Search

Lung cancer's radiomic phenotype may potentially inform clinical decision-making with respect to radical radiotherapy. At present there are no validated biomarkers available for the individualisation of radical radiotherapy in lung cancer and the mortality rate of this disease remains the highest of all other solid tumours. MEDLINE was searched using the terms 'radiomics' and 'lung cancer' according to the Preferred Reporting Items for Systematic Reviews and Met-Analyses (PRISMA) guidance. Radiomics studies were defined as those manuscripts describing the extraction and analysis of at least 10 quantifiable imaging features. Only those studies assessing disease control, survival or toxicity outcomes for patients with lung cancer following radical radiotherapy ± chemotherapy were included. Study titles and abstracts were reviewed by two independent reviewers. The Radiomics Quality Score was applied to the full text of included papers. Of 244 returned results, 44 studies met the eligibility criteria for inclusion. End points frequently reported were local (17%), regional (17%) and distant control (31%), overall survival (79%) and pulmonary toxicity (4%). Imaging features strongly associated with clinical outcomes include texture features belonging to the subclasses Gray level run length matrix, Gray level co-occurrence matrix and kurtosis. The median cohort size for model development was 100 (15-645); in the 11 studies with external validation in a separate independent population, the median cohort size was 84 (21-295). The median number of imaging features extracted was 184 (10-6538). The median Radiomics Quality Score was 11% (0-47). Patient-reported outcomes were not incorporated within any studies identified. No studies externally validated a radiomics signature in a registered prospective study. Imaging-derived indices attained through radiomic analyses could equip thoracic oncologists with biomarkers for treatment response, patterns of failure, normal tissue toxicity and survival in lung cancer. Based on routine scans, their non-invasive nature and cost-effectiveness are major advantages over conventional pathological assessment. Improved tools are required for the appraisal of radiomics studies, as significant barriers to clinical implementation remain, such as standardisation of input scan data, quality of reporting and external validation of signatures in randomised, interventional clinical trials.

Cardiovascular diseases are regarded as the most common reason for worldwide deaths. As per World Health Organization, nearly $ 17.9 $ million people die of heart-related diseases each year. The high shares of cardiovascular-related diseases in total worldwide deaths motivated researchers to focus on ways to reduce the numbers. In this regard, several works focused on the development of machine learning techniques/algorithms for early detection, diagnosis, and subsequent treatment of cardiovascular-related diseases. These works focused on a variety of issues such as finding important features to effectively predict the occurrence of heart-related diseases to calculate the survival probability. This research contributes to the body of literature by selecting a standard well defined, and well-curated dataset as well as a set of standard benchmark algorithms to independently verify their performance based on a set of different performance evaluation metrics. From our experimental evaluation, it was observed that decision tree is the best performing algorithm in comparison to logistic regression, support vector machines, and artificial neural networks. Decision trees achieved $ 14 $% better accuracy than the average performance of the remaining techniques. In contrast to other studies, this research observed that artificial neural networks are not as competitive as the decision tree or support vector machine.

Machine learning has become an important research field in genetics and molecular biology. Survival analysis using machine learning can provide an important computed-aid clinical research scheme for evaluating tumor treatment options. However, the genomic features are high-dimensional, which limits the prediction performance of the survival learning model. Therefore, in this paper, we propose an improved survival prediction model using a deep forest and self-supervised learning. It uses a deep survival forest to perform adaptive learning of high-dimensional genomic data and ensure robustness. In addition, self-supervised learning, as a semi-supervised learning style, is designed to utilize unlabeled samples to improve model performance. Based on four cancer datasets from The Cancer Genome Atlas (TCGA), the experimental results show that our proposed method outperforms four advanced survival analysis methods in terms of the C-index and brier score. The developed prediction model will help doctors rethink patient characteristics’ relevance to survival time and personalize treatment decisions.

Radiomics is the quantitative analysis of standard-of-care medical imaging; the information obtained can be applied within clinical decision support systems to create diagnostic, prognostic, and/or predictive models. Radiomics analysis can be performed by extracting hand-crafted radiomics features or via deep learning algorithms. Radiomics has evolved tremendously in the last decade, becoming a bridge between imaging and precision medicine. Radiomics exploits sophisticated image analysis tools coupled with statistical elaboration to extract the wealth of information hidden inside medical images, such as computed tomography (CT), magnetic resonance (MR), and/or Positron emission tomography (PET) scans, routinely performed in the everyday clinical practice. Many efforts have been devoted in recent years to the standardization and validation of radiomics approaches, to demonstrate their usefulness and robustness beyond any reasonable doubts. However, the booming of publications and commercial applications of radiomics approaches warrant caution and proper understanding of all the factors involved to avoid "scientific pollution" and overly enthusiastic claims by researchers and clinicians alike. For these reasons the present review aims to be a guidebook of sorts, describing the process of radiomics, its pitfalls, challenges, and opportunities, along with its ability to improve clinical decision-making, from oncology and respiratory medicine to pharmacological and genotyping studies.

Purpose The aims of the present study were to investigate the symptom clusters in terminally ill patients with cancer using the European Organization for Research and Treatment of Cancer Quality of Life Questionnaire Core 15 Palliative Care (EORTC QLQ-C15-PAL), and to examine whether these symptom clusters influenced prognosis. Methods We analyzed data from 130 cancer patients hospitalized in the palliative care unit from June 2018 to December 2019 in an observational study. Principal component analysis was used to detect symptom clusters using the scored date of 14 items in the QLQ-C15-PAL, except for overall QOL, at the time of hospitalization. The influence of the existence of these symptom clusters and Palliative Performance Scale (PPS) on survival was analyzed by Cox proportional hazards regression analysis, and survival curves were compared between the groups with or without existing corresponding symptom clusters using the log-rank test. Results The following symptom clusters were identified: cluster 1 (pain, insomnia, emotional functioning), cluster 2 (dyspnea, appetite loss, fatigue, and nausea), and cluster 3 (physical functioning). Cronbach’s alpha values for the symptom clusters ranged from 0.72 to 0.82. An increased risk of death was significantly associated with the existence of cluster 2 and poor PPS (log-rank test, p = 0.016 and p Conclusion In terminally ill patients with cancer, three symptom clusters were detected based on QLQ-C15-PAL scores. Poor PPS and the presence of symptom cluster that includes dyspnea, appetite loss, fatigue, and nausea indicated poor prognosis.

Although lung cancer survival status and survival length predictions have primarily been studied individually, a scheme that leverages both fields in an interpretable way for physicians remains elusive. We propose a two-phase data analytic framework that is capable of classifying survival status for 0.5-, 1-, 1.5-, 2-, 2.5-, and 3-year time-points (phase I) and predicting the number of survival months within 3 years (phase II) using recent Surveillance, Epidemiology, and End Results data from 2010 to 2017. In this study, we employ three analytical models (general linear model, extreme gradient boosting, and artificial neural networks), five data balancing techniques (synthetic minority oversampling technique (SMOTE), relocating safe level SMOTE, borderline SMOTE, adaptive synthetic sampling, and majority weighted minority oversampling technique), two feature selection methods (least absolute shrinkage and selection operator (LASSO) and random forest), and the one-hot encoding approach. By implementing a comprehensive data preparation phase, we demonstrate that a computationally efficient and interpretable method such as GLM performs comparably to more complex models. Moreover, we quantify the effects of individual features in phase I and II by exploiting GLM coefficients. To the best of our knowledge, this study is the first to (a) implement a comprehensive data processing approach to develop performant, computationally efficient, and interpretable methods in comparison to black-box models, (b) visualize top factors impacting survival odds by utilizing the change in odds ratio, and (c) comprehensively explore short-term lung cancer survival using a two-phase approach.

Technology-assisted diagnosis is increasingly important in healthcare systems. Brain tumors are a leading cause of death worldwide, and treatment plans rely heavily on accurate survival predictions. Gliomas, a type of brain tumor, have particularly high mortality rates and can be further classified as low- or high-grade, making survival prediction challenging. Existing literature provides several survival prediction models that use different parameters, such as patient age, gross total resection status, tumor size, or tumor grade. However, accuracy is often lacking in these models. The use of tumor volume instead of size may improve the accuracy of survival prediction. In response to this need, we propose a novel model, the enhanced brain tumor identification and survival time prediction (ETISTP), which computes tumor volume, classifies it into low- or high-grade glioma, and predicts survival time with greater accuracy. The ETISTP model integrates four parameters: patient age, survival days, gross total resection (GTR) status, and tumor volume. Notably, ETISTP is the first model to employ tumor volume for prediction. Furthermore, our model minimizes the computation time by allowing for parallel execution of tumor volume computation and classification. The simulation results demonstrate that ETISTP outperforms prominent survival prediction models.

