Artificial intelligence for prediction of response to cancer immunotherapy.

Artificial intelligence (AI) indicates the application of machines to imitate intelligent behaviors for solving complex tasks with minimal human intervention, including machine learning and deep learning. The use of AI in medicine improves health-care systems in multiple areas such as diagnostic confirmation, risk stratification, analysis, prognosis prediction, treatment surveillance, and virtual health support, which has considerable potential to revolutionize and reshape medicine. In terms of immunotherapy, AI has been applied to unlock underlying immune signatures to associate with responses to immunotherapy indirectly as well as predict responses to immunotherapy responses directly. The AI-based analysis of high-throughput sequences and medical images can provide useful information for management of cancer immunotherapy considering the excellent abilities in selecting appropriate subjects, improving therapeutic regimens, and predicting individualized prognosis. In present review, we aim to evaluate a broad framework about AI-based computational approaches for prediction of response to cancer immunotherapy on both indirect and direct manners. Furthermore, we summarize our perspectives about challenges and opportunities of further AI applications on cancer immunotherapy relating to clinical practicability.

Safety and efficacy profile of mogamulizumab (Poteligeo) in the treatment of cancers: an update evidence from 14 studies.

BACKGROUND: CC chemokine receptor 4 (CCR4), the receptor for CCL22 and CCL17, is expressed on the surface of effector Tregs that have the highest suppressive effects on antitumor immune response. CCR4 is also widely expressed on the surface of tumor cells from patients with adult T-cell leukemia/lymphoma (ATL), peripheral T-cell lymphoma (PTCL) and cutaneous T-cell lymphoma (CTCL). Mogamulizumab is a humanized, IgG1 kappa monoclonal antibody that is directed against CCR4. By reducing the number of CCR4-positive Tregs and tumor cells, the mogamulizumab can reduce tumor burden and boost antitumor immunity to achieve antitumor effects. METHODS: We examined the PubMed and ClinicalTrials.gov until 1 February 2020. Considering variability in different studies, we selected the adverse events (AEs), overall survival (OS), progression-free survival (PFS), objective responses rate (ORR) and Hazard Ratio (HR) for PFS to evaluate the safety and efficacy profile of mogamulizumab. RESULTS: When patients were treated with mogamulizumab monotherapy, the most common all-grade AEs were lymphopenia, infusion reaction, fever, rash and chills while the most common grade ≥ 3 AEs were lymphopenia, neutropenia and rash. When patients were treated with combined therapy of mogamulizumab and other drugs, the most common all-grade AEs were neutropenia, anaemia, lymphopenia and gastrointestinal disorder, while the most common grade ≥ 3 AEs was lymphopenia. For patients treated with mogamulizumab monotherapy, the pooled ORR and mean PFS were 0.430 (95% CI: 0.393-0.469) and 1.060 months (95% CI: 1.043-1.077), respectively. For patients treated with combined therapy of mogamulizumab and other drugs, the pooled ORR was 0.203 (95% CI: 0.022-0.746) while the pooled PFS and OS were 2.093 months (95% CI: 1.602-2.584) and 6.591 months (95% CI: 6.014-7.167), respectively. CONCLUSIONS: Based on present evidence, we believed that mogamulizumab had clinically meaningful antitumor activity with acceptable toxicity which is a novel therapy in treating patients with cancers.

The clinical characteristics and prognostic factors of combined Hepatocellular Carcinoma and Cholangiocarcinoma, Hepatocellular Carcinoma and Intrahepatic Cholangiocarcinoma after Surgical Resection: A propensity score matching analysis.

