Stability, bifurcation, and chaos in a class of scalar quartic polynomial delay systems.

In this paper, a class of scalar quartic polynomial delay systems is investigated. We found rich dynamics in this system through numerical simulation, including chaotic attractors, chaotic saddles, and intermittent chaos. Moreover, this chaotic quartic system may serve as an approximation, through Taylor expansion, for a wide class of scalar delay differential equations. Thus, these nonlinear systems may exhibit chaotic behaviors, and the studies in our paper may provide an insight into the emergence of chaos in other time-delay nonlinear systems. We also conduct a detailed theoretical analysis of the system, including the stability of equilibria and Hopf bifurcation analysis based on the theory of normal form and center manifold. Additionally, a numerical analysis is provided to give numerical evidence for the existence of chaos.

Classification of anatomy and treatment approaches for aneurysms originating from the proximal of the A1 segment of the anterior cerebral artery in clinical settings.

Objective: To explore the spatial relationship between A1 segment proximal anterior cerebral artery aneurysms and their main trunks, classify them anatomically and develop targeted treatment strategies. Methods: This single-center retrospective analysis involved 39 patients diagnosed with aneurysms originating from the proximal of A1 segment of the anterior cerebral artery (2014-2023). Classify the patient's aneurysm into 5 types based on the location of the neck involving the carrier artery and the spatial relationship and projection direction of the aneurysm body with the carrier artery, and outcomes from treatment methods were compared. Results: Among 39 aneurysms, 18 cases underwent endovascular intervention treatment, including 6 cases of stent assisted embolization, 1 case of flow-diverter embolization, 5 cases of balloon assisted embolization, and 6 cases of simple coiling. At discharged, the mRS score of all endovascularly treated patients was 0, and the GOS score was 5 at 6 months after discharge. At discharge, the mRS score of microsurgical clipping treated patients was 0 for 15 cases, 3 for 1 case, 4 for 1 case and 5 for 2 cases. Six months after discharge, the GOS score was 5 for 16 cases, 4 for 2 cases, 3 for 2 cases, and 1 for 1 case. GOS outcomes at 6 months were better for endovascularly treated patients (p = 0.047). Conclusion: Results showed better outcomes for the endovascular treatment group compared to microsurgical clipping at 6 months after surgery. The anatomical classification of aneurysms in this region may be of help to develop effective treatment strategies.

Tumor-Associated Antigen Burden Correlates with Immune Checkpoint Blockade Benefit in Tumors with Low Levels of T-cell Exhaustion.

Tumor-associated antigens (TAAs) are important targets for cancer vaccines. However, TAA-based vaccines have not yet achieved their full potential in clinical trials. In contrast, immune checkpoint blockade (ICB) has emerged as an effective therapy, leading to durable responses in selected cancer patients. To date, few generalizable associations between TAAs and ICB benefit have been reported, with most studies focusing on melanoma that has the highest mutation rate in cancer. In this study, we developed a TAA burden (TAB) algorithm based on known and putative TAAs and investigated the association of TAB with ICB benefit. Analysis of the IMVigor210 patient cohort of urothelial carcinoma treated with anti-PD-L1 revealed that high tumor mutation burden (TMB) weakened the association of TAB with ICB benefit. Furthermore, TAB correlated with ICB efficacy in tumors characterized by negative PD-L1 staining on immune cells, while high levels of PD-L1 staining on immune cells were linked to T-cell exhaustion. Validation across independent clinical datasets-including urothelial carcinoma cohorts treated with anti-PD1/PD-L1 agents and neoadjuvant anti-PD1 trials for head and neck cancers-corroborated the finding that TAB correlates with ICB benefit in tumors with low T-cell exhaustion. Pan-cancer analyses revealed that in most cancer entities, tumors with higher T-cell exhaustion exhibited lower TAB levels, implying possible immunoediting of TAAs in tumors with established antitumor immunity. Our study challenges the prevailing notion of a lack of association between TAAs and ICB response. It also underscores the need for future investigations into the immunogenicity of TAAs and TAA-based vaccine strategies in tumors with low levels of T-cell exhaustion.

Graph Embedding Interclass Relation-Aware Adaptive Network for Cross-Scene Classification of Multisource Remote Sensing Data.

