An AND-Gate Photoacoustic Probe for Cys and H2S Precise Photoacoustic Sensing in Localized Tumors.

Photoacoustic (PA) tomography has shown many promising aspects in noninvasive and precise imaging of deep-localized biomarkers. However, these traditional single-locked PA probes always face challenges in precise PA imaging with high specificity. Here, we report a novel AND-gate photoacoustic probe, BAE, to improve tumor imaging accuracy via the combination of two tumor-associated biomarkers, cysteine (Cys) and hydrogen sulfide (H2S). Only when Cys and H2S are concurrently introduced into the detection system does the absorption of BAE red-shift from the initial 680 to 810 nm, thereby showing a 5.29-fold enhancement in its PA signal at 810 nm. The good specificity of BAE is proven, since an obvious PA signal could be observed only in the solution containing both Cys and H2S and was not affected by other reactive sulfur species. After being taken up by tumors with the assistance of a nanomicelle, the AND-gate PA probe BAE was applied for dynamic real-time monitoring of Cys and H2S in vivo, achieving precise identification of tumors. This AND-gate PA probe provides a potential technical tool for precise sensing analysis of deep-seated diseases.

High-Contrast Photoacoustic Imaging of Localized Cysteine in Orthotopic Breast Cancer Enabled by A Totally-Caged Methylene Blue Probe.

High-contrast photoacoustic sensing imaging (PASI) was greatly determined by optical absorption changes of the absorbers usually enabled by activatable probes via controllably converting the absorbed electromagnetic energy to ultrasound waves. However, most of current photoacoustic probes still suffer from limited imaging contrast towards specific species because of their small absorption spectral changes in the near infrared (NIR) region. Herein, we developed a methylene blue-based photoacoustic probe with its NIR optical absorption totally caged, which could afford dramatical "OFF-to-ON" absorption transition for high-contrast photoacoustic imaging towards the localized cysteine. The rationally designed methylene blue-based probe for cysteine (MB-Cys) would keep in off state with almost no absorption in NIR region, while upon activated by cysteine through cyclization reaction with acrylates, it would reconstruct the π-conjugation system to release the free methylene blue with strong absorption centered at 665 nm (>130-fold enhancement). The unique responsive behavior could enable the PASI for photoacoustic mapping the cysteine in orthotopic breast cancer in a high-contrast manner. Therefore, this work established an up-to-date strategy to originally eliminate the background photoacoustic signal for PASI to accurately monitor cysteine in vivo.

Hydroxysafflor Yellow A Exerts Neuroprotective Effects by Inhibiting Protein Carbonyl Formation in Cerebral Ischemia-Reperfusion Injury.

Protein carbonylation by reactive oxygen species (ROS) is an important factor in the pathogenesis of cerebral ischemia-reperfusion injury (CIRI). Carbonyls are mainly produced by peroxynitrite (ONOO-) and hemin/hydrogen peroxide (H2O2)/sodium nitrite (NaNO2)-mediated reactions. As the main active water-soluble chalcone chemical ingredient derived from Carthamus tinctorius L, hydroxysafflor yellow A (HSYA) has been increasingly applied in the treatment of cerebrovascular disease (CVD). In this study, rats were randomly divided into 3 groups: the sham-surgery group (sham), the CIRI group (CIRI) and the CIRI treated with HSYA group (HSYA). We evaluated the protective properties of HSYA in a CIRI model in vivo, assessed its efficacy against ONOO- and hemin/H2O2/NaNO2-induced oxidative damage to cerebral cortical tissues in vitro, and explored the probable molecular mechanisms underlying its neuroprotective effects. The results showed that HSYA protected rats against CIRI by improving their neurological function score (P < .05), reducing infarct volume (P < .01), decreasing the content of protein carbonyls (P < .01) and elevating the glutathione (GSH) levels (P < .01). Further in vitro investigations found that HSYA pretreatment could inhibit protein carbonylation induced by exogenous ONOO- application in cortical brain tissues in a dose-dependent manner (P < .01). In terms of hemin/H2O2/NaNO2-triggered oxidative damage, HSYA slightly promoted the formation of carbonyl groups (P < .05). In conclusion, this study demonstrates that the neuroprotective capabilities of HSYA in CIRI are attributable, at least in part, to the enhancement in antioxidant capacity and the attenuation of protein oxidation, probably via the combined processes of ONOO- scavenging and the suppression of protein carbonyl formation.

Synthesis and study on aggregation behaviours in liquid phase of three prepared cyanine dyes.