(1) Background: Predicting the survival of patients in end-of-life care is crucial, and evaluating their performance status is a key factor in determining their likelihood of survival. However, the current traditional methods for predicting survival are limited due to their subjective nature. Wearable technology that provides continuous patient monitoring is a more favorable approach for predicting survival outcomes among palliative care patients. (2) Aims and objectives: In this study, we aimed to explore the potential of using deep learning (DL) model approaches to predict the survival outcomes of end-stage cancer patients. Furthermore, we also aimed to compare the accuracy of our proposed activity monitoring and survival prediction model with traditional prognostic tools, such as the Karnofsky Performance Scale (KPS) and the Palliative Performance Index (PPI). (3) Method: This study recruited 78 patients from the Taipei Medical University Hospital’s palliative care unit, with 66 (39 male and 27 female) patients eventually being included in our DL model for predicting their survival outcomes. (4) Results: The KPS and PPI demonstrated an overall accuracy of 0.833 and 0.615, respectively. In comparison, the actigraphy data exhibited a higher accuracy at 0.893, while the accuracy of the wearable data combined with clinical information was even better, at 0.924. (5) Conclusion: Our study highlights the significance of incorporating clinical data alongside wearable sensors to predict prognosis. Our findings suggest that 48 h of data is sufficient for accurate predictions. The integration of wearable technology and the prediction model in palliative care has the potential to improve decision making for healthcare providers and can provide better support for patients and their families. The outcomes of this study can possibly contribute to the development of personalized and patient-centered end-of-life care plans in clinical practice.

Treatment of hepatocellular carcinoma (HCC) depends on the stage of disease. In the Western Hemisphere, the Barcelona Clinic Liver Cancer classification (BCLC) is the preferred staging system. Approximately one-third of patients initially present with intermediate-stage disease. For these patients, transarterial chemoembolization (TACE) is the treatment of choice. However, the intermediate-stage comprises a heterogeneous subgroup of patients with considerable differences in tumor burden and liver function. In addition, differences in individual factors that are not captured by the BCLC framework, such as the tumor growth pattern, degree of hypervascularity, and vascular supply, complicate further evaluation of these patients. Due to these differences, not all patients benefit equally from TACE. Several tools and scoring systems have been devised to provide decision-making support. All of these have shown promising initial results but failed external evaluation and have not been translated to the clinic. Nevertheless, criteria for objectifying treatment decisions in daily clinical practice are needed in all stages of disease. Therefore, this review provides a concise practical step-by-step guide on current strategies for patient selection and decision-making, with a focus on TACE, to critically evaluate the existing decision-support tools and provide a summary of the latest updates in the field.

Producción Científica, Glioblastoma is an aggressive and fast-growing brain tumor with poor prognosis. Predicting the expected survival of patients with glioblastoma is a key task for efficient treatment and surgery planning. Survival predictions could be enhanced by means of a radiomic system. However, these systems demand high numbers of multicontrast images, the acquisitions of which are time consuming, giving rise to patient discomfort and low healthcare system efficiency. Synthetic MRI could favor deployment of radiomic systems in the clinic by allowing practitioners not only to reduce acquisition time, but also to retrospectively complete databases or to replace artifacted images. In this work we analyze the replacement of an actually acquired MR weighted image by a synthesized version to predict survival of glioblastoma patients with a radiomic system. Each synthesized version was realistically generated from two acquired images with a deep learning synthetic MRI approach based on a convolutional neural network. Specifically, two weighted images were considered for the replacement one at a time, a T2w and a FLAIR, which were synthesized from the pairs T1w and FLAIR, and T1w and T2w, respectively. Furthermore, a radiomic system for survival prediction, which can classify patients into two groups (survival >480 days and 480 days), was built. Results show that the radiomic system fed with the synthesized image achieves similar performance compared with using the acquired one, and better performance than a model that does not include this image. Hence, our results confirm that synthetic MRI does add to glioblastoma survival prediction within a radiomics-based approach., Ministerio de Ciencia e Innovación (research grants RTI 2018-094569-B-I00, PRE2019-089176 y PID2020-115339RB-I0), Asociación Española Contra el Cáncer (subvención PRDVL19001MOYA)

BackgroundThe study aimed to investigate the prognostic factors of spinal cord astrocytoma (SCA) and establish a nomogram prognostic model for the management of patients with SCA.MethodsPatients diagnosed with SCA between 1975 and 2016 were extracted from the Surveillance, Epidemiology, and End Results (SEER) database and randomly divided into training and testing datasets (7:3). The primary outcomes of this study were overall survival (OS) and cancer-specific survival (CSS). Cox hazard proportional regression model was used to identify the prognostic factors of patients with SCA in the training dataset and feature importance was obtained. Based on the independent prognostic factors, nomograms were established for prognostic prediction. Calibration curves, concordance index (C-index), and time-dependent receiver operating characteristic (ROC) curves were used to evaluate the calibration and discrimination of the nomogram model, while Kaplan-Meier (KM) survival curves and decision curve analyses (DCA) were used to evaluate the clinical utility. Web-based online calculators were further developed to achieve clinical practicability.ResultsA total of 818 patients with SCA were included in this study, with an average age of 30.84 ± 21.97 years and an average follow-up time of 117.57 ± 113.51 months. Cox regression indicated that primary site surgery, age, insurance, histologic type, tumor extension, WHO grade, chemotherapy, and post-operation radiotherapy (PRT) were independent prognostic factors for OS. While primary site surgery, insurance, tumor extension, PRT, histologic type, WHO grade, and chemotherapy were independent prognostic factors for CSS. For OS prediction, the calibration curves in the training and testing dataset illustrated good calibration, with C-indexes of 0.783 and 0.769. The area under the curves (AUCs) of 5-year survival prediction were 0.82 and 0.843, while 10-year survival predictions were 0.849 and 0.881, for training and testing datasets, respectively. Moreover, the DCA demonstrated good clinical net benefit. The prediction performances of nomograms were verified to be superior to that of single indicators, and the prediction performance of nomograms for CSS is also excellent.ConclusionsNomograms for patients with SCA prognosis prediction demonstrated good calibration, discrimination, and clinical utility. This result might benefit clinical decision-making and patient management for SCA. Before further use, more extensive external validation is required for the established web-based online calculators.

BackgroundThe alternative usage of promoters provides a way to regulate gene expression, has a significant influence on the transcriptome, and contributes to the cellular transformation of cancer. However, the function of alternative promoters (APs) in hepatocellular carcinoma (HCC) has not been systematically studied yet. In addition, the potential mechanism of regulation to the usage of APs remains unclear. DNA methylation, one of the most aberrant epigenetic modifications in cancers, is known to regulate transcriptional activity. Whether DNA methylation regulates the usage of APs needs to be explored. Here, we aim to investigate the effects of DNA methylation on usage of APs in HCC.MethodsPromoter activities were calculated based on RNA-seq data. Functional enrichment analysis was implemented to conduct GO terms. Correlation tests were used to detect the correlation between promoter activity and methylation status. The LASSO regression model was used to generate a diagnostic model. Kaplan–Meier analysis was used to compare the overall survival between high and low methylation groups. RNA-seq and whole-genome bisulfite sequencing (WGBS) in HCC samples were performed to validate the correlation of promoter activity and methylation.ResultsWe identified 855 APs in total, which could be well used to distinguish cancer from normal samples. The correlation of promoter activity and DNA methylation in APs was observed, and the APs with negative correlation were defined as methylation-regulated APs (mrAPs). Six mrAPs were identified to generate a diagnostic model with good performance (AUC = 0.97). Notably, the majority of mrAPs had CpG sites that could be used to predict clinical outcomes by methylation status. Finally, we verified 85.6% of promoter activity variation and 92.3% of methylation changes in our paired RNA-seq and WGBS samples, respectively. The negative correlation between promoter activity and methylation status was further confirmed in our HCC samples.ConclusionThe aberrant methylation status plays a critical role in the precision usage of APs in HCC, which sheds light on the mechanism of cancer development and provides a new insight into cancer screening and treatment.

Discontinuing ad creatives at an appropriate time is one of the most important ad operations that can have a significant impact on sales. Such operational support for ineffective ads has been less explored than that for effective ads. After pre-analyzing 1,000,000 real-world ad creatives, we found that there are two types of discontinuation: short-term (i.e., cut-out) and long-term (i.e., wear-out). In this paper, we propose a practical prediction framework for the discontinuation of ad creatives with a hazard function-based loss function inspired by survival analysis. Our framework predicts the discontinuations with a multi-modal deep neural network that takes as input the ad creative (e.g., text, categorical, image, numerical features). To improve the prediction performance for the two different types of discontinuations and for the ad creatives that contribute to sales, we introduce two new techniques: (1) a two-term estimation technique with multi-task learning and (2) a click-through rate-weighting technique for the loss function. We evaluated our framework using the large-scale ad creative dataset, including 10 billion scale impressions. In terms of the concordance index (short: 0.896, long: 0.939, and overall: 0.792), our framework achieved significantly better performance than the conventional method (0.531). Additionally, we confirmed that our framework (i) demonstrated the same degree of discontinuation effect as manual operations for short-term cases, and (ii) accurately predicted the ad discontinuation order, which is important for long-running ad creatives for long-term cases., Comment: 23 pages, 5 figures. Accepted by Appl. Sci. on March 29th, 2022

Background: Score-based survival prediction in patients with advanced heart failure (HF) is complicated. Easy-to-use prognostication tools could inform clinical decision-making and palliative care delivery. Objective: To compare the prognostic utility of the Seattle HF model (SHFM), the surprise question (SQ), and the number of HF hospitalizations (NoH) within the last 12 months for predicting 1-year survival in patients with advanced HF. Methods: We retrospectively analyzed data from a cluster-randomized controlled trial of advanced HF patients, predominantly with reduced ejection fraction. Primary outcome was the prognostic discrimination of SHFM, SQ (“Would you be surprised if this patient were to die within 1 year?”) answered by HF cardiologists, and NoH, assessed by receiver operating characteristic (ROC) curve analysis. Optimal cut-offs were calculated using Youden’s index (SHFM

