Independent External Cohort Research Articles

Predicted survival of patients with human immunodeficiency virus-associated non-Hodgkin’s lymphoma based on clinical and imaging factors: A multicenter retrospective study

BACKGROUND: Non-Hodgkin’s lymphoma (NHL) has a poor prognosis and serious risk of mortality. Furthermore, the clinical and imaging characteristics differ between human immunodeficiency virus (HIV)-positive and HIV-negative NHL. We aimed to create a nomogram based on imaging, clinical, and laboratory indicators to predict the mortality risk of patients with HIV-positive NHL. MATERIALS AND METHODS: A total of 306 patients were enrolled. The training cohort comprised 194 patients with HIV-positive NHL treated at four Chinese medical centers between April 2012 and October 2020. A series of statistical methods were used to screen potential predictive factors for inclusion in a prognostic nomogram. The performance of the nomogram was assessed by internal validation, external validation, and clinical utility. The independent external verification cohort comprised 112 patients treated between January 2013 and November 2020. RESULTS: After investigating 39 potentially predictive factors, a nomogram containing eight factors (three imaging factors, four clinical factors, and one HIV-infection special factor) was developed. Internal and external validation revealed good discrimination (concordance index: 0.837 vs. 0.817; 95% confidence interval, 0.826–0.848 vs. 0.798–0.836) and excellent calibration. Regarding the clinical utility, our nomogram was more accurate in predicting survival than the International Prognostic Index (area under the curve, 0.9217 vs. 0.8150; sensitivity, 0.85 vs. 0.67; and specificity, 0.89 vs. 0.87). The nomogram identified low-risk, intermediate-risk, and high-risk groups with 1-year survival rates of 95%, 59%, and 2%, respectively. CONCLUSION: The nomogram model based on imaging, clinical, and laboratory indicators may be useful in predicting the treatment efficacy and long-term mortality risk of patients with HIV-positive NHL. This may provide a new scientific basis for clinical decision-making.

Short-term mortality prediction using a combination of clinical and CT features: Refining the prognosis of critically ill patients in shock

PurposeTo assess the predictive value of combining CT and clinical findings for predicting 10-day mortality in critically ill patients in shock. Materials and methodsFrom January 1, 2018, to December 31, 2021, 289 consecutives critically ill patients in shock who underwent a contrast enhanced CT were included. Variables at the time of the CT were retrospectively extracted from medical charts. CT examinations were blindly analyzed by two independent radiologists. Multivariable analysis was performed, combining clinical and CT features. A simple survival score for 10-day mortality prediction was built and validated in a further independent external cohort of 70 patients. Results10-day mortality rate was 135/289 (47%) in the study sample. At multivariate analysis, catecholamine infusion (OR = 2.11; 95%CI [1.21–4.18], P = 0.011), lactates level > 5 mmol/l (OR = 3.54; 95%CI [1.94–6.54], P < 0.001); total bilirubin > 50 mg/l (OR = 1.79 CI 95% [1.03–3.13], P = 0.039); small bowel dilation (OR = 1.82; 95%CI [1.01–3.32], P = 0.047); diffuse kidney infarction (OR = 2.76; 95%CI [1.26–6.37], P = 0.013) and superior mesentery artery < 5 mm (OR = 1.96; 95%CI [1.10–3.49], P = 0.021) were associated with 10-days mortality. The AUC of the combined model was 0.79; 95%CI [0.74–0.85] in the study sample and 0.87; 95%CI [0.71–0.91] in the validation cohort. ConclusionThe combination of CT imaging features and clinical data should emerge as a novel approach to predict short-term mortality in critically ill patients in shock.

Identification of T-cell exhaustion-related gene signature for predicting prognosis in glioblastoma multiforme.

Glioblastoma multiforme (GBM) is a highly malignant primary brain tumour with a poor prognosis in adults. Identifying biomarkers that can aid in the molecular classification and risk stratification of GBM is critical. Here, we conducted a transcriptional profiling analysis of T-cell immunity in the tumour microenvironment of GBM patients and identified two novel T cell exhaustion (TEX)-related GBM subtypes (termed TEX-C1 and TEX-C2) using the consensus clustering. Our multi-omics analysis revealed distinct immunological, molecular and clinical characteristics for these two subtypes. Specifically, the TEX-C1 subtype had higher infiltration levels of immune cells and expressed higher levels of immune checkpoint molecules than the TEX-C2 subtype. Functional analysis revealed that upregulated genes in the TEX-C1 subtype were significantly enriched in immune response and signal transduction pathways, and upregulated genes in the TEX-C2 subtype were predominantly associated with cell fate and nervous system development pathways. Notably, patients with activated T-cell activity status in the TEX-C1 subgroup demonstrated a significantly worse prognosis than those with severe T cell exhaustion status in the TEX-C2 subgroup. Finally, we proposed a machine-learning-derived novel gene signature comprising 12 TEX-related genes (12TexSig) to indicate tumour subtyping. In the TCGA cohort, the 12TexSig demonstrated the ability to accurately predict the prognosis of GBM patients, and this prognostic value was further confirmed in two independent external cohorts. Taken together, our results suggest that the TEX-derived subtyping and gene signature has the potential to serve as a clinically helpful biomarker for guiding the management of GBM patients, pending further prospective validation.

