Clinical significance and molecular annotation of cellular morphometric subtypes in lower-grade gliomas discovered by machine learning

Artificial intelligence-empowered cellular morphometric risk score improves prognostic stratification of cutaneous squamous cell carcinoma

BACKGROUND

Risk stratification of cutaneous squamous cell carcinoma (cSCC) is essential for managing patients.

OBJECTIVES

To determine if artificial intelligence and machine learning might help to stratify patients with cSCC by risk using more than solely clinical and histopathological factors.

METHODS

We retrieved a retrospective cohort of 104 patients whose cSCCs had been excised with clear margins. Clinical and histopathological risk factors were evaluated. Haematoxylin and eosin-stained slides were scanned and analysed by an algorithm based on the stacked predictive sparse decomposition technique. Cellular morphometric biomarkers (CMBs) were identified via machine learning and used to derive a cellular morphometric risk score (CMRS) that classified cSCCs into clusters of differential prognoses. Concordance analysis, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and accuracy were calculated and compared with results obtained with the Brigham and Women's Hospital (BWH) staging system. The performance of the combination of the BWH staging system and the CMBs was also analysed.

RESULTS

There were no differences among the CMRS groups in terms of clinical and histopathological risk factors and T-stage assignment, but there were significant differences in prognosis. Combining the CMRS with BWH staging systems increased distinctiveness and improved prognostic performance. C-indices were 0.91 local recurrence and 0.91 for nodal metastasis when combining the two approaches. The NPV was 94.41% and 96.00%, the PPV was 36.36% and 41.67%, and accuracy reached 86.75% and 89.16%, respectively, with the combined approach.

CONCLUSIONS

CMRS is helpful for cSCC risk stratification beyond classic clinical and histopathological risk features. Combining the information from the CMRS and the BWH staging system offers outstanding prognostic performance for patients with high-risk cSCC.

Preliminary Evidence of the Use of Generative AI in Health Care Clinical Services: Systematic Narrative Review

BACKGROUND

Generative artificial intelligence tools and applications (GenAI) are being increasingly used in health care. Physicians, specialists, and other providers have started primarily using GenAI as an aid or tool to gather knowledge, provide information, train, or generate suggestive dialogue between physicians and patients or between physicians and patients' families or friends. However, unless the use of GenAI is oriented to be helpful in clinical service encounters that can improve the accuracy of diagnosis, treatment, and patient outcomes, the expected potential will not be achieved. As adoption continues, it is essential to validate the effectiveness of the infusion of GenAI as an intelligent technology in service encounters to understand the gap in actual clinical service use of GenAI.

OBJECTIVE

This study synthesizes preliminary evidence on how GenAI assists, guides, and automates clinical service rendering and encounters in health care The review scope was limited to articles published in peer-reviewed medical journals.

METHODS

We screened and selected 0.38% (161/42,459) of articles published between January 1, 2020, and May 31, 2023, identified from PubMed. We followed the protocols outlined in the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines to select highly relevant studies with at least 1 element on clinical use, evaluation, and validation to provide evidence of GenAI use in clinical services. The articles were classified based on their relevance to clinical service functions or activities using the descriptive and analytical information presented in the articles.

RESULTS

Of 161 articles, 141 (87.6%) reported using GenAI to assist services through knowledge access, collation, and filtering. GenAI was used for disease detection (19/161, 11.8%), diagnosis (14/161, 8.7%), and screening processes (12/161, 7.5%) in the areas of radiology (17/161, 10.6%), cardiology (12/161, 7.5%), gastrointestinal medicine (4/161, 2.5%), and diabetes (6/161, 3.7%). The literature synthesis in this study suggests that GenAI is mainly used for diagnostic processes, improvement of diagnosis accuracy, and screening and diagnostic purposes using knowledge access. Although this solves the problem of knowledge access and may improve diagnostic accuracy, it is oriented toward higher value creation in health care.

CONCLUSIONS

GenAI informs rather than assisting or automating clinical service functions in health care. There is potential in clinical service, but it has yet to be actualized for GenAI. More clinical service-level evidence that GenAI is used to streamline some functions or provides more automated help than only information retrieval is needed. To transform health care as purported, more studies related to GenAI applications must automate and guide human-performed services and keep up with the optimism that forward-thinking health care organizations will take advantage of GenAI.