Background: Clinical characteristics and prognosis among combined hepatocellular carcinoma (HCC) and cholangiocarcinoma (cHCC-CC) with HCC and intrahepatic cholangiocarcinoma (ICC) were inconsistent in previous studies. The aim of this study was to compare postoperative prognosis among cHCC-CC, HCC and ICC, and investigated the prognostic risk factor of cHCC-CC after surgical resection. Methods: A total of 1041 eligible patients with pathological diagnosis of cHCC-CC (n=135), HCC (n=698) and ICC (n=208) were enrolled in this study. Univariate and multivariate Cox analysis were applied for assessing important risk factors. cHCC-CC were further 1:1 matched with HCC and ICC on important clinical risk factors. Survival curves of matched and unmatched cohorts were depicted by Kaplan-Meier method with log-rank test. Results: Patients with cHCC-CC had similar rate of sex, age and cirrhosis with HCC (p<0.05) and comparable incidence of hepatitis B or C with ICC (p=0.197). Patients of cHCC-CC had intermediate prognosis between HCC and ICC, with median overall survival (OS) time of cHCC-CC, HCC and ICC of 20.5 months, 35.7 months and 11.6 months (p<0.001). In matched cohorts, the OS of cHCC-CC were worse than HCC (p<0.001) but comparable with ICC (p=0.06), while the disease-free survival (DFS) of cHCC-CC was worse than HCC but better than ICC (p<0.05). And lymph node infiltration and postoperative transarterial chemoembolization (TACE) were independent risk factors of cHCC-CC associated with prognosis. Conclusion: The long term survival of cHCC-CC was worse than HCC but comparable with ICC when matched on albumin level, tumor size, lymph node infiltration, tumor stage and margin. Presence of lymph node infiltration and no postoperative TACE were associated with poor prognosis of cHCC-CC.

Development and validation of a comprehensive radiomics nomogram for prognostic prediction of primary hepatic sarcomatoid carcinoma after surgical resection.

Objective: This study aimed to establish and validate a radiomics nomogram comprised of clinical factors and radiomics signatures to predict prognosis of primary hepatic sarcomatoid carcinoma (PHSC) patients after surgical resection. Methods: In this retrospective study, 79 patients with pathological confirmation of PHSC and underwent surgical resection were recruited. A radiomics nomogram was developed by radiomics signatures and independent clinical risk factors selecting from multivariate Cox regression. All patients were stratified as high risk and low risk by nomogram. Model performance and clinical usefulness were assessed by C-index, calibration curve, decision curve analysis (DCA) and survival curve. Results: A total of 79 PHSC were included with 1-year and 3-year overall survival rates of 63.3% and 35.4%, respectively. The least absolute shrinkage and selection operator (LASSO) method selected 3 features. Multivariate Cox analysis found six independent prognostic factors. The radiomics nomogram showed a significant prediction value with overall survival (HR: 7.111, 95%CI: 3.933-12.858, P<0.001). C-index of nomogram was 0.855 and 0.829 in training and validation set, respectively. Decision curve analysis validated the clinical utility of this nomogram. There was a significant difference in the 1-year and 3-year survival rates of stratified high-risk and low-risk patients in the whole cohort (30.6% vs. 90.1% and 5.6% vs. 62.4%, respectively, P < 0.001). Conclusion: This radiomics nomogram serve as a potential tool for predicting prognosis of PHSC after surgical resection, and help to identify high risk patients who may obtain feeble survival benefit from surgical resection.

The preoperative prognostic value of the radiomics nomogram based on CT combined with machine learning in patients with intrahepatic cholangiocarcinoma.

