Deep learning-based survival prediction of oral cancer patients

Bibliometric analysis of the application of deep learning in cancer from 2015 to 2023

BACKGROUND

Recently, the application of deep learning (DL) has made great progress in various fields, especially in cancer research. However, to date, the bibliometric analysis of the application of DL in cancer is scarce. Therefore, this study aimed to explore the research status and hotspots of the application of DL in cancer.

METHODS

We retrieved all articles on the application of DL in cancer from the Web of Science database Core Collection database. Biblioshiny, VOSviewer and CiteSpace were used to perform the bibliometric analysis through analyzing the numbers, citations, countries, institutions, authors, journals, references, and keywords.

RESULTS

We found 6,016 original articles on the application of DL in cancer. The number of annual publications and total citations were uptrend in general. China published the greatest number of articles, USA had the highest total citations, and Saudi Arabia had the highest centrality. Chinese Academy of Sciences was the most productive institution. Tian, Jie published the greatest number of articles, while He Kaiming was the most co-cited author. IEEE Access was the most popular journal. The analysis of references and keywords showed that DL was mainly used for the prediction, detection, classification and diagnosis of breast cancer, lung cancer, and skin cancer.

CONCLUSIONS

Overall, the number of articles on the application of DL in cancer is gradually increasing. In the future, further expanding and improving the application scope and accuracy of DL applications, and integrating DL with protein prediction, genomics and cancer research may be the research trends.

Machine learning methods in predicting the risk of malignant transformation of oral potentially malignant disorders: A systematic review

BACKGROUND

Oral Potentially Malignant Disorders (OPMDs) refer to a heterogenous group of clinical presentations with heightened rate of malignant transformation. Identification of risk levels in OPMDs is crucial to determine the need for active intervention in high-risk patients and routine follow-up in low-risk ones. Machine learning models has shown tremendous potential in several areas of dentistry that strongly suggest its application to estimate rate of malignant transformation of precancerous lesions.

METHODS

A comprehensive literature search was performed on Pubmed/MEDLINE, Web of Science, Scopus, Embase, Cochrane Library database to identify articles including machine learning models and algorithms to predict malignant transformation in OPMDs. Relevant bibliographic data, study characteristics, and outcomes were extracted for eligible studies. Quality of the included studies was assessed through the IJMEDI checklist.

RESULTS

Fifteen articles were found suitable for the review as per the PECOS criteria. Amongst all studies, highest sensitivity (100%) was recorded for U-net architecture, Peaks Random forest model, and Partial least squares discriminant analysis (PLSDA). Highest specificity (100%) was noted for PLSDA. Range of overall accuracy in risk prediction was between 95.4% and 74%.

CONCLUSION

Machine learning proved to be a viable tool in risk prediction, demonstrating heightened sensitivity, automation, and improved accuracy for predicting transformation of OPMDs. It presents an effective approach for incorporating multiple variables to monitor the progression of OPMDs and predict their malignant potential. However, its sensitivity to dataset characteristics necessitates the optimization of input parameters to maximize the efficiency of the classifiers.

Application of deep learning radiomics in oral squamous cell carcinoma-Extracting more information from medical images using advanced feature analysis

OBJECTIVE

To conduct a systematic review with meta-analyses to assess the recent scientific literature addressing the application of deep learning radiomics in oral squamous cell carcinoma (OSCC).

MATERIALS AND METHODS

Electronic and manual literature retrieval was performed using PubMed, Web of Science, EMbase, Ovid-MEDLINE, and IEEE databases from 2012 to 2023. The ROBINS-I tool was used for quality evaluation; random-effects model was used; and results were reported according to the PRISMA statement.

RESULTS

A total of 26 studies involving 64,731 medical images were included in quantitative synthesis. The meta-analysis showed that, the pooled sensitivity and specificity were 0.88 (95 %CI: 0.87∼0.88) and 0.80 (95 %CI: 0.80∼0.81), respectively. Deeks' asymmetry test revealed there existed slight publication bias (P = 0.03).

CONCLUSIONS

The advances in the application of radiomics combined with learning algorithm in OSCC were reviewed, including diagnosis and differential diagnosis of OSCC, efficacy assessment and prognosis prediction. The demerits of deep learning radiomics at the current stage and its future development direction aimed at medical imaging diagnosis were also summarized and analyzed at the end of the article.

Enhancing oral squamous cell carcinoma detection: a novel approach using improved EfficientNet architecture

PROBLEM

Oral squamous cell carcinoma (OSCC) is the eighth most prevalent cancer globally, leading to the loss of structural integrity within the oral cavity layers and membranes. Despite its high prevalence, early diagnosis is crucial for effective treatment.

AIM

This study aimed to utilize recent advancements in deep learning for medical image classification to automate the early diagnosis of oral histopathology images, thereby facilitating prompt and accurate detection of oral cancer.

METHODS

A deep learning convolutional neural network (CNN) model categorizes benign and malignant oral biopsy histopathological images. By leveraging 17 pretrained DL-CNN models, a two-step statistical analysis identified the pretrained EfficientNetB0 model as the most superior. Further enhancement of EfficientNetB0 was achieved by incorporating a dual attention network (DAN) into the model architecture.

RESULTS

The improved EfficientNetB0 model demonstrated impressive performance metrics, including an accuracy of 91.1%, sensitivity of 92.2%, specificity of 91.0%, precision of 91.3%, false-positive rate (FPR) of 1.12%, F1 score of 92.3%, Matthews correlation coefficient (MCC) of 90.1%, kappa of 88.8%, and computational time of 66.41%. Notably, this model surpasses the performance of state-of-the-art approaches in the field.

CONCLUSION

Integrating deep learning techniques, specifically the enhanced EfficientNetB0 model with DAN, shows promising results for the automated early diagnosis of oral cancer through oral histopathology image analysis. This advancement has significant potential for improving the efficacy of oral cancer treatment strategies.

Deep-learning survival analysis for patients with calcific aortic valve disease undergoing valve replacement

Calcification of the aortic valve (CAVDS) is a major cause of aortic stenosis (AS) leading to loss of valve function which requires the substitution by surgical aortic valve replacement (SAVR) or transcatheter aortic valve intervention (TAVI). These procedures are associated with high post-intervention mortality, then the corresponding risk assessment is relevant from a clinical standpoint. This study compares the traditional Cox Proportional Hazard (CPH) against Machine Learning (ML) based methods, such as Deep Learning Survival (DeepSurv) and Random Survival Forest (RSF), to identify variables able to estimate the risk of death one year after the intervention, in patients undergoing either to SAVR or TAVI. We found that with all three approaches the combination of six variables, named albumin, age, BMI, glucose, hypertension, and clonal hemopoiesis of indeterminate potential (CHIP), allows for predicting mortality with a c-index of approximately 80 % . Importantly, we found that the ML models have a better prediction capability, making them as effective for statistical analysis in medicine as most state-of-the-art approaches, with the additional advantage that they may expose non-linear relationships. This study aims to improve the early identification of patients at higher risk of death, who could then benefit from a more appropriate therapeutic intervention.

Survival estimation of oral cancer using fuzzy deep learning

BACKGROUND

Oral cancer is a deadly disease and a major cause of morbidity and mortality worldwide. The purpose of this study was to develop a fuzzy deep learning (FDL)-based model to estimate the survival time based on clinicopathologic data of oral cancer.

METHODS

Electronic medical records of 581 oral squamous cell carcinoma (OSCC) patients, treated with surgery with or without radiochemotherapy, were collected retrospectively from the Oral and Maxillofacial Surgery Clinic and the Regional Cancer Center from 2011 to 2019. The deep learning (DL) model was trained to classify survival time classes based on clinicopathologic data. Fuzzy logic was integrated into the DL model and trained to create FDL-based models to estimate the survival time classes.

RESULTS

The performance of the models was evaluated on a test dataset. The performance of the DL and FDL models for estimation of survival time achieved an accuracy of 0.74 and 0.97 and an area under the receiver operating characteristic (AUC) curve of 0.84 to 1.00 and 1.00, respectively.

CONCLUSIONS

The integration of fuzzy logic into DL models could improve the accuracy to estimate survival time based on clinicopathologic data of oral cancer.

Explainable and visualizable machine learning models to predict biochemical recurrence of prostate cancer

PURPOSE

Machine learning (ML) models presented an excellent performance in the prognosis prediction. However, the black box characteristic of ML models limited the clinical applications. Here, we aimed to establish explainable and visualizable ML models to predict biochemical recurrence (BCR) of prostate cancer (PCa).

MATERIALS AND METHODS

A total of 647 PCa patients were retrospectively evaluated. Clinical parameters were identified using LASSO regression. Then, cohort was split into training and validation datasets with a ratio of 0.75:0.25 and BCR-related features were included in Cox regression and five ML algorithm to construct BCR prediction models. The clinical utility of each model was evaluated by concordance index (C-index) values and decision curve analyses (DCA). Besides, Shapley Additive Explanation (SHAP) values were used to explain the features in the models.