Here we investigate the aggregation behaviours of three prepared dyes in the liquid phase to pick out one possessing J-aggregation characteristic that is of significant interest for organic materials used in multiple bio-applications. The self-assembly of dyes usually leads to various forms of aggregates, for example, H-aggregates or J-aggregates and it is easy to distinguish bathochromic J-aggregation from hypsochromic H-aggregation using UV/vis light spectroscopy. Enlightened by the cyanine dyes that have shown a great tendency to self-associate, we designed and synthesized three cyanine dyes: Cy7-Ph, DCy7-Ph, and SN-Cy7-Ph, followed by the study of the influence of multiple factors on their aggregation behaviours, including solvent polarity, ionic strength, and temperature. Finally, we found that of the three molecules only SN-Cy7-Ph could self-assemble into J-aggregates conveniently and stably in the aqueous phase under normal conditions.

Dual-pulse laser ignition of ethylene-air mixtures in a supersonic combustor.

To reduce the energy of an individual laser pulse, dual-pulse laser ignitions (LIs) at various pulse intervals were investigated in a Mach 2.92 scramjet engine fueled with ethylene. For comparison, experiments on a single-pulse LI were also performed. Schlieren visualization and high-speed photography were employed to observe the ignition processes simultaneously. The results indicate that the energy of an individual laser pulse can be reduced by half via a dual-pulse LI method as compared with a single-pulse LI with the same total energy. The reduction of the individual laser pulse energy degrades the requirements on the laser source and the beam delivery system, which facilitates the practical application of LI in hypersonic vehicles. A pulse interval shorter than 40 µs is suggested for dual-pulse LI in the present study. Because of the intense heat loss and radical dissipation in high-speed flows, the pulse interval for dual-pulse LI should be short enough to narrow the spatial distribution of the initial flame kernel.

Single Side-Chain-Modulatory of Hemicyanine for Optimized Fluorescence and Photoacoustic Dual-Modality Imaging of H2S In Vivo.

Near-infrared fluorescence (NIRF)/photoacoustic (PA) dual-modality imaging integrated high-sensitivity fluorescence imaging with deep-penetration PA imaging has been recognized as a reliable tool for disease detection and diagnosis. However, it remains an immense challenge for a molecule probe to achieve the optimal NIRF and PA imaging by adjusting the energy allocation between radiative transition and nonradiative transition. Herein, a simple but effective strategy is reported to engineer a NIRF/PA dual-modality probe (Cl-HDN3) based on the near-infrared hemicyanine scaffold to optimize the energy allocation between radiative and nonradiative transition. Upon activation by H2S, the Cl-HDN3 shows a 3.6-fold enhancement in the PA signal and a 4.3-fold enhancement in the fluorescence signal. To achieve the sensitive and selective detection of H2S in vivo, the Cl-HDN3 is encapsulated within an amphiphilic lipid (DSPE-PEG2000) to form the Cl-HDN3-LP, which can successfully map the changes of H2S in a tumor-bearing mouse model with the NIRF/PA dual-modality imaging. This work presents a promising strategy for optimizing fluorescence and PA effects in a molecule probe, which may be extended to the NIRF/PA dual-modality imaging of other disease-relevant biomarkers.

Totally Caged Type I Pro-Photosensitizer for Oxygen-Independent Synergistic Phototherapy of Hypoxic Tumors.

Activatable type I photosensitizers are an effective way to overcome the insufficiency and imprecision of photodynamic therapy in the treatment of hypoxic tumors, however, the incompletely inhibited photoactivity of pro-photosensitizer and the limited oxidative phototoxicity of post-photosensitizer are major limitations. It is still a great challenge to address these issues using a single and facile design. Herein, a series of totally caged type I pro-photosensitizers (Pro-I-PSs) are rationally developed that are only activated in tumor hypoxic environment and combine two oxygen-independent therapeutic mechanisms under single-pulse laser irradiation to enhance the phototherapeutic efficacy. Specifically, five benzophenothiazine-based dyes modified with different nitroaromatic groups, BPN 1-5, are designed and explored as latent hypoxia-activatable Pro-I-PSs. By comparing their optical responses to nitroreductase (NTR), it is identified that the 2-methoxy-4-nitrophenyl decorated dye (BPN 2) is the optimal Pro-I-PSs, which can achieve NTR-activated background-free fluorescence/photoacoustic dual-modality tumor imaging. Furthermore, upon activation, BPN 2 can simultaneously produce an oxygen-independent photoacoustic cavitation effect and a photodynamic type I process at single-pulse laser irradiation. Detailed studies in vitro and in vivo indicated that BPN 2 can effectively induce cancer cell apoptosis through synergistic effects. This study provides promising potential for overcoming the pitfalls of hypoxic-tumor photodynamic therapy.