Short Timeframe Prediction of Kidney Failure among Patients with Advanced Chronic Kidney Disease.

Development of a short timeframe (6-12 months) kidney failure risk prediction model may serve to improve transitions from advanced chronic kidney disease (CKD) to kidney failure and reduce rates of unplanned dialysis. The optimal model for short timeframe kidney failure risk prediction remains unknown. This retrospective study included 1757 consecutive patients with advanced CKD (mean age 66 years, estimated glomerular filtration rate 18 mL/min/1.73 m2). We compared the performance of Cox regression models using (a) baseline variables alone, (b) time-varying variables and machine learning models, (c) random survival forest, (d) random forest classifier in the prediction of kidney failure over 6/12/24 months. Performance metrics included area under the receiver operating characteristic curve (AUC-ROC) and maximum precision at 70% recall (PrRe70). Top-performing models were applied to 2 independent external cohorts. Compared to the baseline Cox model, the machine learning and time-varying Cox models demonstrated higher 6-month performance [Cox baseline: AUC-ROC 0.85 (95% CI 0.84-0.86), PrRe70 0.53 (95% CI 0.51-0.55); Cox time-varying: AUC-ROC 0.88 (95% CI 0.87-0.89), PrRe70 0.62 (95% CI 0.60-0.64); random survival forest: AUC-ROC 0.87 (95% CI 0.86-0.88), PrRe70 0.61 (95% CI 0.57-0.64); random forest classifier AUC-ROC 0.88 (95% CI 0.87-0.89), PrRe70 0.62 (95% CI 0.59-0.65)]. These trends persisted, but were less pronounced, at 12 months. The random forest classifier was the highest performing model at 6 and 12 months. At 24 months, all models performed similarly. Model performance did not significantly degrade upon external validation. When predicting kidney failure over short timeframes among patients with advanced CKD, machine learning incorporating time-updated data provides enhanced performance compared with traditional Cox models.

Selection of optimal quantile protein biomarkers based on cell-level immunohistochemistry data

BackgroundProtein biomarkers of cancer progression and response to therapy are increasingly important for improving personalized medicine. Advanced quantitative pathology platforms enable measurement of protein expression in tissues at the single-cell level. However, this rich quantitative cell-by-cell biomarker information is most often not exploited. Instead, it is reduced to a single mean across the cells of interest or converted into a simple proportion of binary biomarker-positive or -negative cells.ResultsWe investigated the utility of retaining all quantitative information at the single-cell level by considering the values of the quantile function (inverse of the cumulative distribution function) estimated from a sample of cell signal intensity levels in a tumor tissue. An algorithm was developed for selecting optimal cutoffs for dichotomizing cell signal intensity distribution quantiles as predictors of continuous, categorical or survival outcomes. The proposed algorithm was used to select optimal quantile biomarkers of breast cancer progression based on cancer cells’ cell signal intensity levels of nuclear protein Ki-67, Proliferating cell nuclear antigen, Programmed cell death 1 ligand 2, and Progesterone receptor. The performance of the resulting optimal quantile biomarkers was validated and compared to the standard cancer compartment mean signal intensity markers using an independent external validation cohort. For Ki-67, the optimal quantile biomarker was also compared to established biomarkers based on percentages of Ki67-positive cells. For proteins significantly associated with PFS in the external validation cohort, the optimal quantile biomarkers yielded either larger or similar effect size (hazard ratio for progression-free survival) as compared to cancer compartment mean signal intensity biomarkers.ConclusionThe optimal quantile protein biomarkers yield generally improved prognostic value as compared to the standard protein expression markers. The proposed methodology has a broad application to single-cell data from genomics, transcriptomics, proteomics, or metabolomics studies at the single cell level.

Identification and validation of a novel HOX-related classifier signature for predicting prognosis and immune microenvironment in pediatric gliomas.

