Lactylation signature identifies liver fibrosis phenotypes and traces fibrotic progression to hepatocellular carcinoma.

Introduction: Precise staging and classification of liver fibrosis are crucial for the hierarchy management of patients. The roles of lactylation are newly found in the progression of liver fibrosis. This study is committed to investigating the signature genes with histone lactylation and their connection with immune infiltration among liver fibrosis with different phenotypes. Methods: Firstly, a total of 629 upregulated and 261 downregulated genes were screened out of 3 datasets of patients with liver fibrosis from the GEO database and functional analysis confirmed that these differentially expressed genes (DEGs) participated profoundly in fibrosis-related processes. After intersecting with previously reported lactylation-related genes, 12 DEGs related to histone lactylation were found and narrowed down to 6 core genes using R algorithms, namely S100A6, HMGN4, IFI16, LDHB, S100A4, and VIM. The core DEGs were incorporated into the Least absolute shrinkage and selection operator (LASSO) model to test their power to distinguish the fibrotic stage. Results: Advanced fibrosis presented a pattern of immune infiltration different from mild fibrosis, and the core DEGs were significantly correlated with immunocytes. Gene set and enrichment analysis (GSEA) results revealed that core DEGs were closely linked to immune response and chemokine signaling. Samples were classified into 3 clusters using the LASSO model, followed by gene set variation analysis (GSVA), which indicated that liver fibrosis can be divided into status featuring lipid metabolism reprogramming, immunity immersing, and intermediate of both. The regulatory networks of the core genes shared several transcription factors, and certain core DEGs also presented dysregulation in other liver fibrosis and idiopathic pulmonary fibrosis (IPF) cohorts, indicating that lactylation may exert comparable functions in various fibrotic pathology. Lastly, core DEGs also exhibited upregulation in HCC. Discussion: Lactylation extensively participates in the pathological progression and immune infiltration of fibrosis. Lactylation and related immune infiltration could be a worthy focus for the investigation of HCC developed from liver fibrosis.

Multimodal Machine Learning-Based Marker Enables Early Detection and Prognosis Prediction for Hyperuricemia.

Hyperuricemia (HUA) has emerged as the second most prevalent metabolic disorder characterized by prolonged and asymptomatic period, triggering gout and metabolism-related outcomes. Early detection and prognosis prediction for HUA and gout are crucial for pre-emptive interventions. Integrating genetic and clinical data from 421287 UK Biobank and 8900 Nanfang Hospital participants, a stacked multimodal machine learning model is developed and validated to synthesize its probabilities as an in-silico quantitative marker for hyperuricemia (ISHUA). The model demonstrates satisfactory performance in detecting HUA, exhibiting area under the curves (AUCs) of 0.859, 0.836, and 0.779 within the train, internal, and external test sets, respectively. ISHUA is significantly associated with gout and metabolism-related outcomes, effectively classifying individuals into low- and high-risk groups for gout in the train (AUC, 0.815) and internal test (AUC, 0.814) sets. The high-risk group shows increased susceptibility to metabolism-related outcomes, and participants with intermediate or favorable lifestyle profiles have hazard ratios of 0.75 and 0.53 for gout compared with those with unfavorable lifestyles. Similar trends are observed for other metabolism-related outcomes. The multimodal machine learning-based ISHUA marker enables personalized risk stratification for gout and metabolism-related outcomes, and it is unveiled that lifestyle changes can ameliorate these outcomes within high-risk group, providing guidance for preventive interventions.

A high reticulocyte count is a risk factor for the onset of metabolic dysfunction-associated steatotic liver disease: Cross-sectional and prospective studies of data of 310,091 individuals from the UK Biobank.