Pathological complete response (pCR) after neoadjuvant chemotherapy (NAC) is a strong prognostic factor in breast cancer (BC). The aim of this study was to investigate whether semiquantitative parameters derived from baseline [18F]Fluorodeoxyglucose ([18F]FDG) positron emission computed tomography/computed tomography (PET/CT) could predict pCR after NAC and survival outcomes in patients affected by different molecular subtypes of BC. We retrospectively retrieved patients from the databases of two Italian hospitals (Centre A: University Hospital of Ferrara; Centre B: University of Padua) meeting the following inclusion criteria: (1) diagnosis of BC; (2) history of NAC; (3) baseline [18F]FDG PET/CT performed before the first cycle of NAC; (4) available follow-up data (response after NAC and survival information). For each [18F]FDG PET/CT scan, semiquantitative parameters (SUVmax, SUVmean, MTV and TLG) related to the primary tumor (B), to the reference lesion for both axillary (N) and distant lymph node (DN), and to the whole-body burden of disease (WB) were evaluated. Patients enrolled were 133: 34 from centre A and 99 from centre B. Patients’ molecular subtypes were: 9 luminal A, 49 luminal B, 33 luminal B + HER-2, 10 HER-2 enriched, and 32 triple negative (TNBC). Luminal A and HER-2 enriched BC patients were excluded from the analysis due to the small sample size. pCR after NAC was achieved in 47 patients (41.2%). [18F]FDG PET/CT detected the primary tumor in 98.3% of patients and lymph node metastases were more frequently detected in Luminal B subgroup. Among Luminal B patients, median SUVmean_B values were significantly higher (p = 0.027) in responders (7.06 ± 5.9) vs. non-responders (4.4 ± 2.1) to NAC. Luminal B + HER-2 non-responders showed a statistically significantly higher median MTV_B (7.3 ± 4.2 cm3 vs. 3.5 ± 2.5 cm3; p = 0.003) and TLG_B (36.5 ± 24.9 vs. 18.9 ± 17.7; p = 0.025) than responders at baseline [18F]FDG PET/CT. None of the semiquantitative parameters predicted pCR after NAC in TNBC patients. However, among TNBC patients who achieved pCR after NAC, 4 volumetric parameters (MTV_B, TLG_B, MTV_WB and TLG_WB) were significantly higher in patients dead at follow-up. If confirmed in further studies, these results could open up a widespread use of [18F]FDG PET/CT as a baseline predictor of response to NAC in luminal B and luminal B + HER-2 patients and as a prognostic tool in TNBC.

Gliomas are tumors of the central nervous system, which usually start within the glial cells of the brain or the spinal cord. These are extremely migratory and diffusive tumors, which quickly expand to the surrounding regions in the brain. There are different grades of gliomas, hinting about their growth patterns and aggressiveness and potential response to the treatment. As part of routine clinical procedure for gliomas, both radiology images (rad), such as multiparametric MR images, and digital pathology images (path) from tissue samples are acquired. Each of these data streams are used separately for prediction of the survival outcome of gliomas, however, these images provide complimentary information, which can be used in an integrated way for better prediction. There is a need to develop an image-based method that can utilise the information extracted from these imaging sequences in a synergistic way to predict patients’ outcome and to potentially assist in building comprehensive and patient-centric treatment plans. The objective of this study is to improve survival prediction outcomes of gliomas by integrating radiology and pathology imaging. Multiparametric magnetic resonance imaging (MRI), rad images, and path images of glioma patients were acquired from The Cancer Imaging Archive. Quantitative imaging features were extracted from tumor regions in rad and path images. The features were given as input to an ensemble regression machine learning pipeline, including support vector regression, AdaBoost, gradient boost, and random forest. The performance of the model was evaluated in several configurations, including leave-one-out, five-fold cross-validation, and split-train-test. Moreover, the quantitative performance evaluations were conducted separately in the complete cohort (n = 171), high-grade gliomas (HGGs), n = 75, and low-grade gliomas (LGGs), n = 96. The combined rad and path features outperformed individual feature types in all the configurations and datasets. In leave-one-out configuration, the model comprising both rad and path features was successfully validated on the complete dataset comprising HGFs and LGGs (R=0.84p=2.2×10−16). The Kaplan–Meier curves generated on the predictions of the proposed model yielded a hazard ratio of 3.314[95%CI:1.718−6.394],log−rank(P)=2×10−4 on combined rad and path features. Conclusion: The proposed approach emphasizes radiology experts and pathology experts’ clinical workflows by creating prognosticators upon ‘rad’ radiology images and digital pathology ‘path’ images independently, as well as combining the power of both, also through delivering integrated analysis, that can contribute to a collaborative attempt between different departments for administration of patients with gliomas.

Simple SummaryGlioblastoma (GBM) is the most common and aggressive primary brain tumor. Diffusion kurtosis imaging (DKI) has characterized non-Gaussian diffusion behaviors in brain normal tissue and gliomas, but there are very limited efforts in investigating treatment responses of kurtosis in GBM. This study aimed to investigate whether any parameter derived from the DKI is a significant predictor of overall survival (OS). We found that the large mean, 80 and 90 percentile kurtosis values in the contrast enhanced gross tumor volume (Gd-GTV) on post-Gd T1-weighted images pre-RT were significantly associated with reduced OS. In the multivariate Cox model, the mean kurtosis Gd-GTV pre-RT after considering effects of age, extent of surgery, and methylation were significant predictors of OS. In addition, the 80 and 90 percentile kurtosis values in Gd-GTV post RT were significantly associated with progression free survival (PFS). The DKI model demonstrates the potential to predict outcomes in the patients with GBM.PurposeNon-Gaussian diffusion behaviors in gliomas have been characterized by diffusion kurtosis imaging (DKI). But there are very limited efforts in investigating the kurtosis in glioblastoma (GBM) and its prognostic and predictive values. This study aimed to investigate whether any of the diffusion kurtosis parameters derived from DKI is a significant predictor of overall survival.Methods and MaterialsThirty-three patients with GBM had pre-radiation therapy (RT) and mid-RT diffusion weighted (DW) images. Kurtosis and diffusion coefficient (DC) values in the contrast enhanced gross tumor volume (Gd-GTV) on post-Gd T1 weighted images pre-RT and mid-RT were calculated. Univariate and multivariate Cox models were used to evaluate the DKI parameters and clinical factors for prediction of OS and PFS.ResultsThe large mean kurtosis values in the Gd-GTV pre-RT were significantly associated with reduced OS (p = 0.02), but the values at mid-RT were not (p > 0.8). In the multivariate Cox model, the mean kurtosis in the Gd-GTV pre-RT (p = 0.009) was still a significant predictor of OS after adjusting effects of age, O6-Methylguanine-DNA Methyl transferase (MGMT) methylation and extent of resection. In Gd-GTV post-RT, 80 and 90 percentile kurtosis values were significant predictors (p ≤ 0.05) for progression free survival (PFS).ConclusionThe DKI model demonstrates the potential to predict OS and PFS in the patients with GBM. Further development and histopathological validation of the DKI model will warrant its role in clinical management of GBM.

One pivotal feature of transcriptomics data is the unwanted variations caused by disparate experimental handling, known as handling effects. Various data normalization methods were developed to alleviate the adverse impact of handling effects in the setting of differential expression analysis. However, little research has been done to evaluate their performance in the setting of survival outcome prediction, an important analysis goal for transcriptomics data in biomedical research. Leveraging a unique pair of datasets for the same set of tumor samples—one with handling effects and the other without, we developed a benchmarking tool for conducting such an evaluation in microRNA microarrays. We applied this tool to evaluate the performance of three popular normalization methods—quantile normalization, median normalization and variance stabilizing normalization—in survival prediction using various approaches for model building and designs for sample assignment. We showed that handling effects can have a strong impact on survival prediction and that quantile normalization, a most popular method in current practice, tends to underperform median normalization and variance stabilizing normalization. We demonstrated with a small example the reason for quantile normalization’s poor performance in this setting. Our finding highlights the importance of putting normalization evaluation in the context of the downstream analysis setting and the potential of improving the development of survival predictors by applying median normalization. We make available our benchmarking tool for performing such evaluation on additional normalization methods in connection with prediction modeling approaches.

