Prognostic Outcome Prediction Research Articles

Exploration of a noninvasive radiomics classifier for breast cancer tumor microenvironment categorization and prognostic outcome prediction

Rationale and Objectives: Breast cancer progression and treatment response are significantly influenced by the tumor microenvironment (TME). Traditional methods for assessing TME are invasive, posing a challenge for patient care. This study introduces a non-invasive approach to TME classification by integrating radiomics and machine learning, aiming to predict the TME status using imaging data, thereby aiding in prognostic outcome prediction. Materials and MethodsUtilizing multi-omics data from The Cancer Genome Atlas (TCGA) and The Cancer Imaging Archive (TCIA), this study employed CIBERSORT and MCP-counter algorithms analyze immune infiltration in breast cancer. A radiomics classifier was developed using a random forest algorithm, leveraging quantitative features extracted from intratumoral and peritumoral regions of Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) scans. The classifer’s ability to predict diverse TME states were and their prognostic implications were evaluated using Kaplan-Meier survival curves. ResultsThree distinct TME states were identified using RNA-Seq data, each displaying unique prognostic and biological characteristics. Notably, patients with increased immune cell infiltration showed significantly improved prognoses (P < 0.05). The classifier, comprising 24 radiomic features, demonstrated high predictive accuracy (AUC of training set = 0.960, 95 % CI: 0.922, 0.997; AUC of testing set = 0.853, 95 % CI: 0.687, 1.000) in differentiating these TME states. Predictions from the classifier also correlated significantly with overall patient survival (P < 0.05). ConclusionThis study offers a detailed analysis of the complex TME states in breast cancer and presents a reliable, noninvasive radiomics classifier for TME assessment. The classifer’s accurate prediction of TME status and its correlation with prognosis highlight its potential as a tool in personalized breast cancer treatment, paving the way for more individualized and less invasive therapeutic strategies.

Recent advancements in 18F-FDG PET/CT for the diagnosis, staging, and treatment management of HIV-related lymphoma.

Infection with the Human Immunodeficiency Virus (HIV) is one of the most pressing issues facing public health on a worldwide scale. Currently, HIV-related lymphoma is the most common cause of death among people living with HIV, and warrants more attention. The unique challenges associated with HIV-related lymphoma management derive from the underlying HIV infection and its immunosuppressive effects. 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) has gained significant prominence in the past few years as a valuable diagnostic and therapeutic instrument for the treatment of HIV-related lymphoma. This review will start with an overview of the subtypes, risk factors, and therapeutic choices for individuals with HIV-related lymphoma. We will then briefly discuss the current application of 18F-FDG PET/CT in the medical management of HIV-related lymphoma patients, followed by the initial staging of the disease, the evaluation of therapeutic response, the prediction of prognostic outcomes, the decision-making process for radiotherapy guided by PET findings, and the distinguishing of various diagnoses.

Attention-based generative adversarial networks improve prognostic outcome prediction of cancer from multimodal data.

The prediction of prognostic outcome is critical for the development of efficient cancer therapeutics and potential personalized medicine. However, due to the heterogeneity and diversity of multimodal data of cancer, data integration and feature selection remain a challenge for prognostic outcome prediction. We proposed a deep learning method with generative adversarial network based on sequential channel-spatial attention modules (CSAM-GAN), a multimodal data integration and feature selection approach, for accomplishing prognostic stratification tasks in cancer. Sequential channel-spatial attention modules equipped with an encoder-decoder are applied for the input features of multimodal data to accurately refine selected features. A discriminator network was proposed to make the generator and discriminator learning in an adversarial way to accurately describe the complex heterogeneous information of multiple modal data. We conducted extensive experiments with various feature selection and classification methods and confirmed that the CSAM-GAN via the multilayer deep neural network (DNN) classifier outperformed these baseline methods on two different multimodal data sets with miRNA expression, mRNA expression and histopathological image data: lower-grade glioma and kidney renal clear cell carcinoma. The CSAM-GAN via the multilayer DNN classifier bridges the gap between heterogenous multimodal data and prognostic outcome prediction.

Prognostic significance of controlling nutritional status score for patients with gastric cancer: A systematic review and meta‑analysis.