Background: Pediatric gliomas (PGs) are highly aggressive and predominantly occur in young children. In pediatric gliomas, abnormal expression of Homeobox (HOX) family genes (HFGs) has been observed and is associated with the development and progression of the disease. Studies have found that overexpression or underexpression of certain HOX genes is linked to the occurrence and prognosis of gliomas. This aberrant expression may contribute to the dysregulation of important pathological processes such as cell proliferation, differentiation, and metastasis. This study aimed to propose a novel HOX-related signature to predict patients' prognosis and immune infiltrate characteristics in PGs. Methods: The data of PGs obtained from publicly available databases were utilized to reveal the relationship among abnormal expression of HOX family genes (HFGs), prognosis, tumor immune infiltration, clinical features, and genomic features in PGs. The HFGs were utilized to identify heterogeneous subtypes using consensus clustering. Then random forest-supervised classification algorithm and nearest shrunken centroid algorithm were performed to develop a prognostic signature in the training set. Finally, the signature was validated in an internal testing set and an external independent cohort. Results: Firstly, we identified HFGs significantly differentially expressed in PGs compared to normal tissues. The individuals with PGs were then divided into two heterogeneous subtypes (HOX-SI and HOX-SII) based on HFGs expression profiles. HOX-SII showed higher total mutation counts, lower immune infiltration, and worse prognosis than HOX-SI. Then, we constructed a HOX-related gene signature (including HOXA6, HOXC4, HOXC5, HOXC6, and HOXA-AS3) based on the cluster for subtype prediction utilizing random forest supervised classification and nearest shrunken centroid algorithm. The signature was revealed to be an independent prognostic factor for patients with PGs by multivariable Cox regression analysis. Conclusion: Our study provides a novel method for the prognosis classification of PGs. The findings also suggest that the HOX-related signature is a new biomarker for the diagnosis and prognosis of patients with PGs, allowing for more accurate survival prediction.

A machine learning model for predicting hepatocellular carcinoma risk in patients with chronic hepatitis B.

Machine learning (ML) algorithms can be used to overcome the prognostic performance limitations of conventional hepatocellular carcinoma (HCC) risk models. We established and validated an ML-based HCC predictive model optimized for patients with chronic hepatitis B (CHB) infections receiving antiviral therapy (AVT). Treatment-naïve CHB patients who were started entecavir (ETV) or tenofovir disoproxil fumarate (TDF) were enrolled. We used a training cohort (n = 960) to develop a novel ML model that predicted HCC development within 5 years and validated the model using an independent external cohort (n = 1937). ML algorithms consider all potential interactions and do not use predefined hypotheses. The mean age of the patients in the training cohort was 48 years, and most patients (68.9%) were men. During the median 59.3 (interquartile range 45.8-72.3) months of follow-up, 69 (7.2%) patients developed HCC. Our ML-based HCC risk prediction model had an area under the receiver-operating characteristic curve (AUC) of 0.900, which was better than the AUCs of CAMD (0.778) and REAL B (0.772) (both p < .05). The better performance of our model was maintained (AUC = 0.872 vs. 0.788 for CAMD and 0.801 for REAL B) in the validation cohort. Using cut-off probabilities of 0.3 and 0.5, the cumulative incidence of HCC development differed significantly among the three risk groups (p < .001). Our new ML model performed better than models in terms of predicting the risk of HCC development in CHB patients receiving AVT.

Metabolomic profiling reveals the mechanisms underlying the nephrotoxicity of methotrexate in children with acute lymphoblastic leukemia.

Methotrexate is widely recommended as a first-line treatment for the intensive systemic and consolidation phases of childhood acute lymphoblastic leukemia. However, methotrexate-induced nephrotoxicity is a severe adverse reaction, of which the mechanisms remain unclear. An untargeted metabolomics analysis of serum from childhood acute lymphoblastic leukemia patients with delayed methotrexate excretion, with or without acute kidney injury, was performed to identify altered metabolites and metabolic pathways. An independent external validation cohort and in vitro HK-2 cell assays further verified the candidate metabolites, and explored the mechanisms underlying the nephrotoxicity of methotrexate. Four metabolites showed significant differences between normal excretion and delayed excretion, seven metabolites reflected the differences between groups with or without acute kidney injury, and six pathways were finally enriched. In particular, oxidized glutathione was confirmed as a candidate metabolite involved in the toxicity of methotrexate. We further explored the role of glutathione deprivation-induced ferroptosis on methotrexate cytotoxicity, and it was found that methotrexate overload significantly reduced cell viability, triggered reactive oxygen species and intracellular Fe2+ accumulation, and altered the expression of ferroptosis-related proteins in HK-2 cells. These methotrexate-induced changes were alleviated or reversed by the administration of a ferroptosis inhibitor, further suggesting that ferroptosis promoted methotrexate-induced cytotoxicity in HK-2 cells. Our findings revealed complex metabolomic profiles and provided novel insights into the mechanism by which ferroptosis contributes to the nephrotoxic effects of methotrexate.

Explainable artificial intelligence to predict and identify prostate cancer tissue by gene expression