The unsupervised domain adaptation (UDA) based cross-scene remote sensing image classification has recently become an appealing research topic, since it is a valid solution to unsupervised scene classification by exploiting well-labeled data from another scene. Despite its good performance in reducing domain shifts, UDA in multisource data scenarios is hindered by several critical challenges. The first one is the heterogeneity inherent in multisource data complicates domain alignment. The second challenge is the incomplete representation of feature distribution caused by the neglect of the contribution from global information. The third challenge is the inaccuracies in alignment due to errors in establishing target domain conditional distributions. Since UDA does not guarantee the complete consistency of the distribution of the two domains, networks using simple classifiers are still affected by domain shifts, resulting in poor performance. In this paper, we propose a graph embedding interclass relation-aware adaptive network (GeIraA-Net) for unsupervised classification of multi-source remote sensing data, which facilitates knowledge transfer at the class level for two domains by leveraging aligned features to perceive inter-class relation. More specifically, a graph-based progressive hierarchical feature extraction network is constructed, capable of capturing both local and global features of multisource data, thereby consolidating comprehensive domain information within a unified feature space. To deal with the imprecise alignment of data distribution, a joint de-scrambling alignment strategy is designed to utilize the features obtained by a three-step pseudo-label generation module for more delicate domain calibration. Moreover, an adaptive inter-class topology based classifier is constructed to further improve the classification accuracy by making the classifier domain adaptive at the category level. The experimental results show that GeIraA-Net has significant advantages over the current state-of-the-art cross-scene classification methods.

Anoikis resistance regulates immune infiltration and drug sensitivity in clear-cell renal cell carcinoma: insights from multi omics, single cell analysis and in vitro experiment.

Background: Anoikis is a form of programmed cell death essential for preventing cancer metastasis. In some solid cancer, anoikis resistance can facilitate tumor progression. However, this phenomenon is underexplored in clear-cell renal cell carcinoma (ccRCC). Methods: Using SVM machine learning, we identified core anoikis-related genes (ARGs) from ccRCC patient transcriptomic data. A LASSO Cox regression model stratified patients into risk groups, informing a prognostic model. GSVA and ssGSEA assessed immune infiltration, and single-cell analysis examined ARG expression across immune cells. Quantitative PCR and immunohistochemistry validated ARG expression differences between immune therapy responders and non-responders in ccRCC. Results: ARGs such as CCND1, CDKN3, PLK1, and BID were key in predicting ccRCC outcomes, linking higher risk with increased Treg infiltration and reduced M1 macrophage presence, indicating an immunosuppressive environment facilitated by anoikis resistance. Single-cell insights showed ARG enrichment in Tregs and dendritic cells, affecting immune checkpoints. Immunohistochemical analysis reveals that ARGs protein expression is markedly elevated in ccRCC tissues responsive to immunotherapy. Conclusion: This study establishes a novel anoikis resistance gene signature that predicts survival and immunotherapy response in ccRCC, suggesting that manipulating the immune environment through these ARGs could improve therapeutic strategies and prognostication in ccRCC.

What enlightenment has the development of lung cancer bone metastasis brought in the last 22 years.

BACKGROUND: Lung cancer bone metastasis (LCBM) is a disease with a poor prognosis, high risk and large patient population. Although considerable scientific output has accumulated on LCBM, problems have emerged, such as confusing research structures. AIM: To organize the research frontiers and body of knowledge of the studies on LCBM from the last 22 years according to their basic research and translation, clinical treatment, and clinical diagnosis to provide a reference for the development of new LCBM clinical and basic research. METHODS: We used tools, including R, VOSviewer and CiteSpace software, to measure and visualize the keywords and other metrics of 1903 articles from the Web of Science Core Collection. We also performed enrichment and protein-protein interaction analyses of gene expression datasets from LCBM cases worldwide. RESULTS: Research on LCBM has received extensive attention from scholars worldwide over the last 20 years. Targeted therapies and immunotherapies have evolved into the mainstream basic and clinical research directions. The basic aspects of drug resistance mechanisms and parathyroid hormone-related protein may provide new ideas for mechanistic study and improvements in LCBM prognosis. The produced molecular map showed that ribosomes and focal adhesion are possible pathways that promote LCBM occurrence. CONCLUSION: Novel therapies for LCBM face animal testing and drug resistance issues. Future focus should centre on advancing clinical therapies and researching drug resistance mechanisms and ribosome-related pathways.

Visualization and standardized quantification of surface charge density for triboelectric materials.