Given growing clinical needs, in recent years Artificial Intelligence (AI) techniques have increasingly been used to define the best approaches for survival assessment and prediction in patients with brain tumors. Advances in computational resources, and the collection of (mainly) public databases, have promoted this rapid development. This narrative review of the current state-of-the-art aimed to survey current applications of AI in predicting survival in patients with brain tumors, with a focus on Magnetic Resonance Imaging (MRI). An extensive search was performed on PubMed and Google Scholar using a Boolean research query based on MeSH terms and restricting the search to the period between 2012 and 2022. Fifty studies were selected, mainly based on Machine Learning (ML), Deep Learning (DL), radiomics-based methods, and methods that exploit traditional imaging techniques for survival assessment. In addition, we focused on two distinct tasks related to survival assessment: the first on the classification of subjects into survival classes (short and long-term or eventually short, mid and long-term) to stratify patients in distinct groups. The second focused on quantification, in days or months, of the individual survival interval. Our survey showed excellent state-of-the-art methods for the first, with accuracy up to ∼98%. The latter task appears to be the most challenging, but state-of-the-art techniques showed promising results, albeit with limitations, with C-Index up to ∼0.91. In conclusion, according to the specific task, the available computational methods perform differently, and the choice of the best one to use is non-univocal and dependent on many aspects. Unequivocally, the use of features derived from quantitative imaging has been shown to be advantageous for AI applications, including survival prediction. This evidence from the literature motivates further research in the field of AI-powered methods for survival prediction in patients with brain tumors, in particular, using the wealth of information provided by quantitative MRI techniques.

Fibronectin (FN) plays an essential role in the host’s response to infection. In previous studies, a significant decrease in the FN level was observed in sepsis; however, it has not been clearly elucidated how this parameter affects the patient’s survival. To better understand the relationship between FN and survival, we utilized innovative approaches from the field of explainable machine learning, including local explanations (Break Down, Shapley Additive Values, Ceteris Paribus), to understand the contribution of FN to predicting individual patient survival. The methodology provides new opportunities to personalize informative predictions for patients. The results showed that the most important indicators for predicting survival in sepsis were INR, FN, age, and the APACHE II score. ROC curve analysis showed that the model’s successful classification rate was 0.92, its sensitivity was 0.92, its positive predictive value was 0.76, and its accuracy was 0.79. To illustrate these possibilities, we have developed and shared a web-based risk calculator for exploring individual patient risk. The web application can be continuously updated with new data in order to further improve the model.

ObjectivesThe Prognostic Nutritional Index (PNI) and Controlling Nutritional Status (CONUT) score are immunonutritive scoring systems with proven predictive ability in various cancer entities, including hepatocellular carcinoma (HCC). We performed the first evaluation of the CONUT score for patients undergoing transarterial chemoembolization (TACE) and compared CONUT and PNI in the ability to predict median overall survival (OS).MethodsBetween 2010 and 2020, we retrospectively identified 237 treatment-naïve patients with HCC who underwent initial TACE at our institution. Both scores include the albumin level and total lymphocyte count. The CONUT additionally includes the cholesterol level. Both scores were compared in univariate and multivariate regression analyses taking into account established risk factors. In a second step, a subgroup analysis was performed on BCLC stage B patients, for whom TACE is the recommended first-line treatment.ResultsA high CONUT score and low PNI were associated with impaired median OS (8.7 vs. 22.3 months, pvs. 20.1 months, pvs. 17.9 months, pvs. 22.0 months, pConclusionBoth scores were able to stratify patients according to their median OS, but only the PNI remained an independent prognostic factor. Therefore, PNI should be preferred when evaluating the nutritional status of patients undergoing TACE.

Background Tumor dynamics typically rely on the sum of the longest diameters (SLD) of target lesions, and ignore heterogeneity in individual lesion dynamics located in different organs. Patients and methods Here we evaluated the benefit of analyzing lesion dynamics in different organs to predict survival in 900 patients with metastatic urothelial carcinoma treated with atezolizumab or chemotherapy (IMvigor211 trial). Results Lesion dynamics varied largely across organs, with lymph nodes and lung lesions showing on average a better response to both treatments than those located in the liver and locoregionally. A benefit of atezolizumab was observed on lung and liver lesion dynamics that was attributed to a longer duration of treatment effect as compared to chemotherapy (P value = 0.043 and 0.001, respectively). The impact of lesion dynamics on survival, assessed by a joint model, varied greatly across organs, irrespective of treatment. Liver and locoregional lesion dynamics had a large impact on survival, with an increase of 10 mm of the lesion size increasing the instantaneous risk of death by 12% and 10%, respectively. In comparison, lymph nodes and lung lesions had a lower impact, with a 10-mm increase in the lesion size increasing the instantaneous risk of death by 7% and 5%, respectively. Using our model, we could anticipate the benefit of atezolizumab over chemotherapy as early as 6 months before the end of the study, which is 3 months earlier than a similar model only relying on SLD. Conclusion We showed the interest of organ-level tumor follow-up to better understand and anticipate the treatment effect on survival., Highlights • Nine hundred metastatic urothelial carcinoma patients from the IMvigor211 phase III trial were treated with atezolizumab versus chemotherapy. • A total of 4489 organ-specific measurements were made: 1544 measurements in the lymph, 999 in the lung, 691 in the liver, and 559 locoregionally. • Longer treatment effect was observed in the lung (P value = 0.043) and liver (P = 0.001) lesions under atezolizumab compared to chemotherapy. • Those with a 10-mm growth of liver lesion had their instantaneous risk of death increased by 12%, compared to 5% in the lung. • Treatment effect on overall survival could be predicted based on early organ-specific tumor data 6 months after last patient inclusion.

To explore prognostic and predictive values of a novel quantitative feature set describing intra-tumor heterogeneity in patients with lung cancer treated with concurrent and sequential chemoradiotherapy.Longitudinal PET-CT images of 30 patients with non-small cell lung cancer were analysed. To describe tumor cell heterogeneity, the tumors were partitioned into one to ten concentric regions depending on their sizes, and, for each region, the change in average intensity between the two scans was calculated for PET and CT images separately to form the proposed feature set. To validate the prognostic value of the proposed method, radiomics analysis was performed and a combination of the proposed novel feature set and the classic radiomic features was evaluated. A feature selection algorithm was utilized to identify the optimal features, and a linear support vector machine was trained for the task of overall survival prediction in terms of area under the receiver operating characteristic curve (AUROC).The proposed novel feature set was found to be prognostic and even outperformed the radiomics approach with a significant difference (AUROCA novel feature set designed for capturing intra-tumor heterogeneity was introduced. Judging by their prognostic power, the proposed features have a promising potential for early survival prediction.

Background: Toward the goal of predicting individual long-term cancer survival to guide treatment decisions, this study evaluated the ability of a probabilistic neural network (PNN), an established model used for decision-making in research and clinical settings, to predict the 10-year overall survival in patients with cervical cancer who underwent primary surgical treatment. Patients and Method: The input dataset was derived from 102 patients with cervical cancer FIGO stage IA2-IIB treated by radical hysterectomy. We identified 4 demographic parameters, 13 tumor-related parameters, and 6 selected perioperative variables for each patient and performed computer simulations with DTREG software. The predictive ability of the model was determined on the basis of its error, sensitivity, and specificity, as well as area under the receiver operating characteristic curve. The results of the PNN predictive model were compared with those of logistic regression analysis and a single decision tree as reference models. Results: The PNN model had very high predictive ability, with a sensitivity of 0.949, a specificity of 0.679, and an error rate of 12.5%. The PNN's area under the receiver operating characteristic curve was high, 0.809, a value greater than those for both logistic regression analysis and the single decision tree. Conclusion: The PNN model effectively and reliably predicted 10-year overall survival in women with operable cervical cancer, and may therefore serve as a tool for decision-making process in cancer treatment.

Background The clinical use of patient-reported outcomes as compared to inflammatory biomarkers for predicting cancer survival remains a challenge in palliative care settings. We evaluated the role of the European Organization for Research and Treatment of Cancer Quality of Life Questionnaire Core 15 Palliative scores (EORTC QLQ-C15-PAL) and the inflammatory biomarkers C-reactive protein (CRP), albumin (Alb), and neutrophil-lymphocyte ratio (NLR) for survival prediction in patients with advanced cancer. Methods This was an observational study in terminally ill patients with cancer hospitalized in a palliative care unit between June 2018 and December 2019. Patients’ data collected at the time of hospitalization were analyzed. Cox regression was performed to examine significant factors influencing survival. A receiver operating characteristic (ROC) analysis was performed to estimate cut-off values for predicting survival within 3 weeks, and a log-rank test was performed to compare survival curves between groups divided by the cut-off values. Results Totally, 130 patients participated in the study. Cox regression suggested that the QLQ-C15-PAL dyspnea and fatigue scores and levels of CRP, Alb, and NLR were significantly associated with survival time, and cut-off values were 66.67, 66.67, 3.0 mg/dL, 2.5 g/dL, and 8.2, respectively. The areas under ROC curves of these variables were 0.6–0.7. There were statistically significant differences in the survival curves between groups categorized using each of these cut-off values (p Conclusion Our findings suggest that the assessment of not only objective indicators for the systemic inflammatory response but also patient-reported outcomes using EORTC QLQ-C15-PAL is beneficial for the prediction of short-term survival in terminally ill patients with cancer.