Tumor Mutation Burden-Related Histopathologic Features for Predicting Overall Survival in Gliomas Using Graph Deep Learning

Tumor mutation burden (TMB) is a potential biomarker for evaluating the prognosis and response to immune checkpoint inhibitors, but its costly and time-consuming method of measurement limits its widespread application. This study aimed to identify the TMB-related histopathologic features from hematoxylin and eosin slides and explore their prognostic value in gliomas. TMB-related features were detected using a graph convolutional neural network from whole-slide images of patients from The Cancer Genome Atlas data set (619 patients), and the correlation between features and TMB was evaluated in an external validation set (237 patients). TMB-related features were used for predicting overall survival (OS) of patients to investigate whether these features have potential for prognostic prediction. Moreover, biological pathways underlying the prognostic value of the features were further explored. Histopathologic features derived from whole-slide images were significantly associated with patient TMB (P = 0.007 in the external validation set). TMB-related features showed excellent performance for OS prediction, and patients with lower-grade gliomas could be further stratified into different risk groups according to the features (P = 0.00013; hazard ratio, 4.004). Pathways involved in the cell cycle and execution of immune response were enriched in patients with higher OS risk. The TMB-related features could be used to estimate TMB and aid in prognostic risk stratification of patients with glioma with dysregulated biological pathways.

An alternative extension of telomeres related prognostic model to predict survival in lower grade glioma

OBJECTIVE

The alternative extension of the telomeres (ALT) mechanism is activated in lower grade glioma (LGG), but the role of the ALT mechanism has not been well discussed. The primary purpose was to demonstrate the significance of the ALT mechanism in prognosis estimation for LGG patients.

METHOD

Gene expression and clinical data of LGG patients were collected from the Chinese Glioma Genome Atlas (CGGA) and the Cancer Genome Atlas (TCGA) cohort, respectively. ALT-related genes obtained from the TelNet database and potential prognostic genes related to ALT were selected by LASSO regression to calculate an ALT-related risk score. Multivariate Cox regression analysis was performed to construct a prognosis signature, and a nomogram was used to represent this signature. Possible pathways of the ALT-related risk score are explored by enrichment analysis.

RESULT

The ALT-related risk score was calculated based on the LASSO regression coefficients of 22 genes and then divided into high-risk and low-risk groups according to the median. The ALT-related risk score is an independent predictor of LGG (HR and 95% CI in CGGA cohort: 5.70 (3.79, 8.58); in TCGA cohort: 1.96 (1.09, 3.54)). ROC analysis indicated that the model contained ALT-related risk score was superior to conventional clinical features (AUC: 0.818 vs 0.729) in CGGA cohorts. The results in the TCGA cohort also shown a powerful ability of ALT-related risk score (AUC: 0.766 vs 0.691). The predicted probability and actual probability of the nomogram are consistent. Enrichment analysis demonstrated that the ALT mechanism was involved in the cell cycle, DNA repair, immune processes, and others.

CONCLUSION

ALT-related risk score based on the 22-gene is an important factor in predicting the prognosis of LGG patients.

Multi-center validation of an immune-related lncRNA signature for predicting survival and immune status of patients with renal cell carcinoma: an integrating machine learning-derived study

BACKGROUND

Long noncoding RNAs (lncRNAs) have been reported to play an important role in tumor immune modification. Nonetheless, the clinical implication of immune-associated lncRNAs in renal cell carcinoma (RCC) remains to be further explored.

METHODS

76 combinations of machine learning algorithms were integrated to develop and validate a machine learning-derived immune-related lncRNA signature (MDILS) in five independent cohorts (n = 801). We collected 28 published signatures and collated clinical variables for comparison with MDILS to verify its efficacy. Subsequently, molecular mechanisms, immune status, mutation landscape, and pharmacological profile were further investigated in different stratified patients.

