.72 (90-day), 0.75 (6-month), and 0.68 (1-year).

CONCLUSIONS

The models achieved performance levels that suggest they could serve as therapeutic decision support tools at different times after diagnosis. The selected variables align with the European LeukemiaNet (ELN) 2022 risk classification, and the SEQENS-based feature selection effectively reduced the feature set while maintaining prediction accuracy.

Prognostic nomogram for overall survival in pediatric osteosarcoma with pulmonary metastases: a SEER database analysis

Background

Pulmonary metastasis (PM) is the most common site of distant metastasis in osteosarcoma (OS), particularly in pediatric cases, which are associated with poor prognosis. However, limited research has focused on identifying prognostic factors (PFs) for pediatric osteosarcoma with pulmonary metastasis (POPM). This study aims to identify clinical features and PFs of POPM and develop a validated nomogram to predict overall survival in POPM patients.

Methods

A retrospective analysis was conducted using OS cases from the Surveillance, Epidemiology, and End Results (SEER) database (2010-2021). Clinical characteristics were compared between patients with and without PM. PFs were identified using Least Absolute Shrinkage and Selection Operator (LASSO) regression and evaluated through Kaplan-Meier analysis. Patients were divided into training (N = 148) and validation (N = 64) cohorts. Independent PFs were determined via Cox regression to construct a prognostic nomogram, which was assessed using the concordance index (C-index), the area under the receiver operating characteristic curve (AUC-ROC), and calibration plots. Decision curve analysis (DCA) was used to evaluate clinical applicability.

Results

LASSO regression identified key PFs: AJCC stage, T stage, median household income, systemic therapy, and time from diagnosis to treatment. Among these, all except T stage were validated as independent PFs via Cox regression. The nomogram demonstrated strong predictive accuracy with C-index values of 0.68 (training) and 0.71 (validation). AUC values for 1-, 3-, and 5-year survival were 0.786, 0.709, and 0.711 in the training cohort and 0.780, 0.760, and 0.776 in the validation cohort. Calibration plots showed excellent concordance between predicted and actual survival, and DCA confirmed the nomogram's clinical relevance.

Conclusion

AJCC stage, median household income, systemic therapy, and time from diagnosis to treatment are significant PFs for POPM survival. The validated nomogram provides a valuable tool for personalized prognostic assessment and treatment decision-making in clinical practice.

The Role of mRNA Modifications in Bone Diseases

As a type of epigenetic modifications, mRNA modifications regulate the metabolism of mRNAs, thereby influencing gene expression. Previous studies have indicated that dysregulation of mRNA modifications is closely associated with the occurrence and progression of bone diseases (BDs). In this study, we first introduced the dynamic regulatory processes of five major mRNA modifications and their effects on the nucleus export, stability, and translation of mRNAs. We then summarized the mechanisms of mRNA modifications involved in the development of osteoporosis, osteoarthritis, rheumatoid arthritis, ankylosing spondylitis, fractures, osteomyelitis, and osteosarcoma. Finally, we reviewed therapeutic strategies for BDs based on the above mechanisms, focusing on regulating osteoblast and osteoclast differentiation, inhibiting cellular senescence and injury, and alleviating inflammation. This review identified mRNA modifications as potential targets for treating BDs and proposes perspectives on the diversity, targetability, and safety of mRNA-modifying therapies.

A hybrid machine learning approach for the personalized prognostication of aggressive skin cancers

Accurate prognostication guides optimal clinical management in skin cancer. Merkel cell carcinoma (MCC) is the most aggressive form of skin cancer that often presents in advanced stages and is associated with poor survival rates. There are no personalized prognostic tools in use in MCC. We employed explainability analysis to reveal new insights into mortality risk factors for this highly aggressive cancer. We then combined deep learning feature selection with a modified XGBoost framework, to develop a web-based prognostic tool for MCC termed 'DeepMerkel'. DeepMerkel can make accurate personalised, time-dependent survival predictions for MCC from readily available clinical information. It demonstrated generalizability through high predictive performance in an international clinical cohort, out-performing current population-based prognostic staging systems. MCC and DeepMerkel provide the exemplar model of personalised machine learning prognostic tools in aggressive skin cancers.

COPS5 regulates osteosarcoma progression by upregulating KHSRP to promote Per2 mRNA decay

Osteosarcoma (OS) is a common bone sarcoma that is often seen in children and adolescents. This study delves into the intricate regulatory network involving COP9 signalosome subunit 5 (COPS5), KH-type splicing regulatory protein (KHSRP), and Period circadian clock 2 (Per2) in the context of osteosarcoma cell malignant phenotype. CCK-8 assay was applied to assess cell proliferation. Wound healing or transwell assay was selected to evaluate cell migration or invasion. Apoptosis was determined employing flow cytometry assay. Co-IP and GST-pull down determined the interaction between COPS5 and KHSRP. The interaction relationship between KHSRP and Per2 mRNA was detected by RNA-pull down and RIP assays. We found that COPS5 knockdown repressed proliferation, migration, and invasion and facilitated apoptosis of OS cells. Knockdown of COPS5 also restrained the tumor growth in the nude mice tumor xenograft model. COPS5 interacted with KHSRP to maintain the protein stability of KHSRP. Furthermore, there was a binding relationship between KHSRP and Per2 mRNA. Besides, COPS5 promoted OS cell tumorigenesis by mediating the decay effect of KHSRP on Per2 mRNA. Collectively, COPS5 promoted the decay of Per2 mRNA via contacting and mediating KHSRP, thereby facilitating OS progression. Our study unveils COPS5 as a key modulator in OS.

Machine learning models including preoperative and postoperative albumin-bilirubin score: short-term outcomes among patients with hepatocellular carcinoma

BACKGROUND

We sought to assess the impact of various perioperative factors on the risk of severe complications and post-surgical mortality using a novel maching learning technique.