There is a need to identify potentially useful biomarker(s) for the prediction of prognostic outcomes in patients diagnosed with gastric cancer. This meta-analysis provided updated evidence on the association of controlling nutritional status (CONUT) score with survival and other clinicopathological outcomes in patients with gastric cancer. PubMed and Scopus databases were systematically searched. The review included studies, observational in design, that were conducted among patients with gastric cancer and had documented the association of CONUT score with outcomes of interest. The primary outcomes of interest were overall survival (OS), cancer-specific survival (CSS) and recurrence-free survival (RFS) along with tumour size and extent (T status), nodal status (N status) and tumour staging (TNM staging). STATA was used for statistical analysis. The meta-analysis was conducted with 17 studies. The 5-year OS [hazard ratio (HR), 1.75; 95% confidence interval (CI): 1.55, 1.96], RFS (HR, 1.58; 95% CI: 1.30, 1.91) and CSS (HR, 1.89; 95% CI: 1.01, 3.52) were comparatively poorer in the high CONUT group, than in low CONUT group. High CONUT score was associated with increased risk of having T3/T4 tumour [odds ratio (OR), 1.64; 95% CI: 1.16, 2.34], N2/N3 nodal status (OR, 1.44; 95% CI: 1.17, 1.77) and stage III/IV tumour (OR, 1.64; 95% CI: 1.43, 1.88). The risk of microvascular invasion (OR, 1.46; 95% CI: 1.20, 1.77) and post-operative complications (OR, 1.64; 95% CI: 1.31, 2.06) was higher in those with high CONUT. There were no differences in the risk of poorly differentiated tumour and need for adjuvant chemotherapy between the two groups. Findings suggested that preoperative assessment of CONUT score may be included in the routine assessment of patients with gastric cancer due to its association with survival and other clinical as well as pathological outcomes.

Vesicle-mediated transport-related genes are prognostic predictors and are associated with tumor immunity in lung adenocarcinoma.

Globally, lung adenocarcinoma (LUAD) is the leading cause of cancer-related deaths. It is a progressive disorder that arises from multiple genetic and environmental factors. Dysregulated expression of vesicle-mediated transport-related genes (VMTRGs) have been reported in several cancers. However, the prognostic significance of VMTRGs in LUAD has yet to be established. The VMTRG profiling data for 482 LUAD patients and 59 normal controls were downloaded from The Cancer Genome Altas (TCGA). Univariate Cox regression and Least Absolute Shrinkage and Selection Operator (LASSO) regression analyses were performed to construct and optimize the risk model. Several GEO datasets were used to validate the risk model. The roles of these genes were investigated via the Kyoto Encyclopedia of Genes and Genomes (KEGG) and gene ontology (GO) enrichment analyses. Differences in immune cell infiltrations between risk groups were evaluated using five algorithms. "pRRophetic" was used to investigate anti-cancer drug sensitivities in two groups. Expression of these five genes in LUAD samples and adjacent normal tissues were evaluated by qRT-PCR. Colony formation and wound healing assays were performed to assess the significance of CNIH1 and AP3S1 in LUAD cells. We identified 85 prognosis-associated VMTRGs that could be constructed a risk model for LUAD patients, indicating their potential importance in LUAD development. The risk model including the five VMTRGs (CNIH1, KIF20A, GALNT2, GRIA1, and AP3S1) was associated with clinical outcomes. Tumor stage and risk score were found to be independent prognostic factors for LUAD patients. The five VMTRGs were also correlated with activation of the Notch and p53 signaling pathways. The risk model was significantly associated with immune responses and with high-level expression of immune checkpoints. High-risk group patients were more sensitive to several chemotherapeutic drugs and Lapatinib. Furthermore, CNIH1 and AP3S1 promoted LUAD cell growth and migration in vitro. We constructed a VMTRG-based risk model for effective prediction of prognostic outcomes for LUAD patients. The risk model was associated with immune infiltration levels. These five hub genes are potential targets for immune therapy combined with chemotherapy in LUAD.

Infarct and Penumbra Growth Rate usage in Machine Learning Model Improves Prognostic Outcome Prediction in Acute Ischemic Stroke (4127)

Infarct and Penumbra Growth Rate usage in Machine Learning Model Improves Prognostic Outcome Prediction in Acute Ischemic Stroke (4127)

PO-1764: Prognostic outcome prediction for head and neck cancer patients using convolutional neural networks

PO-1764: Prognostic outcome prediction for head and neck cancer patients using convolutional neural networks

Prognostic outcome prediction by semi-supervised least squares classification

Although great progress has been made in prognostic outcome prediction, small sample size remains a challenge in obtaining accurate and robust classifiers. We proposed the Rescaled linear square Regression based Least Squares Learning (RRLSL), a jointly developed semi-supervised feature selection and classifier, for predicting prognostic outcome of cancer patients. RRLSL used the least square regression to identify the scale factors and then rank the features in available multiple types of molecular data. We applied the unlabeled multiple molecular data in conjunction with the labeled data to develop a similarity graph. RRLSL produced the constraint with kernel functions to bridge the gap between label information and geometry information from messenger RNA and microRNA expression profiling. Importantly, this semi-supervised model proposed the least squares learning with L2 regularization to develop a semi-supervised classifier. RRLSL suggested the performance improvement in the prognostic outcome prediction and successfully discriminated between the recurrent patients and non-recurrent ones. We also demonstrated that RRLSL improved the accuracy and Area Under the Precision Recall Curve (AUPRC) as compared to the baseline semi-supervised methods. RRLSL is available for a stand-alone software package (https://github.com/ShiMGLab/RRLSL). A short abstract We proposed the Rescaled linear square Regression based Least Squares Learning (RRLSL), a jointly developed semi-supervised feature selection and classifier, for predicting prognostic outcome of cancer patients. RRLSL used the least square regression to identify the scale factors to rank the features in available multiple types of molecular data. RRLSL produced the constraint with kernel functions to bridge the gap between label information and geometry information from messenger RNA and microRNA expression profiling. Importantly, this semi-supervised model proposed the least squares learning with L2 regularization to develop the semi-supervised classifier. RRLSL suggested the performance improvement in the prognostic outcome prediction and successfully discriminated between the recurrent patients and non-recurrent ones.