Leucine alleviates cytokine storm syndrome by regulating macrophage polarization via the mTORC1/LXRα signaling pathway.

Cytokine storms are associated with severe pathological damage and death in some diseases. Excessive activation of M1 macrophages and the subsequent secretion of pro-inflammatory cytokines are a major cause of cytokine storms. Therefore, promoting the polarization of M2 macrophages to restore immune balance is a promising therapeutic strategy for treating cytokine storm syndrome (CSS). This study was aimed at investigating the potential protective effects of leucine on lipopolysaccharide (LPS)-induced CSS in mice and exploring the underlying mechanisms. CSS was induced by LPS administration in mice, which were concurrently administered leucine orally. In vitro, bone marrow derived macrophages (BMDMs) were polarized to M1 and M2 phenotypes with LPS and interleukin-4 (IL-4), respectively, and treated with leucine. Leucine decreased mortality in mice treated with lethal doses of LPS. Specifically, leucine decreased M1 polarization and promoted M2 polarization, thus diminishing pro-inflammatory cytokine levels and ameliorating CSS in mice. Further studies revealed that leucine-induced macrophage polarization through the mechanistic target of rapamycin complex 1 (mTORC1)/liver X receptor α (LXRα) pathway, which synergistically enhanced the expression of the IL-4-induced M2 marker Arg1 and subsequent M2 polarization. In summary, this study revealed that leucine ameliorates CSS in LPS mice by promoting M2 polarization through the mTORC1/LXRα/Arg1 signaling pathway. Our findings indicate that a fundamental link between metabolism and immunity contributes to the resolution of inflammation and the repair of damaged tissues.

Advancing insights into in vivo meningeal lymphatic vessels with stereoscopic wide-field photoacoustic microscopy.

Meningeal lymphatic vessels (mLVs) play a pivotal role in regulating metabolic waste from cerebrospinal fluid (CSF). However, the current limitations in field of view and resolution of existing imaging techniques impede understanding the stereoscopic morphology and dynamic behavior of mLVs in vivo. Here, we utilized dual-contrast functional photoacoustic microscopy to achieve wide-field intravital imaging of the lymphatic system, including mLVs and glymphatic pathways. The stereoscopic photoacoustic microscopy based on opto-acoustic confocal features has a depth imaging capability of 3.75 mm, facilitating differentiation between mLVs on the meninges and glymphatic pathways within the brain parenchyma. Subsequently, using this imaging technique, we were able to visualize the dynamic drainage of mLVs and identify a peak drainage period occurring around 20-40 min after injection, along with determining the flow direction from CSF to lymph nodes. Inspiringly, in the Alzheimer's disease (AD) mouse model, we observed that AD mice exhibit a ~ 70% reduction in drainage volume of mLVs compared to wild-type mice. With the development of AD, there is be continued decline in mLVs drainage volume. This finding clearly demonstrates that the AD mouse model has impaired CSF drainage. Our study opens up a horizon for understanding the brain's drainage mechanism and dissecting mLVs-associated neurological disorders.

Stem Cell-Derived Nanovesicles Embedded in Dual-Layered Hydrogel for Programmed ROS Regulation and Comprehensive Tissue Regeneration in Burn Wound Healing.

Burn wounds often bring high risks of delayed healing process and even death. Reactive oxygen species (ROS) play a crucial role in burn wound repair. However, the dynamic process in wound healing requires both the generation of ROS to inhibit bacteria and the subsequent reduction of ROS levels to initiate and promote tissue regeneration, which calls for a more intelligent ROS regulation dressing system. Hence, a dual-layered hydrogel (Dual-Gel) tailored to the process of burn wound repair is designed: the inner layer hydrogel (Gel 2) first responds to bacterial hyaluronidase (Hyal) to deliver aggregation-induced emission photosensitizer functionalized adipose-derived stem cell nanovesicles, which generate ROS upon light irradiation to eliminate bacteria; then the outer layer hydrogel (Gel 1) continuously starts a long-lasting consumption of excess ROS at the wound site to accelerate tissue regeneration. Simultaneously, the stem cell nanovesicles trapped in the burns wound also provide nutrients and mobilize neighboring tissues to thoroughly assist in inflammation regulation, cell proliferation, migration, and angiogenesis. In summary, this study develops an intelligent treatment approach on burn wounds by programmatically regulating ROS and facilitating comprehensive wound tissue repair.