RESULTS

Patients with high MDILS displayed worse overall survival than those with low MDILS. The MDILS could independently predict overall survival and convey robust performance across five cohorts. MDILS has a significantly better performance compared with traditional clinical variables and 28 published signatures. Patients with low MDILS exhibited more abundant immune infiltration and higher potency of immunotherapeutic response, while patients with high MDILS might be more sensitive to multiple chemotherapeutic drugs (e.g., sunitinib and axitinib).

CONCLUSION

MDILS is a robust and promising tool to facilitate clinical decision-making and precision treatment of RCC.

Pan-Cancer Analysis of the Prognostic and Immunological Role of SMG5: A Biomarker for Cancers

INTRODUCTION

SMG5 is involved in tumor cell development and viewed as a potential target for immunotherapy. The purpose of this study was to systematically analyze the expression level, function, and prognostic value of SMG5 in pan-cancers.

METHODS

Differential expression of SMG5 in normal and tumor tissues was analyzed using The Cancer Genome Atlas (TCGA) and the Genotype-Tissue Expression Database (GTEx) data. Survival analysis was performed by Kaplan-Meier method and Cox risk regression. The relationship between SMG5 expression and lymphocyte abundance, tumor cell immune infiltration level, molecular and immune subtypes as well as immune checkpoints was analyzed by tumor-immune system interactions database (TISIDB), Tumor Immune Estimation Resource (TIMER), and Sangerbox databases. The correlation between SMG5 and immune scores was studied using the Estimation of Stromal and Immune Cells in Malignant Tumours using Expression (ESTIMATE) data algorithm. Further, drug sensitivity analysis of SMG5 with low-grade glioma (LGG) was conducted using the CellMiner database.

RESULTS

SMG5 was highly expressed in 23 tumors and only had a significant impact on the prognosis of patients with LGG only. In addition, in tumor microenvironment and tumor immune analysis, we found that the level of immune infiltration, tumor mutational load, microsatellite instability, and immune checkpoints of LGG were significantly correlated with SMG5 expression. Furthermore, SMG5 was significantly associated with immune scores, stromal scores, and sensitivity of some drugs in LGG.

CONCLUSION

SMG5 is differentially expressed in several cancers and is significantly associated with prognosis, immune microenvironment, and immune checkpoints in LGG patients. Therefore, SMG5 could be a potential pan-cancer biomarker and an immunotherapeutic target for LGG.

Recent Advancements in Deep Learning Using Whole Slide Imaging for Cancer Prognosis

This review furnishes an exhaustive analysis of the latest advancements in deep learning techniques applied to whole slide images (WSIs) in the context of cancer prognosis, focusing specifically on publications from 2019 through 2023. The swiftly maturing field of deep learning, in combination with the burgeoning availability of WSIs, manifests significant potential in revolutionizing the predictive modeling of cancer prognosis. In light of the swift evolution and profound complexity of the field, it is essential to systematically review contemporary methodologies and critically appraise their ramifications. This review elucidates the prevailing landscape of this intersection, cataloging major developments, evaluating their strengths and weaknesses, and providing discerning insights into prospective directions. In this paper, a comprehensive overview of the field aims to be presented, which can serve as a critical resource for researchers and clinicians, ultimately enhancing the quality of cancer care outcomes. This review's findings accentuate the need for ongoing scrutiny of recent studies in this rapidly progressing field to discern patterns, understand breakthroughs, and navigate future research trajectories.

Pan-cancer evaluation of clinical value of mitotic network activity index (MNAI) and its predictive value for immunotherapy

Increased mitotic activity is associated with the genesis and aggressiveness of many cancers. To assess the clinical value of mitotic activity as prognostic biomarker, we performed a pan-cancer study on the mitotic network activity index (MNAI) constructed based on 54-gene mitotic apparatus network. Our pan-cancer assessment on TCGA (33 tumor types, 10,061 patients) and validation on other publicly available cohorts (23 tumor types, 9,209 patients) confirmed the significant association of MNAI with overall survival, progression-free survival, and other prognostic endpoints in multiple cancer types, including lower-grade gliomas (LGG), breast invasive carcinoma (BRCA), as well as many others. We also showed significant association between MNAI and genetic instability, which provides a biological explanation of its prognostic impact at pan-cancer landscape. Our association analysis revealed that patients with high MNAI benefitted more from anti-PD-1 and Anti-CTLA-4 treatment. In addition, we demonstrated that multimodal integration of MNAI and the AI-empowered Cellular Morphometric Subtypes (CMS) significantly improved the predictive power of prognosis compared to using MNAI and CMS alone. Our results suggest that MNAI can be used as a potential prognostic biomarker for different tumor types toward different clinical endpoints, and multimodal integration of MNAI and CMS exceeds individual biomarker for precision prognosis.