Potential of Neutrophil Lymphocyte Ratio as a Biomarker in Prediction of Prognostic Outcomes and Response to Neoadjuvant Therapy in Breast Cancer

Waldron, Michael G. MD; Moloney, Brian M. PHD; Waldron, Ronan M. MD; Kerin, Michael J. MD Author Information

Prognostic Value of the Preoperative Tumor Marker Index in Resected Pancreatic Ductal Adenocarcinoma: A Retrospective Single-Institution Study.

The prediction of prognostic outcomes can provide the most suitable strategy for patients with pancreatic ductal adenocarcinoma (PDAC). This study aimed to evaluate the clinical value of the preoperative tumor marker index (pre-TI) in predicting prognostic outcomes after resection for PDAC. For 183 patients who underwent pancreatic resection of PDAC, adjusted carbohydrate antigen 19-9 (CA19-9), carcinoembryonic antigen (CEA), pancreatic cancer-associated antigen-2 (DUpan-2), and s-pancreas-1 antigen (SPan-1) were retrospectively evaluated, and the positive number of these markers was scored as the pre-TI. A high pre-TI (≥ 2) was significantly associated with a larger tumor and lymph node metastases, and the patients with a high pre-TI had worse prognostic outcomes in terms of both relapse-free survival (RFS) (P < 0.0001, log-rank) and overall survival (OS) (P < 0.0001, Λlog-rank) than the patients with a low pre-TI. The pre-TI was one of the independent factors of a poor prognosis for RFS (hazard ratio [HR], 2.36; P < 0.0001) and OS (HR, 2.27; P < 0.0001). In addition, even for the patients with normal adjusted CA19-9 values (n = 74, 40.4%), those with the high pre-TI had a significantly poorer prognosis than those with a low pre-TI (RFS: P = 0.002, log-rank; OS: P = 0.031, log-rank). The pre-TI could be a potent predictive marker of prognostic outcomes for patients with resections for PDAC. Patients with a high pre-TI may need additional strategies to improve their prognosis.

Rationale and design of the REgistry of Fast Myocardial Perfusion Imaging with NExt generation SPECT (REFINE SPECT)

BackgroundWe aim to establish a multicenter registry collecting clinical, imaging, and follow-up data for patients who undergo myocardial perfusion imaging (MPI) with the latest generation SPECT scanners. MethodsREFINE SPECT (REgistry of Fast Myocardial Perfusion Imaging with NExt generation SPECT) uses a collaborative design with multicenter contribution of clinical data and images into a comprehensive clinical-imaging database. All images are processed by quantitative software. Over 290 individual imaging variables are automatically extracted from each image dataset and merged with clinical variables. In the prognostic cohort, patient follow-up is performed for major adverse cardiac events. In the diagnostic cohort (patients with correlating invasive angiography), angiography and revascularization results within 6 months are obtained. ResultsTo date, collected prognostic data include scans from 20,418 patients in 5 centers (57% male, 64.0 ± 12.1 years) who underwent exercise (48%) or pharmacologic stress (52%). Diagnostic data include 2079 patients in 9 centers (67% male, 64.7 ± 11.2 years) who underwent exercise (39%) or pharmacologic stress (61%). ConclusionThe REFINE SPECT registry will provide a resource for collaborative projects related to the latest generation SPECT-MPI. It will aid in the development of new artificial intelligence tools for automated diagnosis and prediction of prognostic outcomes.

MicroRNAs in acute myocardial infarction: Evident value as novel biomarkers?

Traditional circulating biomarkers play a fundamental role in the diagnosis and prognosis of acute myocardial infarction (AMI). However, they have several limitations. microRNAs (miRs), a class of RNA molecules that do not encode proteins, function directly at the RNA level by inhibiting the translation of messenger RNAs. Due to their significant roles in disease development, they can be used as biomarkers. Accumulating evidence has revealed an attractive role of miRs as biomarkers of AMI and its associated symptoms, including vulnerable atherosclerotic plaques, and their role in disease diagnosis, platelet activation monitoring, and prognostic outcome prediction. This manuscript will highlight the recent updates regarding the involvement of miRs as biomarkers in AMI and emphasize their value in vulnerable atherosclerotic plaque prediction and monitoring of platelet activation.

