Prediction of survival in oropharyngeal squamous cell carcinoma using machine learning algorithms: A study based on the surveillance, epidemiology, and end results database

De-escalated radiation for human papillomavirus virus-related oropharyngeal cancer: Who, why, what, where, when, how, how much…and what next?

The emergence of treatment de-escalation as a feasible option for patients with newly diagnosed human papillomavirus (HPV)-associated oropharyngeal squamous cell carcinoma has generated considerable excitement among both providers and patients alike. Since HPV-positive oropharyngeal carcinoma has been shown to be a unique entity with distinct clinical and molecular characteristics, the rationale for customizing treatment for patients with this disease is compelling. Indeed, evidence has accumulated demonstrating that patients with HPV-positive oropharyngeal cancer have a significantly improved prognosis as a result of their exquisite radiosensitivity compared to their HPV-negative counterparts and thus might possibly be targeted with de-escalated approaches. The fundamental goal of de-escalation is to maintain the high cure and survival rates associated with traditional approaches while reducing the intensity of treatment and thus the incidence of both short- and long-term toxicity. Given the rapidly increasing incidence of this disease, particularly among younger patients who are generally healthy, the focus on quality of life seems germane. Although the exact reason for the improved sensitivity of HPV-positive oropharyngeal carcinoma to treatment is uncertain, prospective studies have now been published demonstrating that de-escalated radiation can successfully maintain the high rates of cure and preserve quality of life for appropriately selected patients with this disease. However, these studies have been fairly heterogeneous in design, and it remains questionable how to apply their findings to real-world practice. The potential of integrating translational approaches into clinical paradigms is also just starting to become recognized. Consequently, multiple uncertainties continue to exist with respect to de-escalation for HPV-positive oropharyngeal cancer, and these questions comprise the crux of this review.

Mapping the research landscape of HPV-positive oropharyngeal cancer: a bibliometric analysis

OBJECTIVE

The aim of the study is to evaluate the scientific interest, the collaboration patterns and the emerging trends regarding HPV+ OPSCC diagnosis and treatment.

MATERIALS AND METHODS

A cross-sectional bibliometric analysis of articles reporting on HPV+ OPSCC within Scopus database was performed and all documents published up to December 31th, 2022 were eligible for analysis. Outcomes included the exploration of key characteristics (number of manuscripts published per year, growth rate, top productive countries, most highly cited papers, and the most well-represented journals), collaboration parameters (international collaboration ratio and networks, co-occurrence networks), keywords analysis (trend topics, factorial analysis).

RESULTS

A total of 5200 documents were found, published from March, 1987 to December, 2022. The number of publications increased annually with an average growth rate of 19.94%, reaching a peak of 680 documents published in 2021. The 10 most cited documents (range 1105-4645) were published from 2000 to 2012. The keywords factorial analysis revealed two main clusters: one on epidemiology, diagnosis, prevention and association with other HPV tumors; the other one about the therapeutic options. According to the frequency of keywords, new items are emerging in the last three years regarding the application of Artifical Intelligence (machine learning and radiomics) and the diagnostic biomarkers (circulating tumor DNA).

CONCLUSIONS

This bibliometric analysis highlights the importance of research efforts in prevention, diagnostics, and treatment strategies for this disease. Given the urgency of optimizing treatment and improving clinical outcomes, further clinical trials are needed to bridge unaddressed gaps in the management of HPV+ OPSCC patients.

Creation of a machine learning-based prognostic prediction model for various subtypes of laryngeal cancer

Depending on the source of the blastophore, there are various subtypes of laryngeal cancer, each with a unique metastatic risk and prognosis. The forecasting of their prognosis is a pressing issue that needs to be resolved. This study comprised 5953 patients with glottic carcinoma and 4465 individuals with non-glottic type (supraglottic and subglottic). Five clinicopathological characteristics of glottic and non-glottic carcinoma were screened using univariate and multivariate regression for CoxPH (Cox proportional hazards); for other models, 10 (glottic) and 11 (non-glottic) clinicopathological characteristics were selected using least absolute shrinkage and selection operator (LASSO) regression analysis, respectively; the corresponding survival models were established; and the best model was evaluated. We discovered that RSF (Random survival forest) was a superior model for both glottic and non-glottic carcinoma, with a projected concordance index (C-index) of 0.687 for glottic and 0.657 for non-glottic, respectively. The integrated Brier score (IBS) of their 1-year, 3-year, and 5-year time points is, respectively, 0.116, 0.182, 0.195 (glottic), and 0.130, 0.215, 0.220 (non-glottic), demonstrating the model's effective correction. We represented significant variables in a Shapley Additive Explanations (SHAP) plot. The two models are then combined to predict the prognosis for two distinct individuals, which has some effectiveness in predicting prognosis. For our investigation, we established separate models for glottic carcinoma and non-glottic carcinoma that were most effective at predicting survival. RSF is used to evaluate both glottic and non-glottic cancer, and it has a considerable impact on patient prognosis and risk factor prediction.