Terpinen-4-ol Induces Ferroptosis of Glioma Cells via Downregulating JUN Proto-Oncogene

According to previous research, turmeric seeds exhibit anti-inflammatory, anti-malignancy, and anti-aging properties due to an abundance of terpinen-4-ol (T4O). Although it is still unclear how T4O works on glioma cells, limited data exist regarding its specific effects. In order to determine whether or not glioma cell lines U251, U87, and LN229 are viable, CCK8 was used as an assay and a colony formation assay was performed using different concentrations of T4O (0, 1, 2, and 4 μM). The effect of T4O on the proliferation of glioma cell line U251 was detected through the subcutaneous implantation of the tumor model. Through high-throughput sequencing, a bioinformatic analysis, and real-time quantitative polymerase chain reactions, we identified the key signaling pathways and targets of T4O. Finally, for the measurement of the cellular ferroptosis levels, we examined the relationship between T4O, ferroptosis, and JUN and the malignant biological properties of glioma cells. T4O significantly inhibited glioma cell growth and colony formation and induced ferroptosis in the glioma cells. T4O inhibited the subcutaneous tumor proliferation of the glioma cells in vivo. T4O suppressed JUN transcription and significantly reduced its expression in the glioma cells. The T4O treatment inhibited GPX4 transcription through JUN. The overexpression of JUN suppressed ferroptosis in the cells rescued through T4O treatment. Taken together, our data suggest that the natural product T4O exerts its anti-cancer effects by inducing JUN/GPX4-dependent ferroptosis and inhibiting cell proliferation, and T4O will hope-fully serve as a prospective compound for glioma treatment.

Constructing metabolism-protein interaction relationship to identify glioma prognosis using deep learning

Glioma is heterogeneous disease that requires classification into subtypes with similar clinical phenotypes, prognosis or treatment responses. Metabolic-protein interaction (MPI) can provide meaningful insights into cancer heterogeneity. Moreover, the potential of lipids and lactate for identifying prognostic subtypes of glioma remains relatively unexplored. Therefore, we proposed a method to construct an MPI relationship matrix (MPIRM) based on a triple-layer network (Tri-MPN) combined with mRNA expression, and processed the MPIRM by deep learning to identify glioma prognostic subtypes. These Subtypes with significant differences in prognosis were detected in glioma (p-value < 2e-16, 95% CI). These subtypes had a strong correlation in immune infiltration, mutational signatures and pathway signatures. This study demonstrated the effectiveness of node interaction from MPI networks in understanding the heterogeneity of glioma prognosis.

Chemical mixture exposure patterns and obesity among U.S. adults in NHANES 2005-2012

BACKGROUND

The effect of chemical exposure on obesity has raised great concerns. Real-world chemical exposure always imposes mixture impacts, however their exposure patterns and the corresponding associations with obesity have not been fully evaluated.

OBJECTIVES

To discover obesity-related mixed chemical exposure patterns in the general U.S.

METHODS

Sparse Decompositional Regression (SDR), a model adapted from sparse representation learning technique, was developed to identify exposure patterns of chemical mixtures with exclusion (non-targeted model) and inclusion (targeted model) of health outcomes. We assessed the relationships between the identified chemical mixture patterns and obesity-related indexes. We also conducted a comprehensive evaluation of this SDR model by comparing to the existing models, including generalized linear regression model (GLM), principal component analysis (PCA), and Bayesian kernel machine regression (BKMR).