Background and Aims: Metabolic dysfunction-associated steatotic liver disease (MASLD) poses a considerable health risk. Nevertheless, its risk factors are not thoroughly comprehended, and the association between the reticulocyte count and MASLD remains uncertain. This study aimed to explore the relationship between reticulocyte count and MASLD. Methods: A total of 310,091 individuals from the UK Biobank were included in this cross-sectional study, and 7,316 individuals were included in this prospective study. The cross-sectional analysis categorized reticulocyte count into quartiles, considering the sample distribution. Logistic regression models examined the connection between reticulocyte count and MASLD. In the prospective analysis, Cox analysis was utilized to investigate the association. Results: Our study findings indicate a significant association between higher reticulocyte count and an elevated risk of MASLD in both the cross-sectional and prospective analyses. In the cross-sectional analysis, the adjusted odds ratios (ORs) of MASLD increased stepwise over reticulocyte count quartiles (quartile 2: OR 1.22, 95% CI 1.17-1.28, p < 0.001; quartile 3: OR 1.44; 95% CI 1.38-1.51, p < 0.001; quartile 4: OR 1.66, 95% CI 1.59-1.74, p < 0.001). The results of prospective analyses were similar. Conclusion: Increased reticulocyte count was independently associated with a higher risk of MASLD. This discovery offers new insights into the potential of reticulocytes as biomarkers for MASLD.

Polygenic risk score of metabolic dysfunction-associated steatotic liver disease amplifies the health impact on severe liver disease and metabolism-related outcomes.

BACKGROUND: Although the inherited risk factors associated with fatty liver disease are well understood, little is known about the genetic background of metabolic dysfunction-associated steatotic liver disease (MASLD) and its related health impacts. Compared to non-alcoholic fatty liver disease (NAFLD), MASLD presents significantly distinct diagnostic criteria, and epidemiological and clinical features, but the related genetic variants are yet to be investigated. Therefore, we conducted this study to assess the genetic background of MASLD and interactions between MASLD-related genetic variants and metabolism-related outcomes. METHODS: Participants from the UK Biobank were grouped into discovery and replication cohorts for an MASLD genome-wide association study (GWAS), and base and target cohorts for polygenic risk score (PRS) analysis. Autosomal genetic variants associated with NAFLD were compared with the MASLD GWAS results. Kaplan-Meier and Cox regression analyses were used to assess associations between MASLD and metabolism-related outcomes. RESULTS: Sixteen single-nucleotide polymorphisms (SNPs) were identified at genome-wide significance levels for MASLD and duplicated in the replication cohort. Differences were found after comparing these SNPs with the results of NAFLD-related genetic variants. MASLD cases with high PRS had a multivariate-adjusted hazard ratio of 3.15 (95% confidence interval, 2.54-3.90) for severe liver disease (SLD), and 2.81 (2.60-3.03) for type 2 diabetes mellitus. The high PRS amplified the impact of MASLD on SLD and extrahepatic outcomes. CONCLUSIONS: High PRS of MASLD GWAS amplified the impact of MASLD on SLD and metabolism-related outcomes, thereby refining the process of identification of individuals at high risk of MASLD. Supplementation of this process with relevant genetic backgrounds may lead to more effective MASLD prevention and management.

Association between sarcopenia-related markers and cholelithiasis: A prospective and Mendelian randomization study.

Cholelithiasis is a common digestive disease that drives a myriad of adverse complications. The correlation between sarcopenia and various digestive disorders has been extensively researched, whereas its association with cholelithiasis remains unreported. We aimed to investigate the association through prospective and Mendelian randomization (MR) analyses and establish a quantitative score reflecting the impact of sarcopenia-related markers on cholelithiasis. The prospective study involved 448 627 participants from the UK Biobank. Cox proportional hazard models were employed to investigate the correlation between sarcopenia-related markers and cholelithiasis. To quantitatively assess cholelithiasis risk, the SARCHO score was derived from a multivariable Cox model. Bidirectional two-sample MR analysis was conducted to validate the causal association. A total of 16 738 individuals developed cholelithiasis during a median follow-up of 12 years. Hazard ratios (HRs) of cholelithiasis decreased stepwise over skeletal muscle index tertiles (highest tertile: reference; middle tertile: 1.23, p < .001; lowest tertile: 1.33, p < .001). The tertiles of grip strength showed a similar pattern. Individuals with slow walking pace had a higher risk of cholelithiasis compared to those with normal walking pace (HR 1.23; p < .001). Our SARCHO score better quantifies the risk of cholelithiasis. MR analysis showed a causal relationship between muscle mass and cholelithiasis (OR 0.81; p < .001). No causal effect of cholelithiasis on lean mass was observed. Prospective and MR analyses have consistently demonstrated an increased risk of cholelithiasis in individuals with decreased muscle mass. Additionally, SARCHO score further quantified the cholelithiasis occurrence risk. These findings provide compelling evidence for muscle strengthening in preventing cholelithiasis.