RESULTS

We identified 11 BCR-related features using LASSO regression, then establishing five ML-based models, including random survival forest (RSF), survival support vector machine (SSVM), survival Tree (sTree), gradient boosting decision tree (GBDT), extreme gradient boosting (XGBoost), and a Cox regression model, C-index were 0.846 (95%CI 0.796-0.894), 0.774 (95%CI 0.712-0.834), 0.757 (95%CI 0.694-0.818), 0.820 (95%CI 0.765-0.869), 0.793 (95%CI 0.735-0.852), and 0.807 (95%CI 0.753-0.858), respectively. The DCA showed that RSF model had significant advantages over all models. In interpretability of ML models, the SHAP value demonstrated the tangible contribution of each feature in RSF model.

CONCLUSIONS

Our score system provide reference for the identification for BCR, and the crafting of a framework for making therapeutic decisions for PCa on a personalized basis.

Explainable deep learning-based survival prediction for non-small cell lung cancer patients undergoing radical radiotherapy

BACKGROUND AND PURPOSE

Survival is frequently assessed using Cox proportional hazards (CPH) regression; however, CPH may be too simplistic as it assumes a linear relationship between covariables and the outcome. Alternative, non-linear machine learning (ML)-based approaches, such as random survival forests (RSFs) and, more recently, deep learning (DL) have been proposed; however, these techniques are largely black-box in nature, limiting explainability. We compared CPH, RSF and DL to predict overall survival (OS) of non-small cell lung cancer (NSCLC) patients receiving radiotherapy using pre-treatment covariables. We employed explainable techniques to provide insights into the contribution of each covariable on OS prediction.

MATERIALS AND METHODS

The dataset contained 471 stage I-IV NSCLC patients treated with radiotherapy. We built CPH, RSF and DL OS prediction models using several baseline covariable combinations. 10-fold Monte-Carlo cross-validation was employed with a split of 70%:10%:20% for training, validation and testing, respectively. We primarily evaluated performance using the concordance index (C-index) and integrated Brier score (IBS). Local interpretable model-agnostic explanation (LIME) values, adapted for use in survival analysis, were computed for each model.

RESULTS

The DL method exhibited a significantly improved C-index of 0.670 compared to the CPH and a significantly improved IBS of 0.121 compared to the CPH and RSF approaches. LIME values suggested that, for the DL method, the three most important covariables in OS prediction were stage, administration of chemotherapy and oesophageal mean radiation dose.

CONCLUSION

We show that, using pre-treatment covariables, a DL approach demonstrates superior performance over CPH and RSF for OS prediction and use explainable techniques to provide transparency and interpretability.

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.

Application of deep neural survival networks to the development of risk prediction models for diabetes mellitus, hypertension, and dyslipidemia

OBJECTIVES

: Although numerous risk prediction models have been proposed, few such models have been developed using neural network-based survival analysis. We developed risk prediction models for three cardiovascular disease risk factors (diabetes mellitus, hypertension, and dyslipidemia) among a working-age population in Japan using DeepSurv, a deep feed-forward neural network.

METHODS

: Data were obtained from the Japan Epidemiology Collaboration on Occupational Health Study. A total of 51 258, 44 197, and 31 452 individuals were included in the development of risk models for diabetes mellitus, hypertension, and dyslipidemia, respectively; two-thirds of whom were used to develop prediction models, and the rest were used to validate the models. We compared the performances of DeepSurv-based models with those of prediction models based on the Cox proportional hazards model.

RESULTS

: The area under the receiver-operating characteristic curve was 0.878 [95% confidence interval (CI) = 0.864-0.892] for diabetes mellitus, 0.835 (95% CI = 0.826-0.845) for hypertension, and 0.826 (95% CI = 0.817-0.835) for dyslipidemia. Compared with the Cox proportional hazards-based models, the DeepSurv-based models had better reclassification performance [diabetes mellitus: net reclassification improvement (NRI) = 0.474, P  ≤ 0.001; hypertension: NRI = 0.194, P  ≤ 0.001; dyslipidemia: NRI = 0.397, P  ≤ 0.001] and discrimination performance [diabetes mellitus: integrated discrimination improvement (IDI) = 0.013, P  ≤ 0.001; hypertension: IDI = 0.007, P  ≤ 0.001; and dyslipidemia: IDI = 0.043, P  ≤ 0.001].

CONCLUSION

: This study suggests that DeepSurv has the potential to improve the performance of risk prediction models for cardiovascular disease risk factors.

Development and Validation of Deep Learning Model for Intermediate-Stage Hepatocellular Carcinoma Survival with Transarterial Chemoembolization (MC-hccAI 002): a Retrospective, Multicenter, Cohort Study

Background: There are few effective prediction models for intermediate-stage hepatocellular carcinoma (IM-HCC) patients treated with transarterial chemoembolization (TACE) to predict overall survival (OS) is available. The learning survival neural network (DeepSurv) was developed to showed a better performance than cox proportional hazards model in prediction of OS. This study aimed to develop a deep learning-based prediction model to predict individual OS. Methods: This multicenter, retrospective, cohort study examined data from the electronic medical record system of four hospitals in China between January 1, 2007, to December 31, 2016. Patients were divided into a training set(n=1075) and a test set(n=269) at a ratio of 8:2 to develop a deep learning-based algorithm (deepHAP IV). The deepHAP IV model was externally validated on an independent cohort(n=414) from the other three centers. The concordance index, the area under the receiver operator characteristic curves, and the calibration curve were used to assess the performance of the models. Results: The deepHAP IV model had a c-index of 0.74, whereas AUROC for predicting survival outcomes of 1-, 3-, and 5-year reached 0.80, 0.76, and 0.74 in the training set. Calibration graphs showed good consistency between the actual and predicted OS in the training set and the validation cohort. Compared to the other five Cox proportional-hazards models, the model this study conducted had a better performance. Patients were finally classified into three groups by X-tile plots with predicted 3-year OS rate (low: ≤ 0.11; middle: > 0.11 and ≤ 0.35; high: >0.35). Conclusion: The deepHAP IV model can effectively predict the OS of patients with IM-HCC, showing a better performance than previous Cox proportional hazards models.

Deep learning in oral cancer- a systematic review

BACKGROUND

Oral cancer is a life-threatening malignancy, which affects the survival rate and quality of life of patients. The aim of this systematic review was to review deep learning (DL) studies in the diagnosis and prognostic prediction of oral cancer.

METHODS

This systematic review was conducted following the PRISMA guidelines. Databases (Medline via PubMed, Google Scholar, Scopus) were searched for relevant studies, from January 2000 to June 2023.

RESULTS

Fifty-four qualified for inclusion, including diagnostic (n = 51), and prognostic prediction (n = 3). Thirteen studies showed a low risk of biases in all domains, and 40 studies low risk for concerns regarding applicability. The performance of DL models was reported of the accuracy of 85.0-100%, F1-score of 79.31 - 89.0%, Dice coefficient index of 76.0 - 96.3% and Concordance index of 0.78-0.95 for classification, object detection, segmentation, and prognostic prediction, respectively. The pooled diagnostic odds ratios were 2549.08 (95% CI 410.77-4687.39) for classification studies.

CONCLUSIONS

The number of DL studies in oral cancer is increasing, with a diverse type of architectures. The reported accuracy showed promising DL performance in studies of oral cancer and appeared to have potential utility in improving informed clinical decision-making of oral cancer.

Automatic segmentation of ameloblastoma on ct images using deep learning with limited data

BACKGROUND

Ameloblastoma, a common benign tumor found in the jaw bone, necessitates accurate localization and segmentation for effective diagnosis and treatment. However, the traditional manual segmentation method is plagued with inefficiencies and drawbacks. Hence, the implementation of an AI-based automatic segmentation approach is crucial to enhance clinical diagnosis and treatment procedures.

METHODS

We collected CT images from 79 patients diagnosed with ameloblastoma and employed a deep learning neural network model for training and testing purposes. Specifically, we utilized the Mask R-CNN neural network structure and implemented image preprocessing and enhancement techniques. During the testing phase, cross-validation methods were employed for evaluation, and the experimental results were verified using an external validation set. Finally, we obtained an additional dataset comprising 200 CT images of ameloblastoma from a different dental center to evaluate the model's generalization performance.

RESULTS

During extensive testing and evaluation, our model successfully demonstrated the capability to automatically segment ameloblastoma. The DICE index achieved an impressive value of 0.874. Moreover, when the IoU threshold ranged from 0.5 to 0.95, the model's AP was 0.741. For a specific IoU threshold of 0.5, the model achieved an AP of 0.914, and for another IoU threshold of 0.75, the AP was 0.826. Our validation using external data confirms the model's strong generalization performance.