Triboelectric nanogenerator (TENG) operates on the principle of utilizing contact electrification and electrostatic induction. However, visualization and standardized quantification of surface charges for triboelectric materials remain challenging. Here, we report a surface charge visualization and standardized quantification method using electrostatic surface potential measured by Kevin probe and the iterative regularization strategy. Moreover, a tuning strategy on surface charge is demonstrated based on the corona discharge with a three-electrode design. The long-term stability and dissipation mechanisms of the injected negative or positive charges demonstrate high dependence on deep carrier traps in triboelectric materials. Typically, we achieved a 70-fold enhancement on the output voltage (~135.7 V) for the identical polytetrafluoroethylene (PTFE) based TENG (neg-PTFE/PTFE or posi-PTFE/PTFE triboelectric pair) with stable surface charge density (5% decay after 140 days). The charged PTFE was demonstrated as a robot e-skins for non-contact perception of object geometrics. This work provides valuable tools for surface charge visualization and quantification, giving a new strategy for a deeper understanding of contact electrification.

Mechanism of Lian Hua Qing Wen capsules regulates the inflammatory response caused by M1 macrophage based on cellular experiments and computer simulations.

PURPOSE: The polarization of macrophages with the resulting inflammatory response play a crucial part in tissue and organ damage due to inflammatory. Study has proved Lian Hua Qing Wen capsules (LHQW) can reduce activation of inflammatory response and damage of tissue derived from the inflammatory reactions. However, the mechanism of LHQW regulates the macrophage-induced inflammatory response is unclear. Therefore, we investigated the mechanism of LHQW regulated the inflammatory response of M1 macrophages by cellular experiments and computer simulations. METHODS: This study has analysed the targets and mechanisms of macrophage regulating inflammatory response at gene and protein levels through bioinformatics. The monomeric components of LHQW were analyzed by High Performance Liquid Chromatography (HPLC). We established the in vitro cell model by M1 macrophages (Induction of THP-1 cells into M1 macrophages). RT-qPCR and immunofluorescence were used to detect changes in gene and protein levels of key targets after LHQW treatment. Computer simulations were utilized to verify the binding stability of monomeric components and protein targets. RESULTS: Macrophages had 140,690 gene targets, inflammatory response had 12,192 gene targets, intersection gene targets were 11,772. Key monomeric components (including: Pinocembrin, Fargesone-A, Nodakenin and Bowdichione) of LHQW were screened by HPLC. The results of cellular experiments indicated that LHQW could significantly reduce the mRNA expression of CCR5, CSF2, IFNG and TNF, thereby alleviating the inflammatory response caused by M1 macrophage. The computer simulations further validated the binding stability and conformation of key monomeric components and key protein targets, and IFNG/Nodakenin was able to form the most stable binding conformation for its action. CONCLUSION: In this study, the mechanism of LHQW inhibits the polarization of macrophages and the resulting inflammatory response was investigated by computer simulations and cellular experiments. We found that LHQW may not only reduce cell damage and death by acting on TNF and CCR5, but also inhibit the immune recognition process and inflammatory response by regulating CSF2 and IFNG to prevent polarization of macrophages. Therefore, these results suggested that LHQW may act through multiple targets to inhibit the polarization of macrophages and the resulting inflammatory response.

Pulsatilla decoction alleviates DSS-induced UC by activating FXR-ASBT pathways to ameliorate disordered bile acids homeostasis.