Introduction There is significant potential to analyse and model routinely collected data for radiotherapy patients to provide evidence to support clinical decisions, particularly where clinical trials evidence is limited or non-existent. However, in practice there are administrative, ethical, technical, logistical and legislative barriers to having coordinated data analysis platforms across radiation oncology centres. Methods A distributed learning network of computer systems is presented, with software tools to extract and report on oncology data and to enable statistical model development. A distributed or federated learning approach keeps data in the local centre, but models are developed from the entire cohort. Results The feasibility of this approach is demonstrated across six Australian oncology centres, using routinely collected lung cancer data from oncology information systems. The infrastructure was used to validate and develop machine learning for model-based clinical decision support and for one centre to assess patient eligibility criteria for two major lung cancer radiotherapy clinical trials (RTOG-9410, RTOG-0617). External validation of a 2-year overall survival model for non-small cell lung cancer (NSCLC) gave an AUC of 0.65 and C-index of 0.62 across the network. For one centre, 65% of Stage III NSCLC patients did not meet eligibility criteria for either of the two practice-changing clinical trials, and these patients had poorer survival than eligible patients (10.6 m vs. 15.8 m, P = 0.024). Conclusion Population-based studies on routine data are possible using a distributed learning approach. This has the potential for decision support models for patients for whom supporting clinical trial evidence is not applicable.

Background Existing clinical methods for prognosis evaluating for Epithelial Ovarian Cancer (EOC) patients had defects of invasive, unsystematic and subjective and little data are available for individualizing treatment, therefore, to identify potential prognostic markers and new therapeutic targets for EOC is urgently required. Results Expression of 232 autophagy-related genes (ARGs) in 354 EOC and 56 human ovarian surface epithelial specimens from 7 independent laboratories were analyzed, 31 mRNAs were identified as DEARGs. We did functional and pathway enrichment analysis and constructed protein–protein interaction network for all DEARGs. To screen out candidate DEARGs related to EOC patients’ survival and construct an autophagy-related prognostic risk signature, univariate and multivariate Cox proportional hazards models were established separately. Finally, 5 optimal independent prognostic DEARGs (PEX3, DNAJB9, RB1, HSP90AB1 and CXCR4) were confirmed and the autophagy-related risk model was established by the 5 prognostic DEARGs. The accuracy and robustness of the prognostic risk model for survival prediction were evaluated and verified by analyzing the correlation between EOC patients’ survival status, clinicopathological features and risk scores. Conclusions The autophagy-related prognostic risk model can be independently used to predict overall survival in EOC patients, it can also potentially assist in individualizing treatment and biomarker development.

Breast cancer is the most common malignancy in women, and because it has a high mortality rate, it is urgent to develop computational methods to increase the accuracy of breast cancer survival predictive models. Although multi-omics data such as gene expression have been extensively used in recent studies, the accurate prognosis of breast cancer remains a challenge. Somatic mutations are another important and promising data source for studying cancer development, and its effect on the prognosis of breast cancer remains to be further explored. Meanwhile, these omics datasets are high-dimensional and redundant. Therefore, we adopted multiple kernel learning (MKL) to efficiently integrate somatic mutation to currently molecular data including gene expression, copy number variation (CNV), methylation, and protein expression data for the prediction of breast cancer survival. Before integration, the maximum relevance minimum redundancy (mRMR) feature selection method was utilized to select features that present high relevance to survival and low redundancy among themselves for each type of data. The experimental results demonstrated that the proposed method achieved the most optimal performance and there was a remarkable improvement in the prediction performance when somatic mutations were included, indicating that somatic mutations are critical for improving breast cancer survival predictions. Moreover, mRMR was superior to other feature selection methods used in previous studies. Furthermore, MKL outperformed the other traditional classifiers in multi-omics data integration. Our analysis indicated that through employing promising omics data such as somatic mutations and harnessing the power of proper feature selection methods and effective integration frameworks, the breast cancer survival predictive accuracy can be further increased, thereby providing a more optimal clinical diagnosis and more effective treatment for breast cancer patients.

Glioblastoma (GBM) is the most malignant primary brain tumor for which no curative treatment options exist. Non-invasive qualitative (Visually Accessible Rembrandt Images (VASARI)) and quantitative (radiomics) imaging features to predict prognosis and clinically relevant markers for GBM patients are needed to guide clinicians. A retrospective analysis of GBM patients in two neuro-oncology centers was conducted. The multimodal Cox-regression model to predict overall survival (OS) was developed using clinical features with VASARI and radiomics features in isocitrate dehydrogenase (IDH)-wild type GBM. Predictive models for IDH-mutation, 06-methylguanine-DNA-methyltransferase (MGMT)-methylation and epidermal growth factor receptor (EGFR) amplification using imaging features were developed using machine learning. The performance of the prognostic model improved upon addition of clinical, VASARI and radiomics features, for which the combined model performed best. This could be reproduced after external validation (C-index 0.711 95% CI 0.64–0.78) and used to stratify Kaplan–Meijer curves in two survival groups (p-value &lt, 0.001). The predictive models performed significantly in the external validation for EGFR amplification (area-under-the-curve (AUC) 0.707, 95% CI 0.582–8.25) and MGMT-methylation (AUC 0.667, 95% CI 0.522–0.82) but not for IDH-mutation (AUC 0.695, 95% CI 0.436–0.927). The integrated clinical and imaging prognostic model was shown to be robust and of potential clinical relevance. The prediction of molecular markers showed promising results in the training set but could not be validated after external validation in a clinically relevant manner. Overall, these results show the potential of combining clinical features with imaging features for prognostic and predictive models in GBM, but further optimization and larger prospective studies are warranted.

Purpose Glioma is the most common type of primary brain tumor in adults, and it causes significant morbidity and mortality, especially in high‐grade glioma (HGG) patients. The accurate prognostic prediction of HGG is vital and helpful for clinicians when developing therapeutic strategies. Therefore, we propose a machine learning‐based survival prediction model by analyzing clinical and dose‐volume histogram (DVH) parameters, to improve the performance of the risk model in HGG patients. Methods Eight clinical variables and 39 DVH parameters were extracted for each patient, who received radiotherapy for HGG with active follow‐up. Ninety‐five patients were randomly divided into training and testing cohorts, and we employed random survival forest (RSF), support vector machine (SVM), and Cox proportional hazards (CPHs) models to predict survival. Calibration plots, concordance indexes, and decision curve analyses were used to evaluate the calibration, discrimination, and clinical utility of these three models. Results The RSF model showed the best performance among the three models, with concordance indexes of 0.824 and 0.847 in the training and testing sets, respectively, followed by the SVM (0.792/0.823) and CPH (0.821/0.811) models. Specifically, in the RSF model, we identified age, gross tumor volume (GTV), grade, Karnofsky performance status (KPS), isocitrate dehydrogenase (IDH), and D99 as important variables associated with survival. The AUCs of the testing set were 92.4%, 87.7%, and 84.0% for 1‐, 2‐, and 3‐year survival, respectively. According to this model, HGG patients can be divided into high‐ and low‐risk groups. Conclusion The machine learning‐based RSF model integrating both clinical and DVH variables is an improved and useful tool for predicting the survival of HGG patients., We propose the machine learning‐based RSF and SVM models, and the classical CPH model, to identify predictors for survival and examine treatment outcomes in patients with HGG by integrating clinical and DVH parameters.The RSF model showed the best performance among the three models and is an improved and useful tool for the survival prediction of HGG.

Background Squamous cell carcinoma (SCC) is a main pathological type of non-small cell lung cancer. It is common among elderly patients with poor prognosis. We aimed to establish an accurate nomogram to predict survival for elderly patients (≥ 60 years old) with SCC based on the Surveillance, Epidemiology, and End Results (SEER) database. Methods The gerontal patients diagnosed with SCC from 2010 to 2015 were collected from the Surveillance, Epidemiology, and End Results (SEER) database. The independent prognostic factors were identified using multivariate Cox proportional hazards regression analysis, which were utilized to conduct a nomogram for predicting survival. The novel nomogram was evaluated by Concordance index (C-index), calibration curves, net reclassification improvement (NRI), integrated discrimination improvement (IDI), and decision curve analysis (DCA). Results 32,474 elderly SCC patients were included in the analysis, who were randomly assigned to training cohort (n = 22,732) and validation cohort (n = 9742). The following factors were contained in the final prognostic model: age, sex, race, marital status, tumor site, AJCC stage, surgery, radiation and chemotherapy. Compared to AJCC stage, the novel nomogram exhibited better performance: C-index (training group: 0.789 vs. 0.730, validation group: 0.791 vs. 0.733), the areas under the receiver operating characteristic curve of the training set (1-year AUC: 0.846 vs. 0.791, 3-year AUC: 0.860 vs. 0.801, 5-year AUC: 0.859 vs. 0.794) and the validation set (1-year AUC: 0.846 vs. 0.793, 3-year AUC: 0.863 vs. 0.806, 5-year AUC: 0.866 vs. 0.801), and the 1-, 3- and 5-year calibration plots. Additionally, the NRI and IDI and 1-, 3- and 5-year DCA curves all confirmed that the nomogram was a great prognosis tool. Conclusions We constructed a novel nomogram that could be practical and helpful for precise evaluation of elderly SCC patient prognosis, thus helping clinicians in determining the appropriate therapy strategies for individual SCC patients.