CONCLUSION

In this study, we successfully applied a neural network model based on deep learning that effectively performs automatic segmentation of ameloblastoma. The proposed method offers notable advantages in terms of efficiency, accuracy, and speed, rendering it a promising tool for clinical diagnosis and treatment.

Factors influencing the 5-year survival rate of oral cancer patients in the Mongolian population: a retrospective cohort study

Introduction

The high mortality rate of head and neck cancers, particularly oral cancer, poses a significant health challenge in developing nations such as Mongolia. This retrospective survival analysis study was conducted to identify factors influencing the 5-year survival rate of oral squamous cell carcinoma patients.

Methods

The study analyzed data from 173 patients diagnosed with oral squamous cell carcinoma, including multiple variables such as age, gender, residence, education, tobacco and alcohol consumption, oral health indicators, family history, precancerous conditions, cancer characteristics, treatment, rehabilitation, cancer recurrence, and 5-year survival. Survival analysis was conducted using the Kaplan-Meier method, and STATA was used for statistical analysis.

Results

The study revealed a 5-year survival rate of 50.3% for oral cancer patients, with a survival rate of 38% for tongue cancer patients. Age, residence, cancer stage, and cancer recurrence were identified as significant survival predictors. Compared to those aged 60 or younger, the hazard ratio (HR) for patients aged 61 or older was 1.52. Survival was associated with female gender (HR = 0.47, CI = 0.29-0.77). Urban residence was associated with decreased survival (HR = 1.92, CI = 1.22-3.05). Significantly worse survival was associated with the presence of cancer recurrence (HR = 1.99, CI = 1.15-3.04). Oral cancer patients in stage IV had a fourfold higher risk of mortality compared to those in stage I (HR = 4.08, CI = 1.2-13.84).

Conclusion

This research highlights the influence of age, urban habitation, and cancer recurrence on oral cancer survival. Age, urban residence, and cancer recurrence were all associated with decreased survival, whereas cancer at stage IV substantially increased the risk of death. The significance of early detection, treatment, and active surveillance to identify oral cancer at an early stage is highlighted by these findings. Compared to industrialized nations, Mongolia's lower oral cancer survival rates emphasize the need to increase public awareness and education. A comprehensive approach is required to improve oral cancer patient survival rates and quality of life, including emphasizing early detection through active surveillance, implementing preventive measures, and advancing cancer education initiatives.

Early diagnosis of oral cancer using a hybrid arrangement of deep belief networkand combined group teaching algorithm

Oral cancer can occur in different parts of the mouth, including the lips, palate, gums, and inside the cheeks. If not treated in time, it can be life-threatening. Incidentally, using CAD-based diagnosis systems can be so helpful for early detection of this disease and curing it. In this study, a new deep learning-based methodology has been proposed for optimal oral cancer diagnosis from the images. In this method, after some preprocessing steps, a new deep belief network (DBN) has been proposed as the main part of the diagnosis system. The main contribution of the proposed DBN is its combination with a developed version of a metaheuristic technique, known as the Combined Group Teaching Optimization algorithm to provide an efficient system of diagnosis. The presented method is then implemented in the "Oral Cancer (Lips and Tongue) images dataset" and a comparison is done between the results and other methods, including ANN, Bayesian, CNN, GSO-NN, and End-to-End NN to show the efficacy of the techniques. The results showed that the DBN-CGTO method achieved a precision rate of 97.71%, sensitivity rate of 92.37%, the Matthews Correlation Coefficient of 94.65%, and 94.65% F1 score, which signifies its ability as the highest efficiency among the others to accurately classify positive samples while remaining the independent correct classification of negative samples.

Prediction of postoperative recurrence of oral cancer by artificial intelligence model: Multilayer perceptron

BACKGROUND

Postoperative recurrence of oral cancer is an important factor affecting the prognosis of patients. Artificial intelligence is used to establish a machine learning model to predict the risk of postoperative recurrence of oral cancer.

METHODS

The information of 387 patients with postoperative oral cancer were collected to establish the multilayer perceptron (MLP) model. The comprehensive variable model was compared with the characteristic variable model, and the MLP model was compared with other models to evaluate the sensitivity of different models in the prediction of postoperative recurrence of oral cancer.

RESULTS

The overall performance of the MLP model under comprehensive variable input was the best.

CONCLUSION

The MLP model has good sensitivity to predict postoperative recurrence of oral cancer, and the predictive model with variable input training is better than that with characteristic variable input.

Predicting Glaucoma Progression to Surgery with Artificial Intelligence Survival Models

Purpose

Prior artificial intelligence (AI) models for predicting glaucoma progression have used traditional classifiers that do not consider the longitudinal nature of patients' follow-up. In this study, we developed survival-based AI models for predicting glaucoma patients' progression to surgery, comparing performance of regression-, tree-, and deep learning-based approaches.

Design

Retrospective observational study.

Subjects

Patients with glaucoma seen at a single academic center from 2008 to 2020 identified from electronic health records (EHRs).

Methods

From the EHRs, we identified 361 baseline features, including demographics, eye examinations, diagnoses, and medications. We trained AI survival models to predict patients' progression to glaucoma surgery using the following: (1) a penalized Cox proportional hazards (CPH) model with principal component analysis (PCA); (2) random survival forests (RSFs); (3) gradient-boosting survival (GBS); and (4) a deep learning model (DeepSurv). The concordance index (C-index) and mean cumulative/dynamic area under the curve (mean AUC) were used to evaluate model performance on a held-out test set. Explainability was investigated using Shapley values for feature importance and visualization of model-predicted cumulative hazard curves for patients with different treatment trajectories.

Main Outcome Measures

Progression to glaucoma surgery.

Results

Of the 4512 patients with glaucoma, 748 underwent glaucoma surgery, with a median follow-up of 1038 days. The DeepSurv model performed best overall (C-index, 0.775; mean AUC, 0.802) among the models studied in this article (CPH with PCA: C-index, 0.745; mean AUC, 0.780; RSF: C-index, 0.766; mean AUC, 0.804; GBS: C-index, 0.764; mean AUC, 0.791). Predicted cumulative hazard curves demonstrate how models could distinguish between patient who underwent early surgery and patients who underwent surgery after > 3000 days of follow-up or no surgery.

Conclusions

Artificial intelligence survival models can predict progression to glaucoma surgery using structured data from EHRs. Tree-based and deep learning-based models performed better at predicting glaucoma progression to surgery than the CPH regression model, potentially because of their better suitability for high-dimensional data sets. Future work predicting ophthalmic outcomes should consider using tree-based and deep learning-based survival AI models. Additional research is needed to develop and evaluate more sophisticated deep learning survival models that can incorporate clinical notes or imaging.

Financial Disclosures

Proprietary or commercial disclosure may be found after the references.

Predicting cutaneous malignant melanoma patients' survival using deep learning: a retrospective cohort study

BACKGROUND

Cutaneous malignant melanoma (CMM) has the worst prognosis among skin cancers, especially metastatic CMM. Predicting its prognosis accurately could direct clinical decisions.

METHODS

The Surveillance, Epidemiology, and End Results database was screened to collect CMM patients' data. According to diagnosed time, patients were subdivided into three cohorts, train cohort (diagnosed between 2010 and 2013), validation cohort (diagnosed in 2014), and test cohort (diagnosed in 2015). Train cohort was used to train deep learning survival model for cutaneous malignant melanoma (DeepCMM). DeepCMM was then evaluated in train cohort and validation cohort internally, and validated in test cohort externally.

RESULTS

DeepCMM showed 0.8270 (95% CI, confidence interval, CI 0.8260-0.8280) as area under the receiver operating characteristic curve (AUC) in train cohort, 0.8274 (95% CI 0.8286-0.8298) AUC in validation cohort, and 0.8303 (95% CI 0.8289-0.8316) AUC in test cohort. Then DeepCMM was packaged into a Windows 64-bit software for doctors to use.

CONCLUSION

Deep learning survival model for cutaneous malignant melanoma (DeepCMM) can offer a reliable prediction on cutaneous malignant melanoma patients' overall survival.

Comparison of MRI radiomics-based machine learning survival models in predicting prognosis of glioblastoma multiforme

Objective

To compare the performance of radiomics-based machine learning survival models in predicting the prognosis of glioblastoma multiforme (GBM) patients.

Methods

131 GBM patients were included in our study. The traditional Cox proportional-hazards (CoxPH) model and four machine learning models (SurvivalTree, Random survival forest (RSF), DeepSurv, DeepHit) were constructed, and the performance of the five models was evaluated using the C-index.