Background and Objective: Prostate cancer is one of the most prevalent forms of cancer in men worldwide. Traditional screening strategies such as serum PSA levels, which are not necessarily cancer-specific, or digital rectal exams, which are often inconclusive, are still the screening methods used for the disease. Some studies have focused on identifying biomarkers of the disease but none have been reported for diagnosis in routine clinical practice and few studies have provided tools to assist the pathologist in the decision-making process when analyzing prostate tissue. Therefore, a classifier is proposed to predict the occurrence of PCa that provides physicians with accurate predictions and understandable explanations.Methods: A selection of 47 genes was made based on differential expression between PCa and normal tissue, GO gene ontology as well as the literature to be used as input predictors for different machine learning methods based on eXplainable Artificial Intelligence. These methods were trained using different class-balancing strategies to build accurate classifiers using gene expression data from 550 samples from ’The Cancer Genome Atlas’. Our model was validated in four external cohorts with different ancestries, totaling 463 samples. In addition, a set of SHapley Additive exPlanations was provided to help clinicians understand the underlying reasons for each decision.Results: An in-depth analysis showed that the Random Forest algorithm combined with majority class downsampling was the best performing approach with robust statistical significance. Our method achieved an average sensitivity and specificity of 0.90 and 0.8 with an AUC of 0.84 across all databases. The relevance of DLX1, MYL9 and FGFR genes for PCa screening was demonstrated in addition to the important role of novel genes such as CAV2 and MYLK.Conclusions: This model has shown good performance in 4 independent external cohorts of different ancestries and the explanations provided are consistent with each other and with the literature, opening a horizon for its application in clinical practice. In the near future, these genes, in combination with our model, could be applied to liquid biopsy to improve PCa screening.

Necroptosis-related signatures identify two distinct hepatocellular carcinoma subtypes: Implications for predicting drug sensitivity and prognosis

BackgroundNecroptosis is associated with oncogenesis, tumor immunity and progression. This research aims to investigate the association of necroptosis-related genes with drug sensitivity and prognosis in hepatocellular carcinoma (HCC). MethodsBased on necroptosis-related signatures, HCC patients retrieved from the TCGA database were categorized. Survival outcomes, mutation profile, immune microenvironment, and drug sensitivity between HCC subtypes were further compared. Then, LASSO analysis was performed to construct a necroptosis-related prognostic signature, which was further evaluated using another independent cohort. ResultsA total of 371 patients with HCC could be categorized into two necroptosis-related subtypes. About 36% of patients were allocated to subtype A, with worse survival, more mutant TP53, and a lower likelihood of immunotherapy response. In contrast, patients in subtype B had a favorable prognosis, with lower expression of immunosuppressive signatures but a lower abundance of B and CD8+ T-cell infiltration. The prognostic risk score calculated using the expression levels of nine genes involved in the necroptosis pathway (MLKL, FADD, XIAP, USP22, UHRF1, CASP8, RIPK3, ZBP1, and FAS) showed a significant association with tumor stage, histologic grade, and Child‒Pugh score. Additionally, the risk score model was proven to be accurate in both the training and independent external validation cohorts and performed better than the TNM staging system and three well-recognized risk score models. ConclusionsBased on necroptosis-related signatures, we identified two HCC subtypes with distinctive immune microenvironments, mutation profiles, drug sensitivities, and survival outcomes. A novel well-performing prognostic model was further constructed.

Deep learning based automated delineation of the intraprostatic gross tumour volume in PSMA-PET for patients with primary prostate cancer

PurposeWith the increased use of focal radiation dose escalation for primary prostate cancer (PCa), accurate delineation of gross tumor volume (GTV) in prostate-specific membrane antigen PET (PSMA-PET) becomes crucial. Manual approaches are time-consuming and observer dependent. The purpose of this study was to create a deep learning model for the accurate delineation of the intraprostatic GTV in PSMA-PET. MethodsA 3D U-Net was trained on 128 different 18F-PSMA-1007 PET images from three different institutions. Testing was done on 52 patients including one independent internal cohort (Freiburg: n = 19) and three independent external cohorts (Dresden: n = 14 18F-PSMA-1007, Boston: Massachusetts General Hospital (MGH): n = 9 18F-DCFPyL-PSMA and Dana-Farber Cancer Institute (DFCI): n = 10 68Ga-PSMA-11). Expert contours were generated in consensus using a validated technique. CNN predictions were compared to expert contours using Dice similarity coefficient (DSC). Co-registered whole-mount histology was used for the internal testing cohort to assess sensitivity/specificity. ResultsMedian DSCs were Freiburg: 0.82 (IQR: 0.73–0.88), Dresden: 0.71 (IQR: 0.53–0.75), MGH: 0.80 (IQR: 0.64–0.83) and DFCI: 0.80 (IQR: 0.67–0.84), respectively. Median sensitivity for CNN and expert contours were 0.88 (IQR: 0.68–0.97) and 0.85 (IQR: 0.75–0.88) (p = 0.40), respectively. GTV volumes did not differ significantly (p > 0.1 for all comparisons). Median specificity of 0.83 (IQR: 0.57–0.97) and 0.88 (IQR: 0.69–0.98) were observed for CNN and expert contours (p = 0.014), respectively. CNN prediction took 3.81 seconds on average per patient. ConclusionThe CNN was trained and tested on internal and external datasets as well as histopathology reference, achieving a fast GTV segmentation for three PSMA-PET tracers with high diagnostic accuracy comparable to manual experts.

ACSM6 overexpression indicates a non-inflammatory tumor microenvironment and predicts treatment response in bladder cancer: results from multiple real-world cohorts.