Association between fatty liver index and controlled attenuation parameters as markers of metabolic dysfunction-associated fatty liver disease and bone mineral density: observational and two-sample Mendelian randomization studies.

Previously observational studies did not draw a clear conclusion on the association between fatty liver diseases and bone mineral density (BMD). Our large-scale studies revealed that MAFLD and hepatic steatosis had no causal effect on BMD, while some metabolic factors were correlated with BMD. The findings have important implications for the relationship between fatty liver diseases and BMD, and may help direct the clinical management of MAFLD patients who experience osteoporosis and osteopenia. PURPOSE: Liver and bone are active endocrine organs with several metabolic functions. However, the link between metabolic dysfunction-associated fatty liver disease (MAFLD) and bone mineral density (BMD) is contradictory. METHODS: Using the UK Biobank and National Health and Nutrition Examination Survey (NHANES) dataset, we investigated the association between MAFLD, steatosis, and BMD in the observational analysis. We performed genome-wide association analysis to identify single-nucleotide polymorphisms associated with MAFLD. Large-scale two-sample Mendelian randomization (TSMR) analyses examined the potential causal relationship between MAFLD, hepatic steatosis, or major comorbid metabolic factors, and BMD. RESULTS: After adjusting for demographic factors and body mass index, logistic regression analysis demonstrated a significant association between MAFLD and reduced heel BMD. However, this association disappeared after adjusting for additional metabolic factors. MAFLD was not associated with total body, femur neck, and lumbar BMD in the NHANES dataset. Magnetic resonance imaging-measured steatosis did not show significant associations with reduced total body, femur neck, and lumbar BMD in multivariate analysis. TSMR analyses indicated that MAFLD and hepatic steatosis were not associated with BMD. Among all MAFLD-related comorbid factors, overweight and type 2 diabetes showed a causal relationship with increased BMD, while waist circumference and hyperlipidemia had the opposite effect. CONCLUSION: No causal effect of MAFLD and hepatic steatosis on BMD was observed in this study, while some metabolic factors were correlated with BMD. This has important implications for understanding the relationship between fatty liver disease and BMD, which may help direct the clinical management of MAFLD patients with osteoporosis.

Lower creatinine to cystatin C ratio is associated with an increased risk of MASLD: A cross-sectional and prospective study of 368,634 UK Biobank participants.

OBJECTIVE: Metabolic dysfunction-associated steatotic liver disease (MASLD) affects many populations, and screening out the high-risk populations at an early stage is a challenge. As a sarcopenia index, the relationship between creatinine to cystatin C ratio (CCR) and MASLD remains unclear. This cross-sectional, prospective study aimed to explore the relationship between CCR and MASLD. Design Firstly, explored the correlation between CCR and MASLD in cross-sectional analyses. Then excluded the population with baseeline diagnosis of MASLD and analyzed the association with baseline CCR levels and the onset of MASLD in the population with available follow-up data. Univariate and multivariate logistic regression analyses were used to calculate odds ratios (ORs) to evaluate the association between CCR levels and MASLD. PATIENTS AND MEASUREMENTS: This study included 368,634 participants from the UK Biobank for cross-sectional and prospective analyses. The demographic characteristics and laboratory measurements of all participants were obtained from the UK Biobank. MASLD was diagnosed according to the multi-society consensus nomenclature. Hepatic steatosis was defined as FLI  ≥60. RESULTS: We grouped the study participants according to CCR tertiles. In cross-sectional analyses, participants in CCR tertile 1 had the highest MASLD risk (OR: 1.070, 95% CI: 1.053-1.088, p < .001). And the similar association was observed in the prospective analyses (CCR tertile 1 OR: 1.340, 95% CI: 1.077-1.660, p = .009; CCR tertile 2 OR: 1.217, 95% CI: 1.021-1.450, p = .029, respectively). After stratification by gender, the significant association between CCR and the onset of MASLD was only observed in males (CCR tertile 1 OR: 1.639, 95% CI: 1.160-2.317, p = .005; CCR tertile 2 OR: 1.322, 95% CI: 1.073-1.628, p = .005, respectively). CONCLUSION: Our results indicated that lower CCR was significantly associated with higher risk of MASLD, based on which predictive models can be developed to screen populations at high risk of developing MASLD.