Results

After the screening, 1792 radiomics features were obtained. Seven radiomics features with the strongest relationship with prognosis were obtained following the application of the least absolute shrinkage and selection operator (LASSO) regression. The CoxPH model demonstrated that age (HR = 1.576, p = 0.037), Karnofsky performance status (KPS) score (HR = 1.890, p = 0.006), radiomics risk score (HR = 3.497, p = 0.001), and radiomics risk level (HR = 1.572, p = 0.043) were associated with poorer prognosis. The DeepSurv model performed the best among the five models, obtaining C-index of 0.882 and 0.732 for the training and test set, respectively. The performances of the other four models were lower: CoxPH (0.663 training set / 0.635 test set), SurvivalTree (0.702/0.655), RSF (0.735/0.667), DeepHit (0.608/0.560).

Conclusion

This study confirmed the superior performance of deep learning algorithms based on radiomics relative to the traditional method in predicting the overall survival of GBM patients; specifically, the DeepSurv model showed the best predictive ability.

Deep-learning-based survival prediction of patients with lower limb melanoma

BACKGROUND

For the purpose to examine lower limb melanoma (LLM) and its long-term survival rate, we used data from the Surveillance, Epidemiology and End Results (SEER) database. To estimate the prognosis of LLM patients and assess its efficacy, we used a powerful deep learning and neural network approach called DeepSurv.

METHODS

We gathered data on those who had an LLM diagnosis between 2000 and 2019 from the SEER database. We divided the people into training and testing cohorts at a 7:3 ratio using a random selection technique. To assess the likelihood that LLM patients would survive, we compared the results of the DeepSurv model with those of the Cox proportional-hazards (CoxPH) model. Calibration curves, the time-dependent area under the receiver operating characteristic curve (AUC), and the concordance index (C-index) were all used to assess how accurate the predictions were.

RESULTS

In this study, a total of 26,243 LLM patients were enrolled, with 7873 serving as the testing cohort and 18,370 as the training cohort. Significant correlations with age, gender, AJCC stage, chemotherapy status, surgery status, regional lymph node removal and the survival outcomes of LLM patients were found by the CoxPH model. The CoxPH model's C-index was 0.766, which signifies a good degree of predicted accuracy. Additionally, we created the DeepSurv model using the training cohort data, which had a higher C-index of 0.852. In addition to calculating the 3-, 5-, and 8-year AUC values, the predictive performance of both models was evaluated. The equivalent AUC values for the CoxPH model were 0.795, 0.767, and 0.847, respectively. The DeepSurv model, in comparison, had better AUC values of 0.872, 0.858, and 0.847. In comparison to the CoxPH model, the DeepSurv model demonstrated greater prediction performance for LLM patients, as shown by the AUC values and the calibration curve.

CONCLUSION

We created the DeepSurv model using LLM patient data from the SEER database, which performed better than the CoxPH model in predicting the survival time of LLM patients.

The Use of Artificial Intelligence Algorithms in the Prognosis and Detection of Lymph Node Involvement in Head and Neck Cancer and Possible Impact in the Development of Personalized Therapeutic Strategy: A Systematic Review

Given the increasingly important role that the use of artificial intelligence algorithms is taking on in the medical field today (especially in oncology), the purpose of this systematic review is to analyze the main reports on such algorithms applied for the prognostic evaluation of patients with head and neck malignancies. The objective of this paper is to examine the currently available literature in the field of artificial intelligence applied to head and neck oncology, particularly in the prognostic evaluation of the patient with this kind of tumor, by means of a systematic review. The paper exposes an overview of the applications of artificial intelligence in deriving prognostic information related to the prediction of survival and recurrence and how these data may have a potential impact on the choice of therapeutic strategy, making it increasingly personalized. This systematic review was written following the PRISMA 2020 guidelines.

Application of machine learning in predicting survival outcomes involving real-world data: a scoping review

BACKGROUND

Despite the interest in machine learning (ML) algorithms for analyzing real-world data (RWD) in healthcare, the use of ML in predicting time-to-event data, a common scenario in clinical practice, is less explored. ML models are capable of algorithmically learning from large, complex datasets and can offer advantages in predicting time-to-event data. We reviewed the recent applications of ML for survival analysis using RWD in healthcare.

METHODS

PUBMED and EMBASE were searched from database inception through March 2023 to identify peer-reviewed English-language studies of ML models for predicting time-to-event outcomes using the RWD. Two reviewers extracted information on the data source, patient population, survival outcome, ML algorithms, and the Area Under the Curve (AUC).

RESULTS

Of 257 citations, 28 publications were included. Random survival forests (N = 16, 57%) and neural networks (N = 11, 39%) were the most popular ML algorithms. There was variability across AUC for these ML models (median 0.789, range 0.6-0.950). ML algorithms were predominately considered for predicting overall survival in oncology (N = 12, 43%). ML survival models were often used to predict disease prognosis or clinical events (N = 27, 96%) in the oncology, while less were used for treatment outcomes (N = 1, 4%).

CONCLUSIONS

The ML algorithms, random survival forests and neural networks, are mainly used for RWD to predict survival outcomes such as disease prognosis or clinical events in the oncology. This review shows that more opportunities remain to apply these ML algorithms to inform treatment decision-making in clinical practice. More methodological work is also needed to ensure the utility and applicability of ML models in survival outcomes.

Deep survival analysis using pseudo values and its application to predict the recurrence of stage IV colorectal cancer after tumor resection

An improved DeepSurv model is proposed for predicting the prognosis of colorectal cancer patients at stage IV. Our model, called as PseudoDeepSurv, is optimized by a novel loss function, which is the combination of the average negative log partial likelihood and the mean-squared error derived from the pseudo-observations approach. The public BioStudies dataset including 999 patients was utilized for performance evaluation. Our PseudoDeepSurv model produced a C-index of 0.684 and 0.633 on the training and testing dataset, respectively. While for the original DeepSurv model, the corresponding values are 0.671 and 0.618, respectively.

Prognostic significance of cyclin D1 expression pattern in HPV-negative oral and oropharyngeal carcinoma: A deep-learning approach

BACKGROUND

We aimed to establish image recognition and survival prediction models using a novel scoring system of cyclin D1 expression pattern in patients with human papillomavirus-negative oral or oropharyngeal squamous cell carcinoma.

METHODS

The clinicopathological data of 610 patients with human papillomavirus-negative oral/oropharyngeal squamous cell carcinoma were analyzed retrospectively. Cox univariate and multivariate risk regression analyses were performed to compare cyclin D1 expression pattern scoring with the traditional scoring method-cyclin D1 expression level scoring-in relation to patients' overall and progression-free survival. An image recognition model employing the cyclin D1 expression pattern scoring system was established by YOLOv5 algorithms. From this model, two independent survival prediction models were established using the DeepHit and DeepSurv algorithms.

RESULTS

Cyclin D1 had three expression patterns in oral and oropharyngeal squamous cell carcinoma cancer nests. Superior to cyclin D1 expression level scoring, cyclin D1 expression pattern scoring was significantly correlated with the prognosis of patients with oral squamous cell carcinoma (p < 0.0001) and oropharyngeal squamous cell carcinoma (p < 0.05). Moreover, it was an independent prognostic risk factor in both oral squamous cell carcinoma (p < 0.0001) and oropharyngeal squamous cell carcinoma (p < 0.05). The cyclin D1 expression pattern-derived image recognition model showed an average test set accuracy of 78.48% ± 4.31%. In the overall survival prediction models, the average concordance indices of the test sets established by DeepSurv and DeepHit were 0.71 ± 0.02 and 0.70 ± 0.01, respectively.

CONCLUSION

Combined with the image recognition model of the cyclin D1 expression pattern, the survival prediction model had a relatively good prediction effect on the overall survival prognosis of patients with human papillomavirus-negative oral or oropharyngeal squamous cell carcinoma.

Performance of artificial intelligence-based algorithms to predict prolonged length of stay after head and neck cancer surgery

Background

Medical resource management can be improved by assessing the likelihood of prolonged length of stay (LOS) for head and neck cancer surgery patients. The objective of this study was to develop predictive models that could be used to determine whether a patient's LOS after cancer surgery falls within the normal range of the cohort.

Methods

We conducted a retrospective analysis of a dataset consisting of 300 consecutive patients who underwent head and neck cancer surgery between 2017 and 2022 at a single university medical center. Prolonged LOS was defined as LOS exceeding the 75th percentile of the cohort. Feature importance analysis was performed to evaluate the most important predictors for prolonged LOS. We then constructed 7 machine learning and deep learning algorithms for the prediction modeling of prolonged LOS.