BACKGROUND: Intrahepatic cholangiocarcinoma is an aggressive liver carcinoma with increasing incidence and mortality. A good auxiliary prognostic prediction tool is desperately needed for the development of treatment strategies. The purpose of this study was to explore the prognostic value of the radiomics nomogram based on enhanced CT in intrahepatic cholangiocarcinoma. METHODS: In this retrospective study, 101 patients with pathological confirmation of intrahepatic cholangiocarcinoma were recruited. A radiomics nomogram was developed by radiomics score and independent clinical risk factors selecting from multivariate Cox regression. All patients were stratified as high risk and low risk by a nomogram. Model performance and clinical usefulness were assessed by calibration curve, ROC curve, and survival curve. RESULTS: A total of 101patients (mean age, 58.2 years old; range 36-79 years old) were included in the study. The 1-year, 3-year, and 5-year overall survival rates were 49.5%, 26.6%, and 14.4%, respectively, with a median survival time of 12.2 months in the whole set. The least absolute shrinkage and selection operator (LASSO) method selected 3 features. Multivariate Cox analysis found three independent prognostic factors. The radiomics nomogram showed a significant prognosis value with overall survival. There was a significant difference in the 1-year and 3-year survival rates of stratified high-risk and low-risk patients in the whole set (30.4% vs. 56.4% and 13.0% vs. 30.6%, respectively, p = 0.018). CONCLUSIONS: This radiomics nomogram has potential application value in the preoperative prognostic prediction of intrahepatic cholangiocarcinoma and may facilitate in clinical decision-making.

The efficacy and safety of anti-CD19/CD20 chimeric antigen receptor- T cells immunotherapy in relapsed or refractory B-cell malignancies:a meta-analysis.

BACKGROUND: Chimeric antigen receptor T (CAR T) cells immunotherapy is rapidly developed in treating cancers, especially relapsed or refractory B-cell malignancies. METHODS: To assess the efficacy and safety of CAR T therapy, we analyzed clinical trials from PUBMED and EMBASE. RESULTS: Results showed that the pooled response rate, 6-months and 1-year progression-free survival (PFS) rate were 67%, 65.62% and 44.18%, respectively. We observed that received lymphodepletion (72% vs 44%, P = 0.0405) and high peak serum IL-2 level (85% vs 31%, P = 0.04) were positively associated with patients' response to CAR T cells. Similarly, costimulatory domains (CD28 vs CD137) in second generation CAR T was positively associated with PFS (52.69% vs 33.39%, P = 0.0489). The pooled risks of all grade adverse effects (AEs) and grade ≥ 3 AEs were 71% and 43%. Most common grade ≥ 3 AEs were fatigue (18%), night sweats (14%), hypotension (12%), injection site reaction (12%), leukopenia (10%), anemia (9%). CONCLUSIONS: In conclusion, CAR T therapy has promising outcomes with tolerable AEs in relapsed or refractory B-cell malignancies. Further modifications of CAR structure and optimal therapy strategy in continued clinical trials are needed to obtain significant improvements.

Immune checkpoint HLA-E:CD94-NKG2A mediates evasion of circulating tumor cells from NK cell surveillance.

Circulating tumor cells (CTCs), shed by primary malignancies, function as "seeds" for distant metastasis. However, it is still largely unknown how CTCs escape immune surveillance. Here, we characterize the transcriptomes of human pancreatic ductal adenocarcinoma CTCs, primary, and metastatic lesions at single-cell scale. Cell-interaction analysis and functional studies in vitro and in vivo reveal that CTCs and natural killer (NK) cells interact via the immune checkpoint molecule pair HLA-E:CD94-NKG2A. Disruption of this interaction by blockade of NKG2A or knockdown of HLA-E expression enhances NK-mediated tumor cell killing in vitro and prevents tumor metastasis in vivo. Mechanistic studies indicate that platelet-derived RGS18 promotes the expression of HLA-E through AKT-GSK3ß-CREB signaling, and overexpression of RGS18 facilitates pancreatic tumor hepatic metastasis. In conclusion, platelet-derived RGS18 protects CTCs from NK-mediated immune surveillance by engaging the immune checkpoint HLA-E:CD94-NKG2A. Interruption of the suppressive signaling prevents tumor metastasis in vivo by immune elimination of CTCs.

The role of cancer-associated mesothelial cells in the progression and therapy of ovarian cancer.