Ethnopharmacological relevance: Pulsatilla decoction (PD) is a classical prescription for the treatment of ulcerative colitis. Previous studies have demonstrated that the therapeutic efficacy of PD is closely associated with the activation of Farnesoid X receptor (FXR). The activity of FXR is regulated by apical sodium-dependent bile acid transporter (ASBT), and the FXR-ASBT cascade reaction, centered around bile acid receptor FXR, plays a pivotal role in maintaining bile acid metabolic homeostasis to prevent the occurrence and progression of ulcerative colitis (UC). Aim of the study: To elucidate the underlying mechanism by which PD exerts its proteactive effects against Dextran Sulfate Sodium Salt (DSS)-induced ulcerative colitis, focusing on the modulation of FXR and ASBT. Materials and methods: To establish a model of acute ulcerative colitis, BALB/C mice were administered 3.5% DSS in their drinking water for consecutive 7 days. The disease activity index (DAI) was employed to evaluate the clinical symptoms exhibited by each group of mice. Goblet cell expression in colon tissue was assessed using glycogen schiff periodic acid-Schiff (PAS) and alcian blue staining techniques. Inflammatory cytokine expression in serum and colonic tissues was examined through enzyme-linked immunosorbent assay (ELISA). A PCR Array chip was utilized to screen 88 differential genes associated with the FXR-ASBT pathway in UC treatment with PD. Western blotting (WB) analysis was performed to detect protein expression levels of differentially expressed genes in mouse colon tissue. Results: The PD treatment effectively reduced the Disease Activity Index (DAI) score and mitigated colon histopathological damage, while also restoring weight and colon length. Furthermore, it significantly alleviated the severity of ulcerative colitis (UC), regulated inflammation, modulated goblet cell numbers, and restored bile acid balance. Additionally, a PCR Array analysis identified 21 differentially expressed genes involved in the FXR-ASBT pathway. Western blot results demonstrated significant restoration of FXR, GPBAR1, CYP7A1, and FGF15 protein expression levels following PD treatment; moreover, there was an observed tendency towards increased expression levels of ABCB11 and RXRα. Conclusion: The therapeutic efficacy of PD in UC mice is notable, potentially attributed to its modulation of bile acid homeostasis, enhancement of gut barrier function, and attenuation of intestinal inflammation.

Predicting bond dissociation energies of cyclic hypervalent halogen reagents using DFT calculations and graph attention network model.

Although hypervalent iodine(III) reagents have become staples in organic chemistry, the exploration of their isoelectronic counterparts, namely hypervalent bromine(III) and chlorine(III) reagents, has been relatively limited, partly due to challenges in synthesizing and stabilizing these compounds. In this study, we conduct a thorough examination of both homolytic and heterolytic bond dissociation energies (BDEs) critical for assessing the chemical stability and functional group transfer capability of cyclic hypervalent halogen compounds using density functional theory (DFT) analysis. A moderate linear correlation was observed between the homolytic BDEs across different halogen centers, while a strong linear correlation was noted among the heterolytic BDEs across these centers. Furthermore, we developed a predictive model for both homolytic and heterolytic BDEs of cyclic hypervalent halogen compounds using machine learning algorithms. The results of this study could aid in estimating the chemical stability and functional group transfer capabilities of hypervalent bromine(III) and chlorine(III) reagents, thereby facilitating their development.

Radical-Mediated α-tert-Alkylation of Aldehydes by Consecutive 1,4- and 1,3-(Benzo)thiazolyl Migrations.

The direct alkylation of the α-position of aldehydes is an effective method for accessing a wide range of structurally diverse aldehydes, yet tert-alkylation has proven to be a challenging task. In this study, we present a novel radical-mediated tert-alkylation approach targeting the α-position of aldehydes, enabling the synthesis of complex aliphatic aldehydes. The transformation is initiated by the interaction between an in situ generated enamine intermediate and α-bromo sulfone, forming an electron donor-acceptor (EDA) complex, followed by consecutive 1,4- and 1,3-functional group migrations. This protocol operates under metal-free and mild photochemical conditions, delivering a broad scope of products and providing new mechanistic insights into radical rearrangement reactions.

A Principle Design of Registration-Fusion Consistency: Toward Interpretable Deep Unregistered Hyperspectral Image Fusion.

For hyperspectral image (HSI) and multispectral image (MSI) fusion, it is often overlooked that multisource images acquired under different imaging conditions are difficult to be perfectly registered. Although some works attempt to fuse unregistered images, two thorny challenges remain. One is that registration and fusion are usually modeled as two independent tasks, and there is no yet a unified physical model to tightly couple them. Another is that deep learning (DL)-based methods may lack sufficient interpretability and generalization. In response to the above challenges, we propose an unregistered HSI fusion framework energized by a unified model of registration and fusion. First, a novel registration-fusion consistency physical perception model (RFCM) is designed, which uniformly models the image registration and fusion problem to greatly reduce the sensitivity of fusion performance to registration accuracy. Then, an HSI fusion framework (MoE-PNP) is proposed to learn the knowledge reasoning process for solving RFCM. Each basic module of MoE-PNP one-to-one corresponds to the operation in the optimization algorithm of RFCM, which can ensure clear interpretability of the network. Moreover, MoE-PNP captures the general fusion principle for different unregistered images and therefore has good generalization. Extensive experiments demonstrate that MoE-PNP achieves state-of-the-art performance for unregistered HSI and MSI fusion. The code is available at https://github.com/Jiahuiqu/MoE-PNP.