Relationship between spatial pattern and function of urban land use in Changchun, China.

The urban spatial structure in this study refers to the combination of different categories of land use, and the purpose of the study is to reveal the intrinsic correlation characteristics between urban land use structural combination forms and urban functions. Through the integration of land and population maps and other multi-source data, with the help of exploratory spatial data analysis and other models, this research deals with the land use spatial structure characteristics of Changchun city and its coordination relationship with urban functions. Main conclusions of the study are as follows. The overall density of the land use in the central urban area of Changchun shows patterns of the core being higher than the periphery, the large-scale agglomeration being significant and the small-scale relatively scattered, and the pattern of the mixed land use function index has obvious differentiation characteristics. The study shows that, in the context of the spatial pattern, the overall coupling coordination degree of the land use structure index and the urban function index shows a trend of a gradual decrease, from the core to the periphery. In the context of category differences, the coupling coordination of the land use structure with the population distribution and the Baidu thermal distribution is relatively high, and the coupling coordination with various service facilities is relatively low. Finally, in the context of scale differences, all types of coupling coordination degrees have significant sensitivity to the spatial scales. A large scale significantly reflects the overall decrease in the coupling coordination degrees from the core to the periphery, while a small scale shows the polycentric pattern characteristics of the urban spatial structure.

A dye-quenched/sensitized switching upconversion nanoprobe for high-contrast mapping of the pH-related tumor microenvironment.

Nanoprobes based on lanthanide-doped upconversion nanoparticles (UCNPs) exhibit promising potential in bioimaging and biosensing due to their unique optical properties. However, conventional UCNP nanoprobes based on the dye quenching effect are still limited in biosensing due to their low upconversion efficiency. The advent of dye-sensitized upconversion has resulted in nanoprobes with significantly enhanced efficiency; however, these still suffer from a high initial emissive background. In view of this, herein, we have constructed a dye-quenched/sensitized switching upconversion nanoprobe for high-contrast imaging of the pH-related tumor microenvironment. Under normal conditions, the luminescence of the nanoprobe at 540 nm (UCL540) was significantly quenched by the employed dye. Upon being triggered by an acid, the dye would switch to its fluorescent form to sensitize the luminescence of UCNPs, affording a significant enhancement of UCL540. The switching from dye-quenched UCL to dye-sensitized UCL jointly enables the detection of a high signal-to-background ratio (high up to 50), allowing for high-contrast mapping of the tumor specific acidic microenvironment in vivo. We believe that this nanoplatform holds considerable promise for acid-related sensing.

Learning from the Brain: Bioinspired Nanofluidics.

The human brain completes intelligent behaviors such as the generation, transmission, and storage of neural signals by regulating the ionic conductivity of ion channels in neuron cells, which provides new inspiration for the development of ion-based brain-like intelligence. Against the backdrop of the gradual maturity of neuroscience, computer science, and micronano materials science, bioinspired nanofluidic iontronics, as an emerging interdisciplinary subject that focuses on the regulation of ionic conductivity of nanofluidic systems to realize brain-like functionalities, has attracted the attention of many researchers. This Perspective provides brief background information and the state-of-the-art progress of nanofluidic intelligent systems. Two main categories are included: nanofluidic transistors and nanofluidic memristors. The prospects of nanofluidic iontronics' interdisciplinary progress in future artificial intelligence fields such as neuromorphic computing or brain-computer interfaces are discussed. This Perspective aims to give readers a clear understanding of the concepts and prospects of this emerging interdisciplinary field.

Development and validation of a nomogram model for predicting unfavorable functional outcomes in ischemic stroke patients after acute phase.