Ovarian cancer is currently one of the most common malignant tumors in females with poor survival rates around the world, killing about 200,000 women each year. Although great progress has been made in treatment, most patients receiving first-line therapy experience tumor recurrence. The tumor microenvironment plays an important role in regulating the progression and prognosis of ovarian cancer. Cancer-associated mesothelial cells are the main cell population in the tumor microenvironment, which affect the progression, prognosis and chemical resistance of ovarian cancer. Cancer-associated mesothelial cells can also interact with other microenvironmental components, such as exosomes, macrophages, and adipocytes. Some studies have developed drugs targeting cancer-associated mesothelial cells in ovarian cancer to evaluate the therapeutic efficiency. In this review we highlighted the key role of cancer-associated mesothelial cells in the progression and prognosis of ovarian cancer. We also described the progress of cancer-associated mesothelial cells targeted therapy for ovarian cancer. Continued insight into the role of cancer-associated mesothelial cells in ovarian cancer will potentially contribute to the development of new and effective therapeutic regiments.

Pretreatment Inflammatory Markers Predict Outcomes and Prognosis in Colorectal Cancer Patients With Synchronous Liver Metastasis.

Introduction: Pretreatment inflammatory markers were applied to predict the prognosis of colorectal cancer. However, the role of these markers in predicting survival in patients with synchronous colorectal liver metastasis (CLM) is rarely reported. Notably, lymphocyte-to-monocyte ratio (LMR) was mainly reported in hematologic malignancies and is worth to be further explored to predict the survival of synchronous CLM. Methods: Totally, 196 patients who were diagnosed with synchronous CLM were enrolled. Their clinical and laboratory data before treatment were collected, retrospectively. Univariate and multivariate analyses were performed to analyze the inflammatory biomarkers. Results: LMR (P = .002) and lactate dehydrogenase (LDH) (P = .017) were significantly related to the progression-free survival (PFS). More factors such as neutrophil-to-lymphocyte ratio (NLR) (P = .011), carbohydrate antigen 19-9 (CA19-9) (P = .001), number of metastatic foci (P = .006), and adjuvant chemotherapy (P = .027) were correlated with overall survival (OS). In multivariate analysis, LMR remained statistically associated with PFS (P = .003). Regarding OS, LMR (P = .016) and LDH (P = .013) were significantly independent predictive factors. Conclusions: The higher LMR and lower LDH were strongly correlated with better survival in synchronous CLM patients. In addition, the result also indicated that enhanced LMR was related to better PFS. The LMR and LDH can be used to predict prognosis of the synchronous CLM.

Targeting Myeloid-Derived Suppressor Cells Derived From Surgical Stress: The Key to Prevent Post-surgical Metastasis.

Myeloid-derived suppressor cells (MDSCs) are known to play an essential part in tumor progression under chronic stress settings through their manipulation of adaptive and innate immune systems. Previous researches mainly focus on MDSC's role in the chronic tumor immune environment. In addition, surgery can also serve as a form of acute stress within the patient's internal environment. Nevertheless, the part that MDSCs play in post-surgical tumor development has not gained enough attention yet. Although surgery is known to be an effective definite treatment for most localized solid tumors, there are still plenty of cancer patients who experience recurrence or metastasis after radical resection of the primary tumor. It is believed that surgery has the paradoxical capability to enhance tumor growth. Many possible mechanisms exist for explaining post-surgical metastasis. We hypothesize that surgical resection of the primary tumor can also facilitate the expansion of MDSCs and their pro-tumor role since these surgery-induced MDSCs can prepare the pre-metastatic niche (the "soil") and at the same time interact with circulating tumor cells (the "seeds"). This vicious, reciprocal mechanism is a crucial point in the emergence of post-surgical metastasis. According to our hypothesis, MDSCs can be the precise target to prevent cancer patients from post-surgical recurrence and metastasis during the perioperative phase to break the wretched cycle and provide better long-term survival for these patients. Future studies are needed to validate this hypothesis.

