Machine learning in the prediction of immunotherapy response and prognosis of melanoma: a systematic review and meta-analysis.

Background: The emergence of immunotherapy has changed the treatment modality for melanoma and prolonged the survival of many patients. However, a handful of patients remain unresponsive to immunotherapy and effective tools for early identification of this patient population are still lacking. Researchers have developed machine learning algorithms for predicting immunotherapy response in melanoma, but their predictive accuracy has been inconsistent. Therefore, the present systematic review and meta-analysis was performed to comprehensively evaluate the predictive accuracy of machine learning in melanoma response to immunotherapy. Methods: Relevant studies were searched in PubMed, Web of Sciences, Cochrane Library, and Embase from their inception to July 30, 2022. The risk of bias and applicability of the included studies were assessed using the Prediction Model Risk of Bias Assessment Tool (PROBAST). Meta-analysis was performed on R4.2.0. Results: A total of 36 studies consisting of 30 cohort studies and 6 case-control studies were included. These studies were mainly published between 2019 and 2022 and encompassed 75 models. The outcome measures of this study were progression-free survival (PFS), overall survival (OS), and treatment response. The pooled c-index was 0.728 (95%CI: 0.629-0.828) for PFS in the training set, 0.760 (95%CI: 0.728-0.792) and 0.819 (95%CI: 0.757-0.880) for treatment response in the training and validation sets, respectively, and 0.746 (95%CI: 0.721-0.771) and 0.700 (95%CI: 0.677-0.724) for OS in the training and validation sets, respectively. Conclusion: Machine learning has considerable predictive accuracy in melanoma immunotherapy response and prognosis, especially in the former. However, due to the lack of external validation and the scarcity of certain types of models, further studies are warranted.

Deep skin diseases diagnostic system with Dual-channel Image and Extracted Text.

Background: Due to the lower reliability of laboratory tests, skin diseases are more suitable for diagnosis with AI models. There are limited AI dermatology diagnostic models combining images and text; few of these are for Asian populations, and few cover the most common types of diseases. Methods: Leveraging a dataset sourced from Asia comprising over 200,000 images and 220,000 medical records, we explored a deep learning-based system for Dual-channel images and extracted text for the diagnosis of skin diseases model DIET-AI to diagnose 31 skin diseases, which covers the majority of common skin diseases. From 1 September to 1 December 2021, we prospectively collected images from 6,043 cases and medical records from 15 hospitals in seven provinces in China. Then the performance of DIET-AI was compared with that of six doctors of different seniorities in the clinical dataset. Results: The average performance of DIET-AI in 31 diseases was not less than that of all the doctors of different seniorities. By comparing the area under the curve, sensitivity, and specificity, we demonstrate that the DIET-AI model is effective in clinical scenarios. In addition, medical records affect the performance of DIET-AI and physicians to varying degrees. Conclusion: This is the largest dermatological dataset for the Chinese demographic. For the first time, we built a Dual-channel image classification model on a non-cancer dermatitis dataset with both images and medical records and achieved comparable diagnostic performance to senior doctors about common skin diseases. It provides references for exploring the feasibility and performance evaluation of DIET-AI in clinical use afterward.

The abscopal effect of anti-CD95 and radiotherapy in melanoma.

BACKGROUND: Radiotherapy (RT) is frequently adopted to control cancer cell proliferation, which is achieved by altering the tumor microenvironment (TME) and immunogenicity. Apoptosis of cancer cells is the major effect of radiation on tumor tissues. Fas/APO-1(CD95) receptors on the cell membrane are death receptors that can be activated by diverse factors, including radiation and integration with CD95L on CD8+ T cells. The abscopal effect is defined as tumor regression out of the local RT field, and it is produced through anti-tumor immunity. The immune response against the radiated tumor is characterized by the cross-presentation between antigen-presenting cells (APCs), which includes cytotoxic T cells (CTLs) and dendritic cells (DCs). METHODS: The effect of activation and radiation of CD95 receptors on melanoma cell lines was examined in vivo and in vitro. In vivo, bilateral lower limbs were given a subcutaneous injection of a dual-tumor. Tumors in the right limb were radiated with a single dose of 10 Gy (primary tumor), while tumors in the left limb (secondary tumor) were spared. RESULTS: The anti-CD95 treatment plus radiation (combination treatment) reduced growth rates of both primary and secondary tumors relative to the control or radiation groups. In addition, higher degrees of infiltrating CTLs and DCs were detected in the combination treatment compared to the other groups, but the immune response responsible for secondary tumor rejection was not proven to be tumor specific. In vitro, combination treatment combined with radiation resulted in further apoptosis of melanoma cells relative to controls or cells treated with radiation. CONCLUSIONS: Targeting CD95 on cancer cells will induce tumor control and the abscopal effect.

Altered Gut Microbiota in H1-Antihistamine-Resistant Chronic Spontaneous Urticaria Associates With Systemic Inflammation.