Background: ACSMs play critical roles in lipid metabolism; however, their immunological function within the tumor microenvironment (TME) remains unclear, especially that of ACSM6. In this study, we investigate the latent effect of ACSM6 on bladder cancer (BLCA). Methods: Several real-world cohorts, including the Xiangya (in-house), The Cancer Genome Atlas (TCGA-BLCA), and IMvigor210 cohorts, with TCGA-BLCA cohort serving as the discovery cohort were compared. We investigated the potential immunological effects of ACSM6 in regulating the BLCA tumor microenvironment by analyzing its correlation with immunomodulators, anti-cancer immune cycles, immune checkpoints, tumor-infiltrating immune cells, and the T-cell inflamed score (TIS). Additionally, we assessed the precision of ACSM6 in predicting BLCA molecular subtypes and responses to several treatments using ROC analysis. To ensure the robustness of our findings, all results were confirmed in two independent external cohorts: the IMvigor210 and Xiangya cohorts. Results: ACSM6 expression was markedly upregulated in BLCA. Our analysis suggests that ACSM6 might have significant impact to promote the formation of a non-inflamed tumor microenvironment because of its negative correlation with immunomodulators, anticancer immune cycles, immune checkpoints, tumor-infiltrating immune cells, and the T-cell inflamed score (TIS). Additionally, high ACSM6 expression levels in BLCA may predict the luminal subtype, which is typically associated with resistance to chemotherapy, neoadjuvant chemotherapy, and radiotherapy. These findings were consistent across both the IMvigor210 and Xiangya cohorts. Conclusion: ACSM6 has the potential to serve as a valuable predictor of the tumor microenvironment phenotypes and treatment outcomes in BLCA, thereby contributing to more precise treatment.

An automatic interpretable deep learning pipeline for accurate Parkinson's disease diagnosis using quantitative susceptibility mapping and T1-weighted images.

Parkinson's disease (PD) diagnosis based on magnetic resonance imaging (MRI) is still challenging clinically. Quantitative susceptibility maps (QSM) can potentially provide underlying pathophysiological information by detecting the iron distribution in deep gray matter (DGM) nuclei. We hypothesized that deep learning (DL) could be used to automatically segment all DGM nuclei and use relevant features for a better differentiation between PD and healthy controls (HC). In this study, we proposed a DL-based pipeline for automatic PD diagnosis based on QSM and T1-weighted (T1W) images. This consists of (1) a convolutional neural network model integrated with multiple attention mechanisms which simultaneously segments caudate nucleus, globus pallidus, putamen, red nucleus, and substantia nigra from QSM and T1W images, and (2) an SE-ResNeXt50 model with an anatomical attention mechanism, which uses QSM data and the segmented nuclei to distinguish PD from HC. The mean dice values for segmentation of the five DGM nuclei are all >0.83 in the internal testing cohort, suggesting that the model could segment brain nuclei accurately. The proposed PD diagnosis model achieved area under the the receiver operating characteristic curve (AUCs) of 0.901 and 0.845 on independent internal and external testing cohorts, respectively. Gradient-weighted class activation mapping (Grad-CAM) heatmaps were used to identify contributing nuclei for PD diagnosis on patient level. In conclusion, the proposed approach can potentially be used as an automatic, explainable pipeline for PD diagnosis in a clinical setting.

Combination of alpha-fetoprotein and neutrophil-to-lymphocyte ratio to predict treatment response and survival outcomes of patients with unresectable hepatocellular carcinoma treated with immune checkpoint inhibitors

BackgroundImmune-checkpoint inhibitors (ICIs) have revolutionized the treatment of hepatocellular carcinoma (HCC). However, long-term survival outcomes and treatment response of HCC patients undergoing immunotherapy is unpredictable. The study aimed to evaluate the role of alpha-fetoprotein (AFP) combined with neutrophil-to-lymphocyte ratio (NLR) to predict the prognosis and treatment response of HCC patients receiving ICIs.MethodsPatients with unresectable HCC who received ICI treatment were included. The HCC immunotherapy score was developed from a retrospective cohort at the Eastern Hepatobiliary Surgery Hospital to form the training cohort. The clinical variables independently associated with overall survival (OS) were identified using univariate and multivariate Cox regression analysis. Based on multivariate analysis of OS, a predictive score based on AFP and NLR was constructed, and patients were stratified into three risk groups according to this score. The clinical utility of this score to predict progression-free survival (PFS) and differentiate objective response rate (ORR) and disease control rate (DCR) was also performed. This score was validated in an independent external validation cohort at the First Affiliated Hospital of Wenzhou Medical University.ResultsBaseline AFP ≤ 400 ng/ml (hazard ratio [HR] 0.48; 95% CI, 0.24–0.97; P = 0.039) and NLR ≤ 2.77 (HR 0.11; 95% CI, 0.03–0.37; P<0.001) were found to be independent risk factors of OS. The two labolatory values were used to develop the score to predict survival outcomes and treatment response in HCC patients receiving immunotherapy, which assigned 1 point for AFP > 400 ng/ml and 3 points for NLR > 2.77. Patients with 0 point were classified as the low-risk group. Patients with 1–3 points were categorized as the intermediate-risk group. Patients with 4 points were classified as the high-risk group. In the training cohort, the median OS of the low-risk group was not reached. The median OS of the intermediate-risk group and high-risk group were 29.0 (95% CI 20.8–37.3) months and 16.0 (95% CI 10.8–21.2) months, respectively (P < 0.001). The median PFS of the low-risk group was not reached. The median PFS of the intermediate-risk group and high-risk group were 14.6 (95% CI 11.3–17.8) months and 7.6 (95% CI 3.6–11.7) months, respectively (P < 0.001). The ORR and DCR were highest in the low-risk group, followed by the intermediate-risk group and the high-risk group (P < 0.001, P = 0.007, respectively). This score also had good predictive power using the validation cohort.ConclusionThe HCC immunotherapy score based on AFP and NLR can predict survival outcomes and treatment response in patients receiving ICI treatments, suggesting that this score could serve as a useful tool for identification of HCC patients likely to benefit from immunotherapy.