Results

The algorithms reached accuracy values of 75.40 (radial basis function neural network) to 97.92 (Random Trees) for the training set and 64.90 (multilayer perceptron neural network) to 84.14 (Random Trees) for the testing set. The leading parameters predicting prolonged LOS were operation time, ischemia time, the graft used, the ASA score, the intensive care stay, and the pathological stages. The results revealed that patients who had a higher number of harvested lymph nodes (LN) had a lower probability of recurrence but also a greater LOS. However, patients with prolonged LOS were also at greater risk of recurrence, particularly when fewer (LN) were extracted. Further, LOS was more strongly correlated with the overall number of extracted lymph nodes than with the number of positive lymph nodes or the ratio of positive to overall extracted lymph nodes, indicating that particularly unnecessary lymph node extraction might be associated with prolonged LOS.

Conclusions

The results emphasize the need for a closer follow-up of patients who experience prolonged LOS. Prospective trials are warranted to validate the present results.

Direct deep learning-based survival prediction from pre-interventional CT prior to transcatheter aortic valve replacement

PURPOSE

To investigate survival prediction in patients undergoing transcatheter aortic valve replacement (TAVR) using deep learning (DL) methods applied directly to pre-interventional CT images and to compare performance with survival models based on scalar markers of body composition.

METHOD

This retrospective single-center study included 760 patients undergoing TAVR (mean age 81 ± 6 years; 389 female). As a baseline, a Cox proportional hazards model (CPHM) was trained to predict survival on sex, age, and the CT body composition markers fatty muscle fraction (FMF), skeletal muscle radiodensity (SMRD), and skeletal muscle area (SMA) derived from paraspinal muscle segmentation of a single slice at L3/L4 level. The convolutional neural network (CNN) encoder of the DL model for survival prediction was pre-trained in an autoencoder setting with and without a focus on paraspinal muscles. Finally, a combination of DL and CPHM was evaluated. Performance was assessed by C-index and area under the receiver operating curve (AUC) for 1-year and 2-year survival. All methods were trained with five-fold cross-validation and were evaluated on 152 hold-out test cases.

RESULTS

The CNN for direct image-based survival prediction, pre-trained in a focussed autoencoder scenario, outperformed the baseline CPHM (CPHM: C-index = 0.608, 1Y-AUC = 0.606, 2Y-AUC = 0.594 vs. DL: C-index = 0.645, 1Y-AUC = 0.687, 2Y-AUC = 0.692). Combining DL and CPHM led to further improvement (C-index = 0.668, 1Y-AUC = 0.713, 2Y-AUC = 0.696).

CONCLUSIONS

Direct DL-based survival prediction shows potential to improve image feature extraction compared to segmentation-based scalar markers of body composition for risk assessment in TAVR patients.

Machine learning links T cell function and spatial localization to neoadjuvant immunotherapy and clinical outcome in pancreatic cancer

Tumor molecular datasets are becoming increasingly complex, making it nearly impossible for humans alone to effectively analyze them. Here, we demonstrate the power of using machine learning to analyze a single-cell, spatial, and highly multiplexed proteomic dataset from human pancreatic cancer and reveal underlying biological mechanisms that may contribute to clinical outcome. A novel multiplex immunohistochemistry antibody panel was used to audit T cell functionality and spatial localization in resected tumors from treatment-naive patients with localized pancreatic ductal adenocarcinoma (PDAC) compared to a second cohort of patients treated with neoadjuvant agonistic CD40 (αCD40) monoclonal antibody therapy. In total, nearly 2.5 million cells from 306 tissue regions collected from 29 patients across both treatment cohorts were assayed, and more than 1,000 tumor microenvironment (TME) features were quantified. We then trained machine learning models to accurately predict αCD40 treatment status and disease-free survival (DFS) following αCD40 therapy based upon TME features. Through downstream interpretation of the machine learning models' predictions, we found αCD40 therapy to reduce canonical aspects of T cell exhaustion within the TME, as compared to treatment-naive TMEs. Using automated clustering approaches, we found improved DFS following αCD40 therapy to correlate with the increased presence of CD44+ CD4+ Th1 cells located specifically within cellular spatial neighborhoods characterized by increased T cell proliferation, antigen-experience, and cytotoxicity in immune aggregates. Overall, our results demonstrate the utility of machine learning in molecular cancer immunology applications, highlight the impact of αCD40 therapy on T cells within the TME, and identify potential candidate biomarkers of DFS for αCD40-treated patients with PDAC.

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.

Comparison of deep learning-based recurrence-free survival with random survival forest and Cox proportional hazard models in Stage-I NSCLC patients

BACKGROUND

The curative treatment for Stage I non-small cell lung cancer (NSCLC) is surgical resection. Even for Stage I patients, the probability of recurrence after curative treatment is around 20%.

METHODS

In this retrospective study, we included 268 operated Stage I NSCLC patients between January 2008 and June 2018 to analyze the prognostic factors (pathological stage, histological type, number of sampled mediastinal lymph node stations, type of resection, SUVmax of the lesion) that may affect relapse with three different methods, Cox proportional hazard (CoxPH), random survival forest (RSF), DeepSurv, and to compare the performance of these methods with Harrell's C-index. The dataset was randomly split into two sets, training and test sets.

RESULTS

In the training set, DeepSurv showed the best performance among the three models, the C-index of the training set was 0.832, followed by RSF (0.675) and CoxPH (0.672). In the test set, RSF showed the best performance among the three models, followed by DeepSurv with 0.677 and CoxPH methods with 0.625.

CONCLUSION

In conclusion, machine-learning techniques can be useful in predicting recurrence for lung cancer and guide clinicians both in choosing the adjuvant treatment options and best follow-up programs.

A deep-learning-based clinical risk stratification for overall survival in adolescent and young adult women with breast cancer

OBJECTIVE

The objective of this study is to construct a novel clinical risk stratification for overall survival (OS) prediction in adolescent and young adult (AYA) women with breast cancer.

METHOD

From the Surveillance, Epidemiology, and End Results (SEER) database, AYA women with primary breast cancer diagnosed from 2010 to 2018 were included in our study. A deep learning algorithm, referred to as DeepSurv, was used to construct a prognostic predictive model based on 19 variables, including demographic and clinical information. Harrell's C-index, the receiver operating characteristic (ROC) curve, and calibration plots were adopted to comprehensively assess the predictive performance of the prognostic predictive model. Then, a novel clinical risk stratification was constructed based on the total risk score derived from the prognostic predictive model. The Kaplan-Meier method was used to plot survival curves for patients with different death risks, using the log-rank test to compared the survival disparities. Decision curve analyses (DCAs) were adopted to evaluate the clinical utility of the prognostic predictive model.

RESULTS

Among 14,243 AYA women with breast cancer finally included in this study, 10,213 (71.7%) were White and the median (interquartile range, IQR) age was 36 (32-38) years. The prognostic predictive model based on DeepSurv presented high C-indices in both the training cohort [0.831 (95% CI 0.819-0.843)] and the test cohort [0.791 (95% CI 0.764-0.818)]. Similar results were observed in ROC curves. The excellent agreement between the predicted and actual OS at 3 and 5 years were both achieved in the calibration plots. The obvious survival disparities were observed according to the clinical risk stratification based on the total risk score derived from the prognostic predictive model. DCAs also showed that the risk stratification possessed a significant positive net benefit in the practical ranges of threshold probabilities. Lastly, a user-friendly Web-based calculator was generated to visualize the prognostic predictive model.

CONCLUSION

A prognostic predictive model with sufficient prediction accuracy was construct for predicting OS of AYA women with breast cancer. Given its public accessibility and easy-to-use operation, the clinical risk stratification based on the total risk score derived from the prognostic predictive model may help clinicians to make better-individualized management.

Artificial Intelligence for Image Analysis in Oral Squamous Cell Carcinoma: A Review

Head and neck tumor differential diagnosis and prognosis have always been a challenge for oral pathologists due to their similarities and complexity. Artificial intelligence novel applications can function as an auxiliary tool for the objective interpretation of histomorphological digital slides. In this review, we present digital histopathological image analysis applications in oral squamous cell carcinoma. A literature search was performed in PubMed MEDLINE with the following keywords: "artificial intelligence" OR "deep learning" OR "machine learning" AND "oral squamous cell carcinoma". Artificial intelligence has proven to be a helpful tool in histopathological image analysis of tumors and other lesions, even though it is necessary to continue researching in this area, mainly for clinical validation.