Introduction: Prediction of post-stroke functional outcome is important for personalized rehabilitation treatment, we aimed to develop an effective nomogram for predicting long-term unfavorable functional outcomes in ischemic stroke patients after acute phase. Methods: We retrospectively analyzed clinical data, rehabilitation data, and longitudinal follow-up data from ischemic stroke patients who underwent early rehabilitation at multiple centers in China. An unfavorable functional outcome was defined as a modified Rankin Scale (mRS) score of 3-6 at 90 days after onset. Patients were randomly allocated to either a training or test cohort in a ratio of 4:1. Univariate and multivariate logistic regression analyses were used to identify the predictors for the development of a predictive nomogram. The area under the receiver operating characteristic curve (AUC) was used to evaluate predictive ability in both the training and test cohorts. Results: A total of 856 patients (training cohort: n = 684; test cohort: n = 172) were included in this study. Among them, 518 patients experienced unfavorable outcomes 90 days after ischemic stroke. Trial of ORG 10172 in Acute Stroke Treatment classification (p = 0.024), antihypertensive agents use [odds ratio (OR) = 1.86; p = 0.041], 15-day Barthel Index score (OR = 0.930; p < 0.001) and 15-day mRS score (OR = 13.494; p < 0.001) were selected as predictors for the unfavorable outcome nomogram. The nomogram model showed good predictive performance in both the training (AUC = 0.950) and test cohorts (AUC = 0.942). Conclusion: The constructed nomogram model could be a practical tool for predicting unfavorable functional outcomes in ischemic stroke patients underwent early rehabilitation after acute phase.

Specific disruption of glutathione-defense system with activatable single molecule-assembled nanoprodrug for boosted photodynamic/chemotherapy eradication of drug-resistant tumors.

Developing single molecule-assembled nanoprodrugs that can reverse the glutathione (GSH)-mediated drug resistance of tumors provides promising potentials for precision and effective cancer theranostics. Herein, we developed a novel single molecule-assembled nanoprodrug for effective photodynamic/chemotherapeutic eradication of drug-resistant tumors via the multistage GSH-depletion. The nanoprodrug MSSP-NP could be fancily fabricated by self-assembly of an amphiphilic activatable molecular MSSP, which is synthesized by covalently conjugating the photosensitizer methylene blue (MB) with a GSH-sensitive cisplatin prodrug via a tumor targeting thiolated polypeptide. Upon the nanoprodrug MSSP-NP systematic administrated, its photoactivities and pharmacological effects can be thoroughly switched on by intracellular GSH to produce the photosensitizer MB and chemotherapeutic drug cisplatin, along with the multi-step consumption of GSH, which could remarkably boost oxidative stress and reverse the drug resistance. As a result, the nanoprodrug could effectively disrupt the tumor GSH-defense system to afford high-efficiency photodynamic/chemotherapeutic inhibition of drug resistance tumors (96.4%) with minimum side effects.

Switching the NIR upconversion of nanoparticles for the orthogonal activation of photoacoustic imaging and phototherapy.

Phototheranostics based on upconversion nanoparticles (UCNPs) offer the integration of imaging diagnostics and phototherapeutics. However, the programmable control of the photoactivation of imaging and therapy with minimum side effects is challenging due to the lack of ideal switchable UCNPs agents. Here we demonstrate a facile strategy to switch the near infrared emission at 800 nm from rationally designed UCNPs by modulating the irradiation laser into pulse output. We further synthesize a theranostic nanoagent by combining with a photosensitizer and a photoabsorbing agent assembled on the UCNPs. The orthogonal activation of in vivo photoacoustic imaging and photodynamic therapy can be achieved by altering the excitation modes from pulse to continuous-wave output upon a single 980 nm laser. No obvious harmful effects during photoexcitation was identified, suggesting their use for long-term imaging-guidance and phototherapy. This work provides an approach to the orthogonal activation of imaging diagnostics and photodynamic therapeutics.

Mitochondria-Specific Agents for Photodynamic Cancer Therapy: A Key Determinant to Boost the Efficacy.

Mitochondria-targeted photodynamic therapy (Mt-PDT), which enables the photogenerated cytotoxic oxygen species with fatal oxidative damage to block mitochondrial functions, has been considered as a promising method to enhance the anticancer effectiveness. Aiming at the challenges of PDT, in the past few decades, numerous mitochondria-targeting molecular agents have been developed to boost the PDT efficacy via directly destroying the mitochondria or activating mitochondria-mediated cell death pathways. Herein, a review for recent advances of Mt-PDT is highlighted including: mitochondrial targeting design principles and strategies, therapeutic performance of mitochondria-targeted agents-mediated PDT as well as the agent-free Mt-PDT. In addition, it puts together the achievements of the combinatory mitochondria-anchoring PDT and other anticancer strategies, demonstrating the advantages provided by Mt-PDT. The existing challenges are discussed and future settlements for the development of mitochondria-specific agents are also forecasted.

Versatile gadolinium(III)-phthalocyaninate photoagent for MR/PA imaging-guided parallel photocavitation and photodynamic oxidation at single-laser irradiation.