This study aimed to investigate the performance of a deep learning-based survival-prediction model, which predicts the overall survival (OS) time of glioblastoma patients who have received surgery followed by concurrent chemoradiotherapy (CCRT). The medical records of glioblastoma patients who had received surgery and CCRT between January 2011 and December 2017 were retrospectively reviewed. Based on our inclusion criteria, 118 patients were selected and semi-randomly allocated to training and test datasets (3:1 ratio, respectively). A convolutional neural network–based deep learning model was trained with magnetic resonance imaging (MRI) data and clinical profiles to predict OS. The MRI was reconstructed by using four pulse sequences (22 slices) and nine images were selected based on the longest slice of glioblastoma by a physician for each pulse sequence. The clinical profiles consist of personal, genetic, and treatment factors. The concordance index (C-index) and integrated area under the curve (iAUC) of the time-dependent area-under-the-curve curves of each model were calculated to evaluate the performance of the survival-prediction models. The model that incorporated clinical and radiomic features showed a higher C-index (0.768 (95% confidence interval (CI): 0.759, 0.776)) and iAUC (0.790 (95% CI: 0.783, 0.797)) than the model using clinical features alone (C-index = 0.693 (95% CI: 0.685, 0.701); iAUC = 0.723 (95% CI: 0.716, 0.731)) and the model using radiomic features alone (C-index = 0.590 (95% CI: 0.579, 0.600); iAUC = 0.614 (95% CI: 0.607, 0.621)). These improvements to the C-indexes and iAUCs were validated using the 1000-times bootstrapping method; all were statistically significant (p < 0.001). This study suggests the synergistic benefits of using both clinical and radiomic parameters. Furthermore, it indicates the potential of multi-parametric deep learning models for the survival prediction of glioblastoma patients.

The severe spread of the COVID-19 pandemic has created a situation of public health emergency and global awareness. In our research, we analyzed the demographical factors affecting the global pandemic spread along with the features that lead to death due to the infection. Modeling results stipulate that the mortality rate increase as the age increase and it is found that most of the death cases belong to the age group 60-80. Cluster-based analysis of age groups is also conducted to analyze the maximum targeted age-groups. An association between positive COVID-19 cases and deceased cases are also presented, with the impact on male and female death cases due to corona. Additionally, we have also presented an artificial intelligence-based statistical approach to predict the survival chances of corona infected people in South Korea with the analysis of the impact on the exploratory factors, including age-groups, gender, temporal evolution, etc. To analyze the coronavirus cases, we applied machine learning with hyperparameters tuning and deep learning models with an autoencoder-based approach for estimating the influence of the disparate features on the spread of the disease and predict the survival possibilities of the quarantined patients in isolation. The model calibrated in the study is based on positive corona infection cases and presents the analysis over different aspects that proven to be impactful to analyze the temporal trends in the current situation along with the exploration of deceased cases due to coronavirus. Analysis delineates key points in the outbreak spreading, indicating that the models driven by machine intelligence and deep learning can be effective in providing a quantitative view of the epidemical outbreak.

BACKGROUND Investigating molecular biomarkers that accurately predict prognosis is of considerable clinical significance. Accumulating evidence suggests that long non-coding ribonucleic acids (lncRNAs) are frequently aberrantly expressed in colorectal cancer (CRC). AIM To elucidate the prognostic function of multiple lncRNAs serving as biomarkers in CRC. METHODS We performed lncRNA expression profiling using the lncRNA mining approach in large CRC cohorts from The Cancer Genome Atlas (TCGA) database. Receiver operating characteristic analysis was performed to identify the optimal cutoff point at which patients could be classified into the high-risk or low-risk groups. Based on the Cox coefficient of the individual lncRNAs, we identified a nine-lncRNA signature that was associated with the survival of CRC patients in the training set (n = 175). The prognostic value of this nine-lncRNA signature was validated in the testing set (n = 174) and TCGA set (n = 349). The prognostic models, consisting of these nine CRC-specific lncRNAs, performed well for risk stratification in the testing set and TCGA set. Time-dependent receiver operating characteristic analysis indicated that this predictive model had good performance. RESULTS Multivariate Cox regression and stratification analysis demonstrated that this nine-lncRNA signature was independent of other clinical features in predicting overall survival. Functional enrichment analysis of Kyoto Encyclopedia of Genes and Genomes pathways and Gene Ontology terms further indicated that these nine prognostic lncRNAs were closely associated with carcinogenesis-associated pathways and biological functions in CRC. CONCLUSION A nine-lncRNA expression signature was identified and validated that could improve the prognosis prediction of CRC, thereby providing potential prognostic biomarkers and efficient therapeutic targets for patients with CRC.

Highlights • Machine learning models might be a better analytic approach in cervical cancer prognostic prediction than traditional methods. • Our models can provide multitask predictions, which can estimate the individual probability of overall survival, overall recurrence, and site-specific recurrence as well as RFS and OS times at the same time. • A web-based calculator was developed and externally validated to predict prognosis for cervical cancer., Background Machine learning (ML) has been gradually integrated into oncologic research but seldom applied to predict cervical cancer (CC), and no model has been reported to predict survival and site-specific recurrence simultaneously. Thus, we aimed to develop ML models to predict survival and site-specific recurrence in CC and to guide individual surveillance. Methods We retrospectively collected data on CC patients from 2006 to 2017 in four hospitals. The survival or recurrence predictive value of the variables was analyzed using multivariate Cox, principal component, and K-means clustering analyses. The predictive performances of eight ML models were compared with logistic or Cox models. A novel web-based predictive calculator was developed based on the ML algorithms. Results This study included 5112 women for analysis (268 deaths, 343 recurrences): (1) For site-specific recurrence, larger tumor size was associated with local recurrence, while positive lymph nodes were associated with distant recurrence. (2) The ML models exhibited better prognostic predictive performance than traditional models. (3) The ML models were superior to traditional models when multiple variables were used. (4) A novel predictive web-based calculator was developed and externally validated to predict survival and site-specific recurrence. Conclusion ML models might be a better analytic approach in CC prognostic prediction than traditional models as they can predict survival and site-specific recurrence simultaneously, especially when using multiple variables. Moreover, our novel web-based calculator may provide clinicians with useful information and help them make individual postoperative follow-up plans and further treatment strategies.

Background & Aims Acute-on-chronic liver failure (ACLF) is usually associated with a precipitating event and results in the failure of other organ systems and high short-term mortality. Current prediction models fail to adequately estimate prognosis and need for liver transplantation (LT) in ACLF. This study develops and validates a dynamic prediction model for patients with ACLF that uses both longitudinal and survival data. Methods Adult patients on the UNOS waitlist for LT between 11.01.2016-31.12.2019 were included. Repeated model for end-stage liver disease-sodium (MELD-Na) measurements were jointly modelled with Cox survival analysis to develop the ACLF joint model (ACLF-JM). Model validation was carried out using separate testing data with area under curve (AUC) and prediction errors. An online ACLF-JM tool was created for clinical application. Results In total, 30,533 patients were included. ACLF grade 1 to 3 was present in 16.4%, 10.4% and 6.2% of patients, respectively. The ACLF-JM predicted survival significantly (p, Graphical abstract, Highlights • ACLF is a dynamic disease that can rapidly change over time, which greatly influences patient survival without LT. • Currently, the MELD-Na score is used to prioritize patients for LT, but MELD-Na underestimates ACLF disease severity. • The ACLF joint model (ACLF-JM) was developed to dynamically predict survival. • The ACLF-JM significantly outperformed the MELD-Na score for the prediction of mortality on the LT waiting list. • The ACLF-JM can be used online to predict survival in individual patients.

Background Artificial intelligence (AI) typically requires a significant amount of high-quality data to build reliable models, where gathering enough data within a single institution can be particularly challenging. In this study we investigated the impact of using sequential learning to exploit very small, siloed sets of clinical and imaging data to train AI models. Furthermore, we evaluated the capacity of such models to achieve equivalent performance when compared to models trained with the same data over a single centralized database. Methods We propose a privacy preserving distributed learning framework, learning sequentially from each dataset. The framework is applied to three machine learning algorithms: Logistic Regression, Support Vector Machines (SVM), and Perceptron. The models were evaluated using four open-source datasets (Breast cancer, Indian liver, NSCLC-Radiomics dataset, and Stage III NSCLC). Findings The proposed framework ensured a comparable predictive performance against a centralized learning approach. Pairwise DeLong tests showed no significant difference between the compared pairs for each dataset. Interpretation Distributed learning contributes to preserve medical data privacy. We foresee this technology will increase the number of collaborative opportunities to develop robust AI, becoming the default solution in scenarios where collecting enough data from a single reliable source is logistically impossible. Distributed sequential learning provides privacy persevering means for institutions with small but clinically valuable datasets to collaboratively train predictive AI while preserving the privacy of their patients. Such models perform similarly to models that are built on a larger central dataset.

Background Kidney transplantation is the optimal treatment for patients with end-stage renal disease. Short- and long-term kidney graft survival is influenced by a number of donor and recipient factors. Predicting the success of kidney transplantation is important for optimizing kidney allocation. Objective The aim of this study was to predict the risk of kidney graft failure across three temporal cohorts (within 1 year, within 5 years, and after 5 years following a transplant) based on donor and recipient characteristics. We analyzed a large data set comprising over 50,000 kidney transplants covering an approximate 20-year period. Methods We applied machine learning–based classification algorithms to develop prediction models for the risk of graft failure for three different temporal cohorts. Deep learning–based autoencoders were applied for data dimensionality reduction, which improved the prediction performance. The influence of features on graft survival for each cohort was studied by investigating a new nonoverlapping patient stratification approach. Results Our models predicted graft survival with area under the curve scores of 82% within 1 year, 69% within 5 years, and 81% within 17 years. The feature importance analysis elucidated the varying influence of clinical features on graft survival across the three different temporal cohorts. Conclusions In this study, we applied machine learning to develop risk prediction models for graft failure that demonstrated a high level of prediction performance. Acknowledging that these models performed better than those reported in the literature for existing risk prediction tools, future studies will focus on how best to incorporate these prediction models into clinical care algorithms to optimize the long-term health of kidney recipients.