A novel glycolysis-related gene signature for predicting the prognosis of multiple myeloma.

Background: Metabolic reprogramming is an important hallmark of cancer. Glycolysis provides the conditions on which multiple myeloma (MM) thrives. Due to MM's great heterogeneity and incurability, risk assessment and treatment choices are still difficult. Method: We constructed a glycolysis-related prognostic model by Least absolute shrinkage and selection operator (LASSO) Cox regression analysis. It was validated in two independent external cohorts, cell lines, and our clinical specimens. The model was also explored for its biological properties, immune microenvironment, and therapeutic response including immunotherapy. Finally, multiple metrics were combined to construct a nomogram to assist in personalized prediction of survival outcomes. Results: A wide range of variants and heterogeneous expression profiles of glycolysis-related genes were observed in MM. The prognostic model behaved well in differentiating between populations with various prognoses and proved to be an independent prognostic factor. This prognostic signature closely coordinated with multiple malignant features such as high-risk clinical features, immune dysfunction, stem cell-like features, cancer-related pathways, which was associated with the survival outcomes of MM. In terms of treatment, the high-risk group showed resistance to conventional drugs such as bortezomib, doxorubicin and immunotherapy. The joint scores generated by the nomogram showed higher clinical benefit than other clinical indicators. The in vitro experiments with cell lines and clinical subjects further provided convincing evidence for our study. Conclusion: We developed and validated the utility of the MM glycolysis-related prognostic model, which provides a new direction for prognosis assessment, treatment options for MM patients.

Artificial intelligence-assisted ultrasound image analysis to discriminate early breast cancer in Chinese population: a retrospective, multicentre, cohort study.

Early diagnosis of breast cancer has always been a difficult clinical challenge. We developed a deep-learning model EDL-BC to discriminate early breast cancer with ultrasound (US) benign findings. This study aimed to investigate how the EDL-BC model could help radiologists improve the detection rate of early breast cancer while reducing misdiagnosis. In this retrospective, multicentre cohort study, we developed an ensemble deep learning model called EDL-BC based on deep convolutional neural networks. The EDL-BC model was trained and internally validated on B-mode and color Doppler US image of 7955 lesions from 6795 patients between January 1, 2015 and December 31, 2021 in the First Affiliated Hospital of Army Medical University (SW), Chongqing, China. The model was assessed by internal and external validations, and outperformed radiologists. The model performance was validated in two independent external validation cohorts included 448 lesions from 391 patients between January 1 to December 31, 2021 in the Tangshan People's Hospital (TS), Chongqing, China, and 245 lesions from 235 patients between January 1 to December 31, 2021 in the Dazu People's Hospital (DZ), Chongqing, China. All lesions in the training and total validation cohort were US benign findings during screening and biopsy-confirmed malignant, benign, and benign with 3-year follow-up records. Six radiologists performed the clinical diagnostic performance of EDL-BC, and six radiologists independently reviewed the retrospective datasets on a web-based rating platform. The area under the receiver operating characteristic curve (AUC) of the internal validation cohort and two independent external validation cohorts for EDL-BC was 0.950 (95% confidence interval [CI]: 0.909-0.969), 0.956 (95% [CI]: 0.939-0.971), and 0.907 (95% [CI]: 0.877-0.938), respectively. The sensitivity values were 94.4% (95% [CI]: 72.7%-99.9%), 100% (95% [CI]: 69.2%-100%), and 80% (95% [CI]: 28.4%-99.5%), respectively, at 0.76. The AUC for accurate diagnosis of EDL-BC (0.945 [95% [CI]: 0.933-0.965]) and radiologists with artificial intelligence (AI) assistance (0.899 [95% [CI]: 0.883-0.913]) was significantly higher than that of the radiologists without AI assistance (0.716 [95% [CI]: 0.693-0.738]; p<0.0001). Furthermore, there were no significant differences between the EDL-BC model and radiologists with AI assistance (p=0.099). EDL-BC can identify subtle but informative elements on US images of breast lesions and can significantly improve radiologists' diagnostic performance for identifying patients with early breast cancer and benefiting the clinical practice. The National Key R&D Program of China.