Determining the prognosis of Lung cancer from mutated genes using a deep learning survival model: a large multi-center study.

BACKGROUND: Gene status has become the focus of prognosis prediction. Furthermore, deep learning has frequently been implemented in medical imaging to diagnose, prognosticate, and evaluate treatment responses in patients with cancer. However, few deep learning survival (DLS) models based on mutational genes that are directly associated with patient prognosis in terms of progression-free survival (PFS) or overall survival (OS) have been reported. Additionally, DLS models have not been applied to determine IO-related prognosis based on mutational genes. Herein, we developed a deep learning method to predict the prognosis of patients with lung cancer treated with or without immunotherapy (IO). METHODS: Samples from 6542 patients from different centers were subjected to genome sequencing. A DLS model based on multi-panels of somatic mutations was trained and validated to predict OS in patients treated without IO and PFS in patients treated with IO. RESULTS: In patients treated without IO, the DLS model (low vs. high DLS) was trained using the training MSK-MET cohort (HR = 0.241 [0.213-0.273], P < 0.001) and tested in the inter-validation MSK-MET cohort (HR = 0.175 [0.148-0.206], P < 0.001). The DLS model was then validated with the OncoSG, MSK-CSC, and TCGA-LUAD cohorts (HR = 0.420 [0.272-0.649], P < 0.001; HR = 0.550 [0.424-0.714], P < 0.001; HR = 0.215 [0.159-0.291], P < 0.001, respectively). Subsequently, it was fine-tuned and retrained in patients treated with IO. The DLS model (low vs. high DLS) could predict PFS and OS in the MIND, MSKCC, and POPLAR/OAK cohorts (P < 0.001, respectively). Compared with tumor-node-metastasis staging, the COX model, tumor mutational burden, and programmed death-ligand 1 expression, the DLS model had the highest C-index in patients treated with or without IO. CONCLUSIONS: The DLS model based on mutational genes can robustly predict the prognosis of patients with lung cancer treated with or without IO.

The activity of cuproptosis pathway calculated by AUCell algorithm was employed to construct cuproptosis landscape in lung adenocarcinoma.

Cuproptosis is a recently described copper-dependent cell death pathway. Consequently, there are still few studies on lung adenocarcinoma (LUAD)-related cuproptosis, and we aimed to deepen in this matter. In this study, data from 503 patients with lung cancer from the TCGA-LUAD cohort data collection and 11 LUAD single-cells from GSE131907 as well as from 10 genes associated with cuproptosis were analyzed. The AUCell R package was used to determine the copper-dependent cell death pathway activity for each cell subpopulation, calculate the CellChat score, and display cell communication for each cell subpopulation. The PROGENy score was calculated to show the scores of tumor-related pathways in different cell populations. GO and KEGG analyses were used to calculate pathway activity. Univariate COX and random forest analyses were used to screen prognosis-associated genes and construct models. The ssGSEA and xCell algorithms were used to calculate the immunocyte infiltration score. Based on data from the GDSC database, the drug sensitivity score was calculated using oncoPredict. Finally, in vitro experiments were performed to determine the role of TLE1, the most important gene in the prognostic model. The 11 LUAD single-cell samples were classified into 8 different cell populations, from which epithelial cells showed the highest copper-dependent cell death pathway activity. Epithelial cell subsets were significantly positively correlated with MAKP, hypoxia, and other pathways. In addition, cell subgroup communication showed highly active collagen and APP pathways. Using the Findmark algorithm, differentially expressed genes (DEGs) between epithelial and other cell types were identified. Combined with the bulk data in the TCGA-LUAD database, DEGs were enriched in pathways such as EGFR tyrosine kinase inhibitor resistance, Hippo signaling pathway, and tight junction. Subsequently, we selected 4 genes (out of 112) with prognostic significance, ANKRD29, RHOV, TLE1, and NPAS2, and used them to construct a prognostic model. The high- and low-risk groups, distinguished by the median risk score, showed significantly different prognoses. Finally, we chose TLE1 as a biomarker based on the relative importance score in the prognostic model. In vitro experiments showed that TLE1 promotes tumor proliferation and migration and inhibits apoptosis.