Nomograms for Predicting Prognosis of Primary Mediastinal Seminoma: A Population-Based Study.

OBJECTIVES: Primary mediastinal seminoma (PMS) was an uncommon carcinoma, and the appropriate treatment remained controversial due to the low incidence. We aimed to investigate the demographics and tumor biological characteristics to determine the potential effective treatment and predict the prognosis. METHODS: Patients diagnosed with PMS were selected between 1975 and 2016 from Surveillance, Epidemiology, and End Results (SEER) database. Kaplan-Meier analysis and Cox proportional hazard model were conducted to determine the prognostic factors, and nomograms were employed to visually predict the prognosis. Concordance index (C-index), calibration curve, and receiver operating characteristic (ROC) curve were conducted to validate the prediction model. RESULTS: A total of 476 patients were included with a median age of 31 years (range, 2-76 years), and a median size of the tumor was 11.6 cm (range, 0.2-24.0 cm). The 5- and 10-year overall survival (OS) rates were 70.4% and 68.4%, respectively. Age, the extent of the primary site, metastatic status, and surgery performance were independent prognostic factors. Not received surgery was considered a poor prognostic factor for OS (HR, 1.86; 95% CI, 1.13-3.03; P=0.013). The C-index was 0.733 (95% CI, 0.685-0.781) and 0.819 (95% CI, 0.737-0.901) for internal and external validation for predicting OS, respectively. The area under the ROC curve (AUC) was 0.743 (95% CI, 0.681-0.804) for predicting OS (sensitivity, 0.532; specificity, 0.887) in the training cohort. CONCLUSIONS: The nomogram could efficiently predict the survival of patients with PMS. Surgery was the potential effective treatment, and chemotherapy was strongly recommended for patients over 40 years.

Comprehensive radiomics nomogram for predicting survival of patients with combined hepatocellular carcinoma and cholangiocarcinoma.

BACKGROUND: Combined hepatocellular carcinoma (HCC) and cholangiocarcinoma (cHCC-CCA) is defined as a single nodule showing differentiation into HCC and intrahepatic cholangiocarcinoma and has a poor prognosis. AIM: To develop a radiomics nomogram for predicting post-resection survival of patients with cHCC-CCA. METHODS: Patients with pathologically diagnosed cHCC-CCA were randomly divided into training and validation sets. Radiomics features were extracted from portal venous phase computed tomography (CT) images using the least absolute shrinkage and selection operator Cox regression and random forest analysis. A nomogram integrating the radiomics score and clinical factors was developed using univariate analysis and multivariate Cox regression. Nomogram performance was assessed in terms of the C-index as well as calibration, decision, and survival curves. RESULTS: CT and clinical data of 118 patients were included in the study. The radiomics score, vascular invasion, anatomical resection, total bilirubin level, and satellite lesions were found to be independent predictors of overall survival (OS) and were therefore included in an integrative nomogram. The nomogram was more strongly associated with OS (hazard ratio: 8.155, 95% confidence interval: 4.498-14.785, P < 0.001) than a model based on the radiomics score or only clinical factors. The area under the curve values for 1-year and 3-year OS in the training set were 0.878 and 0.875, respectively. Patients stratified as being at high risk of poor prognosis showed a significantly shorter median OS than those stratified as being at low risk (6.1 vs 81.6 mo, P < 0.001). CONCLUSION: This nomogram may predict survival of cHCC-CCA patients after hepatectomy and therefore help identify those more likely to benefit from surgery.

Clinical benefit of neoadjuvant anti-PD-1/PD-L1 utilization among different tumors.