Self-Assembled Nanocomposite DOX/TPOR4@CB[7]4 for Enhanced Synergistic Photodynamic Therapy and Chemotherapy in Neuroblastoma.

DOX/TPOR4@CB[7]4 was synthesized via self-assembly, and its physicochemical properties and ability to generate reactive oxygen species (ROS) were evaluated. The impact of photodynamic therapy on SH-SY5Y cells was assessed using the MTT assay, while flow cytometry analysis was employed to detect cell apoptosis. Confocal laser scanning microscopy was utilized to observe the intracellular distribution of DOX/TPOR4@CB[7]4 in SH-SY5Y cells. Additionally, fluorescence imaging of DOX/TPOR4@CB[7]4 in nude mice bearing SH-SY5Y tumors and examination of the combined effects of photodynamic and chemical therapies were conducted. The incorporation of CB[7] significantly enhanced the optical properties of DOX/TPOR4@CB[7]4, resulting in increased ROS production and pronounced toxicity towards SH-SY5Y cells. Moreover, both the apoptotic and mortality rates exhibited significant elevation. In vivo experiments demonstrated that tumor growth inhibition was most prominent in the DOX/TPOR4@CB[7]4 group. π-π interactions facilitated the binding between DOX and photosensitizer TPOR, with TPOR's naphthalene hydrophilic groups encapsulated within CB[7]'s cavity through host-guest interactions with CB[7]. Therefore, CB[7] can serve as a nanocarrier to enhance the combined application of chemical therapy and photodynamic therapy, thereby significantly improving treatment efficacy against neuroblastoma tumors.

iGenSig-Rx: an integral genomic signature based white-box tool for modeling cancer therapeutic responses using multi-omics data.

Multi-omics sequencing is poised to revolutionize clinical care in the coming decade. However, there is a lack of effective and interpretable genome-wide modeling methods for the rational selection of patients for personalized interventions. To address this, we present iGenSig-Rx, an integral genomic signature-based approach, as a transparent tool for modeling therapeutic response using clinical trial datasets. This method adeptly addresses challenges related to cross-dataset modeling by capitalizing on high-dimensional redundant genomic features, analogous to reinforcing building pillars with redundant steel rods. Moreover, it integrates adaptive penalization of feature redundancy on a per-sample basis to prevent score flattening and mitigate overfitting. We then developed a purpose-built R package to implement this method for modeling clinical trial datasets. When applied to genomic datasets for HER2 targeted therapies, iGenSig-Rx model demonstrates consistent and reliable predictive power across four independent clinical trials. More importantly, the iGenSig-Rx model offers the level of transparency much needed for clinical application, allowing for clear explanations as to how the predictions are produced, how the features contribute to the prediction, and what are the key underlying pathways. We anticipate that iGenSig-Rx, as an interpretable class of multi-omics modeling methods, will find broad applications in big-data based precision oncology. The R package is available: https://github.com/wangxlab/iGenSig-Rx .

Deep Spatial-Spectral Joint-Sparse Prior Encoding Network for Hyperspectral Target Detection.

Hyperspectral target detection aims to locate targets of interest in the scene, and deep learning-based detection methods have achieved the best results. However, black box network architectures are usually designed to directly learn the mapping between the original image and the discriminative features in a single data-driven manner, a choice that lacks sufficient interpretability. On the contrary, this article proposes a novel deep spatial-spectral joint-sparse prior encoding network (JSPEN), which reasonably embeds the domain knowledge of hyperspectral target detection into the neural network, and has explicit interpretability. In JSPEN, the sparse encoded prior information with spatial-spectral constraints is learned end-to-end from hyperspectral images (HSIs). Specifically, an adaptive joint spatial-spectral sparse model (AS 2 JSM) is developed to mine the spatial-spectral correlation of HSIs and improves the accuracy of data representation. An optimization algorithm is designed for iteratively solving AS 2 JSM, and JSPEN is proposed to simulate the iterative optimization process in the algorithm. Each basic module of JSPEN one-to-one corresponds to the operation in the optimization algorithm so that each intermediate result in the network has a clear explanation, which is convenient for intuitive analysis of the operation of the network. With end-to-end training, JSPEN can automatically capture the general sparse properties of HSIs and faithfully characterize the features of background and target. Experimental results verify the effectiveness and accuracy of the proposed method. Code is available at https://github.com/Jiahuiqu/JSPEN.