Efficacy and safety of different PD-1 inhibitors in combination with lenvatinib in the treatment of unresectable primary liver cancer: a multicentre retrospective study.

Immune checkpoint inhibitors (ICIs) are safe and efficacious treatments for advanced primary liver cancer (PLC). The efficacy of different ICIs in the treatment of liver cancer remains unclear. The purpose of this study was to explore whether there is a difference in the efficacy and safety of various programmed cell death protein 1 (PD-1) inhibitors in combination with lenvatinib in the treatment of unresectable PLC. Patients with PLC treated with lenvatinib in combination with PD-1 inhibitors (camrelizumab, tislelizumab, sintilimab, or pembrolizumab) between January 2018 and December 2021 were retrospectively enrolled. Tumor response, adverse events, and grades were evaluated. Kaplan-Meier analysis and log-rank test were used to compare the overall survival and progression-free survival of patients treated with different PD-1 inhibitors. Cox regression analysis was used for univariate and multivariate analyses to identify clinical variables related to treatment efficacy. This study included a total of 176 patients who received a combination of lenvatinib and PD-1 inhibitors. Of these, 103 patients received camrelizumab, 44 received tislelizumab, 20 received sintilimab, and 9 received pembrolizumab. There was no significant difference in the pairwise comparison of camrelizumab, tislelizumab, sintilimab, and pembrolizumab using Kaplan-Meier survival analysis. Adverse events occurred in 40 (22.7%) patients (grade ≥ 3, 2.3%). The incidence of grade 3 adverse events among the four PD-1 inhibitor groups was below 5%. Camrelizumab, tislelizumab, sintilimab, and pembrolizumab are viable options for patients with unresectable PLC. These PD-1 inhibitors in combination with lenvatinib showed good safety profiles. The results guide selecting treatment for patients with unresectable PLC.

Targeting NAD+ metabolism of hepatocellular carcinoma cells by lenvatinib promotes M2 macrophages reverse polarization, suppressing the HCC progression.

BACKGROUND: Lowered nicotinamide adenine dinucleotide (NAD+) levels in tumor cells drive tumor hyperprogression during immunotherapy, and its restoration activates immune cells. However, the effect of lenvatinib, a first-line treatment for unresectable hepatocellular carcinoma (HCC), on NAD+ metabolism in HCC cells, and the metabolite crosstalk between HCC and immune cells after targeting NAD+ metabolism of HCC cells remain unelucidated. METHODS: Liquid chromatography-tandem mass spectrometry (LC-MS/MS) and ultra-high-performance liquid chromatography multiple reaction monitoring-mass spectrometry (UHPLC-MRM-MS) were used to detect and validate differential metabolites. RNA sequencing was used to explore mRNA expression in macrophages and HCC cells. HCC mouse models were used to validate the effects of lenvatinib on immune cells and NAD+ metabolism. The macrophage properties were elucidated using cell proliferation, apoptosis, and co-culture assays. In silico structural analysis and interaction assays were used to determine whether lenvatinib targets tet methylcytosine dioxygenase 2 (TET2). Flow cytometry was performed to assess changes in immune cells. RESULTS: Lenvatinib targeted TET2 to synthesize and increase NAD+ levels, thereby inhibiting decomposition in HCC cells. NAD+ salvage increased lenvatinib-induced apoptosis of HCC cells. Lenvatinib also induced CD8+ T cells and M1 macrophages infiltration in vivo. And lenvatinib suppressed niacinamide, 5-Hydroxy-L-tryptophan and quinoline secretion of HCC cells, and increased hypoxanthine secretion, which contributed to proliferation, migration and polarization function of macrophages. Consequently, lenvatinib targeted NAD+ metabolism and elevated HCC-derived hypoxanthine to enhance the macrophages polarization from M2 to M1. Glycosaminoglycan binding disorder and positive regulation of cytosolic calcium ion concentration were characteristic features of the reverse polarization. CONCLUSIONS: Targeting HCC cells NAD+ metabolism by lenvatinib-TET2 pathway drives metabolite crosstalk, leading to M2 macrophages reverse polarization, thereby suppressing HCC progression. Collectively, these novel insights highlight the role of lenvatinib or its combination therapies as promising therapeutic alternatives for HCC patients with low NAD+ levels or high TET2 levels.