METHODS

Data on patients undergoing resection for HCC were obtained from an international, multi-institutional database between 2000 and 2020. Gradient boosted trees were utilized to construct predictive models.

RESULTS

Among 962 patients who underwent HCC resection, the incidence of severe postoperative complications was 12.7% (n = 122); in-hospital mortality was 2.9% (n = 28). Models that exclusively used preoperative data achieved AUC values of 0.89 (95%CI 0.85 to 0.92) and 0.90 (95%CI 0.84 to 0.96) to predict severe complications and mortality, respectively. Models that combined preoperative and postoperative data achieved AUC values of 0.93 (95%CI 0.91 to 0.96) and 0.92 (95%CI 0.86 to 0.97) for severe morbidity and mortality, respectively. The SHAP algorithm demonstrated that the factor most strongly predictive of severe morbidity and mortality was postoperative day 1 and 3 albumin-bilirubin (ALBI) scores.

CONCLUSION

Incorporation of perioperative data including ALBI scores using ML techniques can help risk-stratify patients undergoing resection of HCC.

Retrospective Analysis of Radiofrequency Ablation in Patients with Small Solitary Hepatocellular Carcinoma: Survival Outcomes and Development of a Machine Learning Prognostic Model

BACKGROUND AND OBJECTIVE

The effectiveness of radiofrequency ablation (RFA) in improving long-term survival outcomes for patients with a solitary hepatocellular carcinoma (HCC) measuring 5 cm or less remains uncertain. This study was designed to elucidate the impact of RFA therapy on the survival outcomes of these patients and to construct a prognostic model for patients following RFA.

METHODS

This study was performed using the Surveillance, Epidemiology, and End Results (SEER) database from 2004 to 2017, focusing on patients diagnosed with a solitary HCC lesion ≤5 cm in size. We compared the overall survival (OS) and cancer-specific survival (CSS) rates of these patients with those of patients who received hepatectomy, radiotherapy, or chemotherapy or who were part of a blank control group. To enhance the reliability of our findings, we employed stabilized inverse probability treatment weighting (sIPTW) and stratified analyses. Additionally, we conducted a Cox regression analysis to identify prognostic factors. XGBoost models were developed to predict 1-, 3-, and 5-year CSS. The XGBoost models were evaluated via receiver operating characteristic (ROC) curves, calibration plots, decision curve analysis (DCA) curves and so on.

RESULTS

Regardless of whether the data were unadjusted or adjusted for the use of sIPTWs, the 5-year OS (46.7%) and CSS (58.9%) rates were greater in the RFA group than in the radiotherapy (27.1%/35.8%), chemotherapy (32.9%/43.7%), and blank control (18.6%/30.7%) groups, but these rates were lower than those in the hepatectomy group (69.4%/78.9%). Stratified analysis based on age and cirrhosis status revealed that RFA and hepatectomy yielded similar OS and CSS outcomes for patients with cirrhosis aged over 65 years. Age, race, marital status, grade, cirrhosis status, tumor size, and AFP level were selected to construct the XGBoost models based on the training cohort. The areas under the curve (AUCs) for 1, 3, and 5 years in the validation cohort were 0.88, 0.81, and 0.79, respectively. Calibration plots further demonstrated the consistency between the predicted and actual values in both the training and validation cohorts.

CONCLUSION

RFA can improve the survival of patients diagnosed with a solitary HCC lesion ≤5 cm. In certain clinical scenarios, RFA achieves survival outcomes comparable to those of hepatectomy. The XGBoost models developed in this study performed admirably in predicting the CSS of patients with solitary HCC tumors smaller than 5 cm following RFA.

The role of Clec11a in bone construction and remodeling

Bone is a dynamically active tissue whose health status is closely related to its construction and remodeling, and imbalances in bone homeostasis lead to a wide range of bone diseases. The sulfated glycoprotein C-type lectin structural domain family 11 member A (Clec11a) is a key factor in bone mass regulation that significantly promotes the osteogenic differentiation of bone marrow mesenchymal stem cells and osteoblasts and stimulates chondrocyte proliferation, thereby promoting longitudinal bone growth. More importantly, Clec11a has high therapeutic potential for treating various bone diseases and can enhance the therapeutic effects of the parathyroid hormone against osteoporosis. Clec11a is also involved in the stress/adaptive response of bone to exercise via mechanical stimulation of the cation channel Pieoz1. Clec11a plays an important role in promoting bone health and preventing bone disease and may represent a new target and novel drug for bone disease treatment. Therefore, this review aims to explore the role and possible mechanisms of Clec11a in the skeletal system, evaluate its value as a potential therapeutic target against bone diseases, and provide new ideas and strategies for basic research on Clec11a and preventing and treating bone disease.

Survival and analysis of prognostic factors for fibroblastic osteosarcoma patients: a population-based study

Background

Osteosarcoma is the most common mesenchymal cell malignancy, 10% of which is fibroblastic osteosarcoma (FOS). Due to the low incidence of osteosarcoma, the impact of many pathological factors on survival is still unclear, especially FOS. The goal of this study was to assess the latest survival rates for FOS and the risk factors affecting survival using the Surveillance, Epidemiology, and End Results (SEER) database.

Methods

Age, sex, race, SEER stage, surgery, radiation, chemotherapy, site of FOS, and survival time were collected from the SEER database for survival and prognostic factor analysis. The patients were randomly assigned to either the training cohort or the testing cohort. The overall survival (OS) curves were obtained by Kaplan-Meier according to different factors. A multivariate Cox regression model and a predictive nomogram have also been constructed.

Results

The study enrolled a total of 120 patients. OS at 1, 3, and 5 years for all patients was 90.83%, 79.17%, and 70.83%, respectively. In the 5-year survival analysis, in distant of SEER stage (P<0.01), radiation (P=0.03), and no surgery (P<0.01) were associated with a worse prognosis in patients with FOS. Multivariate analysis showed that age, and in distant of SEER stage were independent indicators of unfavorable prognosis. A nomogram was used to predict the prognosis of FOS and a calibration curve was used to validate the nomogram prediction against the actual observed survival outcomes.