A deep learning algorithm with good prediction efficacy for cancer-specific survival in osteosarcoma: A retrospective study

OBJECTIVE

Successful prognosis is crucial for the management and treatment of osteosarcoma (OSC). This study aimed to predict the cancer-specific survival rate in patients with OSC using deep learning algorithms and classical Cox proportional hazard models to provide data to support individualized treatment of patients with OSC.

METHODS

Data on patients diagnosed with OSC from 2004 to 2017 were obtained from the Surveillance, Epidemiology, and End Results database. The study sample was then divided randomly into a training cohort and a validation cohort in the proportion of 7:3. The DeepSurv algorithm and the Cox proportional hazard model were chosen to construct prognostic models for patients with OSC. The prediction efficacy of the model was estimated using the concordance index (C-index), the integrated Brier score (IBS), the root mean square error (RMSE), and the mean absolute error (SME).

RESULTS

A total of 3218 patients were randomized into training and validation groups (n = 2252 and 966, respectively). Both DeepSurv and Cox models had better efficacy in predicting cancer-specific survival (CSS) in OSC patients (C-index >0.74). In the validation of other metrics, DeepSurv did not have superiority over the Cox model in predicting survival in OSC patients.

CONCLUSIONS

After validation, our CSS prediction model for patients with OSC based on the DeepSurv algorithm demonstrated satisfactory prediction efficacy and provided a convenient webpage calculator.

Prediction of lung papillary adenocarcinoma-specific survival using ensemble machine learning models

Accurate prognostic prediction is crucial for treatment decision-making in lung papillary adenocarcinoma (LPADC). The aim of this study was to predict cancer-specific survival in LPADC using ensemble machine learning and classical Cox regression models. Moreover, models were evaluated to provide recommendations based on quantitative data for personalized treatment of LPADC. Data of patients diagnosed with LPADC (2004-2018) were extracted from the Surveillance, Epidemiology, and End Results database. The set of samples was randomly divided into the training and validation sets at a ratio of 7:3. Three ensemble models were selected, namely gradient boosting survival (GBS), random survival forest (RSF), and extra survival trees (EST). In addition, Cox proportional hazards (CoxPH) regression was used to construct the prognostic models. The Harrell's concordance index (C-index), integrated Brier score (IBS), and area under the time-dependent receiver operating characteristic curve (time-dependent AUC) were used to evaluate the performance of the predictive models. A user-friendly web access panel was provided to easily evaluate the model for the prediction of survival and treatment recommendations. A total of 3615 patients were randomly divided into the training and validation cohorts (n = 2530 and 1085, respectively). The extra survival trees, RSF, GBS, and CoxPH models showed good discriminative ability and calibration in both the training and validation cohorts (mean of time-dependent AUC: > 0.84 and > 0.82; C-index: > 0.79 and > 0.77; IBS: < 0.16 and < 0.17, respectively). The RSF and GBS models were more consistent than the CoxPH model in predicting long-term survival. We implemented the developed models as web applications for deployment into clinical practice (accessible through https://shinyshine-820-lpaprediction-model-z3ubbu.streamlit.app/ ). All four prognostic models showed good discriminative ability and calibration. The RSF and GBS models exhibited the highest effectiveness among all models in predicting the long-term cancer-specific survival of patients with LPADC. This approach may facilitate the development of personalized treatment plans and prediction of prognosis for LPADC.

Predicting overall survival in chordoma patients using machine learning models: a web-app application

OBJECTIVE

The goal of this study was to evaluate the efficacy of machine learning (ML) techniques in predicting survival for chordoma patients in comparison with the standard Cox proportional hazards (CoxPH) model.