PD-1/PD-L1 (programmed cell death-1 and programmed death-ligand 1) inhibitors utilization in neoadjuvant therapy has been assessed in tumors. This study focused on the clinical benefits of neoadjuvant anti-PD-1/PD-L1 therapy. A comprehensive search was conducted in electronic databases to identify eligible studies. Major response rate (MRR) and complete response rate (CRR) were pooled in this analysis to assess the efficacy of neoadjuvant anti-PD-1/PD-L1 utilization, all grades and high-grade adverse events (AEs) were pooled to evaluate its safety. Twenty studies were included in this meta-analysis, with 828 patients suffering from different tumors. The pooled CRR of triple-negative breast cancer was 0.569 (95% CI 0.514, 0.624, I 2 = 0%) and the pooled MRR of lung cancer was 0.471 (95% CI 0.267, 0.575, I 2 = 0%). The most frequent adverse event was fatigue (0.272 95% CI 0.171, 0.402, I 2 = 87%), and the most common high-grade adverse event was febrile neutropenia (0.084 95% CI 0.063, 0.112, I 2 = 85%). In conclusion, neoadjuvant anti-PD-1/PD-L1 therapy received satisfactory clinical results in these tumors included.

Clinical Utility of Contrast-enhanced Ultrasound for the Diagnosis of Lymphadenopathy.

This meta-analysis aimed to evaluate the diagnostic accuracy of contrast-enhanced ultrasonography (CEUS) in identifying lymphazdenopathy. PubMed, Web of Science, Embase and the Cochrane Library were searched for relevant articles through September 2020. A total of 16 articles, which included 1787 participants, were analyzed. The summary sensitivity, specificity, positive likelihood ratio (LR), negative LR and diagnostic odds ratio of CEUS for diagnosing lymphadenopathy were 0.88 (0.86-0.90), 0.90 (0.88-0.92), 6.04 (3.67-9.95), 0.15 (0.10-0.21) and 47.38 (23.45-95.66), respectively. The summary receiver operating characteristic (SROC) area under the curve (AUC) was 0.9405. After omitting outliers identified in a bivariate box plot and forest plot, heterogeneity was decreased, and the pooled sensitivity and specificity were 0.87 (0.84-0.90) and 0.87 (0.84-0.90), respectively. Furthermore, the SROC AUC was 0.9327. In conclusion, CEUS has the potential to be a valuable tool for characterizing lymphadenopathy and could provide clinical decision support.

The diagnostic performance of the Gynecologic Imaging Reporting and Data System (GI-RADS) in adnexal masses.

BACKGROUND: Adnexal masses, mostly benign, are common in the female genital system. However, adnexal masses are the leading cause of death among women with gynecologic cancer. Ultrasound is a common imaging method for diagnosing adnexal masses. Gynecologic Imaging Reporting and Data System (GI-RADS) is a useful diagnostic tool based on objective ultrasound features to diagnose the malignancy of the female genital system. Therefore, we conducted a meta-analysis to evaluate the ability of GI-RADS to differentiate adnexal masses. METHODS: Published articles were searched in PubMed, Medline, and Embase from 1990 to February 2020. Pooled sensitivity, specificity, positive likelihood ratio (PLR), negative likelihood ratio (NLR), diagnostic odds ratio, and area under the curve (AUC) were estimated via the extracted data from the selected studies. RESULTS: Ten studies and 2,474 patients were included in this meta-analysis. The pooled sensitivity of selected studies was 0.95 [95% confidence intervals (CI): 0.94-0.97], and the pooled specificity was 0.86 (95% CI: 0.84-0.88). The pooled NLR and PLR were 0.06 (95% CI: 0.04-0.10), and 8.30 (95% CI: 4.93-13.97), respectively. Moreover, the pooled diagnostic odds ratio for GI-RADS was 174.59 (95% CI: 76.70-397.42), and the AUC was 0.9806. CONCLUSIONS: This research indicates that GI-RADS might be a valuable tool to distinguish malignancies from adnexal masses.

Apigenin inhibits the growth of colorectal cancer through down-regulation of E2F1/3 by miRNA-215-5p.