Advances in 2D Materials Based Gas Sensors for Industrial Machine Olfactory Applications.

The escalating development and improvement of gas sensing ability in industrial equipment, or "machine olfactory", propels the evolution of gas sensors toward enhanced sensitivity, selectivity, stability, power efficiency, cost-effectiveness, and longevity. Two-dimensional (2D) materials, distinguished by their atomic-thin profile, expansive specific surface area, remarkable mechanical strength, and surface tunability, hold significant potential for addressing the intricate challenges in gas sensing. However, a comprehensive review of 2D materials-based gas sensors for specific industrial applications is absent. This review delves into the recent advances in this field and highlights the potential applications in industrial machine olfaction. The main content encompasses industrial scenario characteristics, fundamental classification, enhancement methods, underlying mechanisms, and diverse gas sensing applications. Additionally, the challenges associated with transitioning 2D material gas sensors from laboratory development to industrialization and commercialization are addressed, and future-looking viewpoints on the evolution of next-generation intelligent gas sensory systems in the industrial sector are prospected.

Production of constrained L-cyclo-tetrapeptides by epimerization-resistant direct aminolysis.

The synthesis of constrained 12-membered rings is notably difficult. The main challenges result from constraints during the linear peptide cyclization. Attempts to overcome constraints through excessive activation frequently cause peptidyl epimerization, while insufficient activation of the C-terminus hampers cyclization and promotes intermolecular oligomer formation. We present a ß-thiolactone framework that enables the synthesis of cyclo-tetrapeptides via direct aminolysis. This tactic utilizes a mechanism that restricts C-terminal carbonyl rotation while maintaining high reactivity, thereby enabling efficient head-to-tail amidation, reducing oligomerization, and preventing epimerization. A broad range of challenging cyclo-tetrapeptides ( > 20 examples) are synthesized in buffer and exhibits excellent tolerance toward nearly all proteinogenic amino acids. Previously unattainable macrocycles, such as cyclo-L-(Pro-Tyr-Pro-Val), have been produced and identified as µ-opioid receptor (MOR) agonists, with an EC50 value of 2.5 nM. Non-epimerizable direct aminolysis offers a practical solution for constrained peptide cyclization, and the discovery of MOR agonist activity highlights the importance of overcoming synthetic challenges for therapeutic development.

Interpretable machine learning for predicting the response duration to Sintilimab plus chemotherapy in patients with advanced gastric or gastroesophageal junction cancer.

Background: Sintilimab plus chemotherapy has proven effective as a combination immunotherapy for patients with advanced gastric and gastroesophageal junction adenocarcinoma (GC/GEJC). A multi-center study conducted in China revealed a median progression-free survival (PFS) of 7.1 months. However, the prediction of response duration to this immunotherapy has not been thoroughly investigated. Additionally, the potential of baseline laboratory features in predicting PFS remains largely unexplored. Therefore, we developed an interpretable machine learning (ML) framework, iPFS-SC, aimed at predicting PFS using baseline (pre-treatment) laboratory features and providing interpretations of the predictions. Materials and methods: A cohort of 146 patients with advanced GC/GEJC, along with their baseline laboratory features, was included in the iPFS-SC framework. Through a forward feature selection process, predictive baseline features were identified, and four ML algorithms were developed to categorize PFS duration based on a threshold of 7.1 months. Furthermore, we employed explainable artificial intelligence (XAI) methodologies to elucidate the relationship between features and model predictions. Results: The findings demonstrated that LightGBM achieved an accuracy of 0.70 in predicting PFS for advanced GC/GEJC patients. Furthermore, an F1-score of 0.77 was attained for identifying patients with PFS durations shorter than 7.1 months. Through the feature selection process, we identified 11 predictive features. Additionally, our framework facilitated the discovery of relationships between laboratory features and PFS. Conclusion: A ML-based framework was developed to predict Sintilimab plus chemotherapy response duration with high accuracy. The suggested predictive features are easily accessible through routine laboratory tests. Furthermore, XAI techniques offer comprehensive explanations, both at the global and individual level, regarding PFS predictions. This framework enables patients to better understand their treatment plans, while clinicians can customize therapeutic approaches based on the explanations provided by the model.