Detection of Cancer Recurrence Using Systemic Inflammatory Markers and Machine Learning after Concurrent Chemoradiotherapy for Head and Neck Cancers

Pretreatment values of the neutrophil-to-lymphocyte ratio (NLR) and the platelet-to-lymphocyte ratio (PLR) are well-established prognosticators in various cancers, including head and neck cancers. However, there are no studies on whether temporal changes in the NLR and PLR values after treatment are related to the development of recurrence. Therefore, in this study, we aimed to develop a deep neural network (DNN) model to discern cancer recurrence from temporal NLR and PLR values during follow-up after concurrent chemoradiotherapy (CCRT) and to evaluate the model's performance compared with conventional machine learning (ML) models. Along with conventional ML models such as logistic regression (LR), random forest (RF), and gradient boosting (GB), the DNN model to discern recurrences was trained using a dataset of 778 consecutive patients with primary head and neck cancers who received CCRT. There were 16 input features used, including 12 laboratory values related to the NLR and the PLR. Along with the original training dataset (N = 778), data were augmented to split the training dataset (N = 900). The model performance was measured using ROC-AUC and PR-AUC values. External validation was performed using a dataset of 173 patients from an unrelated external institution. The ROC-AUC and PR-AUC values of the DNN model were 0.828 ± 0.032 and 0.663 ± 0.069, respectively, in the original training dataset, which were higher than the ROC-AUC and PR-AUC values of the LR, RF, and GB models in the original training dataset. With the recursive feature elimination (RFE) algorithm, five input features were selected. The ROC-AUC and PR-AUC values of the DNN-RFE model were higher than those of the original DNN model (0.883 ± 0.027 and 0.778 ± 0.042, respectively). The ROC-AUC and PR-AUC values of the DNN-RFE model trained with a split dataset were 0.889 ± 0.032 and 0.771 ± 0.044, respectively. In the external validation, the ROC-AUC values of the DNN-RFE model trained with the original dataset and the same model trained with the split dataset were 0.710 and 0.784, respectively. The DNN model with feature selection using the RFE algorithm showed the best performance among the ML models to discern a recurrence after CCRT in patients with head and neck cancers. Data augmentation by splitting training data was helpful for model performance. The performance of the DNN-RFE model was also validated with an external dataset.

Time-related survival prediction in molecular subtypes of breast cancer using time-to-event deep-learning-based models

Background

Breast cancer (BC) survival prediction can be a helpful tool for identifying important factors selecting the effective treatment reducing mortality rates. This study aims to predict the time-related survival probability of BC patients in different molecular subtypes over 30 years of follow-up.

Materials and methods

This study retrospectively analyzed 3580 patients diagnosed with invasive breast cancer (BC) from 1991 to 2021 in the Cancer Research Center of Shahid Beheshti University of Medical Science. The dataset contained 18 predictor variables and two dependent variables, which referred to the survival status of patients and the time patients survived from diagnosis. Feature importance was performed using the random forest algorithm to identify significant prognostic factors. Time-to-event deep-learning-based models, including Nnet-survival, DeepHit, DeepSurve, NMLTR and Cox-time, were developed using a grid search approach with all variables initially and then with only the most important variables selected from feature importance. The performance metrics used to determine the best-performing model were C-index and IBS. Additionally, the dataset was clustered based on molecular receptor status (i.e., luminal A, luminal B, HER2-enriched, and triple-negative), and the best-performing prediction model was used to estimate survival probability for each molecular subtype.

Results

The random forest method identified tumor state, age at diagnosis, and lymph node status as the best subset of variables for predicting breast cancer (BC) survival probabilities. All models yielded very close performance, with Nnet-survival (C-index=0.77, IBS=0.13) slightly higher using all 18 variables or the three most important variables. The results showed that the Luminal A had the highest predicted BC survival probabilities, while triple-negative and HER2-enriched had the lowest predicted survival probabilities over time. Additionally, the luminal B subtype followed a similar trend as luminal A for the first five years, after which the predicted survival probability decreased steadily in 10- and 15-year intervals.

Conclusion

This study provides valuable insight into the survival probability of patients based on their molecular receptor status, particularly for HER2-positive patients. This information can be used by healthcare providers to make informed decisions regarding the appropriateness of medical interventions for high-risk patients. Future clinical trials should further explore the response of different molecular subtypes to treatment in order to optimize the efficacy of breast cancer treatments.

Machine Learning Approach for the Prediction of Age-Specific Probability of SCA3 and DRPLA by Survival Curve Analysis

Background and Objectives

As the number of repeats in the expansion increases, polyglutamine diseases tend to show at a younger age. From this relationship, attempts have been made to predict age at onset by parametric survival analysis. However, a method for a more accurate prediction has been desirable. In this study, we examined 2 methods for survival analysis using machine learning and 6 conventional methods for parametric survival analysis of spinocerebellar ataxia (SCA)3 and dentatorubral-pallidoluysian atrophy (DRPLA).

Methods

We compared the performance of 2 machine learning methods of survival analysis (random survival forest [RSF] and DeepSurv) and 6 methods of parametric survival analysis (Weibull, exponential, Gaussian, logistic, loglogistic, and log Gaussian). Training and evaluation were performed using the leave-one-out cross-validation method, and evaluation criteria included root mean squared error (RMSE), mean absolute error (MAE), and the integrated Brier score. The latter was used as the primary end point, and the survival analysis model yielding the best result was used to predict the asymptomatic probability.

Results

Among the models examined, the RSF and DeepSurv machine learning methods had a higher prediction accuracy than the parametric methods of survival analysis. For both SCA3 and DRPLA, RSF had a higher accuracy than DeepSurv for the assessment of RMSE (SCA3: 7.37, DRPLA: 10.78), MAE (SCA3: 5.52, DRPLA: 8.17), and the integrated Brier score (SCA3: 0.05, DRPLA: 0.077). Using RSF, we determined the age-specific probability distribution of age at onset based on CAG repeat size and current age.

Discussion

In this study, we have demonstrated the superiority of machine learning methods for predicting age at onset of SCA3 and DRPLA using survival analysis. Such accurate prediction of onset will be useful for genetic counseling of carriers and for devising methods to verify the effects of interventions for unaffected individuals.

Predicting the survival of patients with pancreatic neuroendocrine neoplasms using deep learning: A study based on Surveillance, Epidemiology, and End Results database

BACKGROUND

The study aims to evaluate the performance of three advanced machine learning algorithms and a traditional Cox proportional hazard (CoxPH) model in predicting the overall survival (OS) of patients with pancreatic neuroendocrine neoplasms (PNENs).

METHOD

The clinicopathological dataset obtained from the Surveillance, Epidemiology, and End Results database was randomly assigned to the training set and testing set at a ratio of 7:3. The concordance index (C-index) and integrated Brier score (IBS) were used to compare the predictive performance of the models. The accuracy of the model in predicting the 5-year and 10-year survival rates was compared using the receiver operating characteristic curve, decision curve analysis (DCA) and calibration curve.

RESULTS

This study included 3239 patients with PNENs in total. The DeepSurv model had the highest C-index of 0.7882 in the testing set and training set and the lowest IBS of 0.1278 in the testing set compared with the CoxPH, neural multitask logistic and random survival forest models (C-index = 0.7501, 0.7616, and 0.7612, respectively; IBS = 0.1397, 0.1418, and 0.1432, respectively). Moreover, the DeepSurv model had the highest accuracy in predicting 5- and 10-year OS rates (area under the curve: 0.87 and 0.90). DCA showed that the DeepSurv model had high potential for clinical decisions in 5- and 10-year OS models. Finally, we developed an online application based on the DeepSurv model for clinical use (https://whuh-ml-neuroendocrinetumor-app-predict-oyw5km.streamlit.app/).

CONCLUSIONS

All four models analyzed above can predict the prognosis of PNENs well, among which the DeepSurv model has the best prediction performance.

Time and event-specific deep learning for personalized risk assessment after cardiac perfusion imaging

Standard clinical interpretation of myocardial perfusion imaging (MPI) has proven prognostic value for predicting major adverse cardiovascular events (MACE). However, personalizing predictions to a specific event type and time interval is more challenging. We demonstrate an explainable deep learning model that predicts the time-specific risk separately for all-cause death, acute coronary syndrome (ACS), and revascularization directly from MPI and 15 clinical features. We train and test the model internally using 10-fold hold-out cross-validation (n = 20,418) and externally validate it in three separate sites (n = 13,988) with MACE follow-ups for a median of 3.1 years (interquartile range [IQR]: 1.6, 3.6). We evaluate the model using the cumulative dynamic area under receiver operating curve (cAUC). The best model performance in the external cohort is observed for short-term prediction - in the first six months after the scan, mean cAUC for ACS and all-cause death reaches 0.76 (95% confidence interval [CI]: 0.75, 0.77) and 0.78 (95% CI: 0.78, 0.79), respectively. The model outperforms conventional perfusion abnormality measures at all time points for the prediction of death in both internal and external validations, with improvement increasing gradually over time. Individualized patient explanations are visualized using waterfall plots, which highlight the contribution degree and direction for each feature. This approach allows the derivation of individual event probability as a function of time as well as patient- and event-specific risk explanations that may help draw attention to modifiable risk factors. Such a method could help present post-scan risk assessments to the patient and foster shared decision-making.