Efficacy and safety of immune checkpoint inhibitors in elderly patients with primary liver cancer: a retrospective, multicenter, real-world cohort study.

BACKGROUND: There is still no specific real-world data regarding the clinical activity of immune checkpoint inhibitors in the elderly with liver cancer. Our study aimed to compare the efficacy and safety of immune checkpoint inhibitors between patients aged ≥ 65 years and the younger group, while exploring their differences in genomic background and tumor microenvironment. METHODS: This retrospective study was conducted at two hospitals in China and included 540 patients treated with immune checkpoint inhibitors for primary liver cancer between January 2018 and December 2021. Patients' medical records were reviewed for clinical and radiological data and oncologic outcomes. The genomic and clinical data of patients with primary liver cancer were extracted and analyzed from TCGA-LIHC, GSE14520, and GSE140901 datasets. RESULTS: Ninety-two patients were classified as elderly and showed better progression-free survival (P = 0.027) and disease control rate (P = 0.014). No difference was observed in overall survival (P = 0.69) or objective response rate (P = 0.423) between the two age groups. No significant difference was reported concerning the number (P = 0.824) and severity (P = 0.421) of adverse events. The enrichment analyses indicated that the elderly group was linked to lower expression of oncogenic pathways, such as PI3K-Akt, Wnt, and IL-17. The elderly had a higher tumor mutation burden than younger patients. CONCLUSIONS: Our results indicated that immune checkpoint inhibitors might exhibit better efficacy in the elderly with primary liver cancer, with no increased adverse events. Differences in genomic characteristics and tumor mutation burden may partially explain these results.

Characteristics of patients with SARS-COV-2 PCR re-positivity after recovering from COVID-19.

The purpose of this study was to analyse the clinical characteristics of patients with severe acute respiratory syndrome coronavirus 2 (SARS-COV-2) PCR re-positivity after recovering from coronavirus disease 2019 (COVID-19). Patients (n = 1391) from Guangzhou, China, who had recovered from COVID-19 were recruited between 7 September 2021 and 11 March 2022. Data on epidemiology, symptoms, laboratory test results and treatment were analysed. In this study, 42.7% of recovered patients had re-positive result. Most re-positive patients were asymptomatic, did not have severe comorbidities, and were not contagious. The re-positivity rate was 39%, 46%, 11% and 25% in patients who had received inactivated, mRNA, adenovirus vector and recombinant subunit vaccines, respectively. Seven independent risk factors for testing re-positive were identified, and a predictive model was constructed using these variables. The predictors of re-positivity were COVID-19 vaccination status, previous SARs-CoV-12 infection prior to the most recent episode, renal function, SARS-CoV-2 IgG and IgM antibody levels and white blood cell count. The predictive model could benefit the control of the spread of COVID-19.

Predictive Value of the Hepatic Immune Predictive Index for Patients with Primary Liver Cancer Treated with Immune Checkpoint Inhibitors.

BACKGROUND: Immune checkpoint inhibitors (ICIs) have improved survival outcomes and resulted in long-term responses in primary liver cancer in some patients. Nevertheless, not all patients with PLC could benefit from immunotherapy. Therefore, it is necessary to identify patients suitable for such therapy. METHODS: 215 patients with primary liver cancer with immunotherapy from Nanfang Hospital were screened between August 2018 and October 2020 as a training set and our validation set included 71 patients of hepatocellular carcinoma from Jiangxi Cancer Hospital from May 2019 to July 2021. The primary endpoint was the disease control rate (DCR), and the secondary endpoints were overall survival (OS) and progression-free survival. RESULTS: In the training set, neutrophil-lymphocyte ratio (NLR) ≥3 and alpha-fetoprotein (AFP) level ≥20 ng/mL were independently associated with non-DCR in the training set after adjusting for distant metastasis at baseline and targeted therapy combination. Furthermore, a hepatic immune predictive index (HIPI) based on NLR and AFP level was developed and patients with poor HIPI associated with worse clinical outcomes. In validation set, high HIPI was associated with poor OS. CONCLUSION: HIPI, based on NLR and AFP level, is an effective indicator in ICI-treated patients with primary liver cancer. Our findings may help guide the selection and on-treatment strategies for immunotherapies for primary liver cancer patients.