METHODS

Using a Surveillance, Epidemiology, and End Results database of consecutive newly diagnosed chordoma cases between January 2000 and December 2018, we created and validated three ML survival models as well as a traditional CoxPH model in this population-based cohort study. Randomly, the dataset was divided into training and validation datasets. Tuning hyperparameters on the training dataset involved a 1000-iteration random search with fivefold cross-validation. Concordance index (C-index), Brier score, and integrated Brier score were used to evaluate the performance of the model. The receiver operating characteristic (ROC) curves, calibration curves, and area under the ROC curves (AUC) were used to assess the reliability of the models by predicting 5- and 10-year survival probabilities.

RESULTS

A total of 724 chordoma patients were divided into training (n = 508) and validation (n = 216) cohorts. Cox regression identified nine significant prognostic factors (p < 0.05). ML models showed superior performance over CoxPH model, with DeepSurv having the highest C-index (0.795) and the best discrimination for 5- and 10-year survival (AUC 0.84 and 0.88). Calibration curves revealed strong correlation between DeepSurv predictions and actual survival. Risk stratification by DeepSurv model effectively discriminated high- and low-risk groups (p < 0.01). The optimized DeepSurv model was implemented into a web application for clinical use that can be found at https://hust-chengp-ml-chordoma-app-19rjyr.streamlitapp.com/ .

CONCLUSION

ML algorithms based on time-to-event results are effective in chordoma prediction, with DeepSurv having the best discrimination performance and calibration.

De-escalated radiation for human papillomavirus virus-related oropharyngeal cancer: evolving paradigms and future strategies

The incidence of human papillomavirus (HPV)-associated oropharyngeal squamous cell carcinoma has increased dramatically in recent years reaching epidemic-like proportions. Data has emerged not only showing that these cancers are a unique entity with distinct molecular characteristics but that they also have a significantly improved prognosis as a result of their exquisite radiosensitivity compared to their HPV-negative counterparts. This, it has been increasingly suggested that these tumors can be targeted with de-escalated approaches using reduced doses of radiation. The overriding goal of de-escalation is to maintain the high cure and survival rates associated with traditional approaches while reducing the incidence of both short- and long-term toxicity. Although the exact reason for the improved radiosensitivity of HPV-positive oropharyngeal carcinoma is unclear, prospective studies have now been published demonstrating that de-escalated radiation can successfully maintain the high rates of cure and preserve quality of life for appropriately selected patients with this disease. However, these studies have been complicated by such factors as the relatively limited sample sizes, as well as the variability in treatment, inclusion criteria, and follow-up. As the data continues to mature on de-escalation, it is unquestionable that treatment paradigms for this disease will evolve. The ongoing quest to define a standard regimen comprises the subject of this review.

Application of artificial intelligence for overall survival risk stratification in oropharyngeal carcinoma: A validation of ProgTOOL

BACKGROUND

In recent years, there has been a surge in machine learning-based models for diagnosis and prognostication of outcomes in oncology. However, there are concerns relating to the model's reproducibility and generalizability to a separate patient cohort (i.e., external validation).

OBJECTIVES

This study primarily provides a validation study for a recently introduced and publicly available machine learning (ML) web-based prognostic tool (ProgTOOL) for overall survival risk stratification of oropharyngeal squamous cell carcinoma (OPSCC). Additionally, we reviewed the published studies that have utilized ML for outcome prognostication in OPSCC to examine how many of these models were externally validated, type of external validation, characteristics of the external dataset, and diagnostic performance characteristics on the internal validation (IV) and external validation (EV) datasets were extracted and compared.

METHODS

We used a total of 163 OPSCC patients obtained from the Helsinki University Hospital to externally validate the ProgTOOL for generalizability. In addition, PubMed, OvidMedline, Scopus, and Web of Science databases were systematically searched according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines.

RESULTS

The ProgTOOL produced a predictive performance of 86.5% balanced accuracy, Mathew's correlation coefficient of 0.78, Net Benefit (0.7) and Brier score (0.06) for overall survival stratification of OPSCC patients as either low-chance or high-chance. In addition, out of a total of 31 studies found to have used ML for the prognostication of outcomes in OPSCC, only seven (22.6%) reported a form of EV. Three studies (42.9%) each used either temporal EV or geographical EV while only one study (14.2%) used expert as a form of EV. Most of the studies reported a reduction in performance when externally validated.