An immunogenomic signature for molecular classification in melanoma.

e21562 Background: Melanoma is one of the most aggressive tumors in the world, characterized by an increasing incidence and high mortality with half of the patients dying from the advanced tumors. The melanoma tumor is very heterogenous and the appropriate classification of subtypes is the key to guide precision treatment. Previous studies have revealed the important roles of immune cells in melanoma. Therefore, the better classification method and comprehensive analysis of immune cells and immune-related genes can help to better understand the tumor progression and develop effective treatment strategies in melanoma. Methods: Two datasets containing RNA sequencing data and paired patient information with melanoma were collected in this study. The first dataset of skin cutaneous melanoma patients downloaded from The Cancer Genome Atlas database (n = 204) was used as the training set, and the second dataset from a published study was used as internal validation set (n = 102). Single sample gene enrichment analysis (ssGSEA), ESTIMATE, CIBERSORT and k-means analysis were used to classify melanoma patients into two different immune clusters. We then constructed a molecular signature with nine immune related genes that could predict the overall survival (OS) of melanoma patients by LASSO regression and Cox regression analysis. The accuracy of the risk signature was then verified in eight independent cancer types. Results: The melanoma patients were divided into two different immune clusters, the high-immune cell infiltration cluster (Immunity_H) and low-immune cell infiltration cluster (Immunity_L). 1,556 and 1445 differentially expressed genes (DEGs) between the Immunity_H and Immunity_L were detected in the training set and validation set, respectively. Accordingly, 677 and 147 genes associated with overall survival (OS) was further selected by Univariate Cox regression analysis. 59 genes were shared between the 677 and 147 OS related genes. Eventually, 9 DEGs (CST7, CSF2RB, SPARC, SPOCK2, PLA2G2D, MYO1G, NCF1, ICOS and HSH2D) were screened out by LASSO regression analysis and were then subjected to multivariate Cox regression analysis to further construct the prognostic signature. Patients were divided into high-risk and low-risk groups based on the computed risk threshold. Kaplan-Meier analysis indicated that patients in the high-risk group had a significantly worse OS. Finally, 8 independent external pan-cancer cohorts were used to validate the robustness of the model. Conclusions: This study identified two immune-related clusters and a risk signature based on nine immune-related genes was constructed, which could predict the melanoma cancer OS and the constructed model can be used as prognosis predictor in melanoma.

Establishment and validation of a nomogram-based predictive model for idiopathic aldosteronism

Objective: To establish and validate a nomogram-based predictive model for idiopathic hyperaldosteronism (IHA). Methods: This cross-sectional study was conducted with the collected clinical and biochemical data of patients with primary aldosteronism (PA) including 249 patients with unilateral primary aldosteronism (UPA) and 107 patients with IHA, who were treated at the Department of Endocrinology of the First Affiliated Hospital of Chongqing Medical University from November 2013 to November 2022. Plasma aldosterone concentration (PAC) and plasma renin concentration (PRC) were measured by chemiluminescence. Stepwise regression analysis was applied to select the key predictors of IHA, and a nomogram-based scoring model was developed. The model was validated in another external independent cohort of patients with PA including 62 patients with UPA and 43 patients with IHA, who were diagnosed at the Department of Endocrinology, First Affiliated Hospital of Zhengzhou University. An independent-sample t test, Mann-Whitney U test, and χ2 test were used for statistical analysis. Results: In the training cohort, in comparison with the UPA group, the IHA group showed a higher serum potassium level [M(Q1, Q3), 3.4 (3.1, 3.8) mmol/L vs. 2.7 (2.1, 3.1) mmol/L] and higher PRC [4.0 (2.1, 8.2) mU/L vs. 1.5 (0.6, 3.4) mU/L] and a lower PAC post-saline infusion test (SIT) [305 (222, 416) pmol/L vs. 720 (443, 1 136) pmol/L] and a lower rate of unilateral adrenal nodules [33.6% (36/107) vs. 81.1% (202/249)]; the intergroup differences in these measurements were statistically significant (all P<0.001). Serum potassium level, PRC, PAC post-SIT, and the rate of unilateral adrenal nodules showed similar performance in the IHA group in the validation cohort. After stepwise regression analysis for all significant variables in the training cohort, a scoring model based on a nomogram was constructed, and the predictive parameters included the rate of unilateral adrenal nodules, serum potassium concentration, PAC post-SIT, and PRC in the standing position. When the total score was ≥14, the model showed a sensitivity of 0.65 and specificity of 0.90 in the training cohort and a sensitivity of 0.56 and specificity of 1.00 in the validation cohort. Conclusion: The nomogram was used to successfully develop a model for prediction of IHA that could facilitate selection of patients with IHA who required medication directly.