BACKGROUND: Apigenin (API) is a naturally occurring plant-derived flavone, which is abundantly present in common fruits and vegetables, and shows little or no toxicity of daily diet. The treatment of colorectal cancer is limited by high recurrence rate and multidrug resistance. PURPOSE: The purpose of this study was to explore the potential therapeutic effect and possible mechanisms of API on colorectal cancer cells. METHODS: Cell proliferation and apoptosis of human colon cancer cell line HCT116 was assessed after API treatment. A comprehensive transcriptome profile of API-treated HCT116 cells was acquired by high-throughput sequencing. The regulation of miRNA215-5p and E2F1/3 were identified by bioinformatics analyses. An inhibitor of miRNA215-5p, inhibitor 215, was applied to confirm the role of this microRNA played in the anti-cancer effect of API. Luciferase reporter gene assay was performed to identify targeting relationship between miRNA215-5p and E2F1/3. RESULT: API significantly promoted cell apoptosis and anti-proliferation of HCT116 cells in a dose-dependent manner. Bioinformatics analyses identified several altered miRNAs among which the expression of miRNA-215-5p showed markedly increased. Meanwhile, the expression of E2F1 and E2F3 was decreased by API, which was associated with miRNA215-5p. Luciferase reporter gene assay showed miRNA-215-5p could directly bind to 3' UTR of E2F1/3. Inhibition of miRNA-215-5p significantly inhibited apoptosis and cell cycle arrest at G0/G1 phase induced by API. CONCLUSIONS: The result of this study confirmed the anti-cancer effect of API on human colorectal cancer cells and investigated the underlying mechanism by a comprehensive transcriptome profile of API-treated cells.

Differentiation of Intrahepatic Cholangiocarcinoma and Hepatic Lymphoma Based on Radiomics and Machine Learning in Contrast-Enhanced Computer Tomography.

Purpose: This study aimed to explore the ability of texture parameters combining with machine learning methods in distinguishing intrahepatic cholangiocarcinoma (ICCA) and hepatic lymphoma (HL). Method: A total of 28 patients with HL and 101 patients with ICCA were included. A total of 45 texture features were extracted by the software LifeX from contrast-enhanced computer tomography (CECT) images and 38 of them were eligible. A total of 5 feature selection methods and 9 feature classification methods were used to build the best diagnostic models, combining with the 10-fold cross-validation to assess the accuracy of these models. The discriminative ability of each model was evaluated by receiver operating characteristic analysis. Result: A total of 45 predictive models were built by the cross combination of each selection and classification method to differentiate ICCA from HL. According to the results of test group, most of the models performed well with a large area under the curve (AUC) (>0.85) and high accuracy (>0.85). Random Forest (RF)_Linear Discriminant Analysis (LDA) (AUC = 0.997, accuracy = 0.969) was the best model among all the 45 models. Conclusion: Combining texture parameters from CECT with multiple machine learning models can differentiate ICCA and HL effectively, and RF_LDA performed the best in this process.

Contrast-Enhanced CT-based Textural Parameters as Potential Prognostic Factors of Survival for Colorectal Cancer Patients Receiving Targeted Therapy.

PURPOSE: This study was designed to estimate the clinical significance of the contrast-enhanced computed tomography (CT) textural features for prediction of survival in colorectal cancer (CRC) patients receiving targeted therapy (bevacizumab and cetuximab). PROCEDURES: The LifeX software was used to extract the textural parameters of the tumor lesions in the contrast-enhanced CT. We used the least absolute shrinkage and selection operator (LASSO) Cox regression and random forest method to screen the non-redundant radiomic features and constructed the CT imaging score. Univariate and multivariate analyses through the Cox proportional hazards model were performed to assess the prognostic clinical factor. Based on the result of multivariate analysis and CT imaging score, combined nomogram model was constructed to predict the overall survival (OS) of patients. Decision curves analysis was employed to evaluate the performance of the combined model and clinical model. RESULTS: After comparative analysis of the area under curve of the receiver operating characteristic (ROC) curve, we chose the result of random forest model as CT imaging score. Considering the clinical practice and the result of analysis, age, surgery, and lactate dehydrogenase (LDH) level have been introduced into clinical model. Based on the result of analysis and the CT imaging score, we constructed the nomogram combined model. C-index and calibration curve verified the goodness of fit and discrimination of the combined model. Decision curve analysis (DCA) demonstrated that the combined model showed the better net benefit for a 3-year OS than clinical model. CONCLUSIONS: In conclusion, the study provides preliminary evidences that several radiomic parameters of tumor lesions derived from CT images were prognostic factors and predictive markers for CRC patients who are candidates for targeted therapy (bevacizumab and cetuximab).