RESULTS

Eight core exposure patterns were identified using the non-targeted SDR model. Patterns of high levels of MEP, high levels of naphthalene metabolites (ΣOH-Nap), and a pattern of high exposure levels of MCOP, MCNP, and MCPP were positively associated with obesity. Patterns of high levels of BP3, and a pattern of higher mixed levels of MPB, PPB, and MEP were found to have negative associations. Associations were strengthened using the targeted SDR model. In the single chemical analysis by GLM, BP3, MBP, PPB, MCOP, and MCNP showed significant associations with obesity or body indexes. The SDR model exceeded the performance of PCA in pattern identification. Both SDR and BKMR identified a positive contribution of ΣOH-Nap and MCOP, as well as a negative contribution of BP3 and PPB to obesity.

CONCLUSION

Our study identified five core exposure patterns of chemical mixtures significantly associated with obesity using the newly developed SDR model. The SDR model could open a new avenue for assessing health effects of environmental mixture contaminants.

Development and Validation of a Prognostic Nomogram for Lung Adenocarcinoma: A Population-Based Study

PURPOSE

To establish an effective and accurate prognostic nomogram for lung adenocarcinoma (LUAD). Patients and Methods. 62,355 LUAD patients from 1975 to 2016 enrolled in the Surveillance, Epidemiology, and End Results (SEER) database were randomly and equally divided into the training cohort (n = 31,179) and the validation cohort (n = 31,176). Univariate and multivariate Cox regression analyses screened the predictive effects of each variable on survival. The concordance index (C-index), calibration curves, receiver operating characteristic (ROC) curve, and area under the ROC curve (AUC) were used to examine and validate the predictive accuracy of the nomogram. Kaplan-Meier curves were used to estimate overall survival (OS).

RESULTS

10 prognostic factors associated with OS were identified, including age, sex, race, marital status, American Joint Committee on Cancer (AJCC) TNM stage, tumor size, grade, and primary site. A nomogram was established based on these results. C-indexes of the nomogram model reached 0.777 (95% confidence interval (CI), 0.773 to 0.781) and 0.779 (95% CI, 0.775 to 0.783) in the training and validation cohorts, respectively. The calibration curves were well-fitted for both cohorts. The AUC for the 3- and 5-year OS presented great prognostic accuracy in the training cohort (AUC = 0.832 and 0.827, respectively) and validation cohort (AUC = 0.835 and 0.828, respectively). The Kaplan-Meier curves presented significant differences in OS among the groups.

CONCLUSION

The nomogram allows accurate and comprehensive prognostic prediction for patients with LUAD.

iCEMIGE: Integration of CEll-morphometrics, MIcrobiome, and GEne biomarker signatures for risk stratification in breast cancers

BACKGROUND

The development of precision medicine is essential for personalized treatment and improved clinical outcome, whereas biomarkers are critical for the success of precision therapies.

AIM

To investigate whether iCEMIGE (integration of CEll-morphometrics, MIcro biome, and GEne biomarker signatures) improves risk stratification of breast cancer (BC) patients.

METHODS

We used our recently developed machine learning technique to identify cellular morphometric biomarkers (CMBs) from the whole histological slide images in The Cancer Genome Atlas (TCGA) breast cancer (TCGA-BRCA) cohort. Multivariate Cox regression was used to assess whether cell-morphometrics prognosis score (CMPS) and our previously reported 12-gene expression prognosis score (GEPS) and 15-microbe abundance prognosis score (MAPS) were independent prognostic factors. iCEMIGE was built upon the sparse representation learning technique. The iCEMIGE scoring model performance was measured by the area under the receiver operating characteristic curve compared to CMPS, GEPS, or MAPS alone. Nomogram models were created to predict overall survival (OS) and progress-free survival (PFS) rates at 5- and 10-year in the TCGA-BRCA cohort.

RESULTS

We identified 39 CMBs that were used to create a CMPS system in BCs. CMPS, GEPS, and MAPS were found to be significantly independently associated with OS. We then established an iCEMIGE scoring system for risk stratification of BC patients. The iGEMIGE score has a significant prognostic value for OS and PFS independent of clinical factors (age, stage, and estrogen and progesterone receptor status) and PAM50-based molecular subtype. Importantly, the iCEMIGE score significantly increased the power to predict OS and PFS compared to CMPS, GEPS, or MAPS alone.

CONCLUSION

Our study demonstrates a novel and generic artificial intelligence framework for multimodal data integration toward improving prognosis risk stratification of BC patients, which can be extended to other types of cancer.