Conclusions

In summary, older age, and worse SEER stage were associated with poorer OS. The nomogram effectively predicted the probabilities of 1-, 3-, and 5-year OS, demonstrating strong concordance with the actual observed outcomes.

Machine Learning-Assisted Decision Making in Orthopaedic Oncology

» Artificial intelligence is an umbrella term for computational calculations that are designed to mimic human intelligence and problem-solving capabilities, although in the future, this may become an incomplete definition. Machine learning (ML) encompasses the development of algorithms or predictive models that generate outputs without explicit instructions, assisting in clinical predictions based on large data sets. Deep learning is a subset of ML that utilizes layers of networks that use various inter-relational connections to define and generalize data.» ML algorithms can enhance radiomics techniques for improved image evaluation and diagnosis. While ML shows promise with the advent of radiomics, there are still obstacles to overcome.» Several calculators leveraging ML algorithms have been developed to predict survival in primary sarcomas and metastatic bone disease utilizing patient-specific data. While these models often report exceptionally accurate performance, it is crucial to evaluate their robustness using standardized guidelines.» While increased computing power suggests continuous improvement of ML algorithms, these advancements must be balanced against challenges such as diversifying data, addressing ethical concerns, and enhancing model interpretability.

Evaluating the prognostic value of tumor deposits in non-metastatic lymph node-positive colon adenocarcinoma using Cox regression and machine learning

BACKGROUND

The 8th AJCC TNM staging for non-metastatic lymph node-positive colon adenocarcinoma patients(NMLP-CA) stages solely by lymph node status, irrespective of the positivity of tumor deposits (TD). This study uses machine learning and Cox regression to predict the prognostic value of tumor deposits in NMLP-CA.

METHODS

Patient data from the SEER registry (2010-2019) was used to develop CSS nomograms based on prognostic factors identified via multivariate Cox regression. Model performance was evaluated by c-index, dynamic calibration, and Schmid score. Shapley additive explanations (SHAP) were used to explain the selected models.

RESULTS

The study included 16,548 NMLP-CA patients, randomized 7:3 into training (n = 11,584) and test (n = 4964) sets. Multivariate Cox analysis identified TD, age, marital status, primary site, grade, pT stage, and pN stage as prognostic for cancer-specific survival (CSS). In the test set, the gradient boosting machine (GBM) model achieved the best C-index (0.733) for CSS prediction, while the Cox model and GAMBoost model optimized dynamic calibration(6.473) and Schmid score (0.285), respectively. TD ranked among the top 3 most important features in the models, with increasing predictive significance over time.

CONCLUSIONS

Positive tumor deposit status confers worse prognosis in NMLP-CA patients. Tumor deposits may confer higher TNM staging. Furthermore, TD could play a more significant role in the staging system.

A comparative analysis of deep learning-based location-adaptive threshold method software against other commercially available software

Automatic segmentation of the coronary artery using coronary computed tomography angiography (CCTA) images can facilitate several analyses related to coronary artery disease (CAD). Accurate segmentation of the lumen or plaque region is one of the most important factors. This study aimed to analyze the performance of the coronary artery segmentation of a software platform with a deep learning-based location-adaptive threshold method (DL-LATM) against commercially available software platforms using CCTA. The dataset from intravascular ultrasound (IVUS) of 26 vessel segments from 19 patients was used as the gold standard to evaluate the performance of each software platform. Statistical analyses (Pearson correlation coefficient [PCC], intraclass correlation coefficient [ICC], and Bland-Altman plot) were conducted for the lumen or plaque parameters by comparing the dataset of each software platform with IVUS. The software platform with DL-LATM showed the bias closest to zero for detecting lumen volume (mean difference = -9.1 mm3, 95% confidence interval [CI] = -18.6 to 0.4 mm3) or area (mean difference = -0.72 mm2, 95% CI = -0.80 to -0.64 mm2) with the highest PCC and ICC. Moreover, lumen or plaque area in the stenotic region was analyzed. The software platform with DL-LATM showed the bias closest to zero for detecting lumen (mean difference = -0.07 mm2, 95% CI = -0.16 to 0.02 mm2) or plaque area (mean difference = 1.70 mm2, 95% CI = 1.37 to 2.03 mm2) in the stenotic region with significantly higher correlation coefficient than other commercially available software platforms (p < 0.001). The result shows that the software platform with DL-LATM has the potential to serve as an aiding system for CAD evaluation.

Prognostic factors in high-grade pediatric osteosarcoma among children and young adults: Greek Nationwide Registry for Childhood Hematological Malignancies and Solid Tumors (NARECHEM-ST) data along with a systematic review and meta-analysis

The 5-year overall survival of children and adolescents with osteosarcoma has been in plateau during the last 30 years. The present systematic review (1976-2023) and meta-analysis aimed to explore factors implicated in the prognosis of children and young adults with high-grade osteosarcoma. Original studies including patients ≤30 years and the Nationwide Registry for Childhood Hematological Malignancies and Solid Tumors (NARECHEM-ST) data (2010-2021) referred to children ≤14 years were analysed. Individual participant data (IPD) and summary estimates were used to assess the n-year survival rates, as well as the association of risk factors with overall survival (OS) and event-free survival (EFS). IPD and the n-year survival rates were pooled using Kaplan-Meier and Cox regression models, and random effects models, respectively. Data from 8412 patients, including 46 publications, NARECHEM-ST data, and 277 IPD from 10 studies were analysed. The summary 5-year OS rate was 64% [95% confidence interval (95%CI): 62%-66%, 37 studies, 6661 patients] and the EFS was 52% (95%CI: 49%-56%, 30 studies, 5010 patients). The survival rates generally differed in the pre-specified subgroups. Limb-salvage surgery showed a higher 5-year OS rate (69%) versus amputation (47%). Good responders had higher OS rates at 3 years (94%) and 5 years (81%), compared to poor responders at 3 years (66%), and 5 years (56%). Patients with metastatic disease had a higher risk of death [Hazard Ratio (HR): 3.60, 95%CI: 2.52, 5.15, 11 studies]. Sex did not have an impact on EFS (HR females/males: 0.90, 95%CI: 0.54, 1.48, 3 studies), whereas age>18 years seems to adversely affect EFS (HR 18+/<10 years: 1.36, 95%CI: 1.09, 1.86, 3 studies). Our results summarize the collective experience on prognostic factors of high-grade osteosarcoma among children and young adults. Poor response to neoadjuvant chemotherapy and metastatic disease at diagnosis were confirmed as primary risk factors of poor outcome. International collaboration of osteosarcoma study groups is essential to improve survival.