Background: The Cox proportional hazards (CPH) model is the most commonly used statistical method for nasopharyngeal carcinoma (NPC) prognostication. Recently, machine learning (ML) models are increasingly adopted for this purpose. However, only a few studies have compared the performances between CPH and ML models. This study aimed at comparing CPH with two state-of-the-art ML algorithms, namely, conditional survival forest (CSF) and DeepSurv for disease progression prediction in NPC. Methods: From January 2010 to March 2013, 412 eligible NPC patients were reviewed. The entire dataset was split into training cohort and testing cohort in a ratio of 90%:10%. Ten features from patient-related, disease-related, and treatment-related data were used to train the models for progression-free survival (PFS) prediction. The model performance was compared using the concordance index (c-index), Brier score, and log-rank test based on the risk stratification results. Results: DeepSurv (c-index = 0.68, Brier score = 0.13, log-rank test p = 0.02) achieved the best performance compared to CSF (c-index = 0.63, Brier score = 0.14, log-rank test p = 0.38) and CPH (c-index = 0.57, Brier score = 0.15, log-rank test p = 0.81). Conclusions: Both CSF and DeepSurv outperformed CPH in our relatively small dataset. ML-based survival prediction may guide physicians in choosing the most suitable treatment strategy for NPC patients.

Simple Summary Exosomes, carrying small non-coding RNA (miRNA), are known to play a pivotal role in the process of tumor progression. In this prospective study, we identified miR-16, miR-146a, miR-192, and miR- 221 to be significantly deregulated in the plasma of patients with hepatocellular carcinoma (HCC) compared to patients with liver cirrhosis and healthy individuals. MiR-146a revealed diagnostic potential to differentiate HCC patients from liver cirrhosis patients with a sensitivity of 81% and a specificity of 58% in logistic regression model. Furthermore, miR- 192 independently correlated with overall survival in patients with HCC. Abstract We aimed to identify a specific microRNA (miRNA) pattern to determine diagnostic and prognostic value in plasma exosomes of hepatocellular carcinoma (HCC) patients. A two-stage study was carried out: exosomal miRNAs were quantified in plasma of HCC patients and healthy individuals by PCR-based microarray cards containing 45 different miRNAs (training cohort). Then, four deregulated miRNAs (miR-16, miR-146a, miR-192, and miR-221) were quantified in the validation analysis using exosomes derived from 85 HCC patients, 50 liver cirrhosis patients, and 20 healthy individuals. Exosomal miR-146a (p = 0.0001), miR-192 (p = 0.002) and miR-221 (p = 0.032) were upregulated only in HCC patients. Repeated 10-fold cross validation showed that miR-146a differentiated HCC from liver cirrhosis patients with AUC of 0.80 ± 0.14 (sensitivity: 81 ± 13%, specificity: 58 ± 22%) in a logistic regression model. High miR-192 presence is associated with poor overall survival (OS) in all HCC patients (p = 0.027) and was predictor of OS in HCC patients in an uni- and multivariate Cox regression model. Moreover, decreased miR-16 levels correlated with OS in liver cirrhosis patients (p = 0.034). Our results emphasized that exosomes secreted into the plasma carry differentially expressed miRNAs of which in particular, miR-192, miR-146, and miR-16 are promising diagnostic and prognostic markers for both HCC and liver cirrhosis patients.

Several scoring systems have been devised to objectively predict survival for patients with intrahepatic cholangiocellular carcinoma (ICC) and support treatment stratification, but they have failed external validation. The aim of the present study was to improve prognostication using an artificial intelligence-based approach. We retrospectively identified 417 patients with ICC who were referred to our tertiary care center between 1997 and 2018. Of these, 293 met the inclusion criteria. Established risk factors served as input nodes for an artificial neural network (ANN). We compared the performance of the trained model to the most widely used conventional scoring system, the Fudan score. Predicting 1-year survival, the ANN reached an area under the ROC curve (AUC) of 0.89 for the training set and 0.80 for the validation set. The AUC of the Fudan score was significantly lower in the validation set (0.77, p &lt, 0.001). In the training set, the Fudan score yielded a lower AUC (0.74) without reaching significance (p = 0.24). Thus, ANNs incorporating a multitude of known risk factors can outperform conventional risk scores, which typically consist of a limited number of parameters. In the future, such artificial intelligence-based approaches have the potential to improve treatment stratification when models trained on large multicenter data are openly available.

// Sebastien Rinaldetti 1 , Ralph Markus Wirtz 2 , Thomas Stefan Worst 3 , Markus Eckstein 4 , Cleo Aaron Weiss 5 , Johannes Breyer 6 , Wolfgang Otto 6 , Christian Bolenz 7 , Arndt Hartmann 4 and Philipp Erben 3 1 Department of Hematology and Oncology, University Medical Center Mannheim, Medical Faculty Mannheim, University of Heidelberg, 68167 Mannheim, Germany 2 Stratifyer Molecular Pathology GmbH, 50935 Koln, Germany 3 Department of Urology, University Medical Center Mannheim, Medical Faculty Mannheim, University of Heidelberg, 68167 Mannheim, Germany 4 Institute of Pathology, University Erlangen-Nuremberg, 91054 Erlangen, Germany 5 Institute of Pathology, University Medical Center Mannheim, Medical Faculty Mannheim, University of Heidelberg, 68167 Mannheim, Germany 6 Department of Urology, University of Regensburg, 93053 Regensburg, Germany 7 Department of Urology, University of Ulm, 89075 Ulm, Germany Correspondence to: Sebastien Rinaldetti, email: sebastienrinal@hotmail.com Keywords: FOXM1, muscle invasive bladder cancer, KI67, subclassification, survival prediction Received: December 28, 2016 Accepted: April 10, 2017 Published: April 24, 2017 ABSTRACT Forkhead box M1 (FOXM1) is a late cell cycle gene that plays a crucial role in carcinogenesis and chemotherapeutic drug resistance. In this study, the impact of FOXM1 expression on patient outcome was investigated for the first time in formalin fixed and paraffin embedded (FFPE) samples of chemotherapy naive muscle-invasive bladder cancer (MIBC) patients. Expression analyses were performed on the Mannheim cohort (n=84) and validated on the independent Chungbuk cohort (n=61). In a Cox’ proportional hazards model, a distinct FOXM1 expression cut-off dividing both cohorts in a ‘high-risk’ and ‘low-risk’ group has been determined. Multivariate analyses showed that FOXM1 is an independent risk factor for outcome prediction superior to the TNM system. The FOXM1 ‘high-risk’ group had a 4- to 7-fold increased risk of death (p

// Zaixiang Tang 1, 2, 3, 4 , Qinghua Zeng 5 , Yan Li 4 , Xinyan Zhang 4 , Jinlu Ma 5, 6 , Mark J. Suto 5 , Bo Xu 5 , Nengjun Yi 4 1 Department of Biostatistics, School of Public Health, Medical College of Soochow University, Suzhou 215123, China 2 Jiangsu Key Laboratory of Preventive and Translational Medicine for Geriatric Diseases, Medical College of Soochow University, Suzhou, 215123, China 3 Center for Genetic Epidemiology and Genomics, Medical College of Soochow University, Suzhou, 215123, China 4 Department of Biostatistics, University of Alabama at Birmingham, Birmingham, AL 35294, USA 5 Drug Discovery Division, Southern Research Institute, Birmingham, AL 35294, USA 6 Department of Radiation Oncology, The First Hospital, Xi’an Jiaotong University, Xi’an, Shanxi, 710061, China Correspondence to: Nengjun Yi, email: nyi@uab.edu Bo Xu, email: bxu@southernresearch.org , bxu@uab.edu Keywords: gene signature, radio-sensitivity, radiotherapy, survival prediction, sarcoma Received: September 27, 2016 Accepted: January 24, 2017 Published: March 15, 2017 ABSTRACT Adjuvant radiotherapy is an important clinical treatment option for the majority of sarcomas. The motivation of current study is to identify a gene signature and to predict radiosensitive patients who are most likely to benefit from radiotherapy. Using the public available data of soft tissue sarcoma from The Cancer Genome Atlas, we developed a cross-validation procedure for identifying a gene signature and predicting radiosensitive patients through. The result showed that the predicted radiosensitive patients who received radiotherapy had a significantly better survival with a reduced rate of new tumor event and disease progression. Strata analysis showed that the predicted radiosensitive patients had significantly better survival under radiotherapy independent of histologic types. A hierarchical cluster analysis was used to validate the gene signature, and the results showed the predicted sensitivity for each patient well matched the results from cluster analysis. Together, we demonstrate a radiosensitive molecular signature that can be potentially used for identifying radiosensitive patients with sarcoma.