Deep learning to estimate durable clinical benefit and prognosis from patients with non-small cell lung cancer treated with PD-1/PD-L1 blockade.

Different biomarkers based on genomics variants have been used to predict the response of patients treated with PD-1/programmed death receptor 1 ligand (PD-L1) blockade. We aimed to use deep-learning algorithm to estimate clinical benefit in patients with non-small-cell lung cancer (NSCLC) before immunotherapy. Peripheral blood samples or tumor tissues of 915 patients from three independent centers were profiled by whole-exome sequencing or next-generation sequencing. Based on convolutional neural network (CNN) and three conventional machine learning (cML) methods, we used multi-panels to train the models for predicting the durable clinical benefit (DCB) and combined them to develop a nomogram model for predicting prognosis. In the three cohorts, the CNN achieved the highest area under the curve of predicting DCB among cML, PD-L1 expression, and tumor mutational burden (area under the curve [AUC] = 0.965, 95% confidence interval [CI]: 0.949-0.978, P< 0.001; AUC =0.965, 95% CI: 0.940-0.989, P< 0.001; AUC = 0.959, 95% CI: 0.942-0.976, P< 0.001, respectively). Patients with CNN-high had longer progression-free survival (PFS) and overall survival (OS) than patients with CNN-low in the three cohorts. Subgroup analysis confirmed the efficient predictive ability of CNN. Combining three cML methods (CNN, SVM, and RF) yielded a robust comprehensive nomogram for predicting PFS and OS in the three cohorts (each P< 0.001). The proposed deep-learning method based on mutational genes revealed the potential value of clinical benefit prediction in patients with NSCLC and provides novel insights for combined machine learning in PD-1/PD-L1 blockade.

CT images-based 3D convolutional neural network to predict early recurrence of solitary hepatocellular carcinoma after radical hepatectomy.

PURPOSE The high rate of recurrence of hepatocellular carcinoma (HCC) after radical hepatectomy is an important factor that affects the long-term survival of patients. This study aimed to develop a computed tomography (CT) images-based 3-dimensional (3D) convolutional neural network (CNN) for the preoperative prediction of early recurrence (ER) (≤2 years) after radical hepatectomy in patients with solitary HCC and to compare the effects of segmentation sampling (SS) and non-segmentation sampling (NSS) on the prediction performance of 3D-CNN. METHODS Contrast-enhanced CT images of 220 HCC patients were used in this study (training group=178 and test group=42). We used SS and NSS to select the volume-of-interest to train SS-3D-CNN and NSS-3D-CNN separately. The prediction accuracy was evaluated using the test group. Finally, gradient-weighted class activation mappings (Grad-CAMs) were plotted to analyze the difference of prediction logic between the SS-3D-CNN and NSS-3D-CNN. RESULTS The areas under the receiver operating characteristic curves (AUCs) of the SS-3D-CNN and NSS3D-CNN in the training group were 0.824 (95% CI: 0.764-0.885) and 0.868 (95% CI: 0.815-0.921). The AUC of the SS-3D-CNN and NSS-3D-CNN in the test group were 0.789 (95% CI: 0.637-0.941) and 0.560 (95% CI: 0.378-0.742). The SS-3D-CNN could stratify patients into low- and high-risk groups, with significant differences in recurrence-free survival (RFS) (P < .001). But NSS-3D-CNN could not effectively stratify them in the test group. According to the Grad-CAMs, compared with SS-3D-CNN, NSS-3D-CNN was obviously interfered by the nearby tissues. CONCLUSION SS-3D-CNN may be of clinical use for identifying high-risk patients and formulating individualized treatment and follow-up strategies. SS is better than NSS in improving the performance of 3D-CNN in our study.

Use of computed tomography-derived body composition to determine the prognosis of patients with primary liver cancer treated with immune checkpoint inhibitors: a retrospective cohort study.