Artificial Intelligence in Medicine and Dentistry

INTRODUCTION

Artificial intelligence has been applied in various fields throughout history, but its integration into daily life is more recent. The first applications of AI were primarily in academia and government research institutions, but as technology has advanced, AI has also been applied in industry, commerce, medicine and dentistry.

OBJECTIVE

Considering that the possibilities of applying artificial intelligence are developing rapidly and that this field is one of the areas with the greatest increase in the number of newly published articles, the aim of this paper was to provide an overview of the literature and to give an insight into the possibilities of applying artificial intelligence in medicine and dentistry. In addition, the aim was to discuss its advantages and disadvantages.

CONCLUSION

The possibilities of applying artificial intelligence to medicine and dentistry are just being discovered. Artificial intelligence will greatly contribute to developments in medicine and dentistry, as it is a tool that enables development and progress, especially in terms of personalized healthcare that will lead to much better treatment outcomes.

Deep Learning-Based Time-to-Death Prediction Model for COVID-19 Patients Using Clinical Data and Chest Radiographs

Accurate estimation of mortality and time to death at admission for COVID-19 patients is important and several deep learning models have been created for this task. However, there are currently no prognostic models which use end-to-end deep learning to predict time to event for admitted COVID-19 patients using chest radiographs and clinical data. We retrospectively implemented a new artificial intelligence model combining DeepSurv (a multiple-perceptron implementation of the Cox proportional hazards model) and a convolutional neural network (CNN) using 1356 COVID-19 inpatients. For comparison, we also prepared DeepSurv only with clinical data, DeepSurv only with images (CNNSurv), and Cox proportional hazards models. Clinical data and chest radiographs at admission were used to estimate patient outcome (death or discharge) and duration to the outcome. The Harrel's concordance index (c-index) of the DeepSurv with CNN model was 0.82 (0.75-0.88) and this was significantly higher than the DeepSurv only with clinical data model (c-index = 0.77 (0.69-0.84), p = 0.011), CNNSurv (c-index = 0.70 (0.63-0.79), p = 0.001), and the Cox proportional hazards model (c-index = 0.71 (0.63-0.79), p = 0.001). These results suggest that the time-to-event prognosis model became more accurate when chest radiographs and clinical data were used together.

Classifying Histopathological Images of Oral Squamous Cell Carcinoma using Deep Transfer Learning

Oral cancer is a prevalent malignancy that affects the oral cavity in the region of head and neck. The study of oral malignant lesions is an essential step for the clinicians to provide a better treatment plan at an early stage for oral cancer. Deep learning based computer-aided diagnostic system has achieved success in many applications and can provide an accurate and timely diagnosis of oral malignant lesions. In biomedical image classification, getting large training dataset is a challenge, which can be efficiently handled by transfer learning as it retrieves the general features from a dataset of natural images and adapted directly to new image dataset. In this work, to achieve an effective deep learning based computer-aided system, the classifications of Oral Squamous Cell Carcinoma (OSCC) histopathology images are performed using two proposed approaches. In the first approach, to identify the best appropriate model to differentiate between benign and malignant cancers, transfer learning assisted deep convolutional neural networks (DCNNs), are considered. To handle the challenge of small dataset and further increase the training efficiency of the proposed model, the pretrained VGG16, VGG19, ResNet50, InceptionV3, and MobileNet, are fine-tuned by training half of the layers and leaving others frozen. In the second approach, a baseline DCNN architecture, trained from scratch with 10 convolution layers is proposed. In addition, a comparative analysis of these models is carried out in terms of classification accuracy and other performance measures. The experimental results demonstrate that ResNet50 obtains substantially superior performance than selected fine-tuned DCNN models as well as the proposed baseline model with an accuracy of 96.6%, precision and recall values are 97% and 96%, respectively.

Empirical comparison of routinely collected electronic health record data for head and neck cancer-specific survival in machine-learnt prognostic models

BACKGROUND

Knowledge of the prognostic factors and performance of machine learning predictive models for 2-year cancer-specific survival (CSS) is limited in the head and neck cancer (HNC) population.

METHODS

Data from our facilities' oncology information system (OIS) collected for routine practice (OIS dataset, n = 430 patients) and research purposes (research dataset, n = 529 patients) were extracted on adults diagnosed between 2000 and 2017 with squamous cell carcinoma of the head and neck.

RESULTS

Machine learning demonstrated excellent performance (area under the curve, AUC) in the whole cohort (AUC = 0.97, research dataset), larynx cohort (AUC = 0.98, both datasets), and oropharynx cohort (AUC = 0.99, both datasets). Tumor site and T classification were identified as predictors of 2-year CSS in both datasets. Hypothyroidism and fitness for operation were further identified in the research dataset.

CONCLUSIONS

Datasets extracted from an OIS for routine clinical practice and research purposes demonstrated high utility for informing 2-year head and neck CSS.

Machine Learning in Dentistry: A Scoping Review

Machine learning (ML) is being increasingly employed in dental research and application. We aimed to systematically compile studies using ML in dentistry and assess their methodological quality, including the risk of bias and reporting standards. We evaluated studies employing ML in dentistry published from 1 January 2015 to 31 May 2021 on MEDLINE, IEEE Xplore, and arXiv. We assessed publication trends and the distribution of ML tasks (classification, object detection, semantic segmentation, instance segmentation, and generation) in different clinical fields. We appraised the risk of bias and adherence to reporting standards, using the QUADAS-2 and TRIPOD checklists, respectively. Out of 183 identified studies, 168 were included, focusing on various ML tasks and employing a broad range of ML models, input data, data sources, strategies to generate reference tests, and performance metrics. Classification tasks were most common. Forty-two different metrics were used to evaluate model performances, with accuracy, sensitivity, precision, and intersection-over-union being the most common. We observed considerable risk of bias and moderate adherence to reporting standards which hampers replication of results. A minimum (core) set of outcome and outcome metrics is necessary to facilitate comparisons across studies.

Impact of the Rise of Artificial Intelligence in Radiology: What Do Students Think?

The rise of artificial intelligence (AI) in medicine, and particularly in radiology, is becoming increasingly prominent. Its impact will transform the way the specialty is practiced and the current and future education model. The aim of this study is to analyze the perception that undergraduate medical students have about the current situation of AI in medicine, especially in radiology. A survey with 17 items was distributed to medical students between 3 January to 31 March 2022. Two hundred and eighty-one students correctly responded the questionnaire; 79.3% of them claimed that they knew what AI is. However, their objective knowledge about AI was low but acceptable. Only 24.9% would choose radiology as a specialty, and only 40% of them as one of their first three options. The applications of this technology were valued positively by most students, who give it an important Support Role, without fear that the radiologist will be replaced by AI (79.7%). The majority (95.7%) agreed with the need to implement well-established ethical principles in AI, and 80% valued academic training in AI positively. Surveyed medical students have a basic understanding of AI and perceive it as a useful tool that will transform radiology.

Machine Learning and Nomogram Prognostic Modeling for 2-Year Head and Neck Cancer-Specific Survival Using Electronic Health Record Data: A Multisite Study

PURPOSE

There is limited knowledge of the prediction of 2-year cancer-specific survival (CSS) in the head and neck cancer (HNC) population. The aim of this study is to develop and validate machine learning models and a nomogram for the prediction of 2-year CSS in patients with HNC using real-world data collected by major teaching and tertiary referral hospitals in New South Wales (NSW), Australia.

MATERIALS AND METHODS

Data collected in oncology information systems at multiple NSW Cancer Centres were extracted for 2,953 eligible adults diagnosed between 2000 and 2017 with squamous cell carcinoma of the head and neck. Death data were sourced from the National Death Index using record linkage. Machine learning and Cox regression/nomogram models were developed and internally validated in Python and R, respectively.

RESULTS

Machine learning models demonstrated highest performance (C-index) in the larynx and nasopharynx cohorts (0.82), followed by the oropharynx (0.79) and the hypopharynx and oral cavity cohorts (0.73). In the whole HNC population, C-indexes of 0.79 and 0.70 and Brier scores of 0.10 and 0.27 were reported for the machine learning and nomogram model, respectively. Cox regression analysis identified age, T and N classification, and time-corrected biologic equivalent dose in two gray fractions as independent prognostic factors for 2-year CSS. N classification was the most important feature used for prediction in the machine learning model followed by age.

CONCLUSION

Machine learning and nomogram analysis predicted 2-year CSS with high performance using routinely collected and complete clinical information extracted from oncology information systems. These models function as visual decision-making tools to guide radiotherapy treatment decisions and provide insight into the prediction of survival outcomes in patients with HNC.

A comparison of machine learning models and Cox proportional hazards models regarding their ability to predict the risk of gastrointestinal cancer based on metabolic syndrome and its components

Background

Little is known about applying machine learning (ML) techniques to identify the important variables contributing to the occurrence of gastrointestinal (GI) cancer in epidemiological studies. We aimed to compare different ML models to a Cox proportional hazards (CPH) model regarding their ability to predict the risk of GI cancer based on metabolic syndrome (MetS) and its components.