Current light-mediated photodynamic therapy (PDT) is far underutilized in clinical cancer treatment due to its low pharmacological effect. We herein proposed a new gadolinium(III)-phthalocyanine (GdPc)-enabled phototherapeutics, photoacoustic/dynamic therapy (PADT), towards in vivo solid tumors via parallel-produced photocavitation and photodynamic oxidation with excitation by a single pulsed laser. We demonstrated that pulsed irradiation of GdPc could simultaneously produce an intense acoustic effect and a high-level 1O2 quantum yield to afford mitochondrial damage and initiate programmed cell death. Under the guidance of magnetic resonance/photoacoustic dual-modal imaging, the mechanical oxygen-independent destruction of acoustic cavitation and the chemical damage of 1O2 were validated to afford combinatorial inhibition of tumors under either normal or hypoxic conditions after the agent delivered into the cancer cells by a pH-sensitive nanomicelle. The single-laser initiated PADT using GdPc as a versatile photoagent maximizes the use of light energy to minimize the dose requirement of oxygen and agent towards high therapeutic efficacy, surpassing dramatically over conventional PDT.

Nanowired dual-electrodes surface to monitor cerebral ischemia by current-volt measurements.

The level of clotting protein 'factor IX' (FIX) is highly associated with cerebral ischemia, and this research work has developed a sensitive detection of FIX on dielectrode sensor by current-volt measurement. Sensing area was grown with zinc oxide nanowire to attach more probe for FIX interaction. Aptamer was utilized as the detection probe and attached on the sensing electrode surface through amine-aldehyde chemical linkage. In addition, biotin-streptavidin interaction was utilized to attach the higher number aptamers on the electrode surface connected with dual-probe station. FIX detection limit was found as 10 fM in the phosphate buffer saline spiked samples and 1:320 dilution of human serum. The linear ranges were as 10 fM to 100 pM and 1:320 to 1:80, respectively. With a good determination co-efficient [y = 2.6813x - 3.8467; R 2 = 0.9479] this biosensing strategy helps to quantify FIX and monitor the condition of cerebral ischemia.

Machine Learning-Based Model for Predicting Incidence and Severity of Acute Ischemic Stroke in Anterior Circulation Large Vessel Occlusion.

Objectives: Patients with anterior circulation large vessel occlusion are at high risk of acute ischemic stroke, which could be disabling or fatal. In this study, we applied machine learning to develop and validate two prediction models for acute ischemic stroke (Model 1) and severity of neurological impairment (Model 2), both caused by anterior circulation large vessel occlusion (AC-LVO), based on medical history and neuroimaging data of patients on admission. Methods: A total of 1,100 patients with AC- LVO from the Second Hospital of Hebei Medical University in North China were enrolled, of which 713 patients presented with acute ischemic stroke (AIS) related to AC- LVO and 387 presented with the non-acute ischemic cerebrovascular event. Among patients with the non-acute ischemic cerebrovascular events, 173 with prior stroke or TIA were excluded. Finally, 927 patients with AC-LVO were entered into the derivation cohort. In the external validation cohort, 150 patients with AC-LVO from the Hebei Province People's Hospital, including 99 patients with AIS related to AC- LVO and 51 asymptomatic AC-LVO patients, were retrospectively reviewed. We developed four machine learning models [logistic regression (LR), regularized LR (RLR), support vector machine (SVM), and random forest (RF)], whose performance was internally validated using 5-fold cross-validation. The performance of each machine learning model for the area under the receiver operating characteristic curve (ROC-AUC) was compared and the variables of each algorithm were ranked. Results: In model 1, among the included patients with AC-LVO, 713 (76.9%) and 99 (66%) suffered an acute ischemic stroke in the derivation and external validation cohorts, respectively. The ROC-AUC of LR, RLR and SVM were significantly higher than that of the RF in the external validation cohorts [0.66 (95% CI 0.57-0.74) for LR, 0.66 (95% CI 0.57-0.74) for RLR, 0.55 (95% CI 0.45-0.64) for RF and 0.67 (95% CI 0.58-0.76) for SVM]. In model 2, 254 (53.9%) and 31 (37.8%) patients suffered disabling ischemic stroke in the derivation and external validation cohorts, respectively. There was no difference in AUC among the four machine learning algorithms in the external validation cohorts. Conclusions: Machine learning methods with multiple clinical variables have the ability to predict acute ischemic stroke and the severity of neurological impairment in patients with AC-LVO.