BACKGROUND: Immune checkpoint inhibitors (ICIs) have been used to successfully treat primary liver cancer (PLC); however, identifying modifiable patient factors associated with therapeutic benefits is challenging. Obesity is known to be associated with increased survival after ICI treatment; however, the relationship between body composition (muscle, fat) and outcomes is unclear. This study aimed to evaluate the association between sarcopenia and CT-derived fat content and the prognosis of ICIs for the treatment of PLC. METHODS: In this retrospective cohort study of 172 patients with PLC, we measured the skeletal muscle index (SMI), skeletal muscle density, visceral adipose tissue index, subcutaneous adipose tissue index, total adipose tissue index (TATI), and visceral-to-subcutaneous adipose tissue area ratio using CT. In addition, we analyzed the impact of body composition on the prognosis of the patients. Multivariate Cox regression analysis was used to screen for influencing factors. RESULTS: Among the seven body composition components, low SMI (sarcopenia) and low TATI were significantly associated with poor clinical outcomes. Multivariate analysis revealed that sarcopenia (hazard ratio [HR], 5.39; 95% confidence interval [CI], 1.74-16.74; p = 0.004) was a significant predictor of overall survival (OS). Kaplan-Meier curves showed that sarcopenia and TATI were significant predictors of OS. Body mass index was not associated with survival outcomes. CONCLUSIONS: Sarcopenia and fat tissue content appear to be independently associated with reduced survival rates in patients with PLC treated with ICIs.

A Somatic Mutation Signature Predicts the Best Overall Response to Anti-programmed Cell Death Protein-1 Treatment in Epidermal Growth Factor Receptor/Anaplastic Lymphoma Kinase-Negative Non-squamous Non-small Cell Lung Cancer.

Background: We aimed to exploit a somatic mutation signature (SMS) to predict the best overall response to anti-programmed cell death protein-1 (PD-1) therapy in non-small cell lung cancer (NSCLC). Methods: Tumor samples of 248 patients with epidermal growth factor receptor (EGFR)/anaplastic lymphoma kinase (ALK)-negative non-squamous NSCLC treated with anti-PD-1 were molecularly tested by targeted next-generation sequencing or whole exome sequencing. On the basis of machine learning, we developed and validated a predictive model named SMS using the training (n = 83) and validation (n = 165) cohorts. Results: The SMS model comprising a panel of 15 genes (TP53, PTPRD, SMARCA4, FAT1, MGA, NOTCH1, NTRK3, INPP4B, KMT2A, PAK1, ATRX, BCOR, KDM5C, DDR2, and ARID1B) was built to predict best overall response in the training cohort. The areas under the curves of the training and validation cohorts were higher than those of tumor mutational burden and PD-L1 expression. Patients with SMS-high in the training and validation cohorts had poorer progression-free survival [hazard ratio (HR) = 6.01, P < 0.001; HR = 3.89, P < 0.001] and overall survival (HR = 7.60, P < 0.001; HR = 2.82, P < 0.001) than patients with SMS-low. SMS was an independent factor in multivariate analyses of progression-free survival and overall survival (HR = 4.32, P < 0.001; HR = 3.07, P < 0.001, respectively). Conclusion: This study revealed the predictive value of SMS for immunotherapy best overall response and prognosis in EGFR/ALK-negative non-squamous NSCLC as a potential biomarker in anti-PD-1 therapy.

Splenomegaly in predicting the survival of patients with advanced primary liver cancer treated with immune checkpoint inhibitors.

BACKGROUND & AIMS: Immune checkpoint inhibitors (ICIs) play an increasingly important role in the treatment of primary liver cancer (PLC). Some patients with PLC experience symptoms of splenomegaly. Splenomegaly may affect the efficacy of ICIs due to an imbalance of the immune microenvironment. Currently, there is a lack of evidence on the relationship between splenomegaly and prognosis in patients with PLC treated with ICIs. This study analyzed the relationship between splenomegaly and prognosis in patients with PLC treated with ICIs. METHODS: In this retrospective cohort study of 161 patients with PLC treated with ICIs, splenomegaly was diagnosed using computed tomography or magnetic resonance imaging and the impact of splenomegaly on patient survival was analyzed. RESULTS: Through univariate and multivariate Cox regression analyses, we determined that splenomegaly was associated with shortened overall survival (p = 0.002) and progression-free survival (p = 0.013) in patients with PLC treated with ICIs. Kaplan-Meier analysis further validated our results. The overall survival and progression-free survival of patients with splenomegaly were significantly shorter than those of patients without splenomegaly (p < 0.01 and p = 0.02, respectively). CONCLUSIONS: We concluded that splenomegaly was a predictor of prognosis in patients with PLC treated with ICIs. This is the first study to report this important finding.