Development of a machine learning-based model to predict prognosis of alpha-fetoprotein-positive hepatocellular carcinoma

BACKGROUND

Patients with alpha-fetoprotein (AFP)-positive hepatocellular carcinoma (HCC) have aggressive biological behavior and poor prognosis. Therefore, survival time is one of the greatest concerns for patients with AFP-positive HCC. This study aimed to demonstrate the utilization of six machine learning (ML)-based prognostic models to predict overall survival of patients with AFP-positive HCC.

METHODS

Data on patients with AFP-positive HCC were extracted from the Surveillance, Epidemiology, and End Results database. Six ML algorithms (extreme gradient boosting [XGBoost], logistic regression [LR], support vector machine [SVM], random forest [RF], K-nearest neighbor [KNN], and decision tree [ID3]) were used to develop the prognostic models of patients with AFP-positive HCC at one year, three years, and five years. Area under the receiver operating characteristic curve (AUC), confusion matrix, calibration curves, and decision curve analysis (DCA) were used to evaluate the model.

RESULTS

A total of 2,038 patients with AFP-positive HCC were included for analysis. The 1-, 3-, and 5-year overall survival rates were 60.7%, 28.9%, and 14.3%, respectively. Seventeen features regarding demographics and clinicopathology were included in six ML algorithms to generate a prognostic model. The XGBoost model showed the best performance in predicting survival at 1-year (train set: AUC = 0.771; test set: AUC = 0.782), 3-year (train set: AUC = 0.763; test set: AUC = 0.749) and 5-year (train set: AUC = 0.807; test set: AUC = 0.740). Furthermore, for 1-, 3-, and 5-year survival prediction, the accuracy in the training and test sets was 0.709 and 0.726, 0.721 and 0.726, and 0.778 and 0.784 for the XGBoost model, respectively. Calibration curves and DCA exhibited good predictive performance as well.

CONCLUSIONS

The XGBoost model exhibited good predictive performance, which may provide physicians with an effective tool for early medical intervention and improve the survival of patients.

Development and external validation of a machine learning model for prediction of survival in undifferentiated pleomorphic sarcoma

PURPOSE

Machine learning (ML) algorithms to predict cancer survival have recently been reported for a number of sarcoma subtypes, but none have investigated undifferentiated pleomorphic sarcoma (UPS). ML is a powerful tool that has the potential to better prognosticate UPS.

METHODS

The Surveillance, Epidemiology, and End Results (SEER) database was queried for cases of histologically confirmed undifferentiated pleomorphic sarcoma (UPS) (n = 665). Patient, tumor, and treatment characteristics were recorded, and ML models were developed to predict 1-, 3-, and 5-year survival. The best performing ML model was externally validated using an institutional cohort of UPS patients (n = 151).

RESULTS

All ML models performed best at the 1-year time point and worst at the 5-year time point. On internal validation within the SEER cohort, the best models had c-statistics of 0.67-0.69 at the 5-year time point. The Multi-Layer Perceptron Neural Network (MLP) model was the best performing model and used for external validation. Similarly, the MLP model performed best at 1-year and worst at 5-year on external validation with c-statistics of 0.85 and 0.81, respectively. The MLP model was well calibrated on external validation. The MLP model has been made publicly available at https://rachar.shinyapps.io/ups_app/ .

CONCLUSION

Machine learning models perform well for survival prediction in UPS, though this sarcoma subtype may be more difficult to prognosticate than other subtypes. Future studies are needed to further validate the machine learning approach for UPS prognostication.

New perspectives on cancer clinical research in the era of big data and machine learning

In the 21st century, the development of medical science has entered the era of big data, and machine learning has become an essential tool for mining medical big data. The establishment of the SEER database has provided a wealth of epidemiological data for cancer clinical research, and the number of studies based on SEER and machine learning has been growing in recent years. This article reviews recent research based on SEER and machine learning and finds that the current focus of such studies is primarily on the development and validation of models using machine learning algorithms, with the main directions being lymph node metastasis prediction, distant metastasis prediction, and prognosis-related research. Compared to traditional models, machine learning algorithms have the advantage of stronger adaptability, but also suffer from disadvantages such as overfitting and poor interpretability, which need to be weighed in practical applications. At present, machine learning algorithms, as the foundation of artificial intelligence, have just begun to emerge in the field of cancer clinical research. The future development of oncology will enter a more precise era of cancer research, characterized by larger data, higher dimensions, and more frequent information exchange. Machine learning is bound to shine brightly in this field.