Comparison of Diagnostic Performance of Five Different Ultrasound TI-RADS Classification Guidelines for Thyroid Nodules.

OBJECTIVES: We aimed to evaluate and compare the diagnostic performance of five ultrasound thyroid imaging reporting and data system (TI-RADS) classification guidelines for thyroid nodules through a review and meta-analysis. METHODS: We searched for relevant studies before February 2020 in PubMed. Then we pooled the sensitivity, specificity, likelihood ratios, diagnostic odds ratios, and area under the summary receiver operating characteristic curves. And the diagnostic odds ratios were used to compare the performance. RESULTS: We totally included 19 studies with 4,696 lesions in this research. The pooled sensitivity of American College of Radiology (ACR) guidelines, American Thyroid Association (ATA) guidelines, TI-RADS proposed by Kwak (Kwak TI-RADS), Korean Thyroid Association/Korean Society of Thyroid Radiology (KTA/KSThR) guidelines for malignancy risk and European Thyroid Association (ETA) guidelines is between 0.84 and 0.94. The pooled specificity is 0.68, 0.44, 0.62, 0.47, and 0.61, respectively. And the RDOR is 1.57 (ACR vs ATA), 1.37 (ACR vs ETA), 1.80 (ACR vs Kawk), 1.74 (ARC vs KTA). CONCLUSIONS: The results suggest that five classification guidelines are all effective methods for differential diagnosis of benign and malignant thyroid nodules and ACR guideline is a better choice.

Nomogram based on pre-treatment inflammatory biomarkers predicting survival in patients with head and neck soft tissue sarcoma.

BACKGROUND: Systemic inflammatory biomarkers reflect level of inflammatory response, which have been suggested as prognostic factors in cancer patients. OBJECTIVE: To estimate the prognostic value of inflammatory biomarkers in 149 patients with head and neck soft tissue sarcoma (HNSTS). METHODS: Pre-treatment neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), lymphocyte-to-monocyte ratio (LMR), systemic immune-inflammation index (SII), neutrophil-platelet score (NPS) and Aarhus Composite Biomarker Score (ACBS) were analyzed for association with overall survival (OS) and progression-free survival (PFS). Nomograms were consisted of independent predictors for OS and PFS, and evaluated by calibration curve and concordance index (C-index). RESULTS: In multivariate analysis, LMR (HR = 0.42, 95% CI: 0.19-0.94, P= 0.035), ACBS (HR = 2.05, 95% CI: 1.02-4.12, P= 0.045) and AJCC stage were independent prognostic markers of OS. Moreover, high NLR (HR = 1.78, 95% CI: 1.07-2.94, P= 0.024) and advanced AJCC stage were independently related with worse PFS. Calibration curves reflected good discriminative ability of prognosis. The nomograms showed better accuracy of predicting OS (C-index: 0.748 vs. 0.690, P= 0.009) and PFS (C-index: 0.644 vs. 0.612, P= 0.028) than stage. CONCLUSIONS: Pre-treatment LMR, ACBS and AJCC stage were effective predictor of OS. The NLR and AJCC stage could independently predict PFS. The nomogram might act as a promising prognostic model for OS and PFS in HNSTS.