Intrahepatic cholangiocarcinoma (ICC) remains a highly heterogeneous disease with poor prognosis. Tumor‐infiltrating lymphocytes were predictive in various cancers, but their prognostic value in ICC is less clear. A total of 168 ICC patients who had received liver resection were enrolled and assigned to the derivation cohort. Sixteen immune markers in tumor and peritumor regions were examined by immunohistochemistry. A least absolute shrinkage and selection operator model was used to identify prognostic markers and to establish an immune signature for ICC (ISICC). An ISICC‐applied prediction model was built and validated in another independent dataset. Five immune features, including CD3peritumor (P), CD57P, CD45RAP, CD66bintratumoral (T) and PD‐L1P, were identified and integrated into an individualized ISICC for each patient. Seven prognostic predictors, including total bilirubin, tumor numbers, CEA, CA19‐9, GGT, HBsAg and ISICC, were integrated into the final model. The C‐index of the ISICC‐applied prediction model was 0.719 (95% CI, 0.660‐0.777) in the derivation cohort and 0.667 (95% CI, 0.581‐0.732) in the validation cohort. Compared with the conventional staging systems, the new model presented better homogeneity and a lower Akaike information criteria value in ICC. The ISICC‐applied prediction model may provide a better prediction performance for the overall survival of patients with resectable ICC in clinical practice., Using tissue microarray, we examined the density of 16 immune biomarkers in 280 ICC patients who underwent hepatectomy, and established a novel ISICC‐based prediction model (IPM) to predict patients’ overall survival with bilirubin, tumor numbers, CEA, CA19‐9, γ‐glutamyl transferase (GGT), HBsAg and ISICC. The new model may provide a better prediction performance for the overall survival of patients with resectable ICC in clinical practice.

Accurate segmentation of different sub-regions of gliomas such as peritumoral edema, necrotic core, enhancing, and non-enhancing tumor core from multimodal MRI scans has important clinical relevance in diagnosis, prognosis and treatment of brain tumors. However, due to the highly heterogeneous appearance and shape of these tumors, segmentation of the sub-regions is challenging. Recent developments using deep learning models has proved its effectiveness in various semantic and medical image segmentation tasks, many of which are based on the U-Net network structure with symmetric encoding and decoding paths for end-to-end segmentation due to its high efficiency and good performance. In brain tumor segmentation, the 3D nature of multimodal MRI poses challenges such as memory and computation limitations and class imbalance when directly adopting the U-Net structure. In this study we aim to develop a deep learning model using a 3D U-Net with adaptations in the training and testing strategies, network structures, and model parameters for brain tumor segmentation. Furthermore, instead of picking one best model, an ensemble of multiple models trained with different hyper-parameters are used to reduce random errors from each model and yield improved performance. Preliminary results demonstrate the effectiveness of this method and achieved the 9th place in the very competitive 2018 Multimodal Brain Tumor Segmentation (BraTS) challenge. In addition, to emphasize the clinical value of the developed segmentation method, a linear model based on the radiomics features extracted from segmentation and other clinical features are developed to predict patient overall survival. Evaluation of these innovations shows high prediction accuracy in both low-grade glioma and glioblastoma patients, which achieved the 1st place in the 2018 BraTS challenge.

Background The analysis of integrated multi-omics data enables the identification of disease-related biomarkers that cannot be identified from a single omics profile. Although protein-level data reflects the cellular status of cancer tissue more directly than gene-level data, past studies have mainly focused on multi-omics integration using gene-level data as opposed to protein-level data. However, the use of protein-level data (such as mass spectrometry) in multi-omics integration has some limitations. For example, the correlation between the characteristics of gene-level data (such as mRNA) and protein-level data is weak, and it is difficult to detect low-abundance signaling proteins that are used to target cancer. The reverse phase protein array (RPPA) is a highly sensitive antibody-based quantification method for signaling proteins. However, the number of protein features in RPPA data is extremely low compared to the number of gene features in gene-level data. In this study, we present a new method for integrating RPPA profiles with RNA-Seq and DNA methylation profiles for survival prediction based on the integrative directed random walk (iDRW) framework proposed in our previous study. In the iDRW framework, each omics profile is merged into a single pathway profile that reflects the topological information of the pathway. In order to address the sparsity of RPPA profiles, we employ the random walk with restart (RWR) approach on the pathway network. Results Our model was validated using survival prediction analysis for a breast cancer dataset from The Cancer Genome Atlas. Our proposed model exhibited improved performance compared with other methods that utilize pathway information and also out-performed models that did not include the RPPA data utilized in our study. The risk pathways identified for breast cancer in this study were closely related to well-known breast cancer risk pathways. Conclusions Our results indicated that RPPA data is useful for survival prediction for breast cancer patients under our framework. We also observed that iDRW effectively integrates RNA-Seq, DNA methylation, and RPPA profiles, while variation in the composition of the omics data can affect both prediction performance and risk pathway identification. These results suggest that omics data composition is a critical parameter for iDRW. Electronic supplementary material The online version of this article (10.1186/s12920-019-0511-x) contains supplementary material, which is available to authorized users.

Background Although palliative care has been accepted throughout the cancer trajectory, accurate survival prediction for advanced cancer patients is still a challenge. The aim of this study is to identify pre-palliative care predictors and develop a prognostic nomogram for overall survival (OS) in mixed advanced cancer patients. Methods A total of 378 consecutive advanced cancer patients were retrospectively recruited from July 2013 to October 2015 in one palliative care unit in China. Twenty-three clinical and laboratory characters were collected for analysis. Prognostic factors were identified to construct a nomogram in a training cohort (n = 247) and validated in a testing cohort (n = 131) from the setting. Results The median survival time was 48.0 (95% CI: 38.1–57.9) days for the training cohort and 52.0 (95% CI: 34.6–69.3) days for the validation cohort. Among pre-palliative care factors, sex, age, tumor stage, Karnofsky performance status, neutrophil count, hemoglobin, lactate dehydrogenase, albumin, uric acid, and cystatin-C were identified as independent prognostic factors for OS. Based on the 10 factors, an easily obtained nomogram predicting 90-day probability of mortality was developed. The predictive nomogram had good discrimination and calibration, with a high C-index of 0.76 (95% CI: 0.73–0.80) in the development set. The strong discriminative ability was externally conformed in the validation cohort with a C-index of 0.75. Conclusions A validated prognostic nomogram has been developed to quantify the risk of mortality for advanced cancer patients undergoing palliative care. This tool may be useful in optimizing therapeutic approaches and preparing for clinical courses individually. Electronic supplementary material The online version of this article (10.1186/s12904-019-0432-7) contains supplementary material, which is available to authorized users.

Survival prediction systems are used among emergency services at hospitals in order to measure their quality objectively. In order to do so, the estimated mortality rate given by a prediction model is compared with the real rate of the hospital. Hence, the accuracy of the prediction system is a key factor as more reliable estimations can be obtained. Survival prediction systems are aimed at scoring the severity of patients' injuries. Afterward, this score is used to estimate whether the patient will survive or not. Luckily, the number of patients who survive their injuries is greater than that of those who die. However, this degree of imbalance implies a greater difficulty in learning the prediction models. The aim of this paper is to develop a new prediction system for the Hospital of Navarre with the goal of improving the prediction capabilities of the currently used models since it would imply having a more reliable measurement of its quality. In order to do so, we propose a new strategy to conform an ensemble of classifiers using an evolutionary under sampling process in the bagging methodology. The experimental study is carried out over 462 patients who were treated at the Hospital of Navarre. Our new ensemble approach is an appropriate tool to deal with this problem as it is able to outperform the currently used models by the staff of the hospital as well as several state-of-the-art ensemble approaches designed for imbalanced domains. This work was supported in part by the Spanish Ministry of Science and Technology under Project TIN2016-77356-P (AEI/FEDER, UE), in part by the Network Project under Grant TIN2014-56381-REDT, and in part by the Health Department of the Government of Navarre under Project PI-019/11.

Purpose: The aim of this study was to develop radiomics-based machine learning models based on extracted radiomic features and clinical information to predict the risk of death within 5 years for prognosis of clear cell renal cell carcinoma (ccRCC) patients.Methods: According to image quality and clinical data availability, we eventually selected 70 ccRCC patients that underwent CT scans. Manual volume-of-interest (VOI) segmentation of each image was performed by an experienced radiologist using the 3D slicer software package. Prior to feature extraction, image pre-processing was performed on CT images to extract different image features, including wavelet, Laplacian of Gaussian, and resampling of the intensity values to 32, 64 and 128 bin levels. Overall, 2544 3D radiomics features were extracted from each VOI for each patient. Minimum Redundancy Maximum Relevance (MRMR) algorithm was used as feature selector. Four classification algorithms were used, including Generalized Linear Model (GLM), Support Vector Machine (SVM), K-nearest Neighbor (KNN) and XGBoost. We used the Bootstrap resampling method to create validation sets. Area under the receiver operating characteristic (ROC) curve (AUROC), accuracy, sensitivity, and specificity were used to assess the performance of the classification models.Results: The best single performance among 8 different models was achieved by the XGBoost model using a combination of radiomic features and clinical information (AUROC, accuracy, sensitivity, and specificity with 95% confidence interval were 0.95-0.98, 0.93-0.98, 0.93-0.96 and similar to 1.0, respectively).Conclusions: We developed a robust radiomics-based classifier that is capable of accurately predicting overall survival of RCC patients for prognosis of ccRCC patients. This signature may help identifying high-risk patients who require additional treatment and follow up regimens.