Circ_LRP6 facilitates osteosarcoma progression via the miR-122-5p/miR-204-5p/HMGB1 axis

Circ_LRP6 is participated in the occurrence and development of numerous tumors. Nevertheless, its roles and mechanism in osteosarcoma (OS) is unknown. This study aims to illustrate this point. With the use of qRT-PCR, the level of circ_LRP6, miR-122-5p, miR-204-5p and HMGB1 was identified. To observe cell proliferation, migration and invasion, we adopted CCK-8 and Transwell assays in the present study. Besides, to prove the existing interaction, bioinformatics analysis and dual luciferase reporting assays were employed. The influence of circ_LRP6 on osteosarcoma in vivo was evaluated by subcutaneous tumor formation model in nude mice. In osteosarcoma tissues, circ_LRP6 and HMGB1 are strongly denoted, whereas miR-122-5p and miR-204-5p are under-expressed. Circ_LRP6 knockdown could significantly hinder the proliferation, migration and invasion of osteosarcoma cells. Circ_LRP6 hindered the proliferation of osteosarcoma in vivo. Bioinformatics predicted that miR-122-5p and miR-204-5p functioned as direct targets of circ_LRP6, and HMGB1 were possible target genes of miR-122-5p and miR-204-5p. The findings indicated that the low level of miR-122-5p and miR-204-5p and the overexpression of HMGB1 could partially restore and reduce the inhibitory impact of circ_LRP6 on the proliferation, migration and invasion of osteosarcoma cells. Circ_LRP6 affects osteosarcoma progression via the miR-122-5p/miR-204-5p/HMGB1 axis, and is shown to be a molecular biomarker.

Machine learning for predicting the survival in osteosarcoma patients: Analysis based on American and Hebei Province cohort

Osteosarcoma, a rare malignant tumor, has a poor prognosis. This study aimed to find the best prognostic model for osteosarcoma. There were 2912 patients included from the SEER database and 225 patients from Hebei Province. Patients from the SEER database (2008-2015) were included in the development dataset. Patients from the SEER database (2004-2007) and Hebei Province cohort were included in the external test datasets. The Cox model and three tree-based machine learning algorithms (survival tree [ST], random survival forest [RSF] and gradient boosting machine [GBM]) were used to develop the prognostic models by 10-fold cross-validation with 200 iterations. Additionally, performance of models in the multivariable group was compared with the TNM group. The 3-year and 5-year cancer specific survival (CSS) were 72.71% and 65.92% in the development dataset, respectively. The predictive ability in the multivariable group was superior to that in the TNM group. The calibration curves and consistency in the multivariable group were superior to those in the TNM group. The Cox and RSF models performed better than the ST and GBM models. A nomogram was constructed to predict the 3-year and 5-year CSS of osteosarcoma patients. The RSF model can be used as a nonparametric alternative to the Cox model. The constructed nomogram based on the Cox model can provide reference for clinicians to formulate specific therapeutic decisions both in America and China.

Osteosarcoma Explorer: A Data Commons With Clinical, Genomic, Protein, and Tissue Imaging Data for Osteosarcoma Research

PURPOSE

Osteosarcoma research advancement requires enhanced data integration across different modalities and sources. Current osteosarcoma research, encompassing clinical, genomic, protein, and tissue imaging data, is hindered by the siloed landscape of data generation and storage.

MATERIALS AND METHODS

Clinical, molecular profiling, and tissue imaging data for 573 patients with pediatric osteosarcoma were collected from four public and institutional sources. A common data model incorporating standardized terminology was created to facilitate the transformation, integration, and load of source data into a relational database. On the basis of this database, a data commons accompanied by a user-friendly web portal was developed, enabling various data exploration and analytics functions.

RESULTS

The Osteosarcoma Explorer (OSE) was released to the public in 2021. Leveraging a comprehensive and harmonized data set on the backend, the OSE offers a wide range of functions, including Cohort Discovery, Patient Dashboard, Image Visualization, and Online Analysis. Since its initial release, the OSE has experienced an increasing utilization by the osteosarcoma research community and provided solid, continuous user support. To our knowledge, the OSE is the largest (N = 573) and most comprehensive research data commons for pediatric osteosarcoma, a rare disease. This project demonstrates an effective framework for data integration and data commons development that can be readily applied to other projects sharing similar goals.

CONCLUSION

The OSE offers an online exploration and analysis platform for integrated clinical, molecular profiling, and tissue imaging data of osteosarcoma. Its underlying data model, database, and web framework support continuous expansion onto new data modalities and sources.

Identifying depression in the United States veterans using deep learning algorithms, NHANES 2005-2018

BACKGROUND

Depression is a common mental health problem among veterans, with high mortality. Despite the numerous conducted investigations, the prediction and identification of risk factors for depression are still severely limited. This study used a deep learning algorithm to identify depression in veterans and its factors associated with clinical manifestations.

METHODS

Our data originated from the National Health and Nutrition Examination Survey (2005-2018). A dataset of 2,546 veterans was identified using deep learning and five traditional machine learning algorithms with 10-fold cross-validation. Model performance was assessed by examining the area under the subject operating characteristic curve (AUC), accuracy, recall, specificity, precision, and F1 score.

RESULTS

Deep learning had the highest AUC (0.891, 95%CI 0.869-0.914) and specificity (0.906) in identifying depression in veterans. Further study on depression among veterans of different ages showed that the AUC values for deep learning were 0.929 (95%CI 0.904-0.955) in the middle-aged group and 0.924(95%CI 0.900-0.948) in the older age group. In addition to general health conditions, sleep difficulties, memory impairment, work incapacity, income, BMI, and chronic diseases, factors such as vitamins E and C, and palmitic acid were also identified as important influencing factors.

CONCLUSIONS

Compared with traditional machine learning methods, deep learning algorithms achieved optimal performance, making it conducive for identifying depression and its risk factors among veterans.

Machine learning for predicting survival of colorectal cancer patients

Colorectal cancer is one of the most incident types of cancer in the world, with almost 2 million new cases annually. In Brazil, the scenery is the same, around 41 thousand new cases were estimated in the last 3 years. This increase in cases further intensifies the interest and importance of studies related to the topic, especially using new approaches. The use of machine learning algorithms for cancer studies has grown in recent years, and they can provide important information to medicine, in addition to making predictions based on the data. In this study, five different classifications were performed, considering patients' survival. Data were extracted from Hospital Based Cancer Registries of São Paulo, which is coordinated by Fundação Oncocentro de São Paulo, containing patients with colorectal cancer from São Paulo state, Brazil, treated between 2000 and 2021. The machine learning models used provided us the predictions and the most important features for each one of the algorithms of the studies. Using part of the dataset to validate our models, the results of the predictors were around 77% of accuracy, with AUC close to 0.86, and the most important column was the clinical staging in all of them.