CONCLUSION

The performance of the model in this validation study indicates that it may be generalized, therefore, bringing recommendations of the model for clinical evaluation closer to reality. However, the number of externally validated ML-based models for OPSCC is still relatively small. This significantly limits the transfer of these models for clinical evaluation and subsequently reduces the likelihood of the use of these models in daily clinical practice. As a gold standard, we recommend the use of geographical EV and validation studies to reveal biases and overfitting of these models. These recommendations are poised to facilitate the implementation of these models in clinical practice.

Development and validation of survival prediction model for gastric adenocarcinoma patients using deep learning: A SEER-based study

Background

The currently available prediction models, such as the Cox model, were too simplistic to correctly predict the outcome of gastric adenocarcinoma patients. This study aimed to develop and validate survival prediction models for gastric adenocarcinoma patients using the deep learning survival neural network.

Methods

A total of 14,177 patients with gastric adenocarcinoma from the Surveillance, Epidemiology, and End Results (SEER) database were included in the study and randomly divided into the training and testing group with a 7:3 ratio. Two algorithms were chosen to build the prediction models, and both algorithms include random survival forest (RSF) and a deep learning based-survival prediction algorithm (DeepSurv). Also, a traditional Cox proportional hazard (CoxPH) model was constructed for comparison. The consistency index (C-index), Brier score, and integrated Brier score (IBS) were used to evaluate the model's predictive performance. The accuracy of predicting survival at 1, 3, 5, and 10 years was also assessed using receiver operating characteristic curves (ROC), calibration curves, and area under the ROC curve (AUC).

Results

Gastric adenocarcinoma patients were randomized into a training group (n = 9923) and a testing group (n = 4254). DeepSurv showed the best performance among the three models (c-index: 0.772, IBS: 0.1421), which was superior to that of the traditional CoxPH model (c-index: 0.755, IBS: 0.1506) and the RSF with 3-year survival prediction model (c-index: 0.766, IBS: 0.1502). The DeepSurv model produced superior accuracy and calibrated survival estimates predicting 1-, 3- 5- and 10-year survival (AUC: 0.825-0.871).

Conclusions

A deep learning algorithm was developed to predict more accurate prognostic information for gastric cancer patients. The DeepSurv model has advantages over the CoxPH and RSF models and performs well in discriminative performance and calibration.

Survival comparison of different histological subtypes of oropharyngeal squamous cell carcinoma: A propensity-matched score analysis based on SEER database

OBJECTIVE

The purpose of this study was to analyze the difference of survival rates in paitents with oropharyngeal keratinizing squamous cell carcinoma (KSCC), nonkeratinizing squamous cell carcinoma (NKSCC), basaloid squamous cell carcinoma (BSCC), and papillary squamous cell carcinoma (PSCC).

MATERIALS AND METHODS

Patients diagnosed with oropharyngeal squamous cell carcinoma between 2004 and 2015 were collected from the SEER database. Cox proportional hazards models and Kaplan-Meier curves were used for survival analysis. Propensity score matching (PSM) was performed to adjust for the effect of confounding variables. Due to the small sample size of PSCC, this study did not perform PSM between it and other subtypes.

RESULTS

The 5-year cancer-specific survival (CSS) rate of PSCC was higher than that of KSCC, NKSCC, and BSCC (0.627 vs. 0.812 vs. 0.789 vs. 0.875, P < 0.05); And the CSS rate of KSCC was lower than that of other subtypes both before and after PSM. In addition, the 5-year and 10-year CSS rates of BSCC were not different from NKSCC (P > 0.05), but not as good as NKSCC in the long term (P = 0.028). After PSM, the 5-year, 10-year, and long-term prognosis of BSCC were significantly worse than those of NKSCC (P < 0.001).

CONCLUSION

The 5-year CSS of PSCC was better than the other three subtypes. The short-term prognosis of BSCC was not significantly different from NKSCC, but the long-term survival was lower than that of NKSCC, and the difference was more obvious after PSM. Meanwhile, the prognosis of KSCC was worst.