Background and Objective: Chronic spontaneous urticaria (CSU) is a histamine-mediated inflammatory skin disease, and second-generation non-sedating H1-antihistamines (nsAH) at licensed doses have long been the first-line therapy in CSU. However, about 50% of patients are resistant to nsAH, and the precise pathogenesis remains largely unknown but seems to be associated with low-level systemic or intestinal inflammation. We aim to determine the fecal microbial composition and clarify its correlation with the clinical profiles og CSU with nsAH resistance. Methods: A total of 25 CSU patients with or 19 CSU patients without nsAH resistance and 19 healthy controls (HC) were enrolled in this study. The intestinal microbiome was detected by 16S rRNA sequencing. The data were analyzed using R language software. Results: Significantly higher urticarial activity score for 7 days, stool calprotectin, erythrocyte sedimentation rate, serum C-reactive protein, and interleukin-6, but much lower alpha-diversity and evenness of fecal bacterial community were observed in CSU patients with nsAH resistance than in those without (P <0.05 for all variables). Compared to patients with nsAH-responsiveness, the abundance of fecal genera Prevotella, Megamonas, and Escherichia were significantly increased, while that of Blautia, Alistipes, Anaerostipes, and Lachnospira were remarkably reduced in nsAH-resistant patients (uncorrected P <0.05 for all variables). Finally, systemic not intestinal inflammation degree was positively correlated with genera Escherichia, while negatively with genera Blautia, Dorea, Lactobacillus, Eubacterium_hallii_group, and Roseburia. CSU without nsAH resistance and HC individuals showed almost unchanged genera bacterium. Conclusions: Among CSU patients, pro-inflammation phenotype relating to enteric dysbacteriosis features nsAH resistance in CSU patients. The results provide clues for future microbial-based or anti-inflammatory therapies on nsAH resistant CSU.

Curcumin assists anti-EV71 activity of IFN-α by inhibiting IFNAR1 reduction in SH-SY5Y cells.

BACKGROUND AND AIM: Enterovirus 71(EV71) can cause severe hand, foot, and mouth disease (HFMD) with brain tissue involvement. Few effective anti-EV71 drugs are presently available in clinical practice. Interferon-α (IFN-α) was ineffective while Curcumin was effective in restricting EV71 replication in non-neuronal cells. Ubiquitin-proteasome-mediated degradation of interferon-alpha receptor 1 (IFNAR1) protein contributes to IFN-α resistance. Current study aimed to determine synergistic inhibition of EV71 by Curcumin and IFN-α in human neuroblastoma SH-SY5Y cells. METHODS: SH-SY5Y cells were infected with mock-/Curcumin-pre-incubated EV71 or transfected with plasmid containing interferon-stimulated response element (ISRE) or mRNA containing viral internal ribosomal entry site (IRES) following by post-treatment with Curcumin with or without IFN-α. Supernatant IFN-α/ß was detected by ELISA. ISRE, IRSE, proteasome and deubiquitinating activity were measured by luciferase assay. EV71 RNA and viral protein or IFNAR1 were determined by qPCR and western blot, respectively. RESULTS: EV71 flailed to completely block IFN-α/ß production but inhibited IFN-α signal. Curcumin only slightly inhibited EV71 proliferation without modulating virus attachment and internalization. However, Curcumin addition restored IFN-α-mediated ISRE activity thus significantly inhibiting EV71 replication. Furthermore, EV71 also reduced IFNAR1 protein with proteasome-dependence in SH-SY5Y cells, which can be reversed by Curcumin addition with the evidence that it lowered proteasome activity. CONCLUSION: These data demonstrate that Curcumin assists anti-EV71 activity of IFN-α by inhibiting IFNAR1 reduction via ubiquitin-proteasome disruption in SH-SY5Y cells.

Translocating lipopolysaccharide correlates with the severity of enterovirus A71-induced HFMD by promoting pro-inflammation and viral IRES activity.

BACKGROUND: The increase of inflammation-inducing enterobacteria was recently observed in severe hand, foot, and mouth disease (HFMD) caused by Enterovirus A71 (EV-A71). This study aimed to verify the occurrence of bacterial translocation (BT) and further explore the contributory role of BT to severity of EV-A71-mediated HFMD cases. METHODS: Serum specimens from 65 mild and 65 severe EV-A71-associated HFMD cases and 65 healthy children were collected. EV-A71 VP1 in serum, inflammatory mediators including C-reactive protein, IL-1ß, IL-6, interferon-γ and tumor necrosis factor-α, BT related biomarkers including Claudin-3, intestinal fatty acid binding protein, lipopolysaccharide (LPS), soluble CD14 (sCD14) and endotoxin core antibody were measured by ELISA. Bacterial DNA (BactDNA) fragments were quantified by quantified PCR (qPCR). Rhabdomyosarcoma (RD) or SH-SY5Y cells, infected with LPS-pre-incubated EV-A71 or transfected with plasmid containing viral 2Apro or mRNA containing viral internal ribosomal entry site (IRES), were post-treated with or without LPS in vitro. EV-A71 RNA and viral or cellular proteins were determined by qPCR and western blot, respectively. RESULTS: Compared to mild HFMD patients, remarkably higher inflammatory mediators as well as BT-related biomarkers except BactDNA were observed in severe HFMD cases (all P < 0.05). In severe HFMD group, circulating concentrations of LPS and sCD14 showed statistical correlations with inflammation indices (all P < 0.05), serum levels of EV-A71 VP1 were found to be positively correlated with serum LPS (r = 0.341, P = 0.005) and serum sCD14 (r = 0.458, P < 0.001). In vitro, EV-A71 attachment and internalization were only slightly promoted by LPS pre-incubation; however, EV-A71 proliferation and viral 2Apro-mediated IRES activity were significantly accelerated by LPS post-treatment. CONCLUSIONS: Our results collectively indicate that gut-derived translocating LPS contributes to the severity of EV-A71-induced HFMD by driving inflammatory response and viral proliferation via viral 2Apro-mediated IRES.