Clinical-radiomics models based on plain X-rays for prediction of lung metastasis in patients with osteosarcoma

OBJECTIVES

Osteosarcoma (OS) is the most common primary malignant bone tumor in adolescents. Lung metastasis (LM) occurs in more than half of patients at different stages of the disease course, which is one of the important factors affecting the long-term survival of OS. To develop and validate machine learning radiomics model based on radiographic and clinical features that could predict LM in OS within 3 years.

METHODS

486 patients (LM = 200, non-LM = 286) with histologically proven OS were retrospectively analyzed and divided into a training set (n = 389) and a validation set (n = 97). Radiographic features and risk factors (sex, age, tumor location, etc.) associated with LM of patients were evaluated. We built eight clinical-radiomics models (k-nearest neighbor [KNN], logistic regression [LR], support vector machine [SVM], random forest [RF], Decision Tree [DT], Gradient Boosting Decision Tree [GBDT], AdaBoost, and extreme gradient boosting [XGBoost]) and compared their performance. The area under the receiver operating characteristic curve (AUC) and accuracy (ACC) were used to evaluate different models.

RESULTS

The radscore, ALP, and tumor size had significant differences between the LM and non-LM groups (t_radscore = -5.829, χ²_ALP = 97.137, t_size = -3.437, P < 0.01). Multivariable LR analyses showed that ALP was an important indicator for predicting LM of OS (odds ratio [OR] = 7.272, P < 0.001). Among the eight models, the SVM-based clinical-radiomics model had the best performance in the validation set (AUC = 0.807, ACC = 0.784).

CONCLUSION

The clinical-radiomics model had good performance in predicting LM in OS, which would be helpful in clinical decision-making.

Development and validation of nomograms predicting overall and cancer-specific survival for non-metastatic primary malignant bone tumor of spine patients

At present, no study has established a survival prediction model for non-metastatic primary malignant bone tumors of the spine (PMBS) patients. The clinical features and prognostic limitations of PMBS patients still require further exploration. Data on patients with non-metastatic PBMS from 2004 to 2015 were extracted from the Surveillance, Epidemiology, and End Results (SEER) database. Multivariate regression analysis using Cox, Best-subset and Lasso regression methods was performed to identify the best combination of independent predictors. Then two nomograms were structured based on these factors for overall survival (OS) and cancer-specific survival (CSS). The accuracy and applicability of the nomograms were assessed by area under the curve (AUC) values, calibration curves and decision curve analysis (DCA). Results: The C-index indicated that the nomograms of OS (C-index 0.753) and CSS (C-index 0.812) had good discriminative power. The calibration curve displays a great match between the model's predictions and actual observations. DCA curves show our models for OS (range: 0.09-0.741) and CSS (range: 0.075-0.580) have clinical value within a specific threshold probability range compared with the two extreme cases. Two nomograms and web-based survival calculators based on established clinical characteristics was developed for OS and CSS. These can provide a reference for clinicians to formulate treatment plans for patients.

Targeted therapy for osteosarcoma: a review

BACKGROUND

Osteosarcoma is a common primary malignant tumour of the bone that usually occurs in children and adolescents. It is characterised by difficult treatment, recurrence and metastasis, and poor prognosis. Currently, the treatment of osteosarcoma is mainly based on surgery and auxiliary chemotherapy. However, for recurrent and some primary osteosarcoma cases, owing to the rapid progression of disease and chemotherapy resistance, the effects of chemotherapy are poor. With the rapid development of tumour-targeted therapy, molecular-targeted therapy for osteosarcoma has shown promise.

PURPOSE

In this paper, we review the molecular mechanisms, related targets, and clinical applications of targeted osteosarcoma therapy. In doing this, we provide a summary of recent literature on the characteristics of targeted osteosarcoma therapy, the advantages of its clinical application, and development of targeted therapy in future. We aim to provide new insights into the treatment of osteosarcoma.

CONCLUSION

Targeted therapy shows potential in the treatment of osteosarcoma and may offer an important means of precise and personalised treatment in the future, but drug resistance and adverse effects may limit its application.

NSUN2 promotes osteosarcoma progression by enhancing the stability of FABP5 mRNA via m5C methylation

5-methylcytosine (m⁵C) modification, which is mainly induced by the RNA methyltransferase NSUN2 (NOP2/Sun domain family, member 2), is an important chemical posttranscriptional modification in mRNA and has been proven to play important roles in the progression of many cancers. However, the functions and underlying molecular mechanisms of NSUN2-mediated m⁵C in osteosarcoma (OS) remain unclear. In this study, we found NSUN2 was highly expressed in OS tissues and cells. We also discovered that higher expression of NSUN2 predicted poorer prognosis of OS patients. Our study showed that NSUN2 could promote the progression of OS cells. Moreover, we employed RNA sequencing, RNA immunoprecipitation (RIP), and methylated RIP to screen and validate the candidate targets of NSUN2 and identified FABP5 as the target. We observed that NSUN2 stabilized FABP5 mRNA by inducing m⁵C modification and further promoted fatty acid metabolism in OS cells. Moreover, both knocking down the expression of FABP5 and adding fatty acid oxidation inhibitor could counterbalance the promoting effect of NSUN2 on the progression of OS. Our study confirms that NSUN2 can up-regulate the expression of FABP5 by improving the stability of FABP5 mRNA via m⁵C, so as to promote fatty acid metabolism in OS cells, and finally plays the role in promoting the progression of OS. Our findings suggest that NSUN2 is a promising prognostic marker for OS patients and may serve as a potential therapeutic target for OS treatment. A schematic illustration was proposed to summarize our findings.

Long-term survival and second malignant tumor prediction in pediatric, adolescent, and young adult cancer survivors using Random Survival Forests: a SEER analysis

Survival and second malignancy prediction models can aid clinical decision making. Most commonly, survival analysis studies are performed using traditional proportional hazards models, which require strong assumptions and can lead to biased estimates if violated. Therefore, this study aims to implement an alternative, machine learning (ML) model for survival analysis: Random Survival Forest (RSF). In this study, RSFs were built using the U.S. Surveillance Epidemiology and End Results to (1) predict 30-year survival in pediatric, adolescent, and young adult cancer survivors; and (2) predict risk and site of a second tumor within 30 years of the first tumor diagnosis in these age groups. The final RSF model for pediatric, adolescent, and young adult survival has an average Concordance index (C-index) of 92.9%, 94.2%, and 94.4% and average time-dependent area under the receiver operating characteristic curve (AUC) at 30-years since first diagnosis of 90.8%, 93.6%, 96.1% respectively. The final RSF model for pediatric, adolescent, and young adult second malignancy has an average C-index of 86.8%, 85.2%, and 88.6% and average time-dependent AUC at 30-years since first diagnosis of 76.5%, 88.1%, and 99.0% respectively. This study suggests the robustness and potential clinical value of ML models to alleviate physician burden by quickly identifying highest risk individuals.

Establishment of prognostic models of adrenocortical carcinoma using machine learning and big data

Background

Adrenocortical carcinoma (ACC) is a rare malignant tumor with a short life expectancy. It is important to identify patients at high risk so that doctors can adopt more aggressive regimens to treat their condition. Machine learning has the advantage of processing complicated data. To date, there is no research that tries to use machine learning algorithms and big data to construct prognostic models for ACC patients.

Methods

Clinical data of patients with ACC were obtained from the Surveillance, Epidemiology, and End Results (SEER) database. These records were screened according to preset inclusion and exclusion criteria. The remaining data were applied to univariate survival analysis to select meaningful outcome-related candidates. Backpropagation artificial neural network (BP-ANN), random forest (RF), support vector machine (SVM), and naive Bayes classifier (NBC) were chosen as alternative algorithms. The acquired cases were grouped into a training set and a test set at a ratio of 8:2, and a 10-fold cross-validation method repeated 10 times was performed. Area under the receiver operating characteristic (AUROC) curves were used as indices of efficiency.

Results

The calculated 1-, 3-, 5-, and 10-year overall survival rates were 62.3%, 42.0%, 34.9%, and 26.1%, respectively. A total of 825 patients were included in the study. In the training set, the AUCs of BP-ANN, RF, SVM, and NBC for predicting 1-year survival status were 0.921, 0.885, 0.865, and 0.854; those for predicting 3-year survival status were 0.859, 0.865, 0.837, and 0.831; and those for 5-year survival status were 0.888, 0.872, 0.852, and 0.841, respectively. In the test set, AUCs of these four models for 1-year survival status were 0.899, 0.875, 0.886, and 0.862; those for 3-year survival status were 0.871, 0.858, 0.853, and 0.869; and those for 5-year survival status were 0.841, 0.783, 0.836, and 0.867, respectively. The consequences of the 10-fold cross-validation method repeated 10 times indicated that the mean values of 1-, 3-, and 5-year AUROCs of BP-ANN were 0.890, 0.847, and 0.854, respectively, which were better than those of other classifiers (P < 0.008).

Conclusion

The model combined with BP-ANN and big data can precisely predict the survival status of ACC patients and has the potential for clinical application.

Development of nomogram and discussion of radiotherapy effect for osteosarcoma survival

This study aimed to develop a predictive system for prognostic evaluation of osteosarcoma patients. We obtained osteosarcoma sample data from 1998 to 2016 using SEER*Stat software version 8.3.8, and established a multivariable Cox regression model using R-4.0.3 software. Data were extracted from the Surveillance, Epidemiology, and End Results (SEER) database. The diagnosis of the model was completed through influential cases, proportionality, and multicollinearity. The predictive ability of the model was tested using area under the curve (AUC), calibration curves, and Brier scores. Finally, the bootstrap method was used to internally verify the model. In total, data from 3566 patients with osteosarcoma were included in this study. The multivariate Cox regression model was used to determine the independent prognostic variables. A nomogram and Kaplan-Meier survival curve were established. The AUC and Brier scores indicated that the model had a good predictive calibration. In addition, we found that the radiotherapy appears to be a risk factor of patients with osteosarcoma and made a discussion. We developed a prognostic evaluation system for patients with osteosarcoma for 1-, 3-, and 5-year overall survival with good predictive ability using sample data extracted from the SEER database. This has important clinical significance for the early identification and treatment of high-risk groups of osteosarcoma patients.

The research on TBATS and ELM models for prediction of human brucellosis cases in mainland China: a time series study

BACKGROUND

Human brucellosis is a serious public health concern in China. The objective of this study is to develop a suitable model for forecasting human brucellosis cases in mainland China.

METHODS

Data on monthly human brucellosis cases from January 2012 to December 2021 in 31 provinces and municipalities in mainland China were obtained from the National Health Commission of the People's Republic of China website. The TBATS and ELM models were constructed. The MAE, MSE, MAPE, and RMSE were calculated to evaluate the prediction performance of the two models.

RESULTS

The optimal TBATS model was TBATS (1, {0,0}, -, {< 12,4 >}) and the lowest AIC value was 1854.703. In the optimal TBATS model, {0,0} represents the ARIMA (0,0) model, {< 12,4 >} are the parameters of the seasonal periods and the corresponding number of Fourier terms, respectively, and the parameters of the Box-Cox transformation ω are 1. The optimal ELM model hidden layer number was 33 and the R-squared value was 0.89. The ELM model provided lower values of MAE, MSE, MAPE, and RMSE for both the fitting and forecasting performance.

CONCLUSIONS

The results suggest that the forecasting performance of ELM model outperforms the TBATS model in predicting human brucellosis between January 2012 and December 2021 in mainland China. Forecasts of the ELM model can help provide early warnings and more effective prevention and control measures for human brucellosis in mainland China.

A 5‐year survival status prognosis of nonmetastatic cervical cancer patients through machine learning algorithms

BACKGROUND

Prediction models with high accuracy rates for nonmetastatic cervical cancer (CC) patients are limited. This study aimed to construct and compare predictive models on the basis of machine learning (ML) algorithms for predicting the 5-year survival status of CC patients through using the Surveillance, Epidemiology, and End Results public database of the National Cancer Institute.

METHODS

The data registered from 2004 to 2016 were extracted and randomly divided into training and validation cohorts (8:2). The least absolute shrinkage and selection operator (LASSO) regression was employed to identify significant factors. Then, four predictive models were constructed, including logistic regression (LR), random forest (RF), support vector machine (SVM), and extreme gradient boosting (XGBoost). The predictive models were evaluated and compared using Receiver-operating characteristics with areas under the curves (AUCs) and decision curve analysis (DCA), respectively.

RESULTS

A total of 13,802 patients were involved and classified into training (N = 11,041) and validation (N = 2761) cohorts. By using the LASSO regression method, seven factors were identified. In the training cohort, the XGBoost model showed the best performance (AUC = 0.8400) compared to the other three models (all p < 0.05 by Delong's test). In the validation cohort, the XGBoost model also demonstrated a superior prediction ability (AUC = 0.8365) than LR and SVM models (both p < 0.05 by Delong's test), although the difference was not statistically significant between the XGBoost and the RF models (p = 0.4251 by Delong's test). Based on the DCA results, the XGBoost model was also superior, and feature importance analysis indicated that the tumor stage was the most important variable among the seven factors.

CONCLUSIONS

The XGBoost model proved to be an effective algorithm with better prediction abilities. This model is proposed to support better decision-making for nonmetastatic CC patients in the future.

Development and validation of an XGBoost model to predict 5-year survival in elderly patients with intrahepatic cholangiocarcinoma after surgery: a SEER-based study

Background

Nomograms have been established to predict survival in postoperative or elderly intrahepatic cholangiocarcinoma (ICC) patients. There are no models to predict postoperative survival in elderly ICC patients. Extreme gradient boosting (XGBoost) can adjust the errors generated by existing models. This retrospective cohort study aimed to develop and validate an XGBoost model to predict postoperative 5-year survival in elderly ICC patients.

Methods

The Surveillance, Epidemiology, and End Results (SEER) program provided data on elderly ICC patients aged 60 years or older and undergoing surgery. The median follow-up time was 20 months. Totally 1,055 patients were classified as training (n=738) and testing (n=317) sets at a ratio of 7:3. The outcome was postoperative 5-year survival. Demographic, tumor-related and treatment-related variables were collected. Variables were screened using the XGBoost model. The predictive performance of the model was assessed by the area under the receiver operating characteristic (ROC) curve (AUC), sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and Kaplan-Meier curve. Cox regression analysis was conducted to estimate the risk of death in the predicted populations. The predictive abilities of the XGBoost model and the American Joint Commission on Cancer (AJCC) system (7th edition) were compared.

Results

The XGBoost model achieved an AUC of 0.811, a sensitivity of 0.573, a specificity of 0.890, and a PPV of 0.849 in the training set. In the testing set, the model had an AUC of 0.713, a sensitivity of 0.478, a specificity of 0.814, and a PPV of 0.726. The 5-year mortality risk of patients predicted to die was 2.91 times that of patients predicted to survive [hazard ratio (HR) =2.91, 95% confidence interval (CI): 2.42-3.50]. The XGBoost model showed a better predictive performance than the AJCC staging system both in the training and testing sets. AJCC stage, multiple (satellite) tumors/nodules, tumor-node-metastasis (TNM) stage, more than one lobe invaded, direct invasion of adjacent organs, tumor size, and radiotherapy were relatively important features in survival prediction.

Conclusions

The XGBoost model exhibited some predictive capacity, which may be applied to predict postoperative 5-year survival for elderly ICC patients.

A Predictive Model for the 10-year Overall Survival Status of Patients With Distant Metastases From Differentiated Thyroid Cancer Using XGBoost Algorithm-A Population-Based Analysis

Purpose: To explore clinical and non-clinical characteristics affecting the prognosis of patients with differentiated thyroid cancer with distant metastasis (DTCDM) and establish an accurate overall survival (OS) prognostic model.

Patients and methods: Study subjects and related information were obtained from the National Cancer Institute’s surveillance, epidemiology, and results database (SEER). Kaplan‐Meier analysis, log-rank test, and univariate and multivariate Cox analysis were used to screen for factors influencing the OS of patients with DTCDM. Nine variables were introduced to build a machine learning (ML) model, receiver operating characteristic (ROC) was used to evaluate the recognition ability of the model, calibration plots were used to obtain prediction accuracy, and decision curve analysis (DCA) was used to estimate clinical benefit.

Results: After applying the inclusion and exclusion criteria, a total of 3,060 patients with DTCDM were included in the survival analysis from 2004 to 2017. A machine learning prediction model was developed with nine variables: age at diagnosis, gender, race, tumor size, histology, regional lymph node metastasis, primary site surgery, radiotherapy, and chemotherapy. After excluding patients who survived <120 months, variables were sub-coded and machine learning was used to model OS prognosis in patients with DTCDM. Patients 6–50 years of age had the highest scores in the model. Other variables with high scores included small tumor size, male sex, and age 51–76. The AUC and calibration curves confirm that the XGBoost model has good performance. DCA shows that our model can be used to support clinical decision-making in a 10-years overall survival model.

Conclusion: An artificial intelligence model was constructed using the XGBoost algorithms to predict the 10-years overall survival rate of patients with DTCDM. After model validation and evaluation, the model had good discriminative ability and high clinical value. This model could serve as a clinical tool to help inform treatment decisions for patients with DTCDM.