Utility of Neutrophil Lymphocyte Ratio as a Biomarker in Prediction of Prognostic Outcomes in Large-Bowel Malignancy

Waldron, Ronan M. MBBCH, BAO; Kelly, Michael E.; Moloney, Brian M. MB MCh; Joyce, Myles R.; Kerin, Michael J. Author Information

Abstract PR147

Background & Objectives: Predicting long-term neurological outcomes after severe traumatic brain (TBI) is important, but which prognostic model has the best performance remains uncertain. Materials & Methods: This retrospective cohort study included all patients who had severe TBI requiring decompressive craniectomy, between 2004 and 2014, in two neurosurgical centres in Western Australia. Severe disability requiring help with daily living, vegetative state, or death were defined as unfavourable neurological outcomes. Area under the receiver-operating-characteristic curve (AUROC) and slope and intercept of the calibration curve were used to assess discrimination and calibration.of the CRASH (Corticosteroid-Randomisation-After-Significant-Head injury) and IMPACT (International-Mission-For-Prognosis-And-Clinical-Trial) models, respectively. Results: Of the 319 patients included in the study, 118 (37%) had unfavourable neurological outcomes at 18-month after decompressive craniectomy for severe TBI. Both CRASH (AUROC 0.86, 95% confidence interval 0.81–0.90) and IMPACT (AUROC 0.85, 95%CI 0.80–0.89) models were similarly good in discriminating between favourable and unfavourable neurological outcome at 18-month after surgery (p=0.690 for the difference in AUROC derived from the two models). Although both models tended to over-predict the risks of long-term unfavourable outcome, the IMPACT model had a slightly better calibration than the CRASH model (intercept of the calibration curve = -4.1 vs. -5.7, respectively), especially when the predicted risks of unfavourable outcome were <80%. Conclusion: Both CRASH and IMPACT prognostic models were good in discriminating between favourable and unfavourable long-term neurological outcome for patients with severe TBI requiring decompressive craniectomy, but the calibration of the IMPACT full-model was better than the CRASH model. These results suggest that both prognostic models can be used for risk adjustments in randomised controlled trials but the better calibration of the IMPACT model makes it as the preferred model for risk adjustment in observational studies and in providing objective prognostic outcome prediction. Disclosure of Interest: None declared

Overexpression of TG-Interacting Factor Is Associated with Worse Prognosis in Upper Urinary Tract Urothelial Carcinoma

Prognostic outcome prediction would be useful for the treatment of patients with upper urinary tract urothelial carcinoma (UC). However, its prognostic biomarkers are not well established so far. According to the results of analysis of 168 human upper urinary tract UC specimens, overexpressed TG-interacting factor (TGIF) in nuclei of tumor tissues is significantly correlated with poor progression-free survival and higher cancer-related death. When both TGIF and p21 expression are altered, these patients had an even worse prognosis than those with one or no marker altered. Furthermore, to elucidate the role of TGIF in the progression of UC, overexpression of TGIF in RT4 or TSGH8301 cells was performed, and the results revealed that TGIF can significantly increase migration/invasion ability, matrix metalloproteinase expression, and invadopodia formation via the phosphatidylinositol 3-kinase-AKT pathway. In contrast, knockdown of TGIF with its specific short hairpin RNA inhibited the invasion ability of T24 cells. Besides, TGIF could inhibit p21(WAF/CIP1) expression, up-regulate cyclin D1 expression, and phosphorylate retinoblastoma to promote G1-S transition and cellular proliferation. In conclusion, we demonstrated that TGIF contributes to the progression of urothelial carcinoma via the phosphatidylinositol 3-kinase-AKT pathway. It may serve as an attractive therapeutic or prognostic target for selected patients with upper urinary tract UC.

Biomarkers for Cancer Diagnosis: Implications for Nutritional Research

The biology of disease progression is a complex process that involves multiple sequential steps leading to cellular changes and metabolic events. These molecular events, which may serve as potential biomarkers, can be analyzed by laboratory methods and used to detect a disease such as cancer or indicate the biological exposure to environmental substances including dietary intake. Identification of the genetic, molecular, and clinical events involved in the disease process enables the development of effective therapeutic and preventive measures and the prediction of prognostic outcomes. This article describes various factors that influence nutritional and cancer biomarker research, draws similarities between them, and discusses the measures that have been adapted to validate cancer biomarkers that can potentially be applied to nutritional biomarker research. Nutritional research suffers from a lack of means to quantify relationships between diet and cancer. Biomarkers of dietary intake or metabolism, therefore, could have potential application in study designs for establishing a causal relationship between diet and disease.