Methods

A total of 41,837 participants were included in a prospective cohort study. Incident cancer cases were identified by following up with participants until December 2019. We used CPH, random survival forest (RSF), survival trees (ST), gradient boosting (GB), survival support vector machine (SSVM), and extra survival trees (EST) models to explore the impact of MetS on GI cancer prediction. We used the C-index and integrated Brier score (IBS) to compare the models.

Results

In all, 540 incident GI cancer cases were identified. The GB and SSVM models exhibited comparable performance to the CPH model concerning the C-index (0.725). We also recorded a similar IBS for all models (0.017). Fasting glucose and waist circumference were considered important predictors.

Conclusions

Our study found comparably good performance concerning the C-index for the ML models and CPH model. This finding suggests that ML models may be considered another method for survival analysis when the CPH model's conditions are not satisfied.

Risk-aware survival time prediction from whole slide pathological images

Deep-learning-based survival prediction can assist doctors by providing additional information for diagnosis by estimating the risk or time of death. The former focuses on ranking deaths among patients based on the Cox model, whereas the latter directly predicts the survival time of each patient. However, it is observed that survival time prediction for the patients, particularly with close observation times, possibly has incorrect orders, leading to low prediction accuracy. Therefore, in this paper, we present a whole slide image (WSI)-based survival time prediction method that takes advantage of both the risk as well as time prediction. Specifically, we propose to combine these two approaches by extracting the risk prediction features and using them as guides for the survival time prediction. Considering the high resolution of WSIs, we extract tumor patches from WSIs using a pre-trained tumor classifier and apply the graph convolutional network to aggregate information across these patches effectively. Extensive experiments demonstrate that the proposed method significantly improves the time prediction accuracy when compared with direct prediction of the survival times without guidance and outperforms existing methods.

Joint learning sample similarity and correlation representation for cancer survival prediction

BACKGROUND

As a highly aggressive disease, cancer has been becoming the leading death cause around the world. Accurate prediction of the survival expectancy for cancer patients is significant, which can help clinicians make appropriate therapeutic schemes. With the high-throughput sequencing technology becoming more and more cost-effective, integrating multi-type genome-wide data has been a promising method in cancer survival prediction. Based on these genomic data, some data-integration methods for cancer survival prediction have been proposed. However, existing methods fail to simultaneously utilize feature information and structure information of multi-type genome-wide data.

RESULTS

We propose a Multi-type Data Joint Learning (MDJL) approach based on multi-type genome-wide data, which comprehensively exploits feature information and structure information. Specifically, MDJL exploits correlation representations between any two data types by cross-correlation calculation for learning discriminant features. Moreover, based on the learned multiple correlation representations, MDJL constructs sample similarity matrices for capturing global and local structures across different data types. With the learned discriminant representation matrix and fused similarity matrix, MDJL constructs graph convolutional network with Cox loss for survival prediction.

CONCLUSIONS

Experimental results demonstrate that our approach substantially outperforms established integrative methods and is effective for cancer survival prediction.

Machine Learning Heuristics on Gingivobuccal Cancer Gene Datasets Reveals Key Candidate Attributes for Prognosis

Delayed cancer detection is one of the common causes of poor prognosis in the case of many cancers, including cancers of the oral cavity. Despite the improvement and development of new and efficient gene therapy treatments, very little has been carried out to algorithmically assess the impedance of these carcinomas. In this work, from attributes or NCBI's oral cancer datasets, viz. (i) name, (ii) gene(s), (iii) protein change, (iv) condition(s), clinical significance (last reviewed). We sought to train the number of instances emerging from them. Further, we attempt to annotate viable attributes in oral cancer gene datasets for the identification of gingivobuccal cancer (GBC). We further apply supervised and unsupervised machine learning methods to the gene datasets, revealing key candidate attributes for GBC prognosis. Our work highlights the importance of automated identification of key genes responsible for GBC that could perhaps be easily replicated in other forms of oral cancer detection.

Impact of image filtering and assessment of volume-confounding effects on CT radiomic features and derived survival models in non-small cell lung cancer

Background

No evidence supports the choice of specific imaging filtering methodologies in radiomics. As the volume of the primary tumor is a well-recognized prognosticator, our purpose is to assess how filtering may impact the feature/volume dependency in computed tomography (CT) images of non-small cell lung cancer (NSCLC), and if such impact translates into differences in the performance of survival modeling. The role of lesion volume in model performances was also considered and discussed.

Methods

Four-hundred seventeen CT images NSCLC patients were retrieved from the NSCLC-Radiomics public repository. Pre-processing and features extraction were implemented using Pyradiomics v3.0.1. Features showing high correlation with volume across original and filtered images were excluded. Cox proportional hazards (PH) with least absolute shrinkage and selection operator (LASSO) regularization and CatBoost models were built with and without volume, and their concordance (C-) indices were compared using Wilcoxon signed-ranked test. The Mann Whitney U test was used to assess model performances after stratification into two groups based on low- and high-volume lesions.

Results

Radiomic models significantly outperformed models built on only clinical variables and volume. However, the exclusion/inclusion of volume did not generally alter the performances of radiomic models. Overall, performances were not substantially affected by the choice of either imaging filter (overall C-index 0.539-0.590 for Cox PH and 0.589-0.612 for CatBoost). The separation of patients with high-volume lesions resulted in significantly better performances in 2/10 and 7/10 cases for Cox PH and CatBoost models, respectively. Both low- and high-volume models performed significantly better with the inclusion of radiomic features (P<0.0001), but the improvement was largest in the high-volume group (+10.2% against +8.7% improvement for CatBoost models and +10.0% against +5.4% in Cox PH models).

Conclusions

Radiomic features complement well-known prognostic factors such as volume, but their volume-dependency is high and should be managed with vigilance. The informative content of radiomic features may be diminished in small lesion volumes, which could limit the applicability of radiomics in early-stage NSCLC, where tumors tend to be small. Our results also suggest an advantage of CatBoost models over the Cox PH models.

Risk of Mortality Prediction Involving Time-Varying Covariates for Patients with Heart Failure Using Deep Learning

Heart failure (HF) is challenging public medical and healthcare systems. This study aimed to develop and validate a novel deep learning-based prognostic model to predict the risk of all-cause mortality for patients with HF. We also compared the performance of the proposed model with those of classical deep learning- and traditional statistical-based models. The present study enrolled 730 patients with HF hospitalized at Toho University Ohashi Medical Center between April 2016 and March 2020. A recurrent neural network-based model (RNNSurv) involving time-varying covariates was developed and validated. The proposed RNNSurv showed better prediction performance than those of a deep feed-forward neural network-based model (referred as "DeepSurv") and a multivariate Cox proportional hazard model in view of discrimination (C-index: 0.839 vs. 0.755 vs. 0.762, respectively), calibration (better fit with a 45-degree line), and ability of risk stratification, especially identifying patients with high risk of mortality. The proposed RNNSurv demonstrated an improved prediction performance in consideration of temporal information from time-varying covariates that could assist clinical decision-making. Additionally, this study found that significant risk and protective factors of mortality were specific to risk levels, highlighting the demand for an individual-specific clinical strategy instead of a uniform one for all patients.

Machine learning models for identifying predictors of clinical outcomes with first-line immune checkpoint inhibitor therapy in advanced non-small cell lung cancer

Immune checkpoint inhibitors (ICIs) are standard-of-care as first-line (1L) therapy for advanced non-small cell lung cancer (aNSCLC) without actionable oncogenic driver mutations. While clinical trials demonstrated benefits of ICIs over chemotherapy, variation in outcomes across patients has been observed and trial populations may not be representative of clinical practice. Predictive models can help understand heterogeneity of treatment effects, identify predictors of meaningful clinical outcomes, and may inform treatment decisions. We applied machine learning (ML)-based survival models to a real-world cohort of patients with aNSCLC who received 1L ICI therapy extracted from a US-based electronic health record database. Model performance was evaluated using metrics including concordance index (c-index), and we used explainability techniques to identify significant predictors of overall survival (OS) and progression-free survival (PFS). The ML model achieved c-indices of 0.672 and 0.612 for OS and PFS, respectively, and Kaplan-Meier survival curves showed significant differences between low- and high-risk groups for OS and PFS (both log-rank test p < 0.0001). Identified predictors were mostly consistent with the published literature and/or clinical expectations and largely overlapped for OS and PFS; Eastern Cooperative Oncology Group performance status, programmed cell death-ligand 1 expression levels, and serum albumin were among the top 5 predictors for both outcomes. Prospective and independent data set evaluation is required to confirm these results.