Pyroptosis patterns influence the clinical outcome and immune microenvironment characterization in HPV-positive head and neck squamous cell carcinoma

BackgroundHead and neck squamous cell carcinoma (HNSCC) is a heterogeneous tumor with diverse molecular pathological profiles. Recent studies have suggested the vital role of pyroptosis in tumor microenvironment. However, the expression patterns of pyroptosis in HPV-positive HNSCC are still unclear.MethodsUnsupervised clustering analysis was used to identify the pyroptosis patterns based on the RNA-sequencing data of 27 pyroptosis-related genes (PRGs) in HPV-positive HNSCC samples. Random forest classifier and artificial neural network were performed to screen the signature genes associated with pyroptosis, which were verified in two independent external cohorts and qRT-PCR experiment. Principal component analysis was used to develop a scoring system, namely Pyroscore.ResultsThe expression variations of 27 PRGs in HPV-positive HNSCC patients were analyzed from genomic and transcriptional domains. Two pyroptosis-related subtypes with distinct clinical outcomes, enrichment pathways and immune characteristics were identified. Next, six signature genes (GZMB, LAG3, NKG7, PRF1, GZMA and GZMH) associated with pyroptosis were selected for prognostic prediction. Further, a Pyroscore system was constructed to determine the level of pyroptosis in each patient. A low Pyroscore was featured by better survival time, increased immune cell infiltration, higher expression of immune checkpoint molecules and T cell-inflamed genes, as well as elevated mutational burden. The Pyroscore was also related to the sensitivity of chemotherapeutic agents.ConclusionsThe pyroptosis-related signature genes and Pyroscore system may be reliable predictors of prognosis and serve as mediators of immune microenvironment in patients with HPV-positive HNSCC.

The value of machine learning models based on biparametric MRI for diagnosis of prostate cancer and clinically significant prostate cancer

Objective: To evaluate the value of machine learning (ML) models based on biparametric magnetic resonance imaging (bpMRI) for diagnosis of prostate cancer (PCa) and clinically significant prostate cancer (csPCa). Methods: A total of 1 368 patients, aged from 30 to 92 (69.4±8.2) years, from 3 tertiary medical centers in Jiangsu Province were retrospectively collected from May 2015 to December 2020, including 412 cases of csPCa, 242 cases of clinically insignificant prostate cancer (ciPCa) and 714 cases of benign prostate lesions. The data of center 1 and center 2 were randomly divided into training cohort and internal testing cohort at a ratio of 7∶3 by random number sampling without replacement using Python Random package, and the data of center 3 were used as the independent external testing cohort. The training cohort includs 243 cases of csPCa, 135 cases of ciPCa and 384 cases of benign lesions, the internal testing cohort includs 104 cases of csPCa, 58 cases of ciPCa and 165 cases of benign lesions, and the external testing cohort includs 65 cases of csPCa, 49 cases of ciPCa and 165 cases of benign lesions. The radiomics features were extracted on T2-weighted imaging, diffusion-weighted imaging and apparent diffusion coefficient map, and optimal radiomics features were selected by using Pearson correlation coefficient method and analysis of variance. The ML models were built using two ML algorithms, including support vector machine and random forest (RF) and were further tested in the internal testing cohort and external testing cohort. Finally, the PI-RADS scores evaluated by the radiologists were adjusted by the ML models which had superior diagnostic performance, namely adjusted PI-RADS. The receiver operating characteristic (ROC) curves were used to evaluate the diagnostic performance of the ML models and PI-RADS. DeLong test was used to compare the areas under curve (AUC) of models with those of PI-RADS. Results: For PCa diagnosis, in internal testing cohort, the AUC of ML model using RF algorithm and PI-RADS were 0.869 (95%CI: 0.830-0.908) and 0.874 (95%CI: 0.836-0.913), respectively, and the difference between the model and PI-RADS did not reach to the statistical significance (P=0.793). In the external testing cohort, the AUC of model and PI-RADS were 0.845 (95%CI: 0.794-0.897) and 0.915 (95%CI: 0.880-0.951), respectively, and the difference was statistically significant (P=0.01). For csPCa diagnosis, the AUC of ML model using RF algorithm and PI-RADS were 0.874 (95%CI: 0.834-0.914) and 0.892 (95%CI: 0.857-0.927), respectively, in internal testing cohort, and the difference between the model and PI-RADS was not statistically significant (P=0.341). In the external testing cohort, the AUC of model and PI-RADS were 0.876 (95%CI: 0.831-0.920) and 0.884 (95%CI: 0.841-0.926), respectively, and the difference between the model and PI-RADS was not statistically significant (P=0.704). When PI-RADS assessment was adjusted with the assistance of ML models, the specificities increased from 63.0% to 80.0% in the internal testing cohort and from 92.7% to 93.3% in the external test group in diagnosing PCa. In diagnosing csPCa, the specificities increased from 52.5% to 72.6% in the internal testing cohort and from 75.2% to 79.9% in the external testing cohort. Conclusions: The ML models based on bpMRI showed comparable diagnostic performance to PI-RADS assessed by senior radiologists and achieved good generalization ability in both diagnosing PCa and csPCa. The specificities of the PI-